Charging Demand Research Articles

Forecasting Electric Vehicles’ Charging Behavior at Charging Stations: A Data Science-Based Approach

The rising adoption of electric vehicles (EVs), driven by carbon neutrality goals, has prompted the need for accurate forecasting of EVs’ charging behavior. However, this task presents several challenges due to the dynamic nature of EVs’ usage patterns, including fluctuating demand and unpredictable charging durations. In response to these challenges and different from previous works, this paper presents a novel and holistic methodology for day-ahead forecasting of EVs’ plugged-in status and power consumption in charging stations (CSs). The proposed framework encompasses data analysis, pre-processing, feature engineering, feature selection, the use and comparison of diverse machine learning forecasting algorithms, and validation. A real-world dataset from a CS in Boulder City is employed to evaluate the framework’s effectiveness, and the results demonstrate its proficiency in predicting the EVs’ plugged-in status, with XGBoost’s classifier achieving remarkable accuracy with an F1-score of 0.97. Furthermore, an in-depth evaluation of six regression methods highlighted the supremacy of gradient boosting algorithms in forecasting the EVs’ power consumption, with LightGBM emerging as the most effective method due to its optimal balance between prediction accuracy with a 4.22% normalized root-mean-squared error (NRMSE) and computational efficiency with 5 s of execution time. The proposed framework equips power system operators with strategic tools to anticipate and adapt to the evolving EV landscape.

Research on optimization algorithms for localization and capacity determination of chargers considering the spatiotemporal distribution of electric vehicles

The optimized layout of electric vehicle (EV) chargers is not only crucial for users' convenience but also a key element in urban sustainable development, energy transition, and the promotion of new energy vehicles. In order to provide a basis for the problem of localization and capacity determination of chargers and compare the merits of several mainstream algorithms, this paper first establishes an optimization model with the objective of minimizing the total investment cost of all the chargers and the constraint of meeting the charging demands of all electric vehicles. Optimizations were performed using genetic algorithm (GA), surrogate optimization algorithm (SOA), and mixed integer linear programming (MILP) algorithm, respectively. In the case of using MILP, the original nonlinear optimization problem was transformed into a linear problem. In the planning of city-level EV chargers, MILP took 14182.57 s to calculate the minimum cost of 34.62 million yuan. After retaining only 10% of the original data amount, SOA took 87651.34 s to calculate the minimum cost of 3.01 million yuan. The results indicate that GA is prone to falling into local optima and is not suitable for large-scale optimization problems. SOA, on the other hand, requires significant memory consumption, so the issue of memory usage needs to be carefully considered when using it directly. Although MILP is only applicable to linear programming problems, it has the advantages of lower memory usage and higher reliability if the problem can be transformed into a linear one.

EV charging fairness protective management against charging demand uncertainty for a new “1 to N” automatic charging pile

Electric vehicles (EVs) have been popularly adopted and deployed over the past few years. However, the mismatch between EVs and charging infrastructure has become one of the major roadblocks to restricting EV promotion. Target at improve the temporal and spatial utilization rate of charging infrastructure, this paper presents a new “1 to N” automatic charging system with the combination of charging pile and special robotic arm. The connection between the charging pile and arrived EVs can be automatically switched by the robotic arm and the charging demand of EVs parking at the random parking spots could be satisfied. Based on the “1 to N” charging scenario a two-layer iterative charging scheduling strategy is proposed benefits of restraining the impact of the charging demand uncertainty while realizing the fairness in charging behavior. In addition, both the simulations and hardware in the loop experiments are implemented to verify the feasibility and real-time performance of the proposed “1 to N” charging system and charging schedule strategy.

Application of improved Wolf pack algorithm in planning and operation of multi-microgrid systems with electric vehicles

Abstract With the rapid growth of renewable energy sources and the widespread use of electric vehicles (EVs), the planning and operation problems of multiple microgrids (MMGs) have become more complex and diverse. This paper develop an MMG model with multiple renewable energy sources and small-scale EVs, aiming to maximize the use of renewable energy sources and realize the charging demand of EVs, and highlighting the potential role of EVs in MMGs. In addition, the paper underscores the indispensable role of measurement technology in microgrids and the impetus that microgrid development provides for advancements in measurement technology. To this end, this paper proposes an improved Wolf pack algorithm (IWPA) based on the standard Wolf Pack Algorithm (WPA) with a spiral search approach and chaotic updating of individuals to improve the global search capability of the algorithm and the complexity of solving the scheduling problem. Through simulation experiments on ten standard test functions and examples, it is verified that the IWPA algorithm improves the search accuracy by 2.8%–6.8% and 13.9%–18.3% in the worst and best cases, respectively, in comparison with other algorithms, and it also has a faster convergence speed. Meanwhile, this paper proposes a load interval pricing strategy for the shortcomings of time-of-use pricing strategy and traditional real-time pricing strategy, which is simulated under grid-connected operation, isolated grid operation, and multi-microgrid cooperative operation modes, and the simulation results of the arithmetic example show that this strategy can effectively reduce carbon emissions, and IWPA can effectively coordinate renewable energy, EVs, and other energy resources to achieve efficient energy management of MMGs and supply-demand balance.

DiffPLF: A conditional diffusion model for probabilistic forecasting of EV charging load

Due to the vast electric vehicle (EV) penetration to distribution grid, charging load forecasting is essential to promote charging station operation and demand-side management. However, the stochastic charging behaviors and associated exogenous factors render future charging load patterns quite volatile and hard to predict. Accordingly, we devise a novel Diffusion model termed DiffPLF for Probabilistic Load Forecasting of EV charging, which can explicitly approximate the predictive load distribution conditioned on historical data and related covariates. Specifically, we leverage a denoising diffusion model, which can progressively convert the Gaussian prior to real time-series data by learning a reversal of the diffusion process. Besides, we couple such diffusion model with a cross-attention-based conditioning mechanism to execute conditional generation for possible charging demand profiles. We also propose a task-informed fine-tuning technique to better adapt DiffPLF to the probabilistic time-series forecasting task and acquire more accurate and reliable predicted intervals. Finally, we conduct multiple experiments to validate the superiority of DiffPLF to predict complex temporal patterns of erratic charging load and carry out controllable generation based on certain covariate. Results demonstrate that we can attain a notable rise of 39.58% and 49.87% on MAE and CRPS respectively compared to the conventional method.

Meeting the charging demand of Electric Vehicles in Greece: Enabling intercity trips

The increasing need for sustainable transportation has underscored the pivotal role of electric mobility in shaping the future of mobility. Electric Vehicles (EVs) have emerged as a promising solution, but their widespread adoption is contingent upon the availability of a reliable charging network. This challenge extends even to EV adoption pioneers like Norway and China. This study delves into the context of EV adoption in Greece, providing insights into the EV market, existing incentives, and the state of charging infrastructure. Reports indicate that Greece is at a critical juncture, with fast EV adoption but sluggish development of Charging Stations (CSs). To address this issue, a Monte Carlo simulation is employed to evaluate the feasibility of long-distance EV trips in Greece and propose an infrastructure development plan. For EVs, the study reveals a linear relationship between battery size and autonomy, with some exceptions emphasizing the importance of data acquisition and individual EV assessment. The study also provides insights into the relationship between trip length and energy consumption, indicating that longer trips exhibit greater fluctuation in energy consumption due to varying conditions, while energy usage patterns of shorter trips are more predictable. Additionally, the analysis presents average energy consumption values for each EV model in different temperature conditions, highlighting the impact of environmental factors on EV performance.

Design of an Electric Vehicle Charging System Consisting of PV and Fuel Cell for Historical and Tourist Regions

One of the most important problems in the widespread use of electric vehicles is the lack of charging infrastructure. Especially in tourist areas where historical buildings are located, the installation of a power grid for the installation of electric vehicle charging stations or generating electrical energy by installing renewable energy production systems such as large-sized PV (photovoltaic) and wind turbines poses a problem because it causes the deterioration of the historical texture. Considering the need for renewable energy sources in the transportation sector, our aim in this study is to model an electric vehicle charging station using PVPS (photovoltaic power system) and FC (fuel cell) power systems by using irradiation and temperature data from historical regions. This designed charging station model performs electric vehicle charging, meeting the energy demand of a house and hydrogen production by feeding the electrolyzer with the surplus energy from producing electrical energy with the PVPS during the daytime. At night, when there is no solar radiation, electric vehicle charging and residential energy demand are met with an FC power system. One of the most important advantages of this system is the use of hydrogen storage instead of a battery system for energy storage and the conversion of hydrogen into electrical energy with an FC. Unlike other studies, in our study, fossil energy sources such as diesel generators are not included for the stable operation of the system. The system in this study may need hydrogen refueling in unfavorable climatic conditions and the energy storage capacity is limited by the hydrogen fuel tank capacity.

Mapping the charging demand for electric vehicles in 2050 from mobility habits

This paper proposes a method to spatially model and compare charging needs on the European scale, considering local disparities in population density, distance to city centres, car ownership and mobility habits. Mobility habits are modelled across Europe in terms of distance and time frame to elaborate scenarios of charging behaviour. The first step of the method is to calculate the density of electric vehicles with a resolution of 1km2, according to the progressive electrification of the fleet each year between 2020 and 2050. The second step is to quantify the mobility of commuters using their driving distance to work areas and mobility statistics. The model is then applied in a case study in Switzerland to plan the public charging infrastructure required to satisfy the charging needs of the local population. Despite lower motorization rates and driving distances, the results show a stronger need for charging in cities. With 50% of commuters charging at work and 20% at home during the workday, the demand in the evening can be reduced by 50% in the suburban areas compared to the baseline scenario in which all commuters are charging at home in the evening. This model can be used to quantify the energy needs of commuters, plan the deployment of the charging infrastructure, or simulate the effect of policies.

Feature-enhanced deep learning method for electric vehicle charging demand probabilistic forecasting of charging station

The fast proliferation of electric vehicles (EVs) profoundly affects the stable operation of the power system. Since EV charging demand is affected by users volatile behaviors and many other environmental and social factors, their uncertainty is quite pronounced. Traditional deterministic forecasting methods which provide little information on the uncertainty may not be informative to the decision-making of power system with massive EVs. This paper proposes a novel feature-enhanced deep learning method (FEDM) for EV charging demand probabilistic forecasting of individual station, in which a two-stage feature selection model is constructed to introduce the Pearson correlation coefficient between charging demand and external features as a prior knowledge to reweight the initial weights. The performance is improved compared to which is without feature-enhanced. In the comparison with eight benchmarks, FEDM shows superiority in both deterministic and probabilistic evaluation metrics. With high computational efficiency, FEDM has low dependence on the historical data stock, which can still achieve good performance in the case of low data volume. It provides a fast and accurate forecasting scheme for the demand forecasting of individual stations under the limitation of low data stock.

The effects of climate and climate change on electric vehicle charging demand in Toronto, Canada

Battery electric vehicles (BEVs) influence total and peak electricity demand, but few studies account for climate when studying these effects. This study quantifies BEV charging demand in the Greater Toronto and Hamilton Area using a detailed trip level approach, accounting for the effect of present and future temperatures on BEV energy consumption. The impact of temperature on charging demand was largest in winter. In 2019, charging demand increases by 52% on an average January day, and up to 82% on extreme days (relative to mild weather conditions). At 30% penetration, BEVs increase peak demand on January’s coldest day by 600–3600 MW (3%–5%), of which 300–700 MW is driven by temperature, depending on the charging scenario. Climate change introduces small changes, increasing summer and decreasing winter charging demand. These results highlight the importance of adjusting for regional climate variation and temperature extremes when analyzing the impact of BEVs on the grid.

Commercial electric vehicle fleets in U.S. ancillary services markets: A stochastic analysis to inform utility rate design

For commercial fleets in the United States, traditional electricity tariffs can disincentivize vehicle-to-grid (V2G) participation and render electrification less attractive. First, we show that absent a rate redesign, opportunities for both fleets and the grid are missed. We propose a rate design modification: demand charge relaxation during off-peak (overnight) hours. This approach would enable fleets to shift additional load share to overnight hours and increase ancillary service revenues without the expectation of impacting local grid cost drivers (i.e., coincident peak load). Applied to a California case study, operational savings spanning 7.5% and 20.6% are realized via increased capacity revenues and deferred demand charges.

Analyzing EV Charging Patterns: Towards Efficient Infrastructure Deployment

This paper analyzes real-world EV charging data, covering station distribution, volume, duration probability, and utilization efficiency. Future infrastructure developments and improvement recommendations are discussed. Based on diverse station data, including probability distributions and regression analysis, findings reveal disparities in infrastructure availability and charging patterns. Strategic planning and investment are emphasized to meet growing EV charging demands, along with exploring opportunities in renewable energy integration and smart charging technologies. Overall, this study provides insights for promoting widespread EV adoption and sustainable transportation.

From PV to EV: Mapping the Potential for Electric Vehicle Charging with Solar Energy in Europe

The electrification of the transport sector is a key element in decarbonizing our societies. However, energy systems will have to cope with additional electricity demand due to the charging needs of electric vehicles (EVs) together with the integration of fluctuating renewable energy sources. Shifting EV charging during the day can contribute to absorbing photovoltaic (PV) production peaks and limiting the additional demand during peak periods. The EV batteries can then be discharged to the grid or home during the evening or other demand peaks. We developed a new methodology to quantify the flexibility gained from the EV-PV coupling from local mobility habits and local (or decentralized) photovoltaic production. Our approach first focuses on the geospatial modelling of mobility habits across Europe to quantify energy demand for charging. The charging demand is then distributed between residential areas, workplaces and points of interest (shopping, leisure, etc.) to model the spatiotemporal distribution of energy needs. We show and discuss a practical case in Copenhagen illustrating the impact of charging behaviour for three different scenarios. The methodology is implemented as a calculation module in the open-source online geographic tool for energy transition planning, Citiwatts.

Machine learning optimization for hybrid electric vehicle charging in renewable microgrids

Renewable microgrids enhance security, reliability, and power quality in power systems by integrating solar and wind sources, reducing greenhouse gas emissions. This paper proposes a machine learning approach, leveraging Gaussian Process (GP) and Krill Herd Algorithm (KHA), for energy management in renewable microgrids with a reconfigurable structure based on remote switching of tie and sectionalizing. The method utilizes Gaussian Process (GP) for modeling hybrid electric vehicle (HEV) charging demand. To counteract HEV charging effects, two scenarios are explored: coordinated and intelligent charging. A novel optimization method inspired by the Krill Herd Algorithm (KHA) is introduced for the complex problem, along with a self-adaptive modification to tailor solutions to specific situations. Simulation on an IEEE microgrid demonstrates efficiency in both scenarios. The predictive model yields a remarkably low Mean Absolute Percentage Error (MAPE) of 1.02381 for total HEV charging demand. Results also reveal a reduction in microgrid operation cost in the intelligent charging scenario compared to coordinated charging.

Matching analysis of new energy vehicle charging demand and charging infrastructure power supply capacity: A case study of China's capital Beijing

The random charging behavior of new energy vehicles (NEVs) will bring new challenges to the matching between electric vehicle charging facilities (EVCF) and NEVs. In order to explore whether the power supply capacity of urban EVCF can meet the charging requirements of NEVs, using the progression of NEVs in Beijing as a basis, initially, the Monte Carlo simulation (MCS) approach simulates the power demand trajectory for NEVs in the region. Subsequently, to forecast the ownership trends of NEVs across three distinct scenarios from 2021 to 2030, the study employs Grey correlation analysis combined with the bidirectional long short-term memory model (GRA-BiLSTM), facilitating the determination of NEVs’ charging needs. Second, the charging supply of EVCF for the next 10 years is derived by analyzing different development scenarios with three growth rates of EVCF and three combinations of fast and slow pile ratios. The findings indicate a discrepancy between the rate of increase in ownership of NEVs and the rate of increase in charging infrastructure in Beijing between 2021 and 2030. Even under a scenario of high growth in NEV ownership, the balance between supply and demand for charging capacity is not achieved, resulting in suboptimal utilization of charging infrastructure.

Malicious mode attack on electric vehicle coordinated charging and its defense strategy

Power systems exploit Internet of Things (IoT) to coordinate the huge charging demands of numerous electric vehicles (EVs) in intelligent transportation systems (ITSs). However, since connected with public networks, the coordinated charging control system is in a low-level cyber security and greatly vulnerable to malicious attacks. The malicious mode attack (MMA), a new cyber-attack pattern, generates high amplitude forced oscillations, which seriously threats the stability of power systems and the power supply of charging stations. However, the MMA model and attack process is not clear. Moreover, it is difficult to actively eliminate the MMA risk through the existing cyber defense technologies. Therefore, this paper analyzes the characteristics of MMA and provides a multi-information active distribution rejection control (MIADRC) method for the physical smart grid to defense MMA. First, the potential threat of MMA is clarified by investigating the vulnerability of the IoT-based coordinated charging load control system. And an MMA process like Mirai is given as an example, which affects the electricity charging system by penetration, infection and attack. Then, an MMA model is established for impact analysis, where expressions of the mean response (i.e. expected value) and stochastic response (i.e. standard deviation) of the MMA forced oscillation are derived to discover main impact factors. Further, to mitigate the impact of MMA, a defense strategy based on multi-index information active disturbance rejection control is proposed to improve the stability and anti-disturbance ability. Finally, simulations are conducted to verify the existence and characteristics of MMA threats. And it is verified that the proposed MIADRC can suppress 91.8 % of the MMA oscillation amplitude. As far as the authors know, it is the first time that the characteristics of MMA are investigated and multi-information-based defensive strategy for MMA is proposed, which enhances system damping through compensating for the attack disturbance.

Optimal sizing of PV–Wind generators with a smart EV charging framework to build grid friendly Net Zero Energy Campus

Electric Vehicles (EVs) are creating a significant challenge on the electric grid as they demand huge amounts of power for their charging. On-site power generation through renewable energy sources (RES) is one of the viable approaches to meet the demands of EVs and other loads of a campus. Hence, an optimal sizing of a hybrid PV–Wind system is considered in this work to build a Net Zero Energy Campus (NZEC). Generally, EVs are scheduled after obtaining the size of RES through a sizing procedure. As a unique approach of this work, a smart EV charging framework is developed to model the profile of EV charging demand and this modeled load profile of EV is considered along with the local load profile of the campus for optimal sizing procedure. The size of PV–Wind sources are optimized by minimizing three objective functions such as the annual operating cost of the system (AOC), loss of power supply probability (LPSP) and total energy transfer (TET). The optimization is carried out by Non-Dominated Sorting Genetic Algorithm II (NSGA II). The maximum utilization of RES and the reduced grid congestion attained through the proposed sizing approach showcase the grid friendliness of the designed NZEC.

Coordinating Charging Request Allocation Between Self-Interested Navigation Service Platforms

Current electric vehicle market trends indicate an increasing adoption rate across several countries. To meet the expected growing charging demand, it is necessary to scale up the current charging infrastructure and to mitigate current reliability deficiencies, for example, due to broken connectors or misreported charging station availability status. However, even within a properly dimensioned charging infrastructure, a risk for local bottlenecks remains if several drivers cannot coordinate their charging station visit decisions. Here, navigation service platforms can optimally balance charging demand over available stations to reduce possible station visit conflicts and increase user satisfaction. Although such fleet-optimized charging station visit recommendations may alleviate local bottlenecks, they can also harm the system if self-interested navigation service platforms seek to maximize their own customers’ satisfaction. To study these dynamics, we model fleet-optimized charging station allocation as a resource allocation game in which navigation platforms constitute players and assign potentially free charging stations to drivers. We show that no pure Nash equilibrium guarantee exists for this game, which motivates us to study VCG mechanisms both in offline and online settings, to coordinate players’ strategies toward a better social outcome. Extensive numerical studies for the city of Berlin show that by coordinating players through VCG mechanisms, the social cost decreases on average by 42% in the online setting and by 52% in the offline setting. History: Accepted by David Alderson, Area Editor for Network Optimization: Algorithms & Applications. Supplemental Material: The online appendix is available at https://doi.org/10.1287/ijoc.2022.0269 .

Optimal Capacity and Charging Scheduling of Battery Storage through Forecasting of Photovoltaic Power Production and Electric Vehicle Charging Demand with Deep Learning Models

The transition from internal combustion engine vehicles to electric vehicles (EVs) is gaining momentum due to their significant environmental and economic benefits. This study addresses the challenges of integrating renewable energy sources, particularly solar power, into EV charging infrastructures by using deep learning models to predict photovoltaic (PV) power generation and EV charging demand. The study determines the optimal battery energy storage capacity and charging schedule based on the prediction result and actual data. A dataset of a 15 kWp rooftop PV system and simulated EV charging data are used. The results show that simple RNNs are most effective at predicting PV power due to their adept handling of simple patterns, while bidirectional LSTMs excel at predicting EV charging demand by capturing complex dynamics. The study also identifies an optimal battery storage capacity that will balance the use of the grid and surplus solar power through strategic charging scheduling, thereby improving the sustainability and efficiency of solar energy in EV charging infrastructures. This research highlights the potential for integrating renewable energy sources with advanced energy storage solutions to support the growing electric vehicle infrastructure.

Self-Scheduling Virtual Power Plant for Peak Management

An efficient and reliable management system for a cluster of distributed energy resources (DERs) is essential for the sustainable and cost-effective peak management (PM) operation of the power grid. The virtual power plant (VPP) provides an efficient way to manage a variety of DERs for the PM process. This paper proposes a VPP framework for PM of local distribution companies by optimizing the self-scheduling of available resources, considering uncertainties and constraints. The study examines two separate scenarios and introduces novel algorithms for determining threshold values in each scenario. An approach is suggested for the transaction between VPP and the aggregator models. The proposed technique intends to determine the optimal amount of capacity that aggregators can allocate for the day-ahead PM procedure while accounting for both thermostatically controlled and non-thermostatically controlled loads. The proposed VPP framework shows promising results for reducing demand charges and optimizing energy resources for PM.