Charging Behavior Of Vehicles Research Articles

Electric vehicle charging station demand prediction model deploying data slotting

Accurate prediction of energy requirement at charging station is essential for optimizing infrastructure usage, ensuring grid stability, and minimizing operational cost. Literatures suggest deployment of machine learning techniques to forecast the station demand. One major challenge associated with development of machine learning models is the inherent uncertainty in electric vehicle charging behaviour that includes variations in charging patterns, user preferences, and vehicle types. The conventional pre-processing techniques fail to dislodge nonlinearities and highly random patterns that include very low or zero-charging. Employing such techniques affects the model's forecast accuracy. This article performs data-slotting during pre-processing stage and then selects the best among 1-h, 2-h, 3-h and 4-h slots, to frame the feature vectors. The 4-h data with minimum variance is suggested to frame the dataset. Four distinct datasets, comprising different combination of average and total demands as predictor and response respectively are considered. The created dataset is deployed in Random Forest, Categorical Boosting, Extreme Gradient Boosting and Light Gradient Boosting models. The article recommends Categorical Boosting Regression model with least mean absolute error, mean square error and root mean square error of 0.0726, 0.0112, and 0.1059 respectively. Furthermore, the use of feature vector comprising of aggregated load for prescribed slots and the response representing the aggregated demand is observed to provide the least prediction error by the suggested model. The suggested model fed by the proposed feature vector offers significant advantage to charging station operator by enhancing the operational efficiency while performing resource and cost management with strategic planning.

Unraveling the effect of electricity price on electric vehicle charging behavior: A case study in Shenzhen, China

Estimating price elasticity of demand for electric vehicle charging contributes to the accurate determination of charging price, thereby improving electric vehicle adoption and energy sustainability. However, few studies have studied the impact of electricity price on electric vehicle charging behavior, especially the demand spillover effect caused by price fluctuations. To fill the gaps, on a citywide dataset of public charging piles in Shenzhen, China, first, correlation coefficients and hypothesis tests are used to determine the relationship between charging demand and price. A learning model incorporating two-layer graph attention, temporal pattern attention, and knowledge-embedded meta-learning is developed for accurate spatio-temporal regression. Impulse response analysis is conducted to unravel several noteworthy phenomena: (1) public charging demand is inelastic to electricity price, with an average elasticity of −0.76, and distinction between different functional areas and times is revealed; (2) negative price impulses marginally change the elasticity, while positive ones make electric vehicle charging users more price sensitive, and (3) the spillover effects caused by price increases and decreases bring 89.48% and 53.88% of its local demand changes to neighbors, respectively, with a scope of 3.45 kilometer. These findings provide policy implications for promoting electric vehicle charging to facilitate renewable energy transition.

Day-ahead electric vehicle charging behavior forecasting and schedulable capacity calculation for electric vehicle parking lot

The Electric Vehicle Parking Lot (EVPL) aims to address the growing demand for EV charging infrastructure. EVs connected to EVPLs have extended access times compared to those at public charging stations. Consequently, EVPL owners can aggregate the schedulable capacity of connected EVs to participate in day-ahead and ancillary service markets, thereby gaining economic benefits. However, achieving this objective is hindered by the lack of accurate day-ahead forecasts of EV charging behavior. To address this issue, this paper introduces a novel day-ahead forecasting method for EV charging behavior at EVPLs, alongside a strategy for calculating EV schedulable capacity based on these forecasts. Unlike existing methods, this paper presents a day-ahead time-of-use clustering forecasting strategy, which provides more detailed and accurate predictions of EV charging behavior, eliminating the need for numerous assumptions during schedulable capacity calculations. The study demonstrates that the proposed method, validated using actual historical data, enables precise forecasting of EV charging behavior. Furthermore, the proposed day-ahead schedulable capacity calculation strategy is shown to be both effective and practical.

Privacy-preserving estimation of electric vehicle charging behavior: A federated learning approach based on differential privacy

With the popularity of connected electric vehicles, the openness and sharing of charging data between stakeholders allows a more accurate estimation of charging behavior, which is valuable for optimizing energy systems and facilitating travel convenience. However, to enable such an effective mechanism, the challenge of data security and privacy should be addressed. Federated learning in the vehicular network is appealing for utilizing individual vehicle data while preserving data privacy. We propose an improved local differential privacy-based federated learning approach for modeling charging session prediction problems while preserving user privacy against the threat from a honest-but-curious server. In this approach, all vehicles, within the coordination of a cloud server, collaboratively establish a global regression network through parameter exchange. Meanwhile, the servers may belong to third-party model owners and can be semi-honest when inferring private information on the collected model parameters. Hence, local differential privacy is adopted to perturb the parameters. Additionally, a combination of local and global models via elastic synchronization is proposed to improve the accuracy of the learned noisy global model. Through the test on a real data set, the results show the superiority of the proposed algorithm over traditional noisy federated learning methods. Furthermore, the practical value of the proposed method is validated with a real-world charging case. Such an accurate charging session prediction service for electric vehicle drivers facilitates charging and travel convenience in the green transportation world.

An empirical analysis of electric vehicle charging behavior based on real Danish residential charging data

In the last two years there has been a significant increase in the global adoption of electric vehicles (EVs). Particularly in Denmark, 40% of new vehicle registrations in 2023 were electric, marking a notable shift towards e-mobility. As a result, EV loading begins to constitute a large part of residential electricity demand. The concurrent increase in the interest for reduction in charging costs via demand response leads to a growing need for better understanding of charging behavior and its impact on consumption profiles. This works addresses the lack of up-to-date large-scale empirical studies on residential EV charging behavior. It presents a thorough analysis of all important charging characteristics based on a large set of 5534 Danish residential chargers between 2021 and 2023, providing unique insight in the effect of user-induced controlled charging. Our analysis shows the difference between actual charging profiles and those commonly used by distribution system operators in Denmark, and reveals the significant change over the span of one year with the doubling of peak demand per charger from 1.25 kW to 2.5 kW.

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.

Research on the analysis strategy of electric vehicle charging demand based on multi-correlation daily scenario generation

Abstract With the continuous increase of the penetration rate of OFELECTRIC vehicles, their high random charging loads exert a more significant effect on the stability of the electrical system. Simultaneously, the past charging patterns of electric vehicles indirectly influence the possible future charging activities of these vehicles. Therefore, in order to characterize the correlation between the predicted daily charging behavior of electric vehicles and its historical daily charging behavior, this article uses scene generation theory to fully mine the original multi-correlation Internal characteristics of electric vehicle charging behavior among the original multi-correlation day charging scenario set (OMCDCSS), generating massively generating multi-correlation day charging scenarios (GMCDCS) similar to the probability distribution of OMCDCSS. Secondly, the related scene set (RSS) is screened in the generation of multi-correlation day billing scenario (GMCDCSS) on the basis of weighted Spearman rank (SR). Get the forecast result of electric vehicle load interval.

Exploring the Impact of Charging Behavior on Transportation System in the Era of SAEVs: Balancing Current Request with Charging Station Availability

Shared autonomous electric vehicles (SAEVs) can offer safer, more efficient, and more environmentally friendly real-time mobility services with advanced autonomous driving technologies. In this study, a multi-agent-based simulation model considering SAEVs’ vehicle range and charging behavior is proposed. Based on real-world datasets from the Luohu District in Shenzhen, China, various scenarios with different fleet sizes, charging rates, and vehicle ranges are established to evaluate the impact of these parameters on parking demand, charging demand, vehicle miles traveled (VMT), and response time in the era of SAEVs. The results show there would be much more charging demand than parking demand. Moreover, a larger fleet size and longer vehicle range would lead to more parking demand, more charging demand, and more VMT while increasing the charging rate can dramatically reduce the charging demand and VMT. Average response time can be reduced by increasing the fleet size or the charging rate, and a larger vehicle range leads to longer response time due to the longer time spent recharging. It is worth noting that the VMT generated from relocating from the previous request destination to the origin of the upcoming request accounts for nearly 90% of the total VMT, which should be addressed properly with appropriate scheduling. A charging policy considering current requests and the availability of charging stations was proposed and verified in terms of reducing the response time by 2.5% to 18.9%.

Insights into Household Electric Vehicle Charging Behavior: Analysis and Predictive Modeling

In the era of burgeoning electric vehicle (EV) popularity, understanding the patterns of EV users’ behavior is imperative. This paper examines the trends in household charging sessions’ timing, duration, and energy consumption by analyzing real-world residential charging data. By leveraging the information collected from each session, a novel framework is introduced for the efficient, real-time prediction of important charging characteristics. Utilizing historical data and user-specific features, machine learning models are trained to predict the connection duration, charging duration, charging demand, and time until the next session. These models enhance the understanding of EV users’ behavior and provide practical tools for optimizing the EV charging infrastructure and effectively managing the charging demand. As the transportation sector becomes increasingly electrified, this work aims to empower stakeholders with insights and reliable models, enabling them to anticipate the localized demand and contribute to the sustainable integration of electric vehicles into the grid.

Charging prediction for new energy electric vehicles in the context of vehicle to grid using a hybrid ROCNN-BILSTM model

Abstract Vehicle to grid refers to the interaction between electric vehicles and the power grid through charging stations. It aims to guide owners of new energy vehicles to charge in an orderly and staggered manner, and even enabling power supply back to the grid. In the context of vehicle to grid, the charging behavior of new energy vehicles becomes different from the past due to uncertainties introduced by user plug-in/plug-out actions and weather conditions, which may disrupt owners’ future scheduling plans. In this article, we propose a charging prediction study based on the Reordering Convolutional Neural Network-Bidirectional Long Short-Term Memory (ROCNN-BILSTM) hybrid model specifically designed for the vehicle to grid context. The proposed model employs wavelet threshold denoising as a data preprocessing operation to remove unnecessary noise factors that could affect predictions. Subsequently, the 2-Dimensional Convolutional Neural Network (2D-CNN) component retains temporal features while extracting spatial features. Notably, the features are rearranged, combining highly correlated ones, to facilitate the extraction of high-level, abstract spatial features by the 2D-CNN. Finally, the Bidirectional Long Short-Term Memory (BILSTM) component utilizes a bidirectional structure to capture comprehensive dynamic information and assist in achieving the final charging prediction. Our proposed ROCNN-BILSTM eliminates uncertainty in the data, allowing deep learning models to better focus on important features. Additionally, our model emphasizes high-level spatiotemporal feature extraction, which helps achieve high-performance charging prediction. In the context of vehicle to grid, a real-world dataset of new energy vehicle charging data was used for multi-step prediction, different starting point predictions, and comparison with advanced models. The experimental results show that the proposed model outperforms CNN-LSTM and 2D-CNN models by up to 50.1% and 57.1% in terms of mean absolute error (MAE), and 45.8% and 51.5% in terms of mean squared error (MSE). The results validate the strong predictive performance of the hybrid model and provide robust support for the demands of the vehicle to grid market and new energy vehicle charging prediction technology. In future work, we will place greater emphasis on designing high-performance and interpretable models to explore the fundamental reasons behind different charging trends in new energy vehicles.

A Literature Review on the Charging Behaviour of Private Electric Vehicles

Electric mobility is one of the ways of containing greenhouse gas and local pollutants emissions in urban areas. Nevertheless, the massive introduction of battery-powered electric vehicles (EVs) is introducing some concerns related to their energy demand. Modelling vehicle usage and charging behavior is essential for charge demand forecasting and energy consumption estimation. Therefore, it is crucial to understand how the charging decisions of EV owners are influenced by different factors, ranging from the charging infrastructure characteristics to the users’ profiles. This review examines the approaches used to investigate charging behavior and highlights the trends and differences between the results, remarking on any gaps worthy of further investigation.

Research on new energy vehicle charging prediction based on Monte Carlo algorithm and its impact on distribution network

With the vigorous promotion of new energy policies, the large-scale charging of new energy vehicles has put forward higher requirements for the safety and stability of the distribution network. Based on the daily driving habits and charging patterns of new energy vehicles, a Monte Carlo sampling algorithm was used to establish a charging load model for new energy vehicles. The model analyzed the driving range, charging load, and time related parameters of new energy vehicles. By analyzing the law of daily charging power of new energy vehicles, the overall trend of charging load of new energy vehicles is obtained. Combined with the daily electricity consumption law of the distribution network, the total load of the distribution network is obtained, and the degree of impact on the distribution network is analyzed. This provides direction for the scheduling of future electric vehicle charging behavior and the construction of related supporting facilities, and provides strong guidance for the optimization and upgrading of the distribution network.

Driving change: Electric vehicle charging behavior and peak loading

Electric vehicles (EVs) are projected to comprise 40 % of Aotearoa New Zealand's light vehicle fleet by 2040. However, charging decisions made by EV drivers, such as whether to charge immediately or delay charging, will affect peak electricity demand and lifetime of distribution network components. This study uses an agent-based model (ABM) of EV charging to investigate the effect of different EV penetration levels and owner charging decisions on components in New Zealand's residential electricity networks, although the methodology is wholly generalizable to other countries or regions. Monte Carlo simulation is performed for EV charging in a neighborhood of 71 houses, based on a representative residential distribution network, and simulated for 20 days. The key outcome measure is the rate of ‘Exceedance’ of the 300 kVA baseline transformer limit, where greater Exceedance entails shorter lifecycle and increased maintenance or capital costs to the provider. Results show delayed-charging algorithms (‘Altruistic charging’) decrease peak electricity demand and Exceedance, while drivers charging immediately (‘Selfish charging’) increases Exceedance. New Zealand's residential electricity networks are expected to accommodate a 40 % EV transition with 100 % Altruistic charging, as Exceedance is expected to increase less than 20 % from Exceedance without EVs. However, Selfish charging increases the rate of Exceedance by more than 250 %. Longer-term, increasing EV penetration and household electricity demand will require increased workplace charging infrastructure, electricity network upgrades, and/or automated and Internet of Things (IoT)-enabled Demand Side Management (DSM) of EV charging to avoid high rates of Exceedance and increased maintenance and replacement costs.

Research on data mining model of fault operation and maintenance based on electric vehicle charging behavior

In recent years, with the development of new energy technology and the country’s strong support for electric vehicles, there is a lack of effective electric vehicle charging fault analysis and diagnosis methods at this stage. A comprehensive analysis of the working principle of the charging process of electric vehicles, based on the clarification of the failure mechanism of the power battery and charging equipment, analyzes the fault-related factors affecting the power battery and charging equipment from multiple angles, and summarizes the relationship between the power battery and charging equipment. The feature parameters related to equipment failure are discretized by the k-means clustering algorithm. Using the optimized FP-Growth algorithm based on weights, the association rules between the power battery and charging equipment failures and the characteristic parameters of the failure factors are mined, and the correlation of the failures is analyzed based on the association rules, and the correlation between the failure factors and the failures is obtained relevant level.

An optimal coordinated planning strategy for distributed energy station based on characteristics of electric vehicle charging behavior under carbon trading mechanism

Under the dual-carbon goal, the number of electric vehicle (EV) has surged, and the uncertainty of the temporal and spatial characteristics of the load has become prominent, which brings the challenge for higher requirements to the equipment composition of distributed energy station (DES) and performance of station-network. This paper proposes a collaborative planning method for low-carbon DES with networks, which is focusing on the characteristics of EV charging behavior. First of all, based on the quantitative analysis of the temporal and spatial distribution of charging load of four typical types of EV, including private vehicle, public vehicle, taxi and bus, the Monte Carlo method is used to construct the charging load modeling of EV in the region area. In addition, the low-carbon DES is modeled equipped with photovoltaic (PV) and power to gas (P2G) devices, and the Prim algorithm is adopted to search for the optimal network layout of energy transmission pipelines in the region area. Under carbon trading mechanism, aiming at the lowest annualized total cost of the regional station-network, a station-network collaborative planning modeling strategy for the capacity allocation of low-carbon DES with networks is established. Finally, the case study for a project in Beijing China is implemented on MATLAB, to prove the effectiveness of the method proposed in the paper. The time-of-use electricity price scheme changes the temporal and spatial characteristics of EV load. For example, more than 2 MW the EV load can be brought into the valley price range, which reduces the carbon transaction cost and energy purchase cost of DES by 50 thousand yuan almost when peak-valley electricity price difference is close to 1.2 yuan. At the same time, the growth of EV charging load(the penetration rate of EV can reach up to 20%) in the planning area has not increased the investment and operation-maintenance costs of DES equipment.

Effects of long-range electric vehicles on distribution system using probabilistic analysis

The number of electric vehicles with larger battery capacity that charges at higher power levels is increasing in residential areas. This scenario directly impacts users' charging behavior and modifies the demand profile of electric vehicles. This paper evaluates the effects of long-range electric vehicles on total charging demand, transformer loading and voltage quality in a real distribution system. Electric vehicles demand is modeled based on real-world data obtained from a large-scale project developed in the United Kingdom. This study proposes performance indices to perform a qualitative analysis of the system and uses Monte Carlo Simulation to consider uncertainties in residential demand and vehicle charging behavior. The results show that the current trend of adopting long-range vehicles that charge at higher power levels modifies vehicles charging frequency and duration. It increases transformer peak demand, and the number of hours the transformer operates overloaded. Voltage quality violations occur less frequently when three-phase connectors are used to charge vehicles, as they split demand between phases.© 2017 Elsevier Inc. All rights reserved.

Optimal scheduling of electric vehicle charging operations considering real-time traffic condition and travel distance

As the number of electric vehicles (EVs) increases rapidly, the problem of electric vehicle charging has widely become a concern. Therefore, considering the fact that charging time for one EV cannot be shortened quickly and the number of charging stations will not expand rapidly, how to schedule charging operations of electric vehicles in urban areas becomes a very important issue, since it can improve charging efficiency and relieve charging anxiety of EV users. Up to now, there is no scheduling software tool for practical use in this field. Based on the analysis of electric vehicle charging behavior characteristics, this paper investigates the EV charging problem at the scheduling level. First, a mathematical model for coordinated charging of EVs is proposed to minimize the total charging time for a given number of vehicles. Second, an earliest finish charging scheduling algorithm is presented to solve the charging problem. Then, by considering the combinatorial nature and practical applications with large number of EVs, two practical swarm-optimization-based EV charging scheduling algorithms are proposed. A real-life case study is presented to illustrate the proposed approaches.

Situation Awareness of Electric Vehicle Charging Load Based on Random Forest Algorithm

Due to the important characteristics of energy saving and carbon reduction, electric vehicles have attracted worldwide attention. It can be predicted that the power grid will be faced with the access problem of large-scale electric vehicles. In order to master the user behavior characteristics of electric vehicle load, it is necessary to establish the model based on electric vehicle charging behavior. In this paper, combined with the electric vehicle charging demand and the situational awareness results of the dispatchable resources in the station area, the characteristic indicators of the electric vehicle load are quantitatively analyzed. Situational prediction of electric vehicle load based on random forest algorithm is proposed, and the sample set is divided and trained. A simulation example is used to verify the effectiveness of the method provided in load forecasting.

Impact of Dynamic Electricity Tariff and Home PV System Incentives on Electric Vehicle Charging Behavior: Study on Potential Grid Implications and Economic Effects for Households

The rapid increase of electric vehicles (EVs) would lead to a rise in load demand on power grids but create different potential benefits as well. Those benefits comprise EVs serving as a mobile energy storage system to participate in adjusting the load on the power grids and helping manage renewable energy resources. This paper evaluates the effect of dynamic electricity prices and home photovoltaic (PV) system incentives on users’ EVs charging behavior and potential impacts on grid load and household economy. This has been done by establishing and assessing three different optimized charging configurations and comparing them to an uncontrolled charging strategy. In this study, the charging incentives are applied to a representative sample of 100 households with EVs and PV systems in a metropolitan area. The results show that an optimized charging strategy based on the dynamic electricity tariff can reduce charging costs by 18.5%, while a PV-based optimized strategy can reduce the costs by 33.7%. Moreover, the PV-integrated optimization strategies significantly increase the utilization of PV energy by almost 46% on average, compared to uncontrolled charging. In addition, the simulations of this research have depicted the capability of using home PV systems’ incentives to smoothen the charging profiles and hence significantly reduce the maximum grid load. However, the electricity price optimization strategy increases the aggregated charging peaks, which can only be slightly reduced by peak shaving. Therefore, an identical price signal for all households might be critical. Further analyses have shown that direct charging occurs simultaneously with household electricity assigned to a specific low-voltage grid while PV and price incentive charging configurations shift the charging peaks away from household load peaks.

Location and capacity determination of charging station based on electric vehicle charging behavior analysis

The infrastructure construction of charging facilities for electric vehicles (EVs) is one of the key factors influencing the development of electric vehicle industry. A reasonable location and capacity determination scheme is very crucial to this issue. In this study, a probability calculation model that fully analyses the charging behavior of the owners is proposed to predict the charging load of the planned land. Based on the results of electric vehicle load forecasting, a location model with the lowest users travel cost is established. The location of charging station is optimized by genetic algorithm to obtain the location and capacity library of charging station. Especially, the two‐way cost for both the owners and the operators is considered for the location and capacity decision, and the optimal scheme is selected from the location and capacity library as the final planning result. An example analysis shows that the proposed method is effective and feasible for the location and capacity determination of electric vehicles charging stations in cities. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.