Demand For Electric Vehicles Research Articles

Analyzing the influence of electric vehicle charging scheduling on distribution transformer lifespan

The ongoing growth in global electricity demand and rapid proliferation of electric vehicles (EVs) are posing challenges to the operation of the low voltage power networks and their components. This study aims to analyze the impacts of peak-load demand on the distribution transformers, considering mild and extreme combinations of electric energy demand and localized charging of plug-in EVs under their different penetration levels, hypothesizing that shifting the demand for charging throughout the day can reduce the aging of distribution transformers. The proposed method employs a fuzzy-logic-based tool, which incorporates the influence of ambient temperature, higher harmonics, reactive power compensation, reverse power flows, and overload. Three different charging/discharging modes have been considered: demand charging, off-peak charging, and synergy of off-peak charging and vehicle-to-house technology. The results indicate that off-peak charging emerges as 2.1 times more effective than demand charging in terms of the transformer's loss of life, particularly for ultimate EV penetration of 100 %. It is demonstrated that the utilization of charging scheduling for EVs should be prioritized to defer costly system upgrades and reinforcements, particularly when EV penetration exceeds 50 %.

Enhancing hosting capacity for electric vehicles in modern power networks using improved hybrid optimization approaches with environmental sustainability considerations

The increasing adoption of electric vehicles (EVs) presents both opportunities and challenges for power networks. While EVs have the potential to reduce carbon emissions, accommodating their growing power demand requires careful planning to prevent overloading and mitigate environmental impacts. This paper introduces an integrated hosting capacity model to facilitate higher EV penetration while maintaining environmental standards. In addition to EV charging stations, the model incorporates transmission lines, reactive power compensators, energy storage systems, and thyristor-controlled series compensators to ensure a reliable power supply. The model aims to maximize EV charging station deployment, minimize greenhouse gas emissions, and optimize net present value through hosting capacity strategies. Three hosting capacity plans are proposed to analyze the impact of prioritizing one of these objectives over the others in network configurations. Accurate EV demand forecasting is critical for this model, and a swarm intelligence forecasting algorithm is proposed to explore various forecasting approaches. The model is complex and involves nonlinear multi-objective optimization. To solve it, a new hybrid optimization algorithm is introduced, combining the features of the Marine Predators Algorithm and the Honey Badger Algorithm. Three hybridization schemes—Series Hybrid Scheme, Population Division Scheme, and Switching Strategy Scheme—are developed to address the optimization challenges effectively. The results show that the first and second hybridization schemes are the most effective for solving the EV load forecasting models, with a robustness of at least 90%. In contrast, the robustness of the third scheme reaches only 30% in some models. Simulation studies on the IEEE 9-bus network and the IEEE 30-bus system validate the model’s effectiveness in integrating EVs while achieving environmental sustainability objectives. The findings show the superiority of the proposed hybrid schemes in solving the hosting capacity model in terms of finding optimal solutions. However, the third scheme required less computing time than the others, with its convergence time being at least 33.3% shorter.

Modification of Lithium‐Rich Manganese Oxide Materials: Coating, Doping and Single Crystallization

AbstractThe increasing demand for portable electronics, electric vehicles and energy storage devices has spurred enormous research efforts to develop high‐energy‐density advanced lithium‐ion batteries (LIBs). Lithium‐rich manganese oxide (LRMO) is considered as one of the most promising cathode materials because of its high specific discharge capacity (>250 mAh g−1), low cost, and environmental friendliness, all of which are expected to propel the commercialization of lithium‐ion batteries. However, practical applications of LRMO are still limited by low coulombic efficiency, significant capacity and voltage decay, slow reaction kinetics, and poor rate performance. This review focus on recent advancements in the modification methods of LRMO materials, systematically summarizing surface coating with different physical properties (e. g., oxides, metal phosphates, metal fluorides, carbon, conductive polymers, lithium compound coatings, etc.), ion doping with different doping sites (Li sites, TM sites, O sites, etc.), and single crystal structures. Finally, the current states and issues, key challenges of the modification of LRMO are discussed, and the perspectives on the future development trend base on the viewpoint of the commercialization of LRMO are also provided.

PROPOSTA DE ELETROPOSTOS MODULARES PARA CARROS ELÉTRICOS ABASTECIDOS POR ENERGIA SOLAR

In recent years, the growing demand for electric vehicles has intensified the need for adequate infrastructure for their charging. Charging stations, dedicated to supplying energy to these vehicles, play a crucial role in the transition to sustainable urban mobility. This study proposes the development of modular charging stations powered by solar energy, focusing on solutions that favor sustainability and efficiency. The primary objective is to create systems that integrate photovoltaic technology, promoting the use of clean energy and contributing to the reduction of air pollution. The research evaluates the viability of on-grid and off-grid systems, aiming to optimize the efficiency of solar panels and reduce operational costs. Factors such as ideal location, shading prevention, and the environmental impacts of electric mobility are analyzed. Additionally, existing charging station examples are examined to identify best practices and innovations in urban design. The methodology includes exploratory and bibliographic research, utilizing case studies and literature reviews to support the proposal. As a result, the study culminates in a sustainable modular charging station proposal that is adaptable to different locations, promoting more efficient and eco-friendly mobility.

EOS: Impact Evaluation of Electric Vehicle Adoption on Peak Load Shaving Using Agent-Based Modeling

The increasing adoption of electric vehicles (EVs) by the general population creates an opportunity to deploy the energy storage capability of EVs for performing peak energy shaving in their households and ultimately in their neighborhood grid during surging demand. However, the impact of the adoption rate in a neighborhood might be counterbalanced by the energy demand of EVs during off-peak hours. Therefore, achieving optimal peak energy shaving is a product of a sensitive balancing process that depends on the EV adoption rate. In this paper, we propose EOS, an agent-based simulation model, to represent independent household energy usage and estimate the real-time neighborhood energy consumption and peak shaving energy amount of a neighborhood. This study uses Residential Energy Consumption Survey (RECS) and the American Time Use Survey (ATUS) data to model realistic real-time household energy use. We evaluate the impact of the EV adoption rates of a neighborhood on performing energy peak shaving during sudden energy surges. Our findings reveal these trade-offs and, specifically, a reduction of up to 30% of the peak neighborhood energy usage for the optimal neighborhood EV adoption rate in a 1089 household neighborhood.

Electrochemical recycling of lithium‐ion batteries: Advancements and future directions

AbstractLithium‐ion batteries (LIBs) are at the forefront of technological innovation in the current global energy‐transition paradigm, driving surging demand for electric vehicles and renewable energy‐storage solutions. Despite their widespread use and superior energy densities, the environmental footprint and resource scarcity associated with LIBs necessitate sustainable recycling strategies. This comprehensive review critically examines the existing landscape of battery recycling methodologies, including pyrometallurgical, hydrometallurgical, and direct recycling techniques, along with emerging approaches such as bioleaching and electrochemical separation. Our analysis not only underscores the environmental and efficiency challenges posed by conventional recycling methods but also highlights the promising potential of electrochemical techniques for enhancing selectivity, reducing energy consumption, and mitigating secondary waste production. By delving into recent advancements and juxtaposing various recycling methodologies, we pinpoint electrochemical recycling as a pivotal technology for efficiently recovering valuable metals, such as Li, Ni, Co, and Mn, from spent LIBs in an environmentally benign manner. Our discussion extends to the scalability, economic viability, and future directions of electrochemical recycling, and advocates for their integration into global battery‐recycling infrastructure to address the dual challenges of resource depletion and environmental sustainability.image

Design and analysis of a high-efficiency bi-directional DAB converter for EV charging

The escalating demand for electric vehicles (EVs) arises from apprehensions regarding fossil fuel depletion and the ecological repercussions of conventional combustion engines, propelling the transition towards environmentally sustainable alternatives. EVs are conventionally comprised of a powertrain, battery management system, and communication infrastructure, with the battery playing a pivotal role. Achieving an efficient EV battery charger necessitates the implementation of a proficient charging algorithm and a high-power converter capable of adeptly regulating battery parameters. Among the array of available options, a bi-directional DC/DC converter is often employed for this purpose. This study predominantly focuses on the Bi-Directional Dual Active Bridge Converter with Single-Phase Shift Control. It is renowned for attaining a broad voltage range through transformer turn ratio adjustments. Its controllable parameters, such as phase shift ratio and duty cycle, bolster its versatility. Moreover, due to its input–output isolation and minimal passive elements, this converter exhibits superior efficiency due to its soft-switching capabilities. The analytical framework encompasses steady-state and dynamic assessments, small-signal modeling, and system transfer function analysis, all of which contribute to formulating an optimized controller design. Additionally, the study conducts simulations of various battery charging techniques, including constant current (CC), constant voltage (CV), and CCCV mode, employing a 1.5 kW Dual Active Bridge DAB-based charger through MATLAB/SIMULINK. Furthermore, voltage mode control simulations for a 5 kW DAB converter augment the study's insights into effective EV charging strategies.

Efficient energy management and cost optimization using multi-objective grey wolf optimization for EV charging/discharging in microgrid

The depletion of conventional energy sources coupled with the rising demand for electric vehicles (EVs) has significantly underscored the necessity for electric vehicle supply equipment (EVSE) with advanced energy supply management within microgrids. Effective energy management of EVs and EVSEs is imperative to satisfy EV owners and stabilize microgrids. This paper introduces multi-objective grey wolf optimization (MOGWO) to optimize EVSE and EV charging costs. MOGWO achieves substantial cost savings through dynamic pricing based on time of day, state-of-charge and hour-based scheduling which promotes off-peak charging thereby enhancing system efficiency and reducing costs. The algorithm also provides flexibility for trip interruptions and outperforms other optimization algorithms in minimizing EV charging/discharging costs by achieving reductions of up to ₹488 and obtaining average grid efficiency up to 76.41 % during charging and 87.41 % during discharging. Integrating Vehicle-to-Grid and Grid-to-Vehicle systems enhances microgrid resilience and delivers economic benefits to EV owners. The cost optimization for EV charging/discharging has been executed using MATLAB 2023a software to determine the most cost-effective charging paths by considering energy availability and grid conditions. The evolving sustainable energy landscape combined with MOGWO paves the way for smarter and more resilient microgrids in the era of electrified transportation.

Self-building or sharing? The strategy analysis of building charging stations

Charging station sharing, as a new business model, can effectively reduce the building of unnecessary public charging stations and promote sustainable urban development. This study discusses whether the manufacturers introduce a charging station sharing strategy and identify the introduction conditions. We develop a strategic competition model where the two manufacturers engage in electric vehicles (EVs) and charging stations. The results show that charging stations have a facilitating effect on the EV market. In a sharing strategy, the low-end vehicle manufacturer can profit more when the contract cost is smaller. Comparing the strategies of self-building and sharing, the manufacturers should choose a self-building strategy when the cost coefficient of building the station, the brand advantage, and the contract cost are all larger. However, when the brand advantage and the contract cost are smaller, or both in the medium, the manufacturers should choose a sharing strategy. In addition, we also find that the substitutability of EVs and the cross-sensitivity of EVs and charging stations can lead to lower market demand for EVs. In a monopoly production scenario, encroachment by both the platform and the service provider leads to lower profits for the manufacturer. Therefore, it is more favorable for the manufacturer to self-build charging stations in the no-invader condition. Our analysis provides insights into when charging station sharing may be beneficial and when it may be detrimental to vehicle manufacturers.

Acoustic Noise Mitigation in Slip Angle Controlled DTC of Open-End Winding Induction Motor Drive Using Dual Randomized AISPWM for EV Application

Low vibration and acoustical noise as well as effective DC link usage are the demands of industries and Electric Vehicles (EV). Direct Torque Control (DTC) of Induction Motors (IMs) meet the EV and other modern industry requirements. Still, flux as well as torque swings lead to higher acoustical noise. Consequently, EVs as well as working place noise have become major concerns, affecting the health of individuals. Efficiency of dc link use is improved by Space Vector Pulse Width Modulation (SVPWM). Yet, SVPWM is not efficient in lowering acoustical noise. Different RPWM techniques can lower acoustic noise. Still, the lower degree of randomisation makes the noise reduction difficult. This work presents a Hybrid Dual Random PWMs (HDRPWMs) based Alternate Inverter Switching (AIS) strategy for Slip-Angle Controlled Direct Torque Control of an Open End Winding IM Drive (OEWIMD). This technique is aimed to lower the acoustical noise for EVs. The intended PWMs seek to show how well HDRRPWMs distribute the acoustical noise spectra in contrast to conventional techniques.

Empowering sustainable hotels: a guest-centric optimization for vehicle-to-building integration

In light of global warming, hotels account for one of the highest energy demands within the building sector, offering great decarbonization potential. As electrification increases, so does the demand for electric vehicles (EVs) charging stations at hotels and the proportion of Vehicle-to-Building-capable EVs. Therefore, the study explores the potential of guest-centric energy management. To accomplish this, we develop an optimization model for an energy management system that focuses on either cost-efficiency or carbon dioxide equivalents (CO2)-efficiency, grounded in a real-world case study. Through scenario analyses considering seasons as well as different guest mobility behaviors, this study discusses the expenses associated with CO2 savings using digital solutions. It emphasizes the currently perceived conflict between cost reduction and decarbonization goals to achieve a sustainable design of information systems. Thereby, this study highlights the critical importance of individual mobility behavior in enabling sustainable energy management for hotels.

Comparative environmental and economic assessment of emerging hydrometallurgical recycling technologies for Li-ion battery cathodes

The growing demand for electric vehicles has led to a growing concern for battery recycling, particularly for critical raw materials. However, there is insufficient investigation into the environmental and economic impacts of hydrometallurgical recycling methods. In this study we explored emerging hydrometallurgical technologies in economic and environmental perspective to establish conceptual routes to recover Co, Ni and Mn oxides from waste LiNi0.33Mn0.33Co0.33O2 cathode materials from spent Li-ion batteries. After, life cycle assessment and costing techniques were utilized to compare the environmental and economical performances of each conceptual route. Recovery efficiency of metal oxides through each route was also considered as a key factor. Results suggested that deep eutectic solvent-based leaching produces the highest impact under many impact categories while electrolysis-based leaching showed the least. Under purification technologies assessed, ion-exchange based purification showed significantly lower impact under many categories except stratospheric ozone depletion. Solvent based purification has been identified as the worst technology for purification. Hydroxide based calcination has been identified as the most environmentally sustainable calcination method compared to oxalate calcination. The route consists with inorganic leaching, ion-exchange based purification and hydroxide calcination showed the lowest environmental impact (emission effect at 33.8 kg CO2 eq), with lower economic impact ($ 119) and the highest recovery efficiency (78 %) per 1 kg of cathode active materials. However, using electrolysis-based leaching can slightly increase the impacts with lower recovery efficiency (75 %) and better economic performance ($104/kg of cathode active materials). Terrestrial ecotoxicity was identified to be the most affected impact category for the recovery processes. It is recommended that technologies like deep eutectic solvent-based leaching, solvent extraction and environmentally sustainable technologies like supercritical fluid extraction need further studies prior to industrial applications.

A novel energy management of public charging stations using attention-based deep learning model

Electricity grids are complex systems that must balance the supply and demand of electricity in real-time. However, with the increasing adoption of electric vehicles (EVs), managing the grid’s stability has become more challenging. EV charging can cause spikes in electricity demand, leading to peak demand periods that strain the power grid’s infrastructure. With the help of load forecasting, this effect on the grid can be mitigated by predicting the charging demand of electric vehicles in advance. This will help utilities adjust their energy supply in real-time, ensuring enough energy is available to meet demand, and preventing overloads or under utilization of the grid. Moreover, the EV charging demand is influenced by a wide range of factors, including charging station locations, weather, and time of day. Therefore, advanced deep learning models are required to learn these complex relationships and identify patterns in EV charging demand, enabling utilities to make more informed decisions. In this research, an attention-based deep learning approach is proposed for more accurate prediction of EV load demand. This novel approach integrates attention mechanisms with traditional deep learning models like LSTM and GRU, allowing the model to dynamically weight the importance of different features and focus on the most relevant information. The outcomes are compared to conventional deep learning and machine learning algorithms. To test the efficacy of the proposed framework, an actual ACN dataset for public EV charging stations is utilized.

Optimization of the power–transportation coupled power distribution network based on stochastic user equilibrium

With the increasing penetration of electric vehicles (EVs) in road traffic, the spatial and temporal stochasticity of the travel pattern and charging demand of EVs as a mode of transportation and an electrical load have generated different degrees of congestion impacts on both the power grid and the transportation network. Based on this, this paper proposes a power–transportation-coupled distribution network optimization strategy based on stochastic user traffic equilibrium theory. First, a stochastic user equilibrium-mixed traffic flow allocation model that expresses user non-completely rational path selection behavior is established, and the traffic flow equilibrium solution is obtained using an improved method of successive algorithm and mapped to charging loads. Second, a distribution network power flow optimization model under the coupled power–transportation architecture is established to optimize the operation state of the distribution network by combining distributed resources such as energy storage, demand response loads, wind power, photovoltaic, and gas turbines.

Enhanced electric vehicle battery management system employing bat algorithm with chaotic diversification strategies

AbstractAs the demand for electric vehicles (EV) continues to increase, the need for effective charging and switching of battery systems becomes more important. This article presents a method using the Bat Algorithm (BA) improved by chaotic diversification as well as social education to optimize the power source replacement and the electric vehicle charging procedure. The plan is intended to solve the issues of payment delay and battery management failure. The algorithm searches for better positions by combining chaotic diversity, while social learning supports the coordination of battery stations. Thanks to extensive simulation and real‐world testing, our approach shows significant improvements in optimization and a reduced payback period. The results show that the suggested approach outperforms the current algorithms in terms of rotation speed and good solution. This research supports the development of efficient transportation by providing practical solutions to increase the efficiency of electric vehicle transfer and payment and ultimately encourage greater effort.

Stochastic modeling of multiple-server charging stations for electric vehicle networks using feedback strategies: A queueing-theoretic approach

Nowadays, electric vehicles (EVs) significantly affect transportation as they provide a more environmentally friendly alternative to traditional fossil-fueled automobiles. Electric vehicles, which depend on energy stored in batteries, significantly contribute to environmental preservation and comply with worldwide efforts to tackle climate change. However, the growing demand for electric vehicles causes traditional power grids under pressure emphasizing the necessity of establishing a suitable infrastructure for charging electric vehicles. Charging stations are becoming increasingly critical since they allow for the recharging of electric vehicles and play a significant role in stabilizing the power system. In order to optimize charging station infrastructure with multiple servers, the current research incorporates a Markovian queueing modeling approach. The primary objective of the study is to address queue management concerns and boost overall productivity. Considering the real-world challenges, a queue-based stochastic model for multi-server EV systems and individual feedback strategies is developed. Subsequently, a transition state diagram is provided by balancing the input-output rates between the adjacent states. Next, the system of Chapman-Kolmogorov differential-difference equations is formulated to help understand mathematical modeling better. The matrix method is employed to demonstrate the state probability distribution in equilibrium. The infographics are utilized and incorporated for better visualization of the research findings. For a better understanding from an individual's point of view, numerous managerial insights are provided. Lastly, several concluding remarks and future perspectives are provided that can help decision-makers and practitioners to construct and analyze economic strategies based on EV management systems.

Polyethyleneimine Modified Two-Dimensional GO/MXene Composite Membranes with Enhanced Mg2+/Li+ Separation Performance for Salt Lake Brine.

As global demand for renewable energy and electric vehicles increases, the need for lithium has surged significantly. Extracting lithium from salt lake brine has become a cutting-edge technology in lithium resource production. In this study, two-dimensional (2D) GO/MXene composite membranes were fabricated using pressure-assisted filtration with a polyethyleneimine (PEI) coating, resulting in positively charged PEI-GO/MXene membranes. These innovative membranes, taking advantage of the synergistic effects of interlayer channel sieving and the Donnan effect, demonstrated excellent performance in Mg2+/Li+ separation with a mass ratio of 20 (Mg2+ rejection = 85.3%, Li+ rejection = 16.7%, SLi,Mg = 5.7) in simulated saline lake brine. Testing on actual salt lake brine in Tibet, China, confirmed the composite membrane's potential for effective Mg2+/Li+ separation. In the actual brine test with high concentration, Mg2+/Li+ after membrane separation is 2.2, which indicates that the membrane can significantly reduce the concentration of Mg2+ in the brine. Additionally, the PEI-GO/MXene composite membrane demonstrated strong anti-swelling properties and effective divalent ion rejection. This research presents an innovative approach to advance the development of 2D membranes for the selective removal of Mg2+ and Li+ from salt lake brine.

Optimizing peak-shaving cooperation among electric vehicle charging stations: A two-tier optimal dispatch strategy considering load demand response potential

The increase in the grid connection of electric vehicles (EVs) provides great potential for peak load regulation and valley filling of the grid. In order to solve the challenges brought by the integration of new energy vehicles into the power grid and give full play to the potential of EV demand response, this paper proposes a two-layer optimal dispatch strategy for the “distribution network-charging station” system. First, assess EV load demand response potential. The research area is divided into different functional areas by using the data of urban interest points, and the travel habits of users are analyzed by using EV driving data. On this basis, considering the influencing factors such as EV battery capacity (SOC), charging electricity price and spatial characteristics, the EV load response potential evaluation model is constructed by integrating user electricity price response and charging power response. Secondly, taking the evaluation value of EV response potential as the range of load adjustment, in order to optimizing peak-shaving cooperation among EV charging stations and obtaining the peak-shaving measures of each charging station, a “distribution network-charging station” double-layer optimal dispatch is carried out. The upper-level distribution network scheduling aims at minimizing the unfinished peak shaving rate and distribution network loss, and optimizes the scheduling power allocation of the peak tasks of each charging station. The lower-level charging station scheduling is based on the principle of maximizing user charging satisfaction and charging station economic benefits, and completes the peak-shaving scheduling determined by the superior. Finally, the strategy is applied in a specific area of Shaanxi Province, and the scheduling results show that the strategy is more economically feasible.

Assessing the diffusion of photovoltaic technology and electric vehicles using system dynamics modeling

Amidst the sweeping changes in the global electricity and automotive sectors, we observe a rapid surge in the proliferation of distributed generation (DG) and electric vehicles (EVs), primarily driven by the widespread deployment of photovoltaic systems. The widespread embrace of EVs necessitates a dual approach of financial incentives and infrastructure development to enhance the appeal of these vehicles. The findings presented in this paper hold significant importance for policymakers, underscoring the urgency of transitioning toward sustainable decentralized power systems and promoting EV adoption. While this transition offers promising opportunities, it also presents formidable challenges. Successful integration of DG and EVs demands careful attention to policy and regulatory frameworks. Some experts advocate for simultaneous adjustments in design, addressing mobility limitations and offering incentives for DG and EVs. Given the multitude of uncertainties, the authors suggest employing a system dynamics model to analyze the impact of photovoltaic technology and EV diffusion. The paper concludes that, within the Colombian context, the potential exists, under specific conditions, to increase the adoption of solar panels and EVs in households. This, in turn, contributes to a reduction in CO2 emissions and a transformative shift in the composition of the automotive fleet toward EVs.

Electric Vehicle Charging Load Demand Forecasting in Different Functional Areas of Cities with Weighted Measurement Fusion UKF Algorithm

The forecasting of charging demand for electric vehicles (EVs) plays a vital role in maintaining grid stability and optimizing energy distribution. Therefore, an innovative method for the prediction of EV charging load demand is proposed in this study to address the downside of the existing techniques in capturing the spatial–temporal heterogeneity of electric vehicle (EV) charging loads and predicting the charging demand of electric vehicles. Additionally, an innovative method of electric vehicle charging load demand forecasting is proposed, which is based on the weighted measurement fusion unscented Kalman filter (UKF) algorithm, to improve the accuracy and efficiency of forecasting. First, the data collected from OpenStreetMap and Amap are used to analyze the distribution of urban point-of-interest (POI), to accurately classify the functional areas of the city, and to determine the distribution of the urban road network, laying a foundation for modeling. Second, the travel chain theory was applied to thoroughly analyze the travel characteristics of EV users. The Improved Floyd (IFloyd) algorithm is used to determine the optimal route. Also, a Monte Carlo simulation is performed to estimate the charging load for electric vehicle users in a specific region. Then, a weighted measurement fusion UKF (WMF–UKF) state estimator is introduced to enhance the accuracy of prediction, which effectively integrates multi-source data and enables a more detailed prediction of the spatial–temporal distribution of load demand. Finally, the proposed method is validated comparatively against traffic survey data and the existing methods by conducting a simulation experiment in an urban area. The results show that the method proposed in this paper is applicable to predict the peak hours more accurately compared to the reference method, with the accuracy of first peak prediction improved by 53.53% and that of second peak prediction improved by 23.23%. The results not only demonstrate the high performance of the WMF–UKF prediction model in forecasting peak periods but also underscore its potential in supporting grid operations and management, which provides a new solution to improving the accuracy of EV load demand forecasting.