Available via license: CC BY 4.0
Content may be subject to copyright.
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
VOLUME XX, 2017 1
Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.
Digital Object Identifier 10.1109/ACCESS.2017.Doi Number
Prediction of EV Charging Behavior using
Machine Learning
Sakib Shahriar1, A. R. Al-Ali1, (Life Senior Member, IEEE), Ahmed H. Osman2, (Senior
Member, IEEE), Salam Dhou1, (Member, IEEE), and Mais Nijim3, (Member, IEEE)
1 Computer Science and engineering, Department American University of Sharjah, Sharjah, UAE
2 Electrical Engineering Department, Department American University of Sharjah, Sharjah, UAE
3 Electrical Engineering and Computer Science Department, Texas A&M University – Kingsville, Kingsville, TX 78363 USA
Corresponding author: A. R. Al-Ali (e-mail: aali@aus.edu).
ABSTRACT As a key pillar of smart transportation in smart city applications, electric vehicles (EVs) are
becoming increasingly popular for their contribution in reducing greenhouse gas emissions. One of the key
challenges, however, is the strain on power grid infrastructure that comes with large-scale EV deployment.
The solution to this lies in utilization of smart scheduling algorithms to manage the growing public charging
demand. Using data-driven tools and machine learning algorithms to learn the EV charging behavior can
improve scheduling algorithms. Researchers have focused on using historical charging data for predictions
of behavior such as departure time and energy needs. However, variables such as weather, traffic, and nearby
events, which have been neglected to a large extent, can perhaps add meaningful representations, and provide
better predictions. Therefore, in this paper we propose the usage of historical charging data in conjunction
with weather, traffic, and events data to predict EV session duration and energy consumption using popular
machine learning algorithms including random forest, SVM, XGBoost and deep neural networks. The best
predictive performance is achieved by an ensemble learning model, with SMAPE scores of 9.9% and 11.6%
for session duration and energy consumptions, respectively, which improves upon the existing works in the
literature. In both predictions, we demonstrate a significant improvement compared to previous work on the
same dataset and we highlight the importance of traffic and weather information for charging behavior
predictions.
INDEX TERMS Electric vehicles (EVs), charging behavior, machine learning, smart city, smart
transportation
I.
INTRODUCTION
Climate change has become a growing concern in recent years
with thirty-three countries jointly declaring a climate
emergency as of January 2021 [1]. Global energy
consumption is a major contributor to the climate crisis, and in
particular, the transportation sector accounts for over a quarter
of the global energy consumption [2]. The United Nations
(UN) projects that two thirds of the world’s population will
reside in urban areas by 2050 [3]. This would increase the
demand for urban mobility, leading to further energy
consumption and emissions of greenhouse gases. Studies have
shown that electric vehicles (EVs) have the potential to reduce
carbon emissions by 45% compared to conventional internal
combustion engine (ICE) vehicles [4]. EVs were initially
limited by factors such as reliability and battery range, which
have significantly improved in recent years and led to an
increase in EV popularity [5]. As a result, the trust in EV
reliability has grown and satisfaction among EV owners are
higher [6]. The driver flexibility has also increased with the
addition of charging stations in many parts of the world, often
lead by various government initiatives encouraging further
adoption of EVs. These factors have placed EVs to be in a pole
position with regards to providing a clean source of
transportation.
There still remains a few challenges, most notably the
charging time and public charging needs, despite the
promising potential. Although EV charging time has
significantly decreased over the years, it is still on average
much higher than the refueling time for ICE vehicles.
Emerging charging technologies such as extreme fast
charging [7] and wireless charging [8] are promising but are
still overcoming various challenges and will require years
before being adopted. The constraints from charging
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
infrastructure means that most EV owners rely on public
charging stations, which poses a strain on power distribution
grid due to the high-power requirements of the EVs [9]. To
avoid power grid degradation and failures, un-coordinated
charging behavior must be avoided. The optimal solution is
to better manage the scheduling of charging stations. The
research on smart scheduling using data driven approaches
are plentiful and include optimization [10] and metaheuristic
[11] approaches. Furthermore, psychological factors
influencing charging behavior [12] as well as transactions
data and interviews with EV drivers [13] have been used for
charging behavior analysis. A comprehensive review of
charging behavior analysis using machine learning and data-
driven approaches is presented in [14], which concludes that
machine learning based approaches are more suitable to
scheduling approaches with the ability to provide
quantification and more realistic representation.
A.
RELATED WORKS
Although predictions of EV charging behavior can have
various categories, the focus of this work will be on session
duration and energy consumption. Examples of other
charging behavior include the prediction of whether the EVs
will be charged the next day [15], identification of the use of
fast charging [16], prediction of the time to next plug [17],
charge profile prediction [18], charging speed prediction
[19] and prediction of charging capacity and the daily
charging times [20]. These behaviors provide valuable
insights, but the prediction of session duration and energy
time is more valuable for scheduling purposes.
As will be defined in the following sections, session
duration is directly related to the departure time. It is the
arrival time, which is a known variable, minus the departure
time. Therefore, one can assume the prediction of either the
session duration or the departure time to have the same
application. Lee et al. [21] introduced a novel dataset for
non-residential EV charging consisting of over 30000
charging sessions. They used gaussian mixture models
(GMM) to predict session duration and energy needs by
considering the distribution of the known arrival times. The
testing dataset included the month of December 2018 and the
reported symmetric mean absolute percentage errors
(SMAPEs) were 14.4% and 15.9% for the session duration
and energy consumption, respectively. In this work, only
historical charging data was considered for obtaining the
predictions. In [22], the authors used support vector
machines (SVM) for the prediction of arrival and departure
time for EV commuters in a university campus. Using
historical arrival and departure times and temporal features
i.e., week, day, and hour, the reported mean absolute
percentage error (MAPE) was 2.9% and 3.7% for arrival and
departure times, respectively. For comparison, a simple
persistence model was used as reference and SVM
hyperparameter tuning was not addressed in the work.
Frendo et al. [23] predicted the departure time of EVs using
regression models. Historical charging data was utilized, and
eight features were used including, car ID, car type,
weekday, charging point, car park location, parking floor and
arrival time. For prediction, three regression models were
trained namely, linear regression, XGBoost and artificial
neural network (ANN). XGBoost achieved the best results
with mean absolute error (MAE) of 82 minutes. In [24],
ensemble machine learning using SVM, random forest (RF)
and diffusion-based kernel density estimator (DKDE) was
used for session length and energy consumption predictions.
For training, historical charging records from two separate
datasets were used, with one of them being public and the
other being residential charging. The ensemble model
performed better than the individual models in both
predictions and the reported SMAPEs were 10.4% for
duration and 7.5% for the consumption.
TABLE I
SUMMARY OF RELATED WORKS
Source
Prediction
Model
Features
Results
[21]
Session
length,
energy
consumption
GMM
Historical
charging
data
SMAPE:
14.4%
duration,
15.9%
consumption
[22]
Arrival time,
departure
time
SVM
Historical
charging
data
MAPE:
2.9%
arrival,
3.7%
departure
[23]
Departure
time
XGBoost
Historical
charging
data, vehicle
type,
charging
location
MAE: 82
minutes
[24]
Session
length,
energy
consumption
Ensemble
model of
SVM, RF
& DKDE
Historical
charging
data
SMAPE:
10.4%
duration,
7.5%
consumption
[25]
Start time,
session
length,
energy
consumption
Linear
regression
Historical
charging
data
-
[26]
Energy
requirements
XGBoost
Historical
charging
data, season,
weekday,
location
type,
charging
fees
R2: 0.52,
MAE: 4.6
kWh
[27]
Energy
consumption
k-NN
Last few
days energy
consumption
SMAPE:
15.3%
[28]
Energy
consumption
PSF
Last few
days energy
consumption
SMAPE:
14.1%
Xiong et al. [25] predicted the start time and session
duration using mean estimation. Session duration was then
used to obtain energy consumption predictions using linear
regression. The charging behavior predictions were integrated
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
to flatten the charging load profile and stabilize the power grid.
However, the prediction performances were not evaluated
quantitatively. In [26], several regression models were used to
predict the energy requirements from public charging stations
data for the US state of Nebraska. Besides historical charging
data, parameters such as season, weekday, location type and
charging fees were used as input features. On the test set,
XGBoost model outperformed linear regression, RF and SVM
obtaining a R2 score of 0.52 and MAE of 4.6 kWh. The authors
in [27] used k-nearest neighbor (k-NN) to predict the energy
consumption at a charging outlet using data from a university
campus. The problem was formulated as time-series forecast
whereby energy consumption prediction for the next day (next
24 hours) was made using energy consumption of previous
days. The highest SMAPE was 15.3% using k value of 1 (1-
NN) and a time-weighted dot product dissimilarity measure.
Similarly, Majidpour et al. [28] also predicted the next day
energy needs of a charging station based on previous days
energy consumption using various algorithms including SVM
and RF. They also experimented with pattern sequence-based
forecasting (PSF) [29], where clustering is first applied to
classify the days and predictions are made for that day. The
PSF-based approach provided the most accurate results with
average SMAPE value of 14.1%. Table 1 provides a summary
of the related works in the literature.
B.
OBJECTIVES
Although the above works from the literature have
successfully applied machine learning for the prediction of
session duration and energy consumption, they have mainly
focused on utilizing historical charging data. In some cases,
additional derived features such as vehicle information,
charging location information and seasonal information were
used. This has motivated us in this work to investigate the
use of additional input features including weather, traffic and
local events and observe its impact on the accuracy of
charging behavior predictions. The key contributions of this
work are the following:
1) We propose a novel approach in EV charging behavior
prediction that utilizes weather, traffic, and local
events data along with historical charging records.
2) We use several machine learning algorithms including
RF, SVM, XGBoost and ANN for predictions of
session duration and energy consumption on the
adaptive charging network (ACN) dataset.
3) We empirically show that the use of additional data has
a positive impact on the accuracy of predictions and
significantly improves upon the previous work on the
same dataset that used only historical charging
information.
The rest of the paper is organized as follows. Background
information including key concepts in machine learning is
provided in Section II. This is followed by a detailed
explanation of the methodology, including dataset description,
and experimental setup in Section III. Section IV presents and
discusses the results of this work. Future research directions
are provided in Section V, and Section VI concludes the paper.
II.
BACKGROUND
This section summarizes the background information
including the algorithms used in this work and the evaluation
metrics for predictions.
A.
SUPERVISED MACHINE LEARNING
The main objective in machine learning (ML) is to develop a
learning framework that can learn from experience, i.e., the
training dataset, without explicit programming. Primarily, ML
algorithms are classified as either supervised learning or
unsupervised learning. In unsupervised ML, the training data
is not labeled, and the goal of the algorithm is to group similar
data points. Conversely, in supervised learning, the models are
trained from labeled dataset that contains the specified output
or target variable, i.e., the variable to be predicted. The
representation between the input and target variable is learned
iteratively by optimizing a specific objective function. In this
work, the target variables, i.e., the session duration and the
energy consumption are both labeled, and thus supervised
learning will be used. Furthermore, since both target variables
are continuous values, we are going to use regression models
as opposed to classification models which deals with
categorical target values. The four regression models used in
this work are RF, SVM, XGBoost and deep ANN. The
following paragraphs describe each of them briefly.
A decision tree (DT) can be used to separate complex
decisions into a combination of simpler decisions using split
points from the input features. Leaf nodes are the points
where no further split is made whereas a decision node is the
point where decisions take place. Predictions are made by
taking the average value of all the items in the leaf node in
regression. Although simple to implement, a single DT is
prone to overfitting. To overcome this problem, multiple
DTs can be aggregated, and this is the essence of a random
forest (RF) algorithm. Bagging method is used in this case
where the trees are created from various bootstrap sample
which is sample with replacement. The average value of the
predictions across all the trees are taken as the final
prediction for regression problems [30].
Similar to a RF, a gradient boosting algorithm [31] makes
use of multiple DTs. However, in this algorithm each tree is
built sequentially and as a result the errors made by previous
trees are taken into consideration which often leads to
superior performance. XGBoost [32] is a more recent
variation of the gradient boosting algorithm. XGBoost has
gained popularity over the last few years for its success in
machine learning competitions mainly due to it being
effective in dealing with the bias-variance tradeoff [33]. This
means that the algorithm is able to avoid overfitting on the
training data while at the same time maintaining enough
complexity to obtain meaningful representations.
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
A support vector machine (SVM) [34] is used for both
classification and regression problems. It is sometimes
referred to as support vector regression [35] when
exclusively applied to regression problems. SVM separates
the classes with the best hyperplane that can maximize the
margin between the respective classes. The key objective is
to map the inputs to high dimensional feature spaces where
they are linearly separable. This is achieved using kernels
such as linear, polynomial, and radial basis function (RBF).
SVM is not suitable for larger datasets due to its long training
time.
Deep learning-based models contain a large amount of
composition of learned functions. Using layered hierarchy of
concepts, complex concepts are defined in terms of simpler
concepts and more abstract representations are gathered
using less abstract ones [36]. Variations of deep learning
algorithms include convolutional and recurrent neural
networks, which have been successful in image and audio
classification tasks. In this work, we consider artificial neural
networks (ANN), often referred to as a multilayer perceptron
(MLP). MLPs utilize non-linear approximation given a set of
input features and can be used for both regression and
classification. An MLP consists of input layer which is fed
with a given set of input features, the hidden layers which
learns the representations and the output layer which makes
the final predictions. When the number of hidden layers is
two or more, the model is referred to as deep ANN.
In ensemble learning, set of individually trained classifiers
are combined and then used to predict new instances, often
providing more accurate predictive performance than the
individual classifiers [37]. Figure 1 illustrates the concept of
ensemble learning. Both RF and XGBoost are examples of
ensemble learning, where individual models (in these cases
DTs) are first evaluated and then integrated into a single
model. The motivation behind such approach is similar to
asking multiple experts about an opinion, and then taking their
votes to make the final decision [38].
Figure 1. Illustration of ensemble learning
B.
EVALUATION OF REGRESSION MODELS
To assess the performance of predictions made by regression
models, numerous metrics are used as discussed in [39]. In this
work, we will define and use four measures that were
commonly used in related works. Equations (1)-(4) defines the
metrics that will be used in this work:
Root mean square error (RMSE):
!"#$%&%'()*!+*,!-"
#
!$% .%
(1)
Mean absolute error (MAE):
"/$%&%0
.%
12
*!+*,!
2
#
!$%
(2)
Coefficient of determination or R2:
!"&%0+()*!+*,!-"
#
!$%
(3*!+45"
#
!$%
(3)
Symmetric mean absolute percentage error (SMAPE):
#"/6$%&%0
.%
12
*!+*,!
2
)7
*!
7
8
2
*,!
2-
9:;0<<=
#
!$%
(4)
where
*
represents the actual value,
*,
is the predicted value,
4
is the average of the actual values and
.
represents the
groups of values in the dataset. Generally, lower scores of
RMSE, MAE and SMAPE indicate accurate predictions, and
this occurs when the predicted value,
*,
is very close to the
actual value
*
. The R2 value is a measure of goodness of fit for
regression and is usually a score between 0 and 1. A score of
1 indicates perfect predictions and generally a higher value
represents better performance. We do not consider mean
absolute percentage error because it is inconvenient when the
actual value
*
is close to 0, therefore creating a bias. Rather
we consider SMAPE which is more suitable for EV charging
prediction because both the original and the predicted values
are in the denominator [24].
III.
METHODOLOGY
In this section, we define the approach used for the prediction
of charging behavior. We formulate the problem, describe the
dataset, highlight the preprocessing steps, and discuss the
methods for training the learning models.
A.
EV CHARGING BEHAVIOR
Assuming
>&'#
represents the connection time when the car
first plugs in,
>(!)&'#
represents the disconnection time when
the car plugs out and leaves the station and
?
represents the
energy delivered to the car during the session, we consider the
session charging behavior
@)*))!'#
as following:
@)*))!'# %A%
3
>&'#B>(!)&'# B?
5
(5)
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
Based on the above, we can define the length of charging
session or the session duration,
#(+,
, as follows:
#(+, %&%>(!)&'# %+%>&'# %
(6)
In this work, we predict both the session duration and the
session energy consumption of an individual charging record
and assume that the connection time is known.
B.
DATASET DESCRIPTION
Besides the charging dataset, we also make use of weather,
traffic, and local events data in order to predict the charging
behavior. We will briefly describe the datasets used and
highlight their attributes.
Scheduling of EV charging is more significant in public
charging structures due to the unpredictable nature of the
charging behavior, especially in places like shopping malls.
The ACN [21] dataset is among the few publicly available
datasets for non-residential EV charging and will be utilized
in this work. The dataset contains charging records from two
stations in the university campus, namely JPL and Caltech.
Unlike the Caltech station, which is open to public, the JPL
station is only accessible to employees and therefore will not
be considered in this work. Registered users can manually
enter additional details, such as their estimated departure
time and requested energy, by scanning a QR code through
their mobile applications. The dataset can be accessed from
[40] by either a web portal or python application
programming interface (API).
Although there is a small weather station located at the
Caltech campus [41], we did not consider it for this work due
to missing values and irregular interval recordings for the wind
variable. Additionally, this station did not record variables
such as rainfall and snowfall which could potentially impact
charging behavior. We therefore used the weather data from
NASA’s Modern-Era Retrospective analysis for Research and
Applications, Version 2 (MERRA-2) [42] which provides data
for the precise location of the charging station. The accuracy
of satellite weather data in comparison to ground stations has
been compared in [43]. Although it has been shown that given
a specific location some weather parameters may be more
accurately detected using ground stations, for the purpose of
this work we do not require a high level of accuracy but rather
a more general perception of the impact of weather on
charging behaviors. For example, we are interested in
observing how the charging behavior is impacted during
heavy rainfall as opposed to drier conditions.
Obtaining historical traffic data for specific roads and
regions is challenging. Conventional traffic collection
methods include intrusive approaches such as road tubes and
piezoelectric sensors and non-intrusive approaches including
microwave radar and video image detection [44]. With most
of these approaches, scalability is an issue, and in most cases,
specific roads are not covered. For instance, the city of
Pasadena (where the charging data originates from) provides
an open data site [45] for the traffic count around the city.
However, for most roads in the city it contains traffic count for
some period of time and therefore is not usable in our case
where we require regular interval data. Additionally, not all
roads and streets are covered. As a result, we decided to use
traffic data from google maps, which has also been used in
previous machine learning applications [46]. The data is
collected by recording the location data from the commuter’s
mobile devices provided they use the application and have
agreed to share their location. The data collected from
individuals is anonymized and aggregated to address any
privacy concerns [47]. The google maps distance matrix API
can be used to retrieve the data. Given a source and destination
coordinates, the travel distance and the time taken is returned
for a given departure time. We retrieved historical trip time for
9 of the closest roads and streets which one must take to access
the charging station.
Since the charging station is located in the Caltech
university campus, we decided to include campus events and
find out if the number of events have an impact on the charging
behavior. The number of events in an hour were obtained from
the Caltech university website calendar [48]. For
simplification, we decided to round the minutes to the nearest
hour, therefore if an event started at 10.20 am, it was counted
as an event starting at 10 am.
C.
DATA PREPROCESSING
Cleaning and preprocessing the dataset is vital to ensuring
the quality of the predictive models. These include removing
faulty records and outliers.
The presence of outliers can negatively impact the model
performance. A common technique of graphically detecting
outliers is boxplots [49]. The boxplots for both target
variables contained outliers, as shown in Figure 2. We notice
that the outliers for both variables are not consistent, i.e., we
have far too many outlier points for energy consumption than
the session duration. It is possible that certain vehicles
consume far greater amount of energy even if the session
duration is not too long.
Figure 2. Boxplots of energy consumption (left), session duration (right)
As a result, we opted to perform multivariate outlier
detection using the isolation forest algorithm which constructs
an ensemble of iTrees for a given data set. The outliers are
those instances which have short average path lengths on the
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
iTrees [50]. By randomly selecting a variable and a split value
between the minimum and maximum of the selected variable,
the observations are ‘isolated’. Partitioning of observations are
repeated recursively until all of them have been isolated. After
the partitioning, observations that have shorter path lengths for
some particular points are likely to be the outliers. Figure 3
illustrates the process in detecting the outlier of the target
variables. A total of 697 outliers were detected which accounts
for 4% of the total observations.
Figure 3. Outlier detection using isolation forest
For the charging data, we only considered charging records
that were registered, i.e., contained user IDs, and this
accounted for 97% of the records. For the weather data, the
time of recording was in universal time and we used the pytz
[51] library in python to convert the time zone to be the same
as that of the charging records. We also converted the
temperature units from kelvin to degrees Celsius. Then for
each given hour, we also computed average of the previous 7
hours of weather and the average of the next 10 hours. This
would allow us to understand how the previous weather and
the weather after charging impacts charging decision. For
instance, heavy snowfall in the previous hours may account
for shorter charging duration and so on. We also had to convert
the time zone from coordinated universal time for the traffic
data. We then aggregated the traffic for each hour across the
nine selected roads and streets. It must be noted that we
considered the average trip time as well as the maximum trip
time as estimated by google maps. Finally, we aggregated the
total events in the campus for each hour.
To merge the various data, the time-series fields were
converted to date-time objects using pandas [52] library. Then
to obtain weather, traffic, and events for a particular charging
record, we first obtained the nearest hour that the connection
time belongs to. For example, the connection time of 22:11
belongs to 10 pm. This allows us to easily extract the other
information. Instead of simply selecting the traffic level for a
given time, we selected the total traffic after arrival until the
end of the day. If a vehicle arrived at 2 pm, for instance, we
accumulated the traffic from 2 pm until the end of that day.
This would allow the model to learn how the traffic level
impact the charging behavior. Similarly, we considered the
total events after arrival until the end of the day.
D.
FEATURE ENGINEERING
Feature engineering refers to the transformation of data into
meaningful representation using human knowledge. This
process is labor intensive but important nonetheless as this is
a weakness of the learning algorithms. Feature engineering
relies on human ingenuity and prior knowledge to
compensate for the inability of the algorithms to extract and
organize the discriminative information from the data [53].
We discuss the future engineering steps next.
Firstly, we convert the time fields that will be used by the
models into numeric format by simply dividing the minute by
60 and adding to the hour. Then, for each charging record, we
find out their average departure time, session duration and
energy consumption. This is done by finding out the user ID
of the charging record and aggregating his previous records.
We use the arrival time as a numeric feature. However, the
arrival time also has other components such as the date
information. Using this, we extract the hour of the day, day of
the month, month of the year, day of the week, whether the
day is a weekend and whether the day falls in a US federal
holiday. However, temporal information such as day, hour,
and month are cyclic ordinal features. This is because the hour
value of 23 corresponding to 11 pm, for example, is actually
close to the hour value of 0 which corresponds to 12 am. To
represent the proximity of these values, trigonometric
transformation is performed as following:
C-%&%DEF
)
:GC9HIJ
3
C
5-
(7)
C.%&%KLM
)
:GC9HIJ
3
C
5-%
(8)
where
C
represents the cyclic feature to be transformed,
C-
and
C.
represents the first and second components of the cyclic
feature, respectively. To transform other categorical variables,
one-hot encoding was used, where a single variable with n
points and k distinct classes is transformed into k binary
variables with n points each. For numeric variables, feature
scaling is a common transformation where the goal is to
normalize the range of the numeric features. There are various
scaling techniques, including scaling by domain where all the
features are scaled to a specific range such as [0, 1] and scaling
to minmax where the features are scaled to the range [0, R], in
which case the minimum of the maximum value of feature in
all directions is assigned as the radius of the sphere R [54].
However, in this work we have used standardization which
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
ensures the values of each feature to have zero mean and unit
variance. The transformations were performed using the
preprocessing package of the Scikit-learn [55] library. Table
2 lists the features used for training.
TABLE II
LIST OF FEATURES AND THEIR DESCRIPTIONS
Feature
Description
session_length
Length of charging duration, target
variable
kWh_delivered
Session energy consumption, target
variable
time_con
Numerical representation of the
connection time (arrival time)
day_of_week
Day of the week, one-hot encoded
is_weekend
Binary variable indicating whether the
session took place in a weekend
holiday
Binary variable indicating whether the
session took place on a US federal holiday
hr_x, hr_y
Sine and Cosine components of the hour
day_x, day_y
Sine and Cosine components of the day
mnth_x, mnth_y
Sine component of the month
mean_d_time
Historical average departure time
mean_con
Historical average consumption
mean_dur
Historical average session length
traffic_aft_arvl
average traffic level after arrival
max_traffic_aft_arvl
maximum traffic level after arrival
events_after_arrival
total campus events after arrival
avg_temp_prv
average temperature of last 7 hours
avg_temp_nxt
average temperature of next 10 hours
avg_hum_prv
average humidity of last 7 hours
avg_hum_nxt
average humidity of next 10 hours
avg_win_prv
average wind speed of last 7 hours
avg_win_nxt
average wind speed of next 10 hours
avg_rain_prv
average rainfall of last 7 hours
avg_rain_nxt
average rainfall of next 10 hours
avg_snwfall_prv
average snowfall of last 7 hours
avg_snwfall_nxt
average snowfall of next 10 hours
avg_snwdpth_prv
average snow depth of last 7 hours
avg_snwdpth_nxt
average snow depth of next 10 hours
avg_irradiation_prv
average irradiation of last 7 hours
avg_irradiation_nxt
average irradiation of next 10 hours
E.
MODEL SELECTION AND EXPERIMENTAL SETUP
We selected all charging sessions from the ACN dataset that
belonged to the 2019 calendar year, which ensures we take the
seasonal factors into consideration during training. The dataset
was split such that 80% of the records were used for model
training and 20% for evaluation. During the training phase, we
performed K-fold cross validation where the algorithms are
repeatedly trained K times with a fraction 1/K training
examples left out for testing [56]. In this case, we selected the
common K value of 10. To determine model hyperparameters,
we utilized grid search method which determines the optimal
set of parameters from a given list by trying out all possible
values of the specified parameters [57]. We performed the grid
search across K-folds, selected to be 5 in this case to speed up
the grid search. We then evaluated all the models using the
aforementioned regression metrics. Inspired by the success of
ensemble learning methods in previous works, we also
decided to experiment with ensemble learning. We used two
variants of ensemble stacking, namely voting regressor and
stacking regressor, using the ensemble package of the Scikit-
learn library. In a voting regressor, several base regressors are
trained on the entire training set, and the average predictions
made by the base models are treated as the final prediction.
Stacking regressor is based on the concept of stacked
generalization where predictions made by the base models are
used as inputs to a final estimator, which is trained using cross-
validation, to generate predictions [58]. Figure 4 provides a
graphical representation of the framework.
IV.
RESULTS AND DISCUSSION
We begin the experiment with RF algorithm which can be
used to visualize the variable importance [30]. This is a
method for feature selection where certain variables that are
not important and can often hinder performance are removed.
In this case, the inclusion of the least important variables had
a very insignificant performance increase and hence we
decided to include them in model training. Additionally,
variables can be ranked in terms of their relative importance.
This is determined by each feature’s contribution in
determining the most effective splits. In Figures 5 and 6, we
plot the top 10 important variables for session duration and
energy consumption, respectively. The two most important
predictors of session duration are the maximum traffic after
arrival and the time of connection. This indicates the
Figure 4. Graphical representation of the proposed framework
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
usefulness of including traffic information for the prediction
of session duration. However, for energy consumption, the
historical average consumption is by far the most significant.
This is because a specific vehicle will consume similar energy
if the session duration is consistent.
Figure 5. Top ten features for session duration
Figure 6. Top ten features for energy consumption
A.
SESSION DURATION PREDICTIONS
As mentioned earlier, the hyperparameters for the models
were determined using the grid search approach. For the deep
ANN training, we experimentally determined an architecture
with 3 hidden layers of 64, 32 and 16 nodes respectively to
be the most suitable. Rectified linear units (Relu) [59] was
used as the activation function for all hidden layers and the
output layer contained a linear activation as we are expecting
the prediction to be a numeric value. The learning rate value
was set to 0.001 and we used the Adam [60] algorithm for
model optimization. The training batch size was 32 and the
number of iterations were 15 epochs. Appendix 1 displays
the training loss curve and Table 3 summarizes the 10-fold
cross validation scores on the training set.
TABLE III
TRAINING SCORES FOR SESSION DURATION
Metrics/Model
RMSE
(mins)
MAE
(mins)
R2
SMAPE
(%)
RF
100
68.7
0.72
10.1
SVM
102
68.2
0.71
10.2
XGBoost
100
69.3
0.72
10.3
Deep ANN
103
73.1
0.71
10.7
Voting Ensemble
99.5
67.4
0.72
10.0
Stacking Ensemble
99.5
68.0
0.72
10.1
The training scores are very similar for RF, SVM and
XGBoost whereas deep ANN performs slightly worse.
Therefore, we aggregated the 3 best performing models in
the training phase into 2 ensemble models, which resulted in
improved cross validation scores. Next, we present the
results on the test set. For reference, we also selected the user
estimates of their departures as prediction. This value was
collected through a smart phone app where users were asked
to enter their estimates of their departure time and
consumption upon arrival. We summarize the results on the
test set in Table 4.
TABLE IV
TEST SCORES FOR SESSION DURATION
Metrics/Model
RMSE
(mins)
MAE
(mins)
R2
SMAPE
(%)
RF
98.7
68.0
0.63
10.1
SVM
101
67.4
0.64
10.1
XGBoost
97.9
68.0
0.63
10.1
Deep ANN
101
73.7
0.57
10.9
Voting Ensemble
97.7
66.5
0.73
9.92
Stacking Ensemble
97.5
67.1
0.73
9.95
User predictions
430
394
-4.20
69.9
As highlighted, the best results are obtained using the
ensemble learning approach, which is consistent with
previous works [15], [24]. Voting regressor performs best on
2 metrics and stacking regressor performs the best in terms
of RMSE, whereas they both achieve the same R2 score. The
results are consistent with the training performance with RF,
SVM and XGBoost resulting in similar performance and
deep ANN performs the worst of the four base models.
Predictions made by user about their own session length is
also far off the actual session length. This indicates that
perhaps relying on users to provide an estimate of their own
departure time is perhaps not suitable.
B.
ENERGY CONSUMPTION PREDICTIONS
Similar approach to the session duration prediction was also
used here. The only exception was the deep ANN
architecture which in this case contained 2 hidden layers with
64 and 16 nodes, respectively. The training batch size was
64 and the number of epochs was set to 20. Appendix 2
presents the loss curve from the training phase. Table 5
summarizes the 10-fold cross validation scores on the
training set.
TABLE V
TRAINING SCORES FOR ENERGY CONSUMPTION
Metrics/Model
RMSE
(kWh)
MAE
(kWh)
R2
SMAPE
(%)
RF
5.49
3.40
0.69
11.9
SVM
5.65
3.53
0.67
12.6
XGBoost
5.56
3.49
0.68
12.4
Deep ANN
5.61
3.60
0.67
12.9
Voting Ensemble
5.50
3.42
0.69
12.0
Stacking Ensemble
5.48
3.40
0.69
11.9
RF has the best cross validation scores whereas the other
3 models have similar scores. We selected the top 3 models,
i.e., RF, SVM and XGBoost to form the 2 ensemble models.
In this case, the ensemble models did not improve upon the
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
best performing RF model but rather achieved similar results
on training. The results from the test set are presented in
Table 6. We also compare the results with user predictions
about their consumptions.
The best results as highlighted were obtained using the
stacking ensemble model. The improvement using ensemble
learning for energy consumption prediction was perhaps not
as significant when we compare with the session duration.
The user predictions about their consumptions are not
accurate in this case as well.
TABLE VI
TEST SCORES FOR ENERGY CONSUMPTION
Metrics/Model
RMSE
(kWh)
MAE
(kWh)
R2
SMAPE
(%)
RF
5.50
3.39
0.54
11.7
SVM
5.69
3.54
0.51
12.4
XGBoost
5.61
3.48
0.51
12.1
Deep ANN
5.65
3.55
0.55
12.5
Voting Ensemble
5.54
3.41
0.69
11.8
Stacking Ensemble
5.50
3.38
0.70
11.6
User predictions
20.6
11.8
0.04
55.0
C.
COMPARISON AND DISCUSSION
When we compare across both predictions, looking at the
overall R2 and the SMAPE, it appears that the prediction of
energy consumption is perhaps more difficult. This is
consistent with the previous work on the ACN data [21].
However, in another case the opposite was observed [24],
i.e., the prediction of energy consumption was easier.
Moreover, in both scenarios, it was also noticed that the user
predictions about their own behavior is very different to their
actual behavior, which further emphasizes the need for
predictive analytics. The users’ predictions in terms of their
energy consumption are slightly more accurate when
compared to their predictions of session duration as indicated
by better R2 and SMAPE values. This could be due to the
users’ lack of interest in entering their estimates every time
they decide to charge their vehicles. We also noticed that the
performance using deep ANN was the least accurate in both
cases. Although deep learning models are proven superior in
dealing with images and audio data where feature extraction
is not performed, in applications such as this where we
perform feature extraction, traditional ML models usually
perform better. Furthermore, predictions made by ensemble
learning outperformed predictions made by individual ML
models in both scenarios, although the impact was more
significant for session duration prediction. This is most likely
because in the first scenario, the top 3 performing models had
similar training performance and combining their predictions
resulted in an improvement. However, in the latter scenario,
one model clearly outperformed the rest in training and
hence the improvement using ensemble learning was not
significant.
Looking at the previous works in the literature, the results
in this work outperformed all the previous works that
reported similar evaluation metrics ([21], [23], [26], [27],
[28]). We summarize the results from the previous works in
comparison to the one achieved in this work in Table 6. In
comparison to [24], the results obtained in this work for
session duration is more accurate although we do not
improve upon their results for energy consumption. This is
most likely because the authors in [24] utilized both
residential and non-residential data for their predictions, and
residential charging behavior in most cases are more
consistent. However, it must be noted that all previous works
except [21] used a different dataset to this work and therefore
a comparison is perhaps not suitable. Therefore, keeping the
comparison across the same dataset, we can conclude that the
utilization of the additional weather, traffic and events data
resulted in an improvement in the EV charging behavior
predictions.
TABLE VI
PERFORMANCE COMPARISON WITH PREVIOUS WORKS
Source
Session
Duration
Energy
Consumption
Dataset Used
[21]
SMAPE:
14.4%
SMAPE: 15.9%
ACN (historical
charging)
[23]
MAE: 82
minutes
Not considered
German charging
data (historical
charging, vehicle &
location info)
[24]
SMAPE:
10.4%
SMAPE: 7.5%
UCLA campus
(historical charging)
and Residential
charging data from
UK
[26]
Not
considered
R2: 0.52
Nebraska public
charging (historical
charging, temporal
& location)
[27]
Not
considered
SMAPE: 15.3%
UCLA campus
(historical energy)
[28]
Not
considered
SMAPE: 14.1%
UCLA campus
(historical energy)
Our
work
SMAPE:
9.92%,
MAE: 66.5
minutes
SMAPE:
11.6%, R2: 0.7
ACN, weather,
traffic, and events
data
V.
RECOMMENDATIONS AND FUTURE WORK
We have quantitatively shown in the previous section that the
traffic and weather data were important predictors in EV
charging behavior, particularly in the case of session duration.
Although the use of local events data (campus events in this
case) had insignificant impact in terms of performance gain, it
cannot be ruled out for future work. In this work, we obtained
all campus events from the university calendar. However,
perhaps only the significant events that draw more crowd
should be taken into consideration. It is possible that events
data may not impact predictions in a university campus
setting. However, for other public spaces such as shopping
malls for example, events like end of the year sale could be
important predictors. Therefore, similar experiments on other
public charging spaces should be carried out to find the impact
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
of local events. Social media can also be explored as a means
to obtain information about local events as well as driver
behavior. For instance, social media has been shown to be a
good tool for estimating human behavior [61] and also is a
significant predictor of truck drivers’ travel time [62]. It is also
likely that the use of vehicle information such as the vehicle
model and vehicle type can improve predictions, especially in
terms of energy consumption. Some of the previous works
have utilized vehicle information [23] but not in conjunction
with weather, traffic, and events. Finally, to better understand
the charging behavior during the COVID-19 pandemic, a case
study should be conducted using the proposed approach to
validate the predictive performance in uncertain situations.
VI.
CONCLUSION
In this work, we presented a framework for the prediction of
two of the most important EV charging behaviors with regards
to scheduling, namely EV session duration and energy
consumption. Unlike previous work, we utilized weather,
traffic, and events data along with the historical charging data.
We trained four popular ML models along with two ensemble
learning algorithms for the prediction of charging behavior.
The results obtained in terms of prediction performance is
superior to the results in the previous works. We have also
provided a significant improvement of charging behavior
prediction on the ACN dataset and demonstrated the potential
of utilizing traffic and weather information in charging
behavior prediction.
APPENDIX
Appendix 1. Validation loss curve for session duration
Appendix 2. Validation loss curve for energy consumption
ACKNOWLEDGMENT
The work in this paper was supported, in part, by the Computer
Science and Engineering department and the Open Access
Program from the American University of Sharjah, UAE. This
paper represents the opinions of the authors and does not mean
to represent the position or opinions of the American
University of Sharjah.
REFERENCES
[1] “Climate Emergency Declaration and Mobilisation In Action,”
CEDAMIA. https://www.cedamia.org/global/ (accessed Jan. 17, 2021).
[2] “Key World Energy Statistics 2018 – Analysis,” IEA.
https://www.iea.org/reports/key-world-energy-statistics-2019 (accessed
Jun. 01, 2020).
[3] “68% of the world population projected to live in urban areas by
2050, says UN,” UN DESA | United Nations Department of Economic and
Social Affairs, May 16, 2018.
https://www.un.org/development/desa/en/news/population/2018-revision-
of-world-urbanization-prospects.html (accessed Jun. 01, 2020).
[4] X. Zhang, F. Gao, X. Gong, Z. Wang, and Y. Liu, “Comparison
of Climate Change Impact Between Power System of Electric Vehicles and
Internal Combustion Engine Vehicles,” in Advances in Energy and
Environmental Materials, Singapore, 2018, pp. 739–747.
[5] “Global EV Outlook 2019 – Analysis,” IEA.
https://www.iea.org/reports/global-ev-outlook-2019 (accessed Jun. 01,
2020).
[6] Y. Kwon, S. Son, and K. Jang, “User satisfaction with battery
electric vehicles in South Korea,” Transp. Res. Part Transp. Environ., vol.
82, p. 102306, 2020, doi: https://doi.org/10.1016/j.trd.2020.102306.
[7] D. Ronanki, A. Kelkar, and S. S. Williamson, “Extreme Fast
Charging Technology—Prospects to Enhance Sustainable Electric
Transportation,” Energies, vol. 12, no. 19, 2019, doi: 10.3390/en12193721.
[8] S. A. Q. Mohammed and J.-W. Jung, “A Comprehensive State-
of-the-Art Review of Wired/Wireless Charging Technologies for Battery
Electric Vehicles: Classification/Common Topologies/Future Research
Issues,” IEEE Access, vol. 9, pp. 19572–19585, 2021, doi:
10.1109/ACCESS.2021.3055027.
[9] A. Ramanujam, P. Sankaranarayanan, A. Vasan, R. Jayaprakash,
V. Sarangan, and A. Sivasubramaniam, “Qantifying The Impact of Electric
Vehicles On The Electric Grid: A Simulation Based Case-Study,” in
Proceedings of the Eighth International Conference on Future Energy
Systems, New York, NY, USA, 2017, pp. 228–233. doi:
10.1145/3077839.3077854.
[10] M. Ş. Kuran, A. Carneiro Viana, L. Iannone, D. Kofman, G.
Mermoud, and J. P. Vasseur, “A Smart Parking Lot Management System
for Scheduling the Recharging of Electric Vehicles,” IEEE Trans. Smart
Grid, vol. 6, no. 6, pp. 2942–2953, 2015, doi: 10.1109/TSG.2015.2403287.
[11] J. García-Álvarez, M. A. González, and C. R. Vela,
“Metaheuristics for solving a real-world electric vehicle charging
scheduling problem,” Appl. Soft Comput., vol. 65, pp. 292–306, 2018, doi:
https://doi.org/10.1016/j.asoc.2018.01.010.
[12] L. Hu, J. Dong, and Z. Lin, “Modeling charging behavior of
battery electric vehicle drivers: A cumulative prospect theory based
approach,” Transp. Res. Part C Emerg. Technol., vol. 102, pp. 474–489,
2019, doi: https://doi.org/10.1016/j.trc.2019.03.027.
[13] J. Spoelstra, “Charging behaviour of Dutch EV drivers,”
Master’s Thesis, 2014.
[14] S. Shahriar, A. R. Al-Ali, A. H. Osman, S. Dhou, and M. Nijim,
“Machine Learning Approaches for EV Charging Behavior: A Review,”
IEEE Access, vol. 8, pp. 168980–168993, 2020, doi:
10.1109/ACCESS.2020.3023388.
[15] S. Ai, A. Chakravorty, and C. Rong, “Household EV Charging
Demand Prediction Using Machine and Ensemble Learning,” in 2018 IEEE
International Conference on Energy Internet (ICEI), 2018, pp. 163–168.
[16] Y. Yang, Z. Tan, and Y. Ren, “Research on Factors That
Influence the Fast Charging Behavior of Private Battery Electric Vehicles,”
Sustainability, vol. 12, no. 8, 2020, doi: 10.3390/su12083439.
[17] S. Venticinque and S. Nacchia, “Learning and Prediction of E-
Car Charging Requirements for Flexible Loads Shifting,” in Internet and
Distributed Computing Systems, Cham, 2019, pp. 284–293.
[18] O. Frendo, J. Graf, N. Gaertner, and H. Stuckenschmidt, “Data-
driven smart charging for heterogeneous electric vehicle fleets,” Energy AI,
vol. 1, p. 100007, 2020, doi: https://doi.org/10.1016/j.egyai.2020.100007.
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
[19] J. J. Mies, J. R. Helmus, and R. Van den Hoed, “Estimating the
Charging Profile of Individual Charge Sessions of Electric Vehicles in The
Netherlands,” World Electr. Veh. J., vol. 9, no. 2, 2018, doi:
10.3390/wevj9020017.
[20] Y. Lu et al., “The Application of Improved Random Forest
Algorithm on the Prediction of Electric Vehicle Charging Load,” Energies,
vol. 11, no. 11, 2018, doi: 10.3390/en11113207.
[21] Z. J. Lee, T. Li, and S. H. Low, “ACN-Data: Analysis and
Applications of an Open EV Charging Dataset,” in Proceedings of the Tenth
ACM International Conference on Future Energy Systems, New York, NY,
USA, 2019, pp. 139–149. doi: 10.1145/3307772.3328313.
[22] Z. Xu, “Forecasting Electric Vehicle Arrival & Departure Time
On UCSD Campus using Support Vector Machines,” PhD Thesis, UC San
Diego, 2017.
[23] O. Frendo, N. Gaertner, and H. Stuckenschmidt, “Improving
Smart Charging Prioritization by Predicting Electric Vehicle Departure
Time,” IEEE Trans. Intell. Transp. Syst., pp. 1–8, 2020.
[24] Y.-W. Chung, B. Khaki, T. Li, C. Chu, and R. Gadh, “Ensemble
machine learning-based algorithm for electric vehicle user behavior
prediction,” Appl. Energy, vol. 254, p. 113732, 2019, doi:
https://doi.org/10.1016/j.apenergy.2019.113732.
[25] Y. Xiong, C. Chu, R. Gadh, and B. Wang, “Distributed optimal
vehicle grid integration strategy with user behavior prediction,” in 2017
IEEE Power Energy Society General Meeting, 2017, pp. 1–5.
[26] A. Almaghrebi, F. Aljuheshi, M. Rafaie, K. James, and M.
Alahmad, “Data-Driven Charging Demand Prediction at Public Charging
Stations Using Supervised Machine Learning Regression Methods,”
Energies, vol. 13, no. 16, p. 4231, 2020.
[27] M. Majidpour, C. Qiu, P. Chu, R. Gadh, and H. R. Pota, “Fast
Prediction for Sparse Time Series: Demand Forecast of EV Charging
Stations for Cell Phone Applications,” IEEE Trans. Ind. Inform., vol. 11,
no. 1, pp. 242–250, 2015.
[28] M. Majidpour, C. Qiu, P. Chu, R. Gadh, and H. R. Pota, “A novel
forecasting algorithm for electric vehicle charging stations,” in 2014
International Conference on Connected Vehicles and Expo (ICCVE), 2014,
pp. 1035–1040.
[29] N. Bokde, M. W. Beck, F. [Martínez Álvarez, and K. Kulat, “A
novel imputation methodology for time series based on pattern sequence
forecasting,” Pattern Recognit. Lett., vol. 116, pp. 88–96, 2018, doi:
https://doi.org/10.1016/j.patrec.2018.09.020.
[30] A. Liaw, M. Wiener, and others, “Classification and regression
by randomForest,” R News, vol. 2, no. 3, pp. 18–22, 2002.
[31] J. H. Friedman, “Greedy Function Approximation: A Gradient
Boosting Machine,” Ann. Stat., vol. 29, no. 5, pp. 1189–1232, 2001.
[32] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting
System,” in Proceedings of the 22nd ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining, New York, NY,
USA, 2016, pp. 785–794. doi: 10.1145/2939672.2939785.
[33] D. Nielsen, “Tree boosting with xgboost-why does xgboost win"
every" machine learning competition?,” Master’s Thesis, NTNU, 2016.
[34] C. J. C. Burges, “A Tutorial on Support Vector Machines for
Pattern Recognition,” Data Min. Knowl. Discov., vol. 2, no. 2, pp. 121–167,
Jun. 1998, doi: 10.1023/A:1009715923555.
[35] M. Awad and R. Khanna, “Support Vector Regression,” in
Efficient Learning Machines: Theories, Concepts, and Applications for
Engineers and System Designers, M. Awad and R. Khanna, Eds. Berkeley,
CA: Apress, 2015, pp. 67–80. doi: 10.1007/978-1-4302-5990-9_4.
[36] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. The
MIT Press, 2016.
[37] D. Opitz and R. Maclin, “Popular ensemble methods: An
empirical study,” J. Artif. Intell. Res., vol. 11, pp. 169–198, 1999.
[38] R. Polikar, “Ensemble based systems in decision making,” IEEE
Circuits Syst. Mag., vol. 6, no. 3, pp. 21–45, 2006.
[39] A. Botchkarev, “A new typology design of performance metrics
to measure errors in machine learning regression algorithms,” Interdiscip.
J. Inf. Knowl. Manag., vol. 14, pp. 45–76, Jan. 2019.
[40] “ACN-Data -- A Public EV Charging Dataset.”
https://ev.caltech.edu/dataset (accessed Jul. 02, 2020).
[41] “TCCON Weather.” http://tccon-weather.caltech.edu/ (accessed
Jul. 02, 2020).
[42] R. Gelaro et al., “The Modern-Era Retrospective Analysis for
Research and Applications, Version 2 (MERRA-2),” J. Clim., vol. 30, no.
14, pp. 5419–5454, Jul. 2017, doi: 10.1175/JCLI-D-16-0758.1.
[43] R. Mendelsohn, P. Kurukulasuriya, A. Basist, F. Kogan, and C.
Williams, “Climate analysis with satellite versus weather station data,”
Clim. Change, vol. 81, no. 1, pp. 71–83, Mar. 2007, doi: 10.1007/s10584-
006-9139-x.
[44] G. Leduc and others, “Road traffic data: Collection methods and
applications,” Work. Pap. Energy Transp. Clim. Change, vol. 1, no. 55, pp.
1–55, 2008.
[45] “Pasadena Traffic Count Website.”
https://data.cityofpasadena.net/datasets/eaaffc1269994f0e8966e2024647cc
56 (accessed Jan. 21, 2021).
[46] F. Goudarzi, “Travel Time Prediction: Comparison of Machine
Learning Algorithms in a Case Study,” in 2018 IEEE 20th International
Conference on High Performance Computing and Communications; IEEE
16th International Conference on Smart City; IEEE 4th International
Conference on Data Science and Systems (HPCC/SmartCity/DSS), 2018,
pp. 1404–1407. doi: 10.1109/HPCC/SmartCity/DSS.2018.00232.
[47] D. Barth, “The bright side of sitting in traffic: Crowdsourcing
road congestion data,” Google Off. Blog, 2009.
[48] “Calendar | www.caltech.edu.”
https://www.caltech.edu/campus-life-events/master-calendar (accessed Jan.
23, 2021).
[49] J. W. Tukey, Exploratory data analysis, vol. 2. Reading, Mass.,
1977.
[50] F. T. Liu, K. M. Ting, and Z. Zhou, “Isolation Forest,” in 2008
Eighth IEEE International Conference on Data Mining, 2008, pp. 413–422.
doi: 10.1109/ICDM.2008.17.
[51] S. Bishop, Pytz–world timezone definitions for Python.
Online][Cited: May 25, 2012.] http://pytz. sourceforge. net, 2016.
[52] W. McKinney and others, “pandas: a foundational Python library
for data analysis and statistics,” Python High Perform. Sci. Comput., vol.
14, no. 9, pp. 1–9, 2011.
[53] Y. Bengio, A. Courville, and P. Vincent, “Representation
Learning: A Review and New Perspectives,” IEEE Trans. Pattern Anal.
Mach. Intell., vol. 35, no. 8, pp. 1798–1828, 2013, doi:
10.1109/TPAMI.2013.50.
[54] P. Juszczak, D. Tax, and R. P. Duin, “Feature scaling in support
vector data description,” in Proc. asci, 2002, pp. 95–102.
[55] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,”
J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[56] Y. Bengio and Y. Grandvalet, “No unbiased estimator of the
variance of k-fold cross-validation,” J. Mach. Learn. Res., vol. 5, no. Sep,
pp. 1089–1105, 2004.
[57] Qiujun Huang, Jingli Mao, and Yong Liu, “An improved grid
search algorithm of SVR parameters optimization,” in 2012 IEEE 14th
International Conference on Communication Technology, 2012, pp. 1022–
1026. doi: 10.1109/ICCT.2012.6511415.
[58] D. H. Wolpert, “Stacked generalization,” Neural Netw., vol. 5,
no. 2, pp. 241–259, 1992, doi: https://doi.org/10.1016/S0893-
6080(05)80023-1.
[59] V. Nair and G. E. Hinton, “Rectified linear units improve
restricted boltzmann machines,” 2010.
[60] D. P. Kingma and J. Ba, “Adam: A method for stochastic
optimization,” ArXiv Prepr. ArXiv14126980, 2014.
[61] M.-A. Abbasi, S.-K. Chai, H. Liu, and K. Sagoo, “Real-world
behavior analysis through a social media lens,” in International Conference
on Social Computing, Behavioral-Cultural Modeling, and Prediction, 2012,
pp. 18–26.
[62] D. Yuniar, L. Djakfar, A. Wicaksono, and A. Efendi, “Truck
driver behavior and travel time effectiveness using smart GPS,” Civ. Eng.
J., vol. 6, no. 4, pp. 724–732, 2020.
This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Citation information: DOI
10.1109/ACCESS.2021.3103119, IEEE Access
Author Name: Preparation of Papers for IEEE Access (February 2017)
2 VOLUME XX, 2017
Sakib Shahriar received his B.S. (2018) in
Computer Engineering from American University
of Sharjah, U.A.E. He is currently pursuing his
M.S. degree in Computer Engineering at the
American University of Sharjah, U.A.E. He is also
a research assistant at the same university. His
research interests include Machine Learning, Big
Data Analytics and Deep Learning.
A. R. Al-Ali received the Ph.D. in electrical
engineering and a minor in computer science
from Vanderbilt University, Nashville, TN, USA,
1990; MS from Polytechnic Institute of New
York, USA, 1986 and B. Sc.EE from Aleppo
University, Syria, 1979. From 1991-2000, he was
a faculty with the EE Dept. at KFUPM, Saudi
Arabia. Since 2000–present, he is working as
professor of computer engineering with American
University of Sharjah, UAE. His research,
teaching interests include embedded systems, cyber physical systems, IoT
and IIoT applications in smart cities.
Ahmed H. Osman received the B.Sc. and M.Sc.
degrees in electrical engineering from Helwan
University, Cairo, Egypt, in 1991 and 1996,
respectively, and the Ph.D. degree in electrical
engineering from the University of Calgary,
Calgary, AB, Canada, in 2003. From 2004 to
2008, he was an Assistant Professor with the
Department of Electrical and Computer
Engineering, University of Calgary. He is
currently a Professor at the Department of Electrical Engineering, American
University of Sharjah, Sharjah, UAE. His research interests and activities
include power system analysis and power system protection.
Salam Dhou (Member, IEEE) received the
B.Sc. and M.Sc. degrees in computer science
from the Jordan University of Science and
Technology, Irbid, Jordan, in 2004 and 2007,
respectively, and the Ph.D. degree in electrical
and computer engineering from Virginia
Commonwealth University, Richmond, VA,
USA in 2013. She worked as a Postdoctoral
Research Fellow in the Department of Radiation
Oncology at Harvard Medical School, Boston,
Massachusetts, USA, between 2013 and 2016.
She is currently an Assistant Professor in the Department of Computer
Science and Engineering, and the Biomedical Engineering Graduate
Program with the American University of Sharjah, Sharjah, United Arab
Emirates. Her research interests include machine learning and data mining,
computer vision, and medical imaging and informatics.
Mais Nijim received her B.S in Computer Science
from Princess Sumaya University in Amman,
Jordan. She received her M.S. degree in Computer
Science from New Mexico State University in 2004,
and her Ph.D. in Computer Science from New
Mexico Institute of Mining and Technology in 2007.
She has been an Associate Professor with the Department of Electrical
Engineering and Computer Science, Texas A&M University-Kingsville. Her
research interests include Machine Learning, Cyber Physical System,
Cybersecurity, and Wireless Sensor Network. She is the editor of the
International Journal of Sensor Network.
