ArticlePublisher preview available

Predicting Electric Vehicle Charging Demand in Residential Areas Using POI Data and Decision‐Making Model

Wiley
IEEJ Transactions on Electrical and Electronic Engineering
Authors:
Huahao Zhou
Huahao Zhou
Huahao Zhou
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Fangbai Liu
Fangbai Liu
Fangbai Liu
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Hao Chen
Hao Chen
Hao Chen
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Yajia Ni
Yajia Ni
Yajia Ni
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Show all 6 authorsHide
Read publisher preview
Download citation
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

Transport electrification is a crucial element of the ongoing energy transition, essential for achieving carbon peaking and carbon neutrality goals. The proliferation of electric vehicles (EVs) introduces significant challenges to power distribution network stability due to their aggregated charging load in residential areas, particularly during peak electricity consumption periods. This paper proposes a method to predict the spatiotemporal distribution of EV charging demand in residential areas using geographic information points of interest (POI) data features and a decision‐making model. Utilizing real historical data, probability distribution models for EV users' arrival times and charging characteristics were constructed using Gaussian Mixture Models (GMM). The spatiotemporal characteristics of EV travel and charging behaviors were analyzed, and a comprehensive charging decision model incorporating both emergency and stochastic scenarios was developed. The model's efficacy in capturing the probability distributions of characteristic variables was validated through a case study. The results demonstrate the model's potential for accurately predicting EV charging demand, providing valuable insights for infrastructure planning and resource allocation. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.
Figures - available from: IEEJ Transactions on Electrical and Electronic Engineering
This content is subject to copyright. Terms and conditions apply.
A preview of this full-text is provided by Wiley.
Learn more
Content available from IEEJ Transactions on Electrical and Electronic Engineering 
This content is subject to copyright. Terms and conditions apply.
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING
IEEJ Trans 2024
Published online in Wiley Online Library (wileyonlinelibrary.com). DOI:10.1002/tee.24220
Paper
Predicting Electric Vehicle Charging Demand in Residential Areas Using
POI Data and Decision-Making Model
Huahao Zhoua,Non-member
Fangbai Liu, Non-member
Hao Chen, Non-member
Yajia Ni, Non-member
Shenglan Yang, Non-member
Wuhao Xu, Non-member
Transport electrification is a crucial element of the ongoing energy transition, essential for achieving carbon peaking and
carbon neutrality goals. The proliferation of electric vehicles (EVs) introduces significant challenges to power distribution
network stability due to their aggregated charging load in residential areas, particularly during peak electricity consumption
periods. This paper proposes a method to predict the spatiotemporal distribution of EV charging demand in residential areas
using geographic information points of interest (POI) data features and a decision-making model. Utilizing real historical data,
probability distribution models for EV users’ arrival times and charging characteristics were constructed using Gaussian Mixture
Models (GMM). The spatiotemporal characteristics of EV travel and charging behaviors were analyzed, and a comprehensive
charging decision model incorporating both emergency and stochastic scenarios was developed. The model’s efficacy in capturing
the probability distributions of characteristic variables was validated through a case study. The results demonstrate the model’s
potential for accurately predicting EV charging demand, providing valuable insights for infrastructure planning and resource
allocation. ©2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.
Keywords: electric vehicle; charging demand forecasting; residential area; decision-making model; POI; Gaussian mixture model
Received 6 June 2024; Revised 31 July 2024; Accepted 12 October 2024
1. Introduction
Transport electrification represents a crucial component of the
ongoing energy revolution and transition. It is also a pivotal
strategy for achieving carbon peaking and carbon neutrality
goals [1]. The widespread adoption of electric vehicles (EVs)
is considered a critical step toward comprehensive transport
electrification. Consequently, the proportion of electric vehicle
ownership is increasing across all countries. As numerous EVs
connect to the grid for recharging, their collective charging load
poses significant challenges to the grid’s safe and stable operation.
Centralized EV charging in residential area during peak electricity
consumption periods exerts considerable pressure on the power
grid. In this context, vehicle-to-grid (V2G) technology emerges
as an essential element of a new, smart power system [2,3]. To
ensure efficient V2G interaction and maintain the grid’s operational
stability, research into predicting EV travel and charging patterns
is imperative [4–9].
Initially, when EVs entered the market, their acceptance was
low, and the supporting infrastructure was underdeveloped. Con-
sequently, acquiring data on electric vehicles was challenging.
aCorrespondence to: Huahao Zhou. E-mail: 610298919@qq.com
State Grid Yancheng Power Supply Company, Yancheng, 224100, Jiangsu,
China
Early research on EV user behavior often employed a methodol-
ogy that mapped the driving trajectory data of fuel vehicles to EVs
for analysis [10–12]. At this stage, charging demand forecasting
for EVs typically involved mathematical models that considered
factors such as the time of day charging commences, distance trav-
eled, and the status of the charging process. Probabilistic modeling
methods were used to predict the loads on the electrical grid due
to EVs. Among these methods, the Monte Carlo sampling method,
based on the Gaussian distribution probability function, is widely
used for regional EV charging load forecasting. This approach fits
EV driving patterns to a substantial historical dataset, identifying
key parameters in the probability density function for use in fore-
casting [13,14]. For instance, studies [15,16] used the probability
distribution of trips, including departure time, mileage, and return
time, to analyze National Household Travel Survey (NHTS) data.
Assuming that travel characteristics of EVs mirror those of fuel
vehicles, these studies combined the regular characteristics of fuel
vehicle refueling with those of EVs to portray charging demand.
The stochastic nature of EVs was simulated using the Monte Carlo
method to resolve the resulting charging load.
Although existing studies have modeled charging load forecast-
ing, they often fail to capture the spatial and temporal distribution
characteristics of EV charging demand comprehensively. Addi-
tionally, parameters such as departure location, charging time, and
location are generally assumed to be fixed. Most studies have
©2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.
ResearchGate has not been able to resolve any citations for this publication.
Re‐shooting Resistant Blind Watermarking Framework Based on Feature Separation With Gaussian Mixture Model
Article
Full-text available
Watermarking is a technology to embed digital data into a digital image. In particular, blind watermarking is expected to ensure the authenticity and/or accountability of digital images without compromising the visual impression of viewing. A re‐shooting resistant blind watermarking method is proposed in this study. This method uses the features of a given image to select regions, which are modified to embed digital data. As the proposed embedding process preserves these image features, no markers are required to extract the embedded data from the watermarked image. Furthermore, based on the estimation of the watermarked image region, the method crops the re‐shot image before the extraction. Therefore, the proposed method works, even if the re‐shot image includes the outer area surrounding the watermarked image region. Moreover, the proposed method compensates for the geometric transformation of the re‐shot image based on the definition of the coordinate system, which is based on the distribution of the image feature points. Therefore, the proposed method works when the re‐shot image is taken diagonally in front of the watermarked image. Experimental results validated that the proposed method can extract the embedded digital data from re‐shot images of a watermarked image under considerable conditions of re‐shooting. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.
View
Coordinating Flexible Demand Response and Renewable Uncertainties for Scheduling of Community Integrated Energy Systems With an Electric Vehicle Charging Station: A Bi-Level Approach
Article
Full-text available
  • Oct 2021
A community integrated energy system (CIES) with an electric vehicle charging station (EVCS) provides a new way for tackling growing concerns of energy efficiency and environmental pollution, it is a critical task to coordinate flexible demand response and multiple renewable uncertainties. To this end, a novel bi-level optimal dispatching model for the CIES with an EVCS in multi-stakeholder scenarios is established in this paper. In this model, an integrated demand response program is designed to promote a balance between energy supply and demand while maintaining a user comprehensive satisfaction within an acceptable range. To further tap the potential of demand response through flexibly guiding users' energy consumption and electric vehicles' behaviors (charging, discharging and providing spinning reserves), a dynamic pricing mechanism combining time-of-use and real-time pricing is put forward. In the solution phase, by using sequence operation theory (SOT), the original chance-constrained programming (CCP) model is converted into a readily solvable mixed-integer linear programming (MILP) formulation and finally solved by CPLEX solver. The simulation results on a practical CIES located in North China demonstrate that the presented method manages to balance the interests between CIES and EVCS via the coordination of flexible demand response and uncertain renewables.
View
Spatial and temporal modelling of coupled power and transportation systems: A comprehensive review
Article
Full-text available
  • May 2021
Abstract The large‐scale application of electric vehicles can lead to new challenges in the operation of the two complex and coupled networks of electricity and transportation systems, thus creating a new concept—a power—traffic network. The purpose is to provide a comprehensive survey of this emerging field. First, both the transportation system and power grid models are briefly introduced in terms of time and space scales. Then, the power traffic network model and applications at long‐term, mid‐term, and short‐term time scales are summarized, and provided a unified view of these achievements. Based on this analysis, recommendations for future research are presented.
View
Identification of Urban Functional Regions in Chengdu Based on Taxi Trajectory Time Series Data
Article
Full-text available
  • Mar 2020
  • ISPRS
Overall scientific planning of urbanization layout is an important component of the new period of land spatial planning policies. Defining the main functions of different spaces and dividing urban functional areas are of great significance for optimizing the land development pattern. This article identifies and analyses urban functional areas from the perspective of data mining. The results of this method are consistent with the actual situation. In this paper, representative taxi trajectory data are selected as the research basis of urban functional areas. First, based on trajectory data from Didi Chuxing within the high-speed road surrounding Chengdu, we generated trajectory time sequence data and used the dynamic time warping (DTW) algorithm to generate a time series similarity matrix. Second, we utilized the K-medoid clustering algorithm to generate preliminary results of land clustering and selected the results with high classification accuracy as the training samples. Then, the k-nearest neighbour (KNN) classification algorithm based on DTW was performed to classify and identify the urban functional areas. Finally, with the help of point-of-interest (POI) auxiliary analysis,the final functional layout in Chengdu was obtained. The results show that the spatial structure of Chengdu is complex and that the urban functions are interlaced, but there are still rules that are followed. Moreover, traffic volume and inflow data can better reflect the travel rules of residents than simple taxi on–off data. The original DTW calculation method has high temporal complexity, which can be improved by normalization and the reduction of time series dimensionality. The semi-supervised learning classification method is also applicable to trajectory data, and it is best to select training samples from unsupervised learning. This method can provide a theoretical basis for urban land planning and has auxiliary and guiding value for urbanization layout in the context of land spatial planning policies in the new era.
View
Charging demand forecasting of electric vehicles considering uncertainties in a microgrid
Article
  • Feb 2022
  • ENERGY
The currently increasing integration of electric vehicles (EVs) in microgrids (MGs) has gained significant attention. However, affected by the high uncertainties of weather, traffic, and driver behavior, the charging demand of EVs is difficult to forecast accurately. In this study, an optimal parameter forecasting method is presented to improve the forecasting accuracy of charging demand of EVs in an MG. For the methods of forecasting of EV status by sampling from probability distributions, this study modifies the optimal parameter values of probability distributions within fuzzy sets based on the feedback of EVs that have arrived in an MG. Fuzzy sets are utilized to limit the modification ranges of parameter values for the consideration of robustness. Moreover, the average values of multiple sampling results are calculated to improve the stability of forecasting results. Combined with the forecasted results, this study is executed over a rolling time horizon for energy management of EVs, ensuring that acceptable charge levels are reached at the disconnection times. Simulation results show that, compared with other state-of-the-art forecasting methods, the proposed forecasting method is highly effective in reducing forecasting errors of EVs and, hence, has better performance in regulating the charging of EVs in an MG.
View
An ensemble methodology for hierarchical probabilistic electric vehicle load forecasting at regular charging stations
Article
  • Dec 2020
  • APPL ENERG
Transportation electrification is a valid option for supporting decarbonization efforts but, at the same time, the growing number of electric vehicles will produce new and unpredictable load conditions for the electrical networks. Accurate electric vehicle load forecasting becomes essential to reduce adverse effects of electric vehicle integration into the grid. In this paper, a methodology dedicated to probabilistic electric vehicle load forecasting for different geographic regions is presented. The hierarchical approach is applied to decompose the problem into sub-problems at low-level regions, which are resolved through standard probabilistic models such as gradient boosted regression trees, quantile regression forests and quantile regression neural networks, coupled with principal component analysis to reduce the dimensionality of the sub-problems. The hierarchical perspective is then finalized to forecast the aggregate load at a high-level geographic region through an ensemble methodology based on a penalized linear quantile regression model. This paper brings, as relevant contributions, the development of hierarchical probabilistic forecasting framework, its comparison with non-hierarchical frameworks, and the assessment of the role of data dimensionality refduction. Extensive experimental results based on actual electric vehicle load data are presented which confirm that the hierarchical approaches increase the skill of probabilistic forecasts up to 9.5% compared with non-hierarchical approaches.
View
A model predictive control approach in microgrid considering multi-uncertainty of electric vehicles
Article
  • Aug 2020
  • RENEW ENERG
Managing uncertainty is key to enhancing robustness in microgrids. This study focuses on the uncertainties in aggregated electric vehicles (EVs) and establishes a two-layer model predictive control (MPC) strategy for charging EVs with a microgrid. The uncertainty in sampling results of EV connection times to the microgrid and the uncertainty in sampling results of state of charge (SOC) of each EV at the time of the initial connection are both taken into account through multi-uncertainty sampling. In order of consider the impact of extreme scenarios, as feedback from arriving EVs are combined with multi-uncertainty sampling for higher accuracy of sampling results during rolling optimization. Simulation results show that, compared to conventional strategies, the proposed strategy has better performance in reducing forecasting error and regulating the charging and discharging of aggregated EVs with uncertainties.
View
Deep-Learning-Based Probabilistic Forecasting of Electric Vehicle Charging Load With a Novel Queuing Model
Article
  • Apr 2020
With the emerging electric vehicle (EV) and fast charging technologies, EV load forecasting has become a concern for planners and operators of EV charging stations (CSs). Due to the nonstationary feature of the traffic flow (TF) and the erratic nature of the charging procedures, EV charging load is difficult to accurately forecast. In this article, TF is first predicted using a deep-learning-based convolutional neural network (CNN), and different forecast uncertainties are evaluated to formulate the TF prediction intervals (PIs). Then, the EV arrival rates are calculated according to the historical data and the proposed mixture model. Based on TF forecasting and arrival rate results, the EV charging process is studied to convert the TF to the charging load using a novel probabilistic queuing model that takes into consideration charging service limitations and driver behaviors. The proposed models are assessed using the actual TF data, and the results show that the uncertainties of the EV charging load can be learned comprehensively, indicating significant potential for practical applications.
View
Exploring high-penetration electric vehicles impact on urban power grid based on voltage stability analysis
Article
  • Mar 2020
  • ENERGY
Electric vehicles (EVs) have received significant attention in recent years. The high penetration of EVs increased the charging load in the distribution network, which has an enormous impact on “transportation and power grid” coupled energy networks. This paper developed the models and methods to evaluate the capacity of electrical energy supply based on voltage stability in the worst charging case scenario, under the existing coupled network. An optimization method with transportation network constraints is proposed to find the worst charging case scenario. In addition, the mobility of EVs is considered to calculate the load margin and the maximum number of EVs charging that a given grid can support in the critical situation. The method and model are simulated by test cases, which provide a perspective for realizing the EVs integration capacity limitation in urban areas considering the coupling relationship between transportation and power grids. Finally, the impact of charging location and route choice in the voltage margin limitation is emphasized.
View
Electrical Safety Considerations in Large-Scale Electric Vehicle Charging Stations
Article
  • Aug 2019
Several safety regulations particularly concerning the charging electric vehicles (EVs) are developed to ensure the electric safety and prevent the hazardous accidents, in which safety requirements for electric vehicle supply equipment (EVSE) and the EV battery are the two main driving factors. At present, quantitative assessment of electrical safety considering the operation conditions of large-scale electric vehicle charging stations (EVCSs) has still remained a challenge. Driven by the hierarchy of hazard control mechanisms, this paper proposes a holistic approach to evaluate the electrical safety of the large-scale EVCSs when coupled to renewable power generation. Our approach mainly focuses on several topics on the operational safety of EVCS primarily concerning: (1) the facility degradation which could potentially result in a compromised EVSE reliability performance and EVCS protection failure; (2) the cyber-attack challenges when the smart charging and the communication between EVCSs and electric utilities are enabled; (3) the potential mismatch between the renewable output and EVCS demand, which could trigger the system stability challenges during normal operation and inability to supply the critical EV loads during outages. The proposed framework will provide informative guidelines to the EVCS operators for continuous monitoring and effective management of the day-to-day EVCSs operation.
View