Access to this full-text is provided by MDPI.
Content available from Electronics
This content is subject to copyright.
Academic Editor: Dorin Petreus
Received: 16 February 2025
Revised: 28 March 2025
Accepted: 31 March 2025
Published: 6 April 2025
Citation: Jamil, U.; Alva, R.J.; Ahmed,
S.; Jin, Y.-F. Artificial Intelligence-
Driven Optimal Charging Strategy for
Electric Vehicles and Impacts on
Electric Power Grid. Electronics 2025,
14, 1471. https://doi.org/10.3390/
electronics14071471
Copyright: © 2025 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license
(https://creativecommons.org/
licenses/by/4.0/).
Article
Artificial Intelligence-Driven Optimal Charging Strategy for
Electric Vehicles and Impacts on Electric Power Grid
Umar Jamil , Raul Jose Alva, Sara Ahmed and Yu-Fang Jin *
Department of Electrical and Computer Engineering, The University of Texas at San Antonio,
San Antonio, TX 78249, USA; umar.jamil@my.utsa.edu (U.J.); rj.alva@my.utsa.edu (R.J.A.);
sara.ahmed@utsa.edu (S.A.)
*Correspondence: yufang.jin@utsa.edu
Abstract: Electric vehicles (EVs) play a crucial role in achieving sustainability goals, mit-
igating energy crises, and reducing air pollution. However, their rapid adoption poses
significant challenges to the power grid, particularly during peak charging periods, necessi-
tating advanced load management strategies. This study introduces an artificial intelligence
(AI)-integrated optimal charging framework designed to facilitate fast charging and miti-
gate grid stress by smoothing the “duck curve”. Data from Caltech’s Adaptive Charging
Network (ACN) at the National Aeronautics and Space Administration (NASA) Jet Propul-
sion Laboratory (JPL) site was collected and categorized into day and night patterns to
predict charging duration based on key features, including start charging time and energy
requested. The AI-driven charging strategy developed optimizes energy management,
reduces peak loads, and alleviates grid strain. Additionally, the study evaluates the impact
of integrating 1.5 million, 3 million, and 5 million EVs under various AI-based charging
strategies, demonstrating the framework’s effectiveness in managing large-scale EV adop-
tion. The peak power consumption reaches around 22,000 MW without EVs, 25,000 MW
for 1.5 million EVs, 28,000 MW for 3 million EVs, and 35,000 MW for 5 million EVs with-
out any charging strategy. By implementing an AI-driven optimal charging optimization
strategy that considers both early charging and duck curve smoothing, the peak demand is
reduced by approximately 16% for 1.5 million EVs, 21.43% for 3 million EVs, and 34.29%
for 5 million EVs.
Keywords: artificial intelligence; electric vehicles; charging management; optimization;
power grid
1. Introduction
Electric vehicles (EVs) are widely recognized as a key solution for reducing air pollu-
tion and promoting sustainable transportation. According to the U.S. Energy Information
Administration, 3.3 million EVs were recorded in the U.S. in January 2024 [
1
], up from
2 million in 2022 and 1.3 million in 2021. The increasing number of EVs on the roads has
resulted in greater complexity and variability in charging behaviors, driven by diverse user
habits and inconsistent energy demands. Traditional demand response (DR) approaches
primarily depend on inflexible, predetermined load-shifting strategies designed for large
industrial or commercial users, often managed through centralized control by energy
providers [
2
]. However, there is a mismatch between the dynamic, real-time characteristics
of EV charging demands and the static, rigid framework of traditional DR approaches,
underscoring the need for more intelligent, adaptive, and real-time DR strategies [
3
–
5
] to
Electronics 2025,14, 1471 https://doi.org/10.3390/electronics14071471
Electronics 2025,14, 1471 2 of 21
ensure grid stability, optimize energy distribution, and alleviate peak stress on the power
grid caused by EV charging requests [6].
In response to this challenge, recent research has increasingly explored intelligent EV
charging optimization strategies that consider system-wide grid impacts [
7
–
16
]. Further-
more, substantial progress has been made in artificial intelligence (AI)-based EV energy
management systems [
17
–
20
] and the development of intelligent EV charging infrastruc-
ture [
21
,
22
], with the goal of delivering highly adaptive, scalable, and efficient charging
solutions that improve overall grid performance. The AI-driven DR systems dynamically
adjust EV charging schedules based on real-time grid conditions, energy availability, and
predictive analysis [
23
]. Such strategies can enhance grid stability and reduce peak demand
more effectively than traditional DR methods by optimizing charging patterns in alignment
with energy generation trends. Specifically, they help mitigate the duck curve effect by
synchronizing charging with periods of high energy output [
24
]. Although AI-driven strate-
gies require substantial computational resources for training and real-time data processing,
they offer long-term advantages in adaptability and efficiency. Once deployed, these strate-
gies enable self-optimizing, automated decision-making processes that outperform static,
rule-based DR systems in both speed and flexibility [
19
]. To minimize data integrity attacks
within the EV charging control center, a fuzzy inference-based advanced attack recovery
system effectively enhances security in the vehicle–grid system [25].
Machine learning (ML) and density functional theory play an important role in opti-
mizing catalyst development for green hydrogen production, addressing efficiency and
yield challenges [
26
]. The insights gained from ML-driven advancements in hydrogen
production can directly impact EV charging strategies, particularly for hydrogen fuel cell
EVs [
27
]. Additionally, recent studies have incorporated battery-centric parameters such
as state of charge (SoC) and state of health (SoH) to improve scheduling precision and
system reliability [
28
]. These considerations support more effective battery management,
reduce degradation, and enable the early detection of faults—facilitating proactive control
measures to maintain safe and efficient EV operation [
29
]. AI techniques have also been
applied for various predictive tasks, including charging load forecasting [
30
–
36
], user
behavior estimation [
37
], charging point occupancy prediction [
38
], and charging duration
estimation [39,40]. In [41], a degradation knowledge transfer learning approach was used
to estimate battery SOH accurately as compared to other artificial intelligence techniques.
Among these variables, charging duration remains a pivotal factor in EV charging
management, as it depends on critical parameters such as requested energy, start time,
end time, and power level. Daily fluctuations in energy demand, particularly during
peak hours, make it essential to forecast and manage EV charging duration effectively.
Therefore, striking a balance between fast charging and minimizing grid stress represents
a key optimization challenge. Most of the existing literature either focuses on predictive
modeling or employs optimization techniques in isolation (as summarized in Table 1).
Table 1. Review of existing literature and contributions of proposed work.
Reference Artificial Intelligence
Technique
Optimal Charging
Strategy
EVs Impact on
Power Grid
[10,11]×
×
×✓
✓
✓×
×
×
[12–16]×
×
×✓
✓
✓ ✓
✓
✓
[18,21,22,30–40]✓
✓
✓×
×
× ×
×
×
Proposed Work ✓
✓
✓ ✓
✓
✓ ✓
✓
✓
Electronics 2025,14, 1471 3 of 21
This study proposes an AI-enhanced EV charging framework that combines prediction
and optimization to improve load management and flatten the duck curve. The framework
uses AI to predict EV charging duration from features like charging start time and energy
demand. These predictions feed into an optimization algorithm to enhance system-wide
efficiency. The impact of different levels of EV integration under various AI-based strategies
is then analyzed to assess grid performance and stability.
The remainder of this paper is structured as follows: Section 2presents the proposed
methodology. Section 3discusses the experimental results and findings. Section 4offers
concluding remarks and suggestions for future research directions.
2. Methods
The ACN dataset features real data on EV charging across three sites in California—
the Jet Propulsion Laboratory (JPL), the California Institute of Technology (Caltech), and
Office 1. Table 2provides details about each site’s location, the number of electric vehicle
supply equipment (EVSE) units—defined as EV charging stations—and the total number of
EV charging sessions recorded between 2018 and 2021, based on publicly available sources.
This research focuses on the JPL site, due to its significantly higher volume of EV charging
sessions in comparison to the other two locations.
Table 2. ACN charging sites for EVs.
Charging Site Location No. of
EVSE
No. of EV Charging Sessions
2018 2019 2020 2021 Total
JPL A national research lab in
La Canada, California 52 4775 17,411 5576 5876 33,638
Caltech Research university in
Pasadena, California 54 15,297 10,617 2472 3038 31,424
Office 1 An office building situated in the
Silicon Valley area, California 8 0 922 436 325 1683
2.1. EV Charging Data Preprocessing
EV charging data collected from JPL charging sites include multiple features, such
as connection time, disconnect charging time, done charging time, and energy requested
(assumed to be equal to the energy delivered, measured in kilowatt-hours (kWh)). Based
on these existing features, the following additional variables were calculated: charging
duration in hours (h), charging occupancy (h), charging rate or power in kilowatts (kW),
and start charging time (h). A detailed explanation of each feature is provided in Table 3.
The original dataset provided the “connection time” in a datetime format, “Sun, 24 Mar
2019 22:30:47 GMT”. The feature “start charging time” was calculated by extracting the
time and normalizing it to a float number between 0 and 24. For example, 22:30:47 was
normalized to 22.513. The JPL charging station type was classified as level 2; according
to the U.S. Department of Transportation, the estimated charging time for fully depleted
battery EVs is about 4–10 h, while for plug-in hybrid EVs, it is around 1–2 h [
42
]. Therefore,
only sessions with charging durations ranging from 1 to 10 h were considered in this study.
Additionally, the highest observed charging power was generally below 6.6 kW, with only
a few exceptions. As a result, a charging power range of 2.5 to 6.6 kW was selected for
analysis, consistent with the specifications of level 2 charging stations.
Electronics 2025,14, 1471 4 of 21
Table 3. Descriptions of EV charging data features. N/A stands for not applicable.
Data Features Description Data
Type Unit
Connection Time
The time when the EV is first plugged in and begins the charging session.
datetime
N/A
Disconnect Time The time when the EV is unplugged, ending the charging session.
datetime
N/A
Done Charging Time
The time when the EV records its last instance of drawing a non-zero
current, indicating that charging is complete.
datetime
N/A
Energy Requested The amount of energy requested by the user for the charging session. float kWh
Charging
Occupancy
The total time an EV remains connected to a charging station(Difference
between disconnect charging time and connection time). float h
Charging Duration The total time taken for the EV to reach the requested charge level
(Difference between done charging time and connection time). float h
Power
The rate at which electrical energy is transferred to the EV battery during
charging (Ratio between energy requested and charging duration). float kW
Start Charging Time
The connection time converted to hours after removing the date and zone
information from timestamps. float h
In this study, the sessions conducted during weekdays were considered, while week-
ends and national holidays were excluded due to their low session frequency and limited
relevance to typical usage patterns. The maximum number of charging sessions was ob-
served in October 2019, and the complete dataset from this month is illustrated in Figure 1.
To ensure data stability, the peak session month and year were selected, and the final four
days—exhibiting minimal variation in the number of charging sessions—were used for
training. This helps with training a reliable model, while validation based on the remaining
dataset enhances the model’s generalizability.
Electronics 2025, 14, x FOR PEER REVIEW 4 of 23
The original dataset provided the “connection time” in a datetime format, “Sun, 24
Mar 2019 22:30:47 GMT”. The feature “start charging time” was calculated by extracting
the time and normalizing it to a float number between 0 and 24. For example, 22:30:47 was
normalized to 22.513. The JPL charging station type was classified as level 2; according to
the U.S. Department of Transportation, the estimated charging time for fully depleted bat-
tery EVs is about 4–10 h, while for plug-in hybrid EVs, it is around 1–2 h [42]. Therefore,
only sessions with charging durations ranging from 1 to 10 h were considered in this
study. Additionally, the highest observed charging power was generally below 6.6 kW,
with only a few exceptions. As a result, a charging power range of 2.5 to 6.6 kW was se-
lected for analysis, consistent with the specifications of level 2 charging stations.
In this study, the sessions conducted during weekdays were considered, while week-
ends and national holidays were excluded due to their low session frequency and limited
relevance to typical usage paerns. The maximum number of charging sessions was ob-
served in October 2019, and the complete dataset from this month is illustrated in Figure
1. To ensure data stability, the peak session month and year were selected, and the final
four days—exhibiting minimal variation in the number of charging sessions—were used
for training. This helps with training a reliable model, while validation based on the re-
maining dataset enhances the model’s generalizability.
Figure 1. Number of JPL sessions per day for Oct 2019. The number of days selected for model
training is shown in the orange highlighted region.
2.1.1. Spearman’s Correlation Coefficient
To examine the monotonic relationships between the float-type features presented in
Table 2, Spearman’s correlation coefficients are calculated, as defined by (1),
𝜌
=1− 6∑𝑏
𝑚 (𝑚
−1)
(1)
where
𝜌 = Spearman’s correlation coefficient;
𝑏 = difference between ranks of each pair of observations;
𝑚 = the number of observations or data points.
A 𝜌 of 1 indicates a perfect positive correlation, a 𝜌 of −1 indicates a perfect
negative correlation, and a 𝜌 of 0 indicates no correlation.
Figure 1. Number of JPL sessions per day for Oct 2019. The number of days selected for model
training is shown in the orange highlighted region.
2.1.1. Spearman’s Correlation Coefficient
To examine the monotonic relationships between the float-type features presented in
Table 2, Spearman’s correlation coefficients are calculated, as defined by (1),
ρscc =1−6∑b2
j
m(m2−1(1)
Electronics 2025,14, 1471 5 of 21
where
ρscc = Spearman’s correlation coefficient;
bj= difference between ranks of each pair of observations;
m= the number of observations or data points.
A
ρscc
of 1 indicates a perfect positive correlation, a
ρscc
of
−
1 indicates a perfect
negative correlation, and a ρscc of 0 indicates no correlation.
2.1.2. Feature Selection
In this study, “start charging time” and “energy requested (
ei
)” are selected as input
features, while “charging duration” serves as the target (output) feature. Both input features
are significant for predicting charging duration. The energy requested has a direct impact
on duration, as greater energy demands typically result in longer charging sessions. Start
charging time is also crucial, as it aligns with daily grid usage patterns, such as peak and
off-peak hours (e.g., daytime vs. nighttime), which influence both the efficiency and length
of the charging session due to variations in grid demand. For the ith charging session,
charging duration (
di
) is calculated by subtracting the done charging time
(td i)
and the
start charging time (tsi) as shown in (2),
di=tdi−tsi(2)
where input feature
ei
depends on charging power (
ri
) and charging duration (
di
), is defined
by (3)
ei=ridi. (3)
If
T
is the actual starting time (in hours of the day), then
tscti
can be defined for the
entire day by (4) to distinguish between daytime and nighttime charging behaviors,
tscti=(6am ≤T<6pm (Day)
6am >T≥6pm (Night). (4)
2.2. Quality Control of Data
Data visualization methods are employed to examine the data distribution and detect
any inconsistencies within the datasets. In this study, we utilize a violin plot for quality
control, as it effectively highlights the distribution of data. The shape of the violin plot is
created using Kernel Density Estimation (KDE), a method for estimating the probability
density function of a random variable. KDE transforms the distribution of discrete data
points into a smooth, continuous curve, as defined by (5) for a univariate variable x,
ˆ
g(x)=1
mh√2π
m
∑
j=1
e−1
2(x−xj
h)2
, (5)
where
ˆ
g(x)
is estimated density function,
m
is number of data points,
xj
is individual data
point,
h=
1.06
σm−1/5
is a bandwidth, a smoothing parameter, determined by Silverman’s
rule of thumb, and σis the standard deviation of the data.
The mean or average value (
µ
) of the dataset consisting of m samples is defined by (6)
µ=1
m∑m
j=1xi. (6)
Electronics 2025,14, 1471 6 of 21
The median (
M
), defined as the middle value of a dataset in (7), is determined differ-
ently based on the number of observations. If
m
is odd, the median is the middle value; if
mis even, it is the average of the two central values,
M=
xm+1
2, if m is odd
xm
2+xm
2+1
2, if m is even
. (7)
2.3. Artificial Intelligence Model
Four models were implemented in this study to predict charging duration, namely
linear regression (LR), Gaussian mixture regression (GMR), random forest regression (RFR),
and the feedforward fully connected artificial neural network (FFC-ANN). A comparison
between these models in terms of model type, characteristics, ability to handle nonlinearity,
training complexity, and scalability is presented in Table 4. The FFC-ANN is emphasized
due to its superior performance in capturing complex nonlinear relationships in the data,
higher accuracy in predictions, and scalability to handle large datasets. The selection of
an ANN model is driven by its ability to effectively model non-sequential relationships
within the given dataset, making them highly suitable for this problem. Furthermore, they
provide efficient learning with less computational overhead than reinforcement learning
approaches, ensuring faster training and easier implementation. This makes FFC-ANNs an
ideal choice for this task where clear input–output mappings are crucial, and the data are
non-sequential.
Table 4. Factors for characterization of different models.
AI Model LR GMR RFR FFC-ANN
Type Simple
regression
Probabilistic model with
mixture components
Ensemble-based
regression Neural network
Characteristics
Linear
relationship only,
baseline models
Models complex,
multimodal,
and nonlinear relationships
Nonlinear
relationships via
ensemble trees
Models complex,
nonlinear
relationships
Handling
Nonlinearity
Cannot capture
nonlinearity without
transformations
Captures multimodal and
nonlinear relationships
Good for complex,
nonlinear
relationships
Highly capable of
modeling
nonlinearity
Training
Complexity Low Moderate to high; EM
algorithm can be intensive Medium
High, especially with
deep architectures
Scalability High
Moderate;
not as scalable for
large datasets
Fairly high,
but slows with
more trees
High computational
demand
Feedforward Fully Connected ANN Model
In the FFC-ANN model, each neuron in each layer is fully connected to all the neurons
in the next layer, as shown in Figure 2. The input matrix for
m
samples, combining two
inputs eiand tscti, is represented by X∈Rm×2. It can be defined by (8),
Xi=
e1tsct1
.
.
..
.
.
emtsctm
. (8)
Electronics 2025,14, 1471 7 of 21
At Lhidden layers, l=1, 2, . . . L, it can be defined by (9),
q(l)
i=hW(l)q(l−1)
i+b(l), (9)
where
q(0)
i=Xi
,
W(l)
is the weight matrix for layer
l
,
b(l)
is the bias vector for layer
l
, and
h
is the activation function. The output layer generates final predictions of charging duration
ˆ
di, as indicated by (10) and (11),
ˆ
di=W(L)q(L−1)
i+b(L), (10)
ˆ
di=W(L)h·· ·h(W(1)Xi+b(1)···+b(L−1)+b(L). (11)
Electronics 2025, 14, x FOR PEER REVIEW 7 of 23
Figure 2. Structure of FFC-ANN with input, hidden, and output layers.
2.4. Model Evaluation
During model implementation, the data were split into two parts based on (4), dis-
tinguishing between day and night paerns. Each of these datasets was then trained and
tested using an 80% and 20% ratio, respectively, and normalized using min–max scaling.
Model evaluation was conducted using metrics such as Mean Squared Error (MSE), Mean
Absolute Error (MAE), and R-squared (R
2
), as defined in Equations (12) – (14). These met-
rics are essential for assessing the model’s performance in estimating charging duration.
They are calculated based on the real values (
𝑑
) and predicted values (
𝑑
), with
𝑚
repre-
senting the total number of samples as follows,
𝑀𝑆𝐸=1
𝑚(𝑑
−𝑑
)
,
(12)
𝑀𝐴𝐸=1
𝑚(𝑑
−𝑑
)
,
(13)
𝑅
=1−1
𝑚∑𝑑
−𝑑
1
𝑚∑𝑑
−𝑑
.
(14)
where 𝑑 is the mean value of testing sample.
2.5. Optimization
Scheduling of the EV charging was achieved by controlling the charging rate in a
session with different objective functions. The objective function U was established by
promoting charging as shown in (15).
U
=min ∑∑(
t−T)r
(t)
∈
∈
,
(15)
where U is a function of a vector r = {r(1),…, r(T),i∈ν, ν is the set of EV charging
sessions in a specific time period such as one day, the optimization horizon to solve
problem is defined as τ=1,2,3…..T, T is the last element of the time series τ, and r
is a charging rate in kW. By determining the charging rate r for a session i at a specific
time, the system can determine if the EV will not be charged (r(τ)=0), or charged with
Figure 2. Structure of FFC-ANN with input, hidden, and output layers.
2.4. Model Evaluation
During model implementation, the data were split into two parts based on (4), dis-
tinguishing between day and night patterns. Each of these datasets was then trained and
tested using an 80% and 20% ratio, respectively, and normalized using min–max scaling.
Model evaluation was conducted using metrics such as Mean Squared Error (MSE), Mean
Absolute Error (MAE), and R-squared (R
2
), as defined in Equations (12)–(14). These metrics
are essential for assessing the model’s performance in estimating charging duration. They
are calculated based on the real values (
di)
and predicted values (
ˆ
di
, with
m
representing
the total number of samples as follows,
MSE =1
m
m
∑
i=1di−ˆ
di2, (12)
MAE =1
m
m
∑
i=1di−ˆ
di, (13)
R2=1−
1
m∑m
i=1ˆ
di−d2
1
m∑m
i=1di−d2. (14)
Electronics 2025,14, 1471 8 of 21
where dis the mean value of testing sample.
2.5. Optimization
Scheduling of the EV charging was achieved by controlling the charging rate in a
session with different objective functions. The objective function
U1
was established by
promoting charging as shown in (15).
U1=min∑t∈τ∑i∈ν(t−T)ri(t), (15)
where
U1
is a function of a vector
ˆ
r
= {
ri(1)
,
. . .
,
ri(T), i ∈ν}
,
ν
is the set of EV charging
sessions in a specific time period such as one day, the optimization horizon to solve
problem is defined as
τ={1, 2, 3 . . . . . .T}
,
T
is the last element of the time series
τ
, and
r
is a charging rate in kW. By determining the charging rate
r
for a session
i
at a specific
time, the system can determine if the EV will not be charged (
ri(τ)=
0), or charged with
a specific rate (
0<ri≤rmax)
, where
rmax
is the maximum charging rate of a charging
station. The charging rate also affects a load imposing to the power grid.
The objective function U
2
was established to smooth the duck curve as shown in (16).
U2=min∑t∈τˆ
d(t)−ˆ
d(t−1)2, (16)
where
d(t)
represents California ISO’s net power demand at time
t
, which can be scaled up
and down to the charging stations’ system capacity assuming residential usage will not
change significantly. The variable
ˆ
d(t) = d(t)+∑i∈νri(t)
represents the justified power
demand with scheduled EV charging.
The objective U
3
can be considered as a linear combination of the difference between
current time (t) and expected ending time (T),
t−T
, as well as the charging rates
ri(t)
. The
objective function U
3
deploys different weights of the charging rate denoted as a function
f((t−Ti)
ˆ
di)in (17),
U3=min∑t∈τ∑i∈νf(t−Ti)
ˆ
diri(t), (17)
where
Ti
represents the done charging time specific to a session
i
,
(t−Ti)
is then normalized
with its predicted charging duration,
ˆ
di
, such that
t−Ti
ˆ
di
will be limited to the domain
[−1 0]
. Five different concave and mono-increasing weight functions were considered for
f(t−Ti)
ˆ
di
in U
3
, such as
t−Ti
ˆ
di
,
−e−2(t−Ti
ˆ
di)−1
,
log t−Ti
ˆ
di+1.001, ln t−Ti
ˆ
di+1.01,
and 0.05 tant−Ti
ˆ
di+π
2+1.01.
As the ultimate goal was to schedule EV charging with both early charging and a
smooth duck curve, a combination of the U
2
and U
3
objectives were constructed as
U4
, asv
indicated in (18),
U4=(1−n)U3
u3+nU2
u2(18)
where weight
n
is a percentage of the importance of a smooth duck curve, and 1
−
n is the
importance of charging efficiency;
u2
and
u3
are defined as the best values of the separate
minimizations of U2and U3in the previous sessions.
2.6. Computational Framework
Data preprocessing and AI model implementation for charging duration prediction
were carried out using Jupyter Notebook 6.4.8, an open-source web-based interactive
computational environment. The programming language utilized for this task is Python.
3.9.12 All simulations were executed on an AMD Ryzen 7 5800 8-Core Processor) (3.401 GHz)
with 16 logical processors, using an Alienware system manufactured by Dell Technologies,
Electronics 2025,14, 1471 9 of 21
headquartered in Round Rock, Texas, USA. Additionally, the optimization toolbox of
MATLAB-R2024b was used to apply quadratic nonlinear programming functions for
optimization purposes. The framework of the proposed research methodology is shown in
Figure 3.
Electronics 2025, 14, x FOR PEER REVIEW 9 of 23
Figure 3. Flow chart of the proposed AI-driven charging strategies.
3. Results and Discussion
Section 3 has been divided into the following sub-sections:
(a) Correlation analysis;
(b) Data visualization for quality control;
(c) Prediction of charging duration by FFC-ANN model;
(d) Comparison of the FFC-ANN model with other AI models;
(e) Optimization of power by different objective functions;
(f) Impacts of EV integration on electric power grid.
3.1. Correlation Analysis
To examine the relationships among the various data features, Spearman’s correla-
tion analysis was conducted, as shown in Figure 4. A correlation coefficient of 0.8761 was
identified between the energy requested and charging duration, indicating a strong posi-
tive correlation. In contrast, a correlation coefficient of −0.2247 was found between the
start charging time and the charging duration, suggesting a weak negative correlation.
The features, energy requested and start charging time, were considered as input features,
and used as the inputs to the AI models to predict charging duration, which was desig-
nated as the target or output feature.
3.2. Data Visualization for Quality Control
Violin plots are used in data visualization to assess the distribution of data features,
supporting quality control by identifying data trends, variability, and potential outliers.
Figure 5a–c shows the distributions of both the input and output features. The violin plot
for the energy requested input indicates mean and median values of 18.24 kWh and 13.99
kWh, respectively. For the start charging time input, the mean is 4:56 pm (16.93 h out of
24 h) and the median is 2:28 pm (14.46 h). In contrast, the mean and median values for
charging duration as target feature for prediction are 4.08 h and 3.36 h, respectively. In-
terestingly, the start charging time feature showed a clear separation between daytime
and nighime, suggesting two different models for daytime and nighime, respectively.
Figure 3. Flow chart of the proposed AI-driven charging strategies.
3. Results and Discussion
Section 3has been divided into the following sub-sections:
(a)
Correlation analysis;
(b)
Data visualization for quality control;
(c)
Prediction of charging duration by FFC-ANN model;
(d)
Comparison of the FFC-ANN model with other AI models;
(e)
Optimization of power by different objective functions;
(f)
Impacts of EV integration on electric power grid.
3.1. Correlation Analysis
To examine the relationships among the various data features, Spearman’s correlation
analysis was conducted, as shown in Figure 4. A correlation coefficient of 0.8761 was
identified between the energy requested and charging duration, indicating a strong positive
correlation. In contrast, a correlation coefficient of
−
0.2247 was found between the start
charging time and the charging duration, suggesting a weak negative correlation. The
features, energy requested and start charging time, were considered as input features, and
used as the inputs to the AI models to predict charging duration, which was designated as
the target or output feature.
3.2. Data Visualization for Quality Control
Violin plots are used in data visualization to assess the distribution of data features,
supporting quality control by identifying data trends, variability, and potential outliers.
Figure 5a–c shows the distributions of both the input and output features. The violin
plot for the energy requested input indicates mean and median values of 18.24 kWh and
13.99 kWh, respectively. For the start charging time input, the mean is 4:56 pm (16.93 h
out of 24 h) and the median is 2:28 pm (14.46 h). In contrast, the mean and median values
for charging duration as target feature for prediction are 4.08 h and 3.36 h, respectively.
Interestingly, the start charging time feature showed a clear separation between daytime
and nighttime, suggesting two different models for daytime and nighttime, respectively.
Electronics 2025,14, 1471 10 of 21
Electronics 2025, 14, x FOR PEER REVIEW 10 of 23
Figure 4. Correlation analysis among different data features.
(a) (b) (c)
Figure 5. Data visualization for quality control (a) energy requested (b) start charging time, (c)
charging duration of training data.
3.3. Prediction of Charging Duration by FFC-ANN Model
The artificial neural network (ANN) model was trained with various hyperparame-
ters, including the number of neurons, learning rate, number of layers, epochs, and acti-
vation functions, for both the day (6 am≤𝑇<6 pm ) and night (6 am> 𝑇 ≥6 pm ) da-
tasets, as detailed in Tables 5 and 6. Notably, the model’s performance improved with
three hidden layers, as evidenced by the R
2
scores achieved. Specifically, for the daytime
dataset, the model aained an R
2
score of 0.7189 with 50 layers, while the night dataset
Figure 4. Correlation analysis among different data features.
Electronics 2025, 14, x FOR PEER REVIEW 10 of 23
Figure 4. Correlation analysis among different data features.
(a) (b) (c)
Figure 5. Data visualization for quality control (a) energy requested (b) start charging time, (c)
charging duration of training data.
3.3. Prediction of Charging Duration by FFC-ANN Model
The artificial neural network (ANN) model was trained with various hyperparame-
ters, including the number of neurons, learning rate, number of layers, epochs, and acti-
vation functions, for both the day (6 am≤𝑇<6 pm ) and night (6 am >𝑇≥6 pm ) da-
tasets, as detailed in Tables 5 and 6. Notably, the model’s performance improved with
three hidden layers, as evidenced by the R
2
scores achieved. Specifically, for the daytime
dataset, the model aained an R
2
score of 0.7189 with 50 layers, while the night dataset
Figure 5. Data visualization for quality control (a) energy requested (b) start charging time, (c) charg-
ing duration of training data.
3.3. Prediction of Charging Duration by FFC-ANN Model
The artificial neural network (ANN) model was trained with various hyperparameters,
including the number of neurons, learning rate, number of layers, epochs, and activation
functions, for both the day (6
am ≤T<
6
pm
) and night (6
am >T≥
6
pm
) datasets, as
detailed in Tables 5and 6. Notably, the model’s performance improved with three hidden
layers, as evidenced by the R
2
scores achieved. Specifically, for the daytime dataset, the
model attained an R
2
score of 0.7189 with 50 layers, while the night dataset yielded R
2
score of 0.8133. However, these scores were suboptimal compared to those achieved with
100 and 150 epochs.
As observed in Tables 5and 6, the hyperparameters at Sr. No. 12 and 13 demonstrated
superior performance metrics and were thus selected for model training, as shown in Table 7.
Given these hyperparameters for the subsequent experiments, a controlled environment
was established to facilitate a clearer understanding of the model’s performance under
consistent conditions. The mean R
2
scores of 10 data partitions, randomly chosen from the
selected four-day dataset, were 0.9348 for the day dataset and 0.8988 for the night dataset,
using the fixed hyperparameters from serial number 13. The ANN model showed better
Electronics 2025,14, 1471 11 of 21
performance on the nighttime dataset due to reduced variability and noise, as well as more
predictable user behavior, allowing the model to capture stable patterns effectively.
Table 5. Performance of FFC-ANN model at different hyperparameters for daytime pattern.
Sr. No.
Neuron
Learning
Rate Layer Epochs Activation
Function
Batch
Size MSE MAE R2
1 32 0.001 3 150 tanh 64 0.3733 0.4270 0.9066
2 32 0.001 3 150 tanh 32 0.8171 0.6538 0.8788
3 32 0.001 3 150 tanh 16 0.6328 0.6095 0.8732
4 32 0.001 3 100 tanh 64 0.6410 0.5977 0.8732
5 32 0.001 3 50 tanh 64 0.7409 0.7082 0.7189
6 32 0.01 3 150 tanh 64 0.9583 0.7484 0.8444
7 32 0.1 3 150 tanh 64 0.9231 0.7439 0.8284
8 64 0.001 3 150 tanh 64 0.6405 0.6427 0.8396
9 128 0.001 3 150 tanh 64 0.6635 0.6283 0.8832
10 32 0.001 1 150 tanh 64 1.5557 1.0830 0.6931
11 32 0.001 2 150 tanh 64 0.7623 0.7250 0.8228
12 32 0.001 3 150 ReLU 64 0.7494 0.6116 0.9010
13 64 0.001 3 150 ReLU 64 0.3316 0.4886 0.9023
14 128 0.001 3 150 ReLU 64 0.6167 0.6381 0.8759
15 32 0.001 3 100 ReLU 64 0.6603 0.6952 0.8593
Table 6. Performance of FFC-ANN model at different hyperparameters for nighttime pattern.
Sr. No.
Neuron
Learning
Rate Layer Epochs Activation
Function
Batch
Size MSE MAE R2
1 32 0.001 3 150 tanh 64 0.1656 0.3723 0.9139
2 32 0.001 3 150 tanh 32 0.1704 0.3582 0.9121
3 32 0.001 3 150 tanh 16 0.1661 0.3459 0.9136
4 32 0.001 3 100 tanh 64 0.1909 0.3991 0.9001
5 32 0.001 3 50 tanh 64 0.2392 0.4127 0.8133
6 32 0.01 3 150 tanh 64 0.1894 0.3829 0.9185
7 32 0.1 3 150 tanh 64 0.2457 0.3767 0.8162
8 64 0.001 3 150 tanh 64 0.2238 0.4326 0.8871
9 128 0.001 3 150 tanh 64 0.1600 0.3562 0.9159
10 32 0.001 1 150 tanh 64 0.5241 0.5769 0.7168
11 32 0.001 2 150 tanh 64 0.1712 0.3606 0.8778
12 32 0.001 3 150 ReLU 64 0.1268 0.3340 0.9313
13 64 0.001 3 150 ReLU 64 0.1163 0.3118 0.9355
14 128 0.001 3 150 ReLU 64 0.1010 0.2665 0.9433
15 32 0.001 3 100 ReLU 64 0.0873 0.2566 0.9214
The model was established with training datasets from 4 days, from 28 October to
31 October 2019. A total of 80% of the charging sessions were used for training and the
remaining 20% were used for testing. The actual and predicted charging duration of the
testing charging sessions are presented in Figures 6a and 6b for the daytime and nighttime
patterns, respectively.
Model validation was performed using 100 random samples from the non-training
data (excluding the charging sessions from the 4 days used for training) for each data
partition, as presented in Table 8. The mean value of R
2
for the nighttime pattern is
0.9112, which is slightly higher than the mean value of 0.8816 for the daytime pattern. The
evaluation metrics such as MSE, MAE, and R
2
for 10 data partitions from the validation
data for both day and night patterns are visualized in Figures 7a and 7b, respectively. The
Electronics 2025,14, 1471 12 of 21
MSE and MAE values in the daytime pattern are higher than in the nighttime pattern,
suggesting a better performance of the nighttime model.
Table 7. Performance of the FFC-ANN model at fixed hyperparameters.
Dataset Day (6 am ≤T< 6 pm) Night (6 am > T≥6 pm)
Hyperparameter No. #12 #13 #12 #13
Evaluation Metrics MSE MAE R2 MSE MAE R2 MSE MAE R2 MSE MAE R2
Data Partitions
1 0.7494 0.6116
0.9010
0.423 0.5037
0.9118
0.1268
0.3340 0.9313
0.1008
0.2913 0.9498
2 0.4459 0.5143
0.8992
0.3316 0.4886
0.9023
0.1007
0.2770 0.9477
0.0893
0.2621 0.9389
3 0.6100 0.6119
0.8793
0.5694 0.6525
0.8972
0.1092
0.2968 0.9428
0.1049
0.2769 0.9455
4 0.7640 0.6663
0.8733
0.4072 0.5206
0.9175
0.1278
0.3321 0.9396
0.1065
0.2768 0.9446
5 0.5665 0.6093
0.8800
0.5372 0.6034
0.9036
0.0766
0.2432 0.9268
0.1622
0.3578 0.9168
6 0.7352 0.7118
0.8625
0.5929 0.6377
0.8918
0.1378
0.3354 0.9054
0.1180
0.3093 0.9508
7 0.7619 0.7159
0.8629
0.4734 0.5490
0.8901
0.1332
0.3435 0.9074
0.1361
0.3024 0.9247
8 0.6965 0.6945
0.8752
0.4638 0.5382
0.8945
0.1551
0.3417 0.9070
0.0943
0.2638 0.9061
9 0.6081 0.6569
0.8622
0.6628 0.6093
0.8841
0.1455
0.3297 0.9016
0.0693
0.2202 0.9465
10 0.8462 0.7908
0.8779
0.5349 0.5987
0.8950
0.1590
0.3080 0.9332
0.1300
0.3151 0.9240
Mean 0.6784 0.6583
0.8774
0.4997 0.5702
0.8988
0.1272
0.3141 0.9243
0.1111
0.2876 0.9348
Standard Deviation 0.1189 0.0764
0.0139
0.0985 0.0575
0.0102
0.0255
0.0330 0.01737
0.0265
0.0371 0.0157
Electronics 2025, 14, x FOR PEER REVIEW 12 of 23
Hyperparameter No. #12 #13 #12 #13
Evaluation Metrics MSE MAE R2 MSE MAE R2 MSE MAE R2 MSE MAE R2
Data Partitions
1 0.7494 0.6116 0.9010 0.423 0.5037 0.9118 0.1268 0.3340 0.9313 0.1008 0.2913 0.9498
2 0.4459 0.5143 0.8992 0.3316 0.4886 0.9023 0.1007 0.2770 0.9477 0.0893 0.2621 0.9389
3 0.6100 0.6119 0.8793 0.5694 0.6525 0.8972 0.1092 0.2968 0.9428 0.1049 0.2769 0.9455
4 0.7640 0.6663 0.8733 0.4072 0.5206 0.9175 0.1278 0.3321 0.9396 0.1065 0.2768 0.9446
5 0.5665 0.6093 0.8800 0.5372 0.6034 0.9036 0.0766 0.2432 0.9268 0.1622 0.3578 0.9168
6 0.7352 0.7118 0.8625 0.5929 0.6377 0.8918 0.1378 0.3354 0.9054 0.1180 0.3093 0.9508
7 0.7619 0.7159 0.8629 0.4734 0.5490 0.8901 0.1332 0.3435 0.9074 0.1361 0.3024 0.9247
8 0.6965 0.6945 0.8752 0.4638 0.5382 0.8945 0.1551 0.3417 0.9070 0.0943 0.2638 0.9061
9 0.6081 0.6569 0.8622 0.6628 0.6093 0.8841 0.1455 0.3297 0.9016 0.0693 0.2202 0.9465
10 0.8462 0.7908 0.8779 0.5349 0.5987 0.8950 0.1590 0.3080 0.9332 0.1300 0.3151 0.9240
Mean 0.6784 0.6583 0.8774 0.4997 0.5702 0.8988 0.1272 0.3141 0.9243 0.1111 0.2876 0.9348
Standard Deviation 0.1189 0.0764 0.0139 0.0985 0.0575 0.0102 0.0255 0.0330 0.01737 0.0265 0.0371 0.0157
The model was established with training datasets from 4 days, from 28 October to 31
October 2019. A total of 80% of the charging sessions were used for training and the re-
maining 20% were used for testing. The actual and predicted charging duration of the
testing charging sessions are presented in Figure 6 (a) and (b) for the daytime and
nighime paerns, respectively.
Model validation was performed using 100 random samples from the non-training
data (excluding the charging sessions from the 4 days used for training) for each data
partition, as presented in Table 8. The mean value of R
2
for the nighime paern is 0.9112,
which is slightly higher than the mean value of 0.8816 for the daytime paern. The evalu-
ation metrics such as MSE, MAE, and R
2
for 10 data partitions from the validation data for
both day and night paerns are visualized in Figure 7a and Figure 7b, respectively. The
MSE and MAE values in the daytime paern are higher than in the nighime paern,
suggesting a beer performance of the nighime model.
(a) (b)
Figure 6. Actual vs. FFC-ANN-predicted charging duration: (a) daytime paern and (b) nighime
Paern.
Table 8. Performance of FFC-ANN model for validation dataset.
Dataset Day (𝟔 𝐚𝐦≤𝑻<𝟔 𝐩𝐦) Night (𝟔 𝐚𝐦>𝑻≥𝟔 𝐩𝐦)
Evaluation Metrics MSE MAE R2 MSE MAE R2
D
a
t
a
1 0.5318 0.5719 0.8713 0.2000 0.3700 0.9352
Figure 6. Actual vs. FFC-ANN-predicted charging duration: (a) daytime pattern and (b) nighttime Pattern.
Table 8. Performance of FFC-ANN model for validation dataset.
Dataset Day (6 am ≤T< 6 pm) Night (6 am > T≥6 pm)
Evaluation Metrics MSE MAE R2 MSE MAE R2
Data Partitions
1 0.5318 0.5719 0.8713 0.2000 0.3700 0.9352
2 0.7899 0.7251 0.8738 0.2122 0.4095 0.9155
3 0.4518 0.5540 0.8672 0.1672 0.3544 0.8978
4 0.5655 0.5766 0.8944 0.2042 0.4095 0.9250
5 0.5672 0.6373 0.8878 0.1648 0.3531 0.8908
6 0.7885 0.6401 0.8657 0.3825 0.3664 0.8975
7 0.4154 0.5154 0.9110 0.3019 0.4353 0.9044
8 0.7778 0.6546 0.8640 0.1879 0.3619 0.9057
9 0.6308 0.6432 0.8600 0.1867 0.3328 0.9122
10 0.6355 0.6403 0.9208 0.1897 0.3776 0.9276
Mean 0.6154 0.6159 0.8816 0.2197 0.3771 0.9112
Standard Deviation 0.1358 0.0608 0.0211 0.0689 0.0315 0.0146
Electronics 2025,14, 1471 13 of 21
Electronics 2025, 14, x FOR PEER REVIEW 13 of 23
2 0.7899 0.7251 0.8738 0.2122 0.4095 0.9155
3 0.4518 0.5540 0.8672 0.1672 0.3544 0.8978
4 0.5655 0.5766 0.8944 0.2042 0.4095 0.9250
5 0.5672 0.6373 0.8878 0.1648 0.3531 0.8908
6 0.7885 0.6401 0.8657 0.3825 0.3664 0.8975
7 0.4154 0.5154 0.9110 0.3019 0.4353 0.9044
8 0.7778 0.6546 0.8640 0.1879 0.3619 0.9057
9 0.6308 0.6432 0.8600 0.1867 0.3328 0.9122
10 0.6355 0.6403 0.9208 0.1897 0.3776 0.9276
Mean 0.6154 0.6159 0.8816 0.2197 0.3771 0.9112
Standard Deviation 0.1358 0.0608 0.0211 0.0689 0.0315 0.0146
(a) (b)
Figure 7. FFC-ANN model validation: (a) daytime paern and (b) nighime paern.
3.4. Comparison of the FFC-ANN Model with Other AI Models
The FFC-ANN model and other AI models, such as LR, GMR, and RFR, were
compared using evaluation metrics such as MSE, MAE, and R
2
across 10 different data
partitions for daytime and nighime paerns. The results for the LR, GMR, and RFR
models are presented in Tables 9–11, while the FFC-ANN model’s findings are shown in
Table 6.
Table 9. Performance of LR model.
Dataset Day (𝟔 𝐚𝐦≤𝑻<𝟔 𝐩𝐦) Night (𝟔 𝐚𝐦>𝑻≥𝟔 𝐩𝐦)
Evaluation Metrics MSE MAE R2 MSE MAE R2
Data Partitions
1 0.7715 0.6505 0.8757 0.1886 0.3860 0.8554
2 0.9996 0.7745 0.8478 0.2059 0.4129 0.8418
3 1.1700 0.8586 0.8077 0.1527 0.3696 0.8625
4 1.0084 0.7906 0.8086 0.1527 0.3522 0.8883
5 0.8264 0.7527 0.8518 0.2032 0.4026 0.8722
6 0.9030 0.8001 0.8137 0.1548 0.3452 0.8903
7 0.6175 0.6245 0.8598 0.1625 0.3529 0.9092
8 0.8206 0.7199 0.8606 0.1641 0.3704 0.8974
9 0.8677 0.7458 0.8135 0.1276 0.3181 0.9353
10 1.1941 0.8494 0.8032 0.1128 0.2967 0.9112
Mean 0.9179 0.7567 0.8342 0.1625 0.3607 0.8864
Standard Deviation 0.1694 0.0725 0.0260 0.0286 0.0340 0.0272
Table 10. Performance of GMR model.
Figure 7. FFC-ANN model validation: (a) daytime pattern and (b) nighttime pattern.
3.4. Comparison of the FFC-ANN Model with Other AI Models
The FFC-ANN model and other AI models, such as LR, GMR, and RFR, were compared
using evaluation metrics such as MSE, MAE, and R
2
across 10 different data partitions
for daytime and nighttime patterns. The results for the LR, GMR, and RFR models are
presented in Tables 9–11, while the FFC-ANN model’s findings are shown in Table 6.
Table 9. Performance of LR model.
Dataset Day (6 am ≤T< 6 pm) Night (6 am > T≥6 pm)
Evaluation Metrics MSE MAE R2 MSE MAE R2
Data Partitions
1 0.7715 0.6505 0.8757 0.1886 0.3860 0.8554
2 0.9996 0.7745 0.8478 0.2059 0.4129 0.8418
3 1.1700 0.8586 0.8077 0.1527 0.3696 0.8625
4 1.0084 0.7906 0.8086 0.1527 0.3522 0.8883
5 0.8264 0.7527 0.8518 0.2032 0.4026 0.8722
6 0.9030 0.8001 0.8137 0.1548 0.3452 0.8903
7 0.6175 0.6245 0.8598 0.1625 0.3529 0.9092
8 0.8206 0.7199 0.8606 0.1641 0.3704 0.8974
9 0.8677 0.7458 0.8135 0.1276 0.3181 0.9353
10 1.1941 0.8494 0.8032 0.1128 0.2967 0.9112
Mean 0.9179 0.7567 0.8342 0.1625 0.3607 0.8864
Standard Deviation 0.1694 0.0725 0.0260 0.0286 0.0340 0.0272
Table 10. Performance of GMR model.
Dataset Day (6 am ≤T< 6 pm) Night (6 am > T≥6 pm)
Evaluation Metrics MSE MAE R2 MSE MAE R2
Data Partitions
1 1.0034 0.8142 0.8114 0.2711 0.3979 0.8639
2 1.1024 0.9153 0.8086 0.3355 0.4788 0.8048
3 0.7135 0.6805 0.8705 0.3422 0.5282 0.8353
4 1.0761 0.7332 0.8332 0.2167 0.3740 0.8048
5 1.1896 0.7592 0.8136 0.3085 0.4268 0.8047
6 0.5784 0.6214 0.8695 0.3792 0.5211 0.8161
7 0.7303 0.7001 0.8395 0.4096 0.5367 0.8080
8 0.9089 0.7975 0.8516 0.2344 0.3806 0.8385
9 1.0557 0.8240 0.8275 0.2369 0.4214 0.8386
10 0.7636 0.6743 0.8371 0.2072 0.3879 0.8166
Mean 0.9122 0.752 0.8363 0.2941 0.4453 0.8231
Standard Deviation 0.1936 0.0831 0.0212 0.0676 0.0615 0.0190
Electronics 2025,14, 1471 14 of 21
Table 11. Performance of RFR model.
Dataset Day (6 am ≤T< 6 pm) Night (6 am > T≥6 pm)
Evaluation Metrics MSE MAE R2 MSE MAE R2
Data Partitions
1 0.5973 0.5847 0.8756 0.1559 0.3446 0.9193
2 0.6240 0.6339 0.8941 0.1927 0.3705 0.8921
3 0.8293 0.7137 0.8638 0.2627 0.4520 0.8857
4 0.4969 0.4997 0.8838 0.2396 0.4048 0.8789
5 0.5932 0.5428 0.8783 0.1909 0.3433 0.8805
6 0.6726 0.6320 0.8363 0.1529 0.2877 0.9303
7 0.9886 0.7718 0.8336 0.2348 0.3897 0.8654
8 0.7870 0.6085 0.8624 0.1820 0.3461 0.8999
9 0.9238 0.6911 0.8279 0.2150 0.3665 0.8812
10 0.8105 0.6712 0.8711 0.1887 0.3021 0.8689
Mean 0.7323 0.6349 0.8627 0.2015 0.3607 0.8902
Standard Deviation 0.1514 0.0771 0.0216 0.0342 0.0456 0.0199
Graphical representations of the mean values for these models are displayed in
Figures 8a and 8b
, for the daytime and nighttime patterns, respectively. These results
showed that the mean R
2
values for the FFC-ANN model were higher, while the mean MSE
and MAE were lower compared to the other AI models for both the daytime and nighttime
patterns, suggesting good performance of the ANN model for this study. Therefore, the
predicted charging duration obtained by the FFC-ANN model was integrated with defined
objective functions for optimization.
Electronics 2025, 14, x FOR PEER REVIEW 15 of 23
(a)
(b)
Figure 8. Comparison between different AI Models: (a) daytime paern and (b) nighime paern.
3.5. Optimization of Power by Different Objective Functions
Based on the time of training dataset, the scheduling for charging sessions on 28
October 2019 was used for optimization. The predicted charging durations from both the
day and night paerns on this date were integrated into the third and fourth objective
functions. The optimization process for the second and fourth objective functions utilized
the net demand data sourced from the California Independent System Operator (ISO) [18]
for the entire day. The paerns of these data are shown in Figure 9.
The system demand trend, measured in megawas, was compared with forecasted
demand in 5 min intervals. The net demand trend, defined as system demand minus wind
and solar, was also presented in 5 min increments, compared to the total system to forecast
demand, and used for optimization.
Figure 8. Comparison between different AI Models: (a) daytime pattern and (b) nighttime pattern.
Electronics 2025,14, 1471 15 of 21
3.5. Optimization of Power by Different Objective Functions
Based on the time of training dataset, the scheduling for charging sessions on
28
October
2019 was used for optimization. The predicted charging durations from both
the day and night patterns on this date were integrated into the third and fourth objective
functions. The optimization process for the second and fourth objective functions utilized
the net demand data sourced from the California Independent System Operator (ISO) [
18
]
for the entire day. The patterns of these data are shown in Figure 9.
Electronics 2025, 14, x FOR PEER REVIEW 16 of 23
Figure 9. California ISO power data in MW.
The optimization of the charging strategy was assessed by applying the optimized
po wer d ata to e ach i ndi vid ual c har gin g sta tio n. Figure 10 (a) and (b) display the optimized
power results (in kW) for station IDs AG-1F10 and AG-4F3, respectively, across objective
functions U1, U2, U3, and U4. The results indicated that objective function U4 demonstrated
superior performance by achieving faster or earlier charging completion and contributing
to a smoother duck curve. Additionally, U2 was effective in smoothing the duck curve,
while U3 prioritized early charging. Practitioners can balance different objective
weightings based on operational priorities, such as faster charging or smoother duck
curve, as shown in objective function U4.
Three charging sessions were selected, with two sessions from the AG-1F10 charging
station, charging duration from 5AM to 8AM, as well as from 3PM to 8PM, respectively,
and one session from the AG-4F38 charging station from 8AM to 3PM. These three
sessions represented a possible charging window from 4AM to 8PM within a single day.
It was observed that linear optimization strategy, with U1 as the objective function,
showed spikes in power demand near the end of the charging duration. The charging
strategy with U3 demonstrated earlier charging activities with reduced end-of-session
spikes for all three selected charging sessions. The charging strategy with U2 as the
objective function resulted in a smooth power demand curve without end-of-session
spikes, although minor fluctuations may still be present. The charging strategy using U4
achieved both a smooth power profile and an earlier completion of most charging de-
mands.
Figure 9. California ISO power data in MW.
The system demand trend, measured in megawatts, was compared with forecasted
demand in 5 min intervals. The net demand trend, defined as system demand minus wind
and solar, was also presented in 5 min increments, compared to the total system to forecast
demand, and used for optimization.
The optimization of the charging strategy was assessed by applying the optimized
power data to each individual charging station. Figures 10a and 10b display the optimized
power results (in kW) for station IDs AG-1F10 and AG-4F3, respectively, across objective
functions U
1
, U
2
, U
3
, and U
4
. The results indicated that objective function U
4
demonstrated
superior performance by achieving faster or earlier charging completion and contributing
to a smoother duck curve. Additionally, U
2
was effective in smoothing the duck curve,
while U
3
prioritized early charging. Practitioners can balance different objective weightings
based on operational priorities, such as faster charging or smoother duck curve, as shown
in objective function U4.
Three charging sessions were selected, with two sessions from the AG-1F10 charging
station, charging duration from 5AM to 8AM, as well as from 3PM to 8PM, respectively,
and one session from the AG-4F38 charging station from 8AM to 3PM. These three sessions
represented a possible charging window from 4AM to 8PM within a single day. It was
observed that linear optimization strategy, with U
1
as the objective function, showed
spikes in power demand near the end of the charging duration. The charging strategy
with U
3
demonstrated earlier charging activities with reduced end-of-session spikes for all
three selected charging sessions. The charging strategy with U
2
as the objective function
resulted in a smooth power demand curve without end-of-session spikes, although minor
fluctuations may still be present. The charging strategy using U
4
achieved both a smooth
power profile and an earlier completion of most charging demands.
Electronics 2025,14, 1471 16 of 21
Electronics 2025, 14, x FOR PEER REVIEW 17 of 23
(a)
(b)
Figure 10. Power (kW) by objective functions: U
1
: Linear charging schedule; U
2
: Duck curve
smoothing; U
3
: Early/Quick Charging; U
4
: Early Charging + Duck curve smoothing for sessions at
(a) Station ID AG-1F10 and (b) Station ID AG-4F38.
3.6. Impacts of EV integration on electric power grid
The state of California in the United States has set a goal for 100% zero-emission vehicle
(ZEV) new-car sales by 2035. It is anticipated that around 5 million EVs will be on the road
by 2030, with a target of 1.5 million EVs by 2025. A comparison of various scenarios—1.5
million, 3 million, and 5 million EVs integrated into the power grid—reveals that such
Figure 10. Power (kW) by objective functions: U
1
: Linear charging schedule; U
2
: Duck curve
smoothing; U
3
: Early/Quick Charging; U
4
: Early Charging + Duck curve smoothing for sessions at
(a) Station ID AG-1F10 and (b) Station ID AG-4F38.
3.6. Impacts of EV Integration on Electric Power Grid
The state of California in the United States has set a goal for 100% zero-emission
vehicle (ZEV) new-car sales by 2035. It is anticipated that around 5 million EVs will
be on the road by 2030, with a target of 1.5 million EVs by 2025. A comparison of
various
scenarios—1.5 million
, 3 million, and 5 million EVs integrated into the power
Electronics 2025,14, 1471 17 of 21
grid—reveals
that such integrations lead to increased fluctuations in grid stability, as illus-
trated in Figure 11. The figure was generated using the net power demands recorded on
28 October 2019.
Electronics 2025, 14, x FOR PEER REVIEW 18 of 23
integrations lead to increased fluctuations in grid stability, as illustrated in Figure 11. The
figure was generated using the net power demands recorded on 28 October 2019.
Figures 12 and 13 demonstrate that, with the proposed AI-driven charging strategies
with U2 and U4 objective functions, grid fluctuations (such as those seen in the “duck
curve”) are reduced, while charging is completed in a desirable charging duration with
1.5, 3, and 5 million EVs. Compared to the duck curves in Figure 10, the proposed charging
strategies can reduce the peak power demand for smooth duck curves, suggesting the
effectiveness of the proposed charging strategies. The peak power consumption reaches
around 22,000 MW without EVs, 25,000 MW for 1.5 million EVs, 28,000 MW for 3 million
EVs, and 35,000 MW for 5 million EVs without any charging strategy. By implementing
an AI-driven optimal charging optimization strategy that considers both early charging
and duck curve smoothing, the peak demand is reduced by approximately 16% for 1.5
million EVs, 21.43% for 3 million EVs, and 34.29% for 5 million EVs.
Figure 14 showed the duck curves with the integration of 10% of 1.5 million EVs into
the system. Due to lesser EVs being integrated, the impact on charging power demands
caused by EV charging requests is limited. The charging strategies with U
2 and U4
objective functions still show a beer performance as compared to the case with a non-
optimal charging strategy.
Figure 11. Duck curves generated without adopting AI-driven strategy with 1.5 million, 3 million,
and 5 million EVs.
Figure 11. Duck curves generated without adopting AI-driven strategy with 1.5 million, 3 million,
and 5 million EVs.
Figures 12 and 13 demonstrate that, with the proposed AI-driven charging strategies
with U
2
and U
4
objective functions, grid fluctuations (such as those seen in the “duck
curve”) are reduced, while charging is completed in a desirable charging duration with 1.5,
3, and 5 million EVs. Compared to the duck curves in Figure 10, the proposed charging
strategies can reduce the peak power demand for smooth duck curves, suggesting the
effectiveness of the proposed charging strategies. The peak power consumption reaches
around 22,000 MW without EVs, 25,000 MW for 1.5 million EVs, 28,000 MW for 3 million
EVs, and 35,000 MW for 5 million EVs without any charging strategy. By implementing an
AI-driven optimal charging optimization strategy that considers both early charging and
duck curve smoothing, the peak demand is reduced by approximately 16% for 1.5 million
EVs, 21.43% for 3 million EVs, and 34.29% for 5 million EVs.
Electronics 2025, 14, x FOR PEER REVIEW 19 of 23
Figure 12. Duck curves generated by adopting AI-driven strategy using U2 objective function with
1.5 million, 3 million, and 5 million EVs.
Figure 13. Duck curves generated by adopting AI-driven strategy using U4 objective function with
1.5 million, 3 million, and 5 million EVs.
Figure 12. Duck curves generated by adopting AI-driven strategy using U
2
objective function with
1.5 million, 3 million, and 5 million EVs.
Electronics 2025,14, 1471 18 of 21
Electronics 2025, 14, x FOR PEER REVIEW 19 of 23
Figure 12. Duck curves generated by adopting AI-driven strategy using U2 objective function with
1.5 million, 3 million, and 5 million EVs.
Figure 13. Duck curves generated by adopting AI-driven strategy using U4 objective function with
1.5 million, 3 million, and 5 million EVs.
Figure 13. Duck curves generated by adopting AI-driven strategy using U4 objective function with
1.5 million, 3 million, and 5 million EVs.
Figure 14 showed the duck curves with the integration of 10% of 1.5 million EVs into
the system. Due to lesser EVs being integrated, the impact on charging power demands
caused by EV charging requests is limited. The charging strategies with U
2
and U
4
objective
functions still show a better performance as compared to the case with a non-optimal
charging strategy.
Electronics 2025, 14, x FOR PEER REVIEW 20 of 23
Figure 14. Duck curves generated for 10% of total of 1.5 million EVs with and without adopting AI-
driven strategies.
4. Conclusions
Electric vehicles (EVs) are key solutions in intelligent transportation systems, due to
their efficiency and reduced emissions. The efficient scheduling of EV charging is crucial
for optimizing performance and grid stability. This research presents an AI-integrated
optimal charging strategy aimed at enabling early charging and smoothing the power
grid’s duck curve. Data from Caltech’s Adaptive Charging Network (ACN) at NASA’s Jet
Propulsion Laboratory (JPL) were collected and divided into day and night charging
paerns to predict the charging duration based on key input features, as follows: start
charging time and energy requested. The predicted charging duration was then
incorporated into optimization objective functions to enhance charging efficiency.
Furthermore, the impacts of integrating 1.5 million, 3 million, and 5 million EVs were
analyzed to assess system performance under the different levels of EV adoption. The
proposed AI-based charging strategies integrated four different objective functions for
optimization and showed the effectiveness of the charging strategies with various levels
of EV adoption.
It is worth mentioning that discrepancies in the grid demand forecasts and variations
in EV usage rates might pose significant challenges for real-world implementation. Since
inconsistencies in demand forecasting models can impact the performance of AI-based
charging strategies, the sensitivity of these results largely depends on forecasting
accuracy. Unexpected grid disturbances, seasonal fluctuations in consumer demand, or
sudden increases in EV usage may cause deviations from the optimal charging schedules.
In addition, the proposed strategies can be enhanced by incorporating more factors such
as adaptive pricing and incentives to promote off-peak charging, and baery energy
storage systems can help manage high loads. In addition, the current research focuses on
level 2 charging infrastructure, which is widely used for workplace and residential
Figure 14. Duck curves generated for 10% of total of 1.5 million EVs with and without adopting
AI-driven strategies.
4. Conclusions
Electric vehicles (EVs) are key solutions in intelligent transportation systems, due to
their efficiency and reduced emissions. The efficient scheduling of EV charging is crucial for
optimizing performance and grid stability. This research presents an AI-integrated optimal
charging strategy aimed at enabling early charging and smoothing the power grid’s duck
curve. Data from Caltech’s Adaptive Charging Network (ACN) at NASA’s Jet Propulsion
Laboratory (JPL) were collected and divided into day and night charging patterns to predict
the charging duration based on key input features, as follows: start charging time and
Electronics 2025,14, 1471 19 of 21
energy requested. The predicted charging duration was then incorporated into optimization
objective functions to enhance charging efficiency. Furthermore, the impacts of integrating
1.5 million, 3 million, and 5 million EVs were analyzed to assess system performance under
the different levels of EV adoption. The proposed AI-based charging strategies integrated
four different objective functions for optimization and showed the effectiveness of the
charging strategies with various levels of EV adoption.
It is worth mentioning that discrepancies in the grid demand forecasts and variations
in EV usage rates might pose significant challenges for real-world implementation. Since
inconsistencies in demand forecasting models can impact the performance of AI-based
charging strategies, the sensitivity of these results largely depends on forecasting accuracy.
Unexpected grid disturbances, seasonal fluctuations in consumer demand, or sudden
increases in EV usage may cause deviations from the optimal charging schedules. In
addition, the proposed strategies can be enhanced by incorporating more factors such as
adaptive pricing and incentives to promote off-peak charging, and battery energy storage
systems can help manage high loads. In addition, the current research focuses on level
2 charging infrastructure, which is widely used for workplace and residential charging.
Future work will extend this approach to DC fast charging, enabling real-time optimization
for high-power charging stations. To prevent extreme peaks in the grid load while extending
the study to DC fast charging infrastructure, the optimization approach would need to
incorporate strategies such as load shifting, dynamic charging rates, the prioritization of
charging schedules, energy storage, and advanced multi-objective optimization techniques.
These adjustments can ensure that the high power demand associated with DC fast charging
is managed effectively while maintaining grid stability. Furthermore, integrating state of
health (SOH) estimation into the optimal charging strategy framework can improve the
accuracy of cost evaluations in vehicle-to-grid systems.
Author Contributions: Conceptualization, U.J., R.J.A., S.A. and Y.-F.J.; methodology, U.J., S.A. and
Y.-F.J.; software, U.J. and R.J.A.; validation, U.J. and R.J.A.; formal analysis, U.J.; investigation, U.J. and
Y.-F.J.; resources, S.A. and Y.-F.J.; data curation, U.J. and R.J.A.; writing—original draft preparation,
U.J.; writing—review and editing, S.A. and Y.-F.J.; supervision, Y.-F.J.; project administration, Y.-F.J.;
funding acquisition, S.A. and Y.-F.J. All authors have read and agreed to the published version of
the manuscript.
Funding: The authors acknowledge financial support for this research, authorship, and/or publica-
tion from the U.S. National Science Foundation (#2051113) and the U.S. Department of Transportation
through the Transportation Consortium of South-Central States (Tran-SET) under projects 21034
and 21049.
Data Availability Statement: The original contributions presented in this study are included in the
article. Further inquiries can be directed to the corresponding author.
Conflicts of Interest: The authors declare no conflicts of interest.
References
1.
U.S. Energy Information Administration. Use of Energy Explained. Available online: https://www.eia.gov/energyexplained/
use-of-energy/transportation-in-depth.php (accessed on 12 January 2025).
2.
Mohanty, S.; Panda, S.; Parida, S.M.; Rout, P.K.; Sahu, B.K.; Bajaj, M.; Zawbaa, H.M.; Kumar, N.M.; Kamel, S. Demand side
management of electric vehicles in smart grids: A survey on strategies, challenges, modeling, and optimization. Energy Rep. 2022,
8, 12466–12490.
3.
Das, H.S.; Rahman, M.M.; Li, S.; Tan, C. Electric vehicles standards, charging infrastructure, and impact on grid integration: A
technological review. Renew. Sustain. Energy Rev. 2020,120, 109618. [CrossRef]
4.
Rajper, S.Z.; Albrecht, J. Prospects of electric vehicles in the developing countries: A literature review. Sustainability 2020,12, 1906.
[CrossRef]
5. Rapson, D.S.; Muehlegger, E. The economics of electric vehicles. Rev. Environ. Econ. Policy 2023,17, 274–294. [CrossRef]
Electronics 2025,14, 1471 20 of 21
6.
Ahmad, A.; Khalid, M.; Ullah, Z.; Ahmad, N.; Aljaidi, M.; Malik, F.A.; Manzoor, U. Electric vehicle charging modes, technologies
and applications of smart charging. Energies 2022,15, 9471. [CrossRef]
7.
Tie, S.F.; Tan, C.W. A review of energy sources and energy management system in electric vehicles. Renew. Sustain. Energy Rev.
2013,20, 82–102.
8.
Hussain, M.T.; Sulaiman, N.B.; Hussain, M.S.; Jabir, M. Optimal Management strategies to solve issues of grid having Electric
Vehicles (EV): A review. J. Energy Storage 2021,33, 102114.
9.
Elghanam, E.; Abdelfatah, A.; Hassan, M.S.; OSMAN, A. Optimization techniques in electric vehicle charging scheduling, routing
and spatio-temporal demand coordination: A systematic review. IEEE Open J. Veh. Technol. 2024,5, 1294–1313.
10.
Zhao, Y.; Guo, Y.; Guo, Q.; Zhang, H.; Sun, H. Deployment of the electric vehicle charging station considering existing competitors.
IEEE Trans. Smart Grid 2020,11, 4236–4248.
11.
Xiong, Y.; An, B.; Kraus, S. Electric vehicle charging strategy study and the application on charging station placement. Auton.
Agents Multi-Agent Syst. 2021,35, 1–19.
12.
Moghaddam, Z.; Ahmad, I.; Habibi, D.; Phung, Q.V. Smart charging strategy for electric vehicle charging stations. IEEE Trans.
Transp. Electrif. 2017,4, 76–88. [CrossRef]
13.
Hanemann, P.; Behnert, M.; Bruckner, T. Effects of electric vehicle charging strategies on the German power system. Appl. Energy
2017,203, 608–622. [CrossRef]
14.
Soliman, I.A.; Tulsky, V.; Abd el-Ghany, H.A.; ElGebaly, A.E. Efficient allocation of capacitors and vehicle-to-grid integration with
electric vehicle charging stations in radial distribution networks. Appl. Energy 2025,377, 124745. [CrossRef]
15.
Ramkumar, A.; Rajesh, K. A design analysis of EV charging using multiport converter and control strategy using MWOA.
J. Energy Storage 2025,106, 114735.
16.
Lepolesa, L.J.; Adetunji, K.E.; Ouahada, K.; Liu, Z.; Cheng, L. Optimal EV Charging Strategy for Distribution Networks Load
Balancing in a Smart Grid Using Dynamic Charging Price. IEEE Access 2024,12, 47421–47432. [CrossRef]
17.
Khan, M.R.; Haider, Z.M.; Malik, F.H.; Almasoudi, F.M.; Alatawi, K.S.S.; Bhutta, M.S. A comprehensive review of microgrid
energy management strategies considering electric vehicles, energy storage systems, and AI techniques. Processes 2024,12, 270.
[CrossRef]
18.
Yadav, K.; Singh, M. A novel energy management of public charging stations using attention-based deep learning model. Electr.
Power Syst. Res. 2025,238, 111090. [CrossRef]
19.
Arévalo, P.; Ochoa-Correa, D.; Villa-Ávila, E. A systematic review on the integration of artificial intelligence into energy
management systems for electric vehicles: Recent advances and future perspectives. World Electr. Veh. J. 2024,15, 364. [CrossRef]
20.
Recalde, A.; Cajo, R.; Velasquez, W.; Alvarez-Alvarado, M.S. Machine Learning and Optimization in Energy Management Systems
for Plug-In Hybrid Electric Vehicles: A Comprehensive Review. Energies 2024,17, 3059. [CrossRef]
21.
Alansari, M.; Al-Sumaiti, A.S.; Abughali, A. Optimal placement of electric vehicle charging infrastructures utilizing deep learning.
IET Intell. Transp. Syst. 2024,18, 1529–1544. [CrossRef]
22.
Shern, S.J.; Sarker, M.T.; Ramasamy, G.; Thiagarajah, S.P.; Al Farid, F.; Suganthi, S. Artificial Intelligence-Based Electric Vehicle
Smart Charging System in Malaysia. World Electr. Veh. J. 2024,15, 440. [CrossRef]
23.
Cavus, M.; Dissanayake, D.; Bell, M. Next Generation of Electric Vehicles: AI-Driven Approaches for Predictive Maintenance and
Battery Management. Energies 2025,18, 1041. [CrossRef]
24.
Khan, M.A.; Saleh, A.M.; Waseem, M.; Sajjad, I.A. Artificial intelligence enabled demand response: Prospects and challenges in
smart grid environment. Ieee Access 2022,11, 1477–1505.
25.
Lin, J.; Qiu, J.; Liu, G.; Yao, Z.; Yuan, Z.; Lu, X. A Fuzzy Logic Approach to Power System Security with Non-Ideal Electric Vehicle
Battery Models in Vehicle-to-Grid Systems. IEEE Internet Things J. 2025. [CrossRef]
26.
Tian, X.; Zhou, S.; Hao, H.; Ruan, H.; Gaddam, R.R.; Dutta, R.C.; Zhu, T.; Wang, H.; Wu, B.; Brandon, N.P. Machine learning and
density functional theory for catalyst and process design in hydrogen production. Chain 2024,1, 150–166.
27.
Hassan, Q.; Azzawi, I.D.; Sameen, A.Z.; Salman, H.M. Hydrogen fuel cell vehicles: Opportunities and challenges. Sustainability
2023,15, 11501. [CrossRef]
28.
Bree, G.; Hao, H.; Stoeva, Z.; Low, C.T.J. Monitoring state of charge and volume expansion in lithium-ion batteries: An approach
using surface mounted thin-film graphene sensors. RSC Adv. 2023,13, 7045–7054. [CrossRef]
29.
Dini, P.; Saponara, S.; Colicelli, A. Overview on battery charging systems for electric vehicles. Electronics 2023,12, 4295. [CrossRef]
30.
Cadete, E.; Alva, R.; Zhang, A.; Ding, C.; Xie, M.; Ahmed, S.; Jin, Y. Deep learning tackles temporal predictions on charging loads
of electric vehicles. In Proceedings of the 2022 IEEE Energy Conversion Congress and Exposition (ECCE), Detroit, MI, USA, 9–13
October 2022; pp. 1–6.
31.
Siddiqui, J.; Ahmed, U.; Amin, A.; Alharbi, T.; Alharbi, A.; Aziz, I.; Khan, A.R.; Mahmood, A. Electric Vehicle charging station
load forecasting with an integrated DeepBoost approach. Alex. Eng. J. 2025,116, 331–341. [CrossRef]
32.
Shanmuganathan, J.; Victoire, A.A.; Balraj, G.; Victoire, A. Deep learning LSTM recurrent neural network model for prediction of
electric vehicle charging demand. Sustainability 2022,14, 10207. [CrossRef]
Electronics 2025,14, 1471 21 of 21
33.
Almaghrebi, A.; Aljuheshi, F.; Rafaie, M.; James, K.; Alahmad, M. Data-driven charging demand prediction at public charging
stations using supervised machine learning regression methods. Energies 2020,13, 4231. [CrossRef]
34.
Li, C.; Dong, Z.; Chen, G.; Zhou, B.; Zhang, J.; Yu, X. Data-driven planning of electric vehicle charging infrastructure: A case
study of Sydney, Australia. IEEE Trans. Smart Grid 2021,12, 3289–3304. [CrossRef]
35.
Boulakhbar, M.; Farag, M.; Benabdelaziz, K.; Kousksou, T.; Zazi, M. A deep learning approach for prediction of electrical vehicle
charging stations power demand in regulated electricity markets: The case of Morocco. Clean. Energy Syst. 2022,3, 100039.
36.
Ran, J.; Gong, Y.; Hu, Y.; Cai, J. EV load forecasting using a refined CNN-LSTM-AM. Electr. Power Syst. Res. 2025,238, 111091.
[CrossRef]
37.
Straka, M.; De Falco, P.; Ferruzzi, G.; Proto, D.; Van Der Poel, G.; Khormali, S.; Buzna, L. Predicting popularity of electric vehicle
charging infrastructure in urban context. IEEE Access 2020,8, 11315–11327.
38.
Soldan, F.; Bionda, E.; Mauri, G.; Celaschi, S. Short-term forecast of electric vehicle charging stations occupancy using big data
streaming analysis. In Proceedings of the 2021 IEEE International Conference on Environment and Electrical Engineering and
2021 IEEE Industrial and Commercial Power Systems Europe (EEEIC/I&CPS Europe), Bari, Italy, 7–10 September 2021; pp. 1–6.
39.
Mouaad, B.; Farag, M.; Kawtar, B.; Tarik, K.; Malika, Z. A deep learning approach for electric vehicle charging duration prediction
at public charging stations: The case of Morocco. ITM Web Conf. 2022,43, 01024.
40.
Ullah, I.; Liu, K.; Yamamoto, T.; Zahid, M.; Jamal, A. Prediction of electric vehicle charging duration time using ensemble machine
learning algorithm and Shapley additive explanations. Int. J. Energy Res. 2022,46, 15211–15230.
41.
Lu, X.; Qiu, J.; Lei, G.; Zhu, J. State of health estimation of lithium iron phosphate batteries based on degradation knowledge
transfer learning. IEEE Trans. Transp. Electrif. 2023,9, 4692–4703. [CrossRef]
42.
U.S. Department of Transportation. Charger Types and Speeds. Available online: https://www.transportation.gov/rural/ev/
toolkit/ev-basics/charging-speeds (accessed on 23 October 2024).
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.
Content uploaded by Umar Jamil
Author content
All content in this area was uploaded by Umar Jamil on Apr 06, 2025
Content may be subject to copyright.
