Electric Vehicle Charging Research Articles

ChatEV: Predicting electric vehicle charging demand as natural language processing

The increasing popularity of electric vehicles (EVs) in recent times has introduced considerable load conditions for urban power grids and transportation systems, which highlights the importance of accurately predicting charging demand to enhance charging efficiency. However, current forecasting methods still face challenges in effectively aligning diverse data and generating accurate predictions that can be applied to unseen scenarios. To overcome the challenges, this work introduces a novel perspective: employing large language models (LLMs) as EV charging demand predictors. First, we reformulate the prediction task into a text-to-text format, enabling seamless and effective alignment of various features within a unified language semantic space. Subsequently, we fine-tune a LLM using a meta-learning framework to adapt it specifically for EV charging prediction. Through comprehensive evaluations, it has been demonstrated that the proposed model, ChatEV, achieves outstanding performance in EV charging demand forecasting, particularly in scenarios with limited data.

Investigating the effects of variable pulse charging on temperature during charging of battery electric vehicles

This study investigates the efficacy of variable pulse charging (VPC) on charging 18,650 secondary battery packs (12 V, 20 Ah) with NMC chemistry. VPC, a modern technique applied to secondary battery charging, aims to mitigate effects like a thermal runaway and thermal propagation caused by increased charging temperature. VPC involves varied duty factors (10 % to 90 %), charging rates (0.5C, 1C, 1.5C), and an optimal switching frequency determined through frequency response analysis. Its digital model is based on in situ electrochemical impedance spectroscopy measurements and MATLAB/Simulink simulations. At charging rates of 0.5C (10 A), 1C (20 A), and 1.5C (30 A), the temperature of the battery pack reaches 42.46 °C, 57.87 °C, and 70.37 °C, respectively. However, implementing VPC at a 50 % duty factor yields temperature reductions of 3.66 °C, 5.06 °C, and 5.42 °C, respectively. Similarly, employing VPC at a 10 % duty cycle results in temperature reductions of 11.2 °C, 17.7 °C, and 19.1 °C, respectively. The results indicate a significant reduction in charging temperature compared to constant current charging. Furthermore, the 1C condition is validated using a custom-made dual active bridge DC-DC variable pulse charger. In conclusion, applying optimal frequency-based VPC with specific duty factors demonstrates the potential to reduce temperature elevation during battery pack charging significantly.

Design and evaluation of a standalone electric vehicles charging station for a university campus in Argentina

The increasing popularity of electric vehicles in recent years has led to a growing demand for charging stations. In this context, universities are an ideal setting for their installation, as they have a large number of students, professors, and staff who could benefit from them and, at the same time, it serves as teaching material to raise awareness in the use of renewable energy. This work presents the design and proposal of an electric vehicle charging station for the campus of the Universidad Nacional de Rafaela (UNRaf). The station will be located in an area of the campus where the construction of more buildings and sport facilities is planned. This area will not be connected to the electrical grid and instead, will have an energy storage system to guarantee supply. The station will have the capacity to simultaneously charge 4 bicycles and 2 light electric vehicles, with an average energy demand of 0.786 kWh per hour. Homer Pro software was used for the calculations. The most economically viable option was a 100% renewable solution powered only by solar energy. It is expected to consist of a 15-kW solar system that will produce 22,922 kWh/year and a bank of 30 batteries of 3 kWh plus a single battery of 1 kWh. The installation of the electric vehicle charging station on the UNRaf campus will contribute to promoting the adoption of sustainable transportation, which will help reduce greenhouse gas emissions without using the public power grid.

Solar Wireless Electric Vehicle Charging System

This project outlines the design and implementation of a solar-powered electric vehicle charging station that addresses the dual challenges of high gasoline prices and harmful emissions. The number of countries adopting electric vehicles continues to rise, as they not only promote environmental sustainability but also significantly lower transportation costs by substituting expensive fuels with more affordable electricity. In this context, developing an electric vehicle charging infrastructure offers an innovative and effective solution. This system enables electric vehicles to charge while in motion, eliminating the need for stationary charging stops. Powered entirely by solar energy, it requires no additional power supply. The system incorporates solar panels, batteries, transformers, regulator circuits, copper coils, AC/DC converters, Atmega328P controllers, and LCD displays. This technology demonstrates the feasibility of an on-road solar-powered wireless charging system for electric vehicles.

Application of safety and stability optimization algorithms for charging connection devices in high-power charging systems

In response to the safety and stability issues of current electric vehicle charging connection devices, this study proposes a charging system planning for electric vehicles with different capacity charging piles based on the user behavior characteristics of electric vehicles and Monte Carlo methods. It is found that the predicted results under the set management strategy are most consistent with the trend of actual load changes. Moreover, in the prediction of weekly load, the research strategy has better performance than traditional unmanaged strategies. Under the research scheme, the average charging speed of charging piles with capacity of A and B in the peak period was 41.4 min/ and 18.8 min/, respectively, which increased by 29.3% and 11.7% respectively compared with 58.6 min/ and 21.3 min/ in the normal period. The total economic cost of the research plan was 4.871 million yuan, which was 67.0 million yuan and 3.833 million yuan lower than the control methods 1 and 2, respectively. The total number of charging stations of types a and b that need to be purchased for the research method decreased by 18.47% and 63.24% compared to the comparative method 3. The results indicate that the research method significantly improves the utilization rate of charging stations in the electric vehicle charging system. This study has important application value in the intelligent management of electric vehicle charging systems.

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.

A comparative analysis of operational planning for battery swapping and fast charging in electric vehicles

A comparative analysis of operational planning for battery swapping and fast charging in electric vehicles

Innovative Feature Analysis of Electric Vehicle Technology, Charging Infrastructure, Power management, and Control Methods

Lowering the dependence on fossil fuels and reducing pollution from greenhouse gas (GHG) emissions is incredibly achievable through electric vehicle (EVs) technology. EV technology is an innovation that uses electricity, rather than fossil fuels, to power and refuel (recharge) vehicles. The adoption and development of EVs should lead to a decline in future demand for fossil fuels, which are finite in supply and exhaustible. Inherent challenges in EV technology, such as inadequate supply of critical minerals, power grid overload, battery technology constraints, extended charging durations, insufficient charging infrastructures, high initial costs, and limited driving range, must be addressed. The technology of charging infrastructures cannot be over-emphasized in EV technology. EV technology, charging infrastructures, vis-à-vis the impact of their integration into the grid is investigated. Effective control strategies and power management systems (PMSs) are required to optimize energy use to improve EVs' efficiency and lifetime. This research uses comprehensive analysis methods to assess various control strategies, PMSs, and their effects on EV integration into the grid.

A Stochastic Approach to the Power Requirements of the Electric Vehicle Charging Infrastructure: The Case of Spain

Battery electric vehicles represent a technological pathway for reducing carbon emissions in personal road transport. However, for the widespread adoption of this type of vehicle, the user experience should be similar to that of combustion engine vehicles. To achieve this objective, a robust and reliable public charging infrastructure is essential. In Spain, the electric recharging infrastructure is growing quickly in metropolitan areas but much more slowly on roads and highways. The upcoming charging stations must be located along high-volume traffic corridors and in proximity to the Trans-European Transport Network. The main contribution of this research is to offer a method for examining the essential electricity infrastructure investments required in scenarios involving substantial electric vehicle adoption. The methodology includes a sensitivity analysis of fleet composition and market share, recharging user behavior, charging station density, and vehicle efficiency improvements. To this end, the authors have developed a simplified probabilistic model, addressing the effect of the involved parameters through a comprehensive scenario analysis. The results show that the actual number of high-capacity charging plugs on Spanish roads is significantly lower than the European regulation requirements for the year 2030 considering an electric vehicle market share according to the Spanish Integrated National Energy and Climate Plan 2021–2030 objectives and it is far from the necessary infrastructure to cover the expected demand according to the traffic flow. Under these circumstances, the charging peak power demand reaches over 7.4% of the current Spanish total power demand for an electric vehicle fleet, which corresponds to only 12% of the total.

Intelligent Energy Management for Electric Vehicle Charging

Intelligent Energy Management for Electric Vehicle Charging

Policy interventions and urban characteristics in modeling electric vehicle charging infrastructure utilization

The surge in electric vehicles adoption necessitates understanding the impact of policy interventions on public electric vehicle charging infrastructure in urban areas. This research investigates the influence of pricing frameworks on the usage of public charging facilities by analyzing both behavioral and spatial attributes of these infrastructures. Utilizing open data from Palo Alto, United States, this study employs descriptive statistical methods and interpretable machine learning approaches to scrutinize the relationship between policy initiatives and charging behaviors. The analysis underscores the significance of spatial attributes on charging behaviors. Policy interventions yield noticeable alterations in charging metrics, with locations near commercial hubs showing higher utilization, while local and frequent users resist fee adjustments. The research emphasizes the necessity for customized strategies to optimize infrastructure development and management, offering a framework for policymakers and stakeholders in sustainable urban transportation. Future research should explore similar interventions in diverse urban settings using real-time data and advanced optimization techniques to better tailor policies to the unique characteristics of specific facilities.

Data-Driven Clustering Analysis for Representative Electric Vehicle Charging Profile in South Korea

As the penetration of electric vehicles (EVs) increases, an understanding of EV operation characteristics becomes crucial in various aspects, e.g., grid stability and battery degradation. This can be achieved through analyzing large amounts of EV operation data; however, the variability in EV data according to the user complicates unified data analysis and identification of representative patterns. In this research, a framework that captures EV charging characteristics in terms of charge–discharge area is proposed using actual field data. In order to illustrate EV operation characteristics in a unified format, an individual EV operation profile is modeled by the probability distribution of the charging start and end states of charge (SoCs).Then, hierarchical clustering analysis is employed to derive representative charging profiles. Using large amounts of real-world, vehicle-specific EV data in South Korea, the analysis results reveal that EV charging characteristics in terms of the battery charge–discharge area can be summarized into seven representative profiles.

Optimal Energy Management of EVs at Workplaces and Residential Buildings Using Heuristic Graph-Search Algorithm

As the adoption of electric vehicles (EVs) continues to rise, efficient scheduling methods that minimize operational costs are critical. This paper introduces a novel EV scheduling method utilizing a heuristic graph-search algorithm for cost minimization due to its admissible nature. The approach optimizes EV charging and discharging schedules by considering real-time energy prices and battery degradation costs. The method is tested on systems with solar generation, electric loads, and EVs featuring vehicle-to-grid (V2G) connections. Various charging rates, such as standard, fast, and supercharging, along with uncertainties in EV arrival and departure times, are factored into the analysis. Results from various case studies demonstrate that the proposed method outperforms popular heuristic optimization techniques, such as particle swarm optimization and genetic algorithms, by 3–5% for different real-time energy prices. Additionally, the method’s effectiveness in reducing operational costs for workplace EVs is confirmed through extensive case studies under varying uncertain conditions. Finally, the system is implemented on a digital real-time simulator with DNP3 communication, where real-time results align closely with offline simulations, confirming the algorithm’s efficacy for real-world applications.

Demand management and pricing in renewable integrated plug-in electric vehicle charging station using reinforcement learning

ABSTRACT The increasing adaption of Plug-in Electric Vehicles (PEVs) has increased the power demand for charging. Renewable generation can significantly help to meet this demand. The uncertainty of renewable generation and randomness in PEV charging makes the demand management of charging stations challenging. To address these challenges, this study proposes a novel demand management pricing strategy for renewable integrated charging stations. The proposed strategy uses reinforcement learning for charging coordination of PEVs. The renewable generation is estimated using weather data and accordingly PEVs are scheduled for demand management. The strategy decides the PEV power price based on real-time price, renewable tariff and PEV load. The strategy uses the bidirectional power flow with battery degradation cost. The distribution transformer operating cost and loading constraints are included to resemble the real-time environment. The PEV randomness and uncertainty of renewable generations are incorporated in the study. The results of the numerical case study show that the proposed strategy can manage the charging station load efficiently. The proposed strategy has optimized the cost of charging, discharging and charging station profit and increased the service capability of the charging station.

Collaborative Optimization Framework for Coupled Power and Transportation Energy Systems Incorporating Integrated Demand Responses and Electric Vehicle Battery State-of-Charge

The growing adoption of electric vehicles (EVs) and advancements in dynamic wireless charging (DWC) technology have strengthened the interdependence between power distribution networks (PDNs) and electrified transportation networks (ETNs), leading to the emergence of coupled power and transportation energy systems (CPTESs). This development introduces new challenges, particularly as DWC technology shifts EV charging demand from residential plug-in charging to charging-while-driving during commuting hours, causing simultaneous congestion in both ETNs and PDNs during peak times. The present work addresses this issue by developing a collaborative optimization framework for CPTESs that incorporates integrated demand responses (IDRs) and EVs battery state-of-charge (SOC). In the ETN, a multiperiod traffic assignment model with time-shiftable traffic demands (MTA-TSTD) is established to optimize travelers’ routes and departure times while capturing traffic flow distribution. Meanwhile, effective path generation models with EVs battery SOC are proposed to optimize charging energy during driving and construct the effective path sets for MTA-TSTD. In the PDN, a multiperiod optimal power flow model with time-shiftable power demands (MOPF-TSPD) is formulated to schedule local generators and flexible power demands while calculating the power flow distribution. To enhance temporal and spatial coordination in CPTESs, a distributed coordinated operation model considering IDRs is proposed, aiming to optimize energy consumption, alleviate congestion, and ensure system safety. Finally, an adaptive effective path generation algorithm and an ETN–PDN interaction algorithm are devised to efficiently solve these models. Numerical results on two test systems validate the effectiveness of the proposed models and algorithms.

A Review on Advanced Battery Thermal Management Systems for Fast Charging in Electric Vehicles

To protect the environment and reduce dependence on fossil fuels, the world is shifting towards electric vehicles (EVs) as a sustainable solution. The development of fast charging technologies for EVs to reduce charging time and increase operating range is essential to replace traditional internal combustion engine (ICE) vehicles. Lithium-ion batteries (LIBs) are efficient energy storage systems in EVs. However, the efficiency of LIBs depends significantly on their working temperature range. However, the huge amount of heat generated during fast charging increases battery temperature uncontrollably and may lead to thermal runaway, which poses serious hazards during the operation of EVs. In addition, fast charging with high current accelerates battery aging and seriously reduces battery capacity. Therefore, an effective and advanced battery thermal management system (BTMS) is essential to ensure the performance, lifetime, and safety of LIBs, particularly under extreme charging conditions. In this perspective, the current review presents the state-of-the-art thermal management strategies for LIBs during fast charging. The serious thermal problems owing to heat generated during fast charging and its impacts on LIBs are discussed. The core part of this review presents advanced cooling strategies such as indirect liquid cooling, immersion cooling, and hybrid cooling for the thermal management of batteries during fast charging based on recently published research studies in the period of 2019–2024 (5 years). Finally, the key findings and potential directions for next-generation BTMSs toward fast charging are proposed. This review offers an in-depth analysis by providing recommendations and potential solutions to develop reliable and efficient BTMSs for LIBs during fast charging.

Multi-Agent Reinforcement Learning for Smart Community Energy Management

This paper investigates a Local Strategy-Driven Multi-Agent Deep Deterministic Policy Gradient (LSD-MADDPG) method for demand-side energy management systems (EMS) in smart communities. LSD-MADDPG modifies the conventional MADDPG framework by limiting data sharing during centralized training to only discretized strategic information. During execution, it relies solely on local information, eliminating post-training data exchange. This approach addresses critical challenges commonly faced by EMS solutions serving dynamic, increasing-scale communities, such as communication delays, single-point failures, scalability, and nonstationary environments. By leveraging and sharing only strategic information among agents, LSD-MADDPG optimizes decision-making while enhancing training efficiency and safeguarding data privacy—a critical concern in the community EMS. The proposed LSD-MADDPG has proven to be capable of reducing energy costs and flattening the community demand curve by coordinating indoor temperature control and electric vehicle charging schedules across multiple buildings. Comparative case studies reveal that LSD-MADDPG excels in both cooperative and competitive settings by ensuring fair alignment between individual buildings’ energy management actions and community-wide goals, highlighting its potential for advancing future smart community energy management.

Regional Analysis and Evaluation Method for Assessing Potential for Installation of Renewable Energy and Electric Vehicles

Many countries are adopting renewable energy (RE) and electric vehicles (EVs) to achieve net-zero emissions by 2050. The indicators of RE and EV potentials are different. Decision-makers want to introduce RE and EVs; however, they need a method to find suitable areas. In addition, this is required in the time-series analysis to provide a detailed resolution. In this study, we conducted a time-series analysis in Japan to evaluate suitable areas for the combined use of RE and EVs. The results showed the surplus RE areas and shortage RE urban areas. The time-series analysis has quantitatively shown that it is not enough to charge EV batteries using surplus RE. Moreover, a ranking methodology was developed for the evaluation based on electric demand and vehicle numbers. This enables the government’s prioritization of prefectures and the prefectures’ prioritization of municipalities according to their policies.

Discovering Electric Vehicle Charging Locations Based on Clustering Techniques Applied to Vehicular Mobility Datasets

With the proliferation of vehicular mobility traces because of inexpensive on-board sensors and smartphones, utilizing them to further understand road movements have become easily accessible. These huge numbers of vehicular traces can be utilized to determine where to enhance road infrastructures such as the deployment of electric vehicle (EV) charging stations. As more EVs are plying today’s roads, the driving anxiety is minimized with the presence of sufficient charging stations. By correctly extracting the various transportation parameters from a given dataset, one can design an adequate and adaptive EV charging network that can provide comfort and convenience for the movement of people and goods from one point to another. In this study, we determined the possible EV charging station locations based on an urban city’s vehicular capacity distribution obtained from taxi and ride-hailing mobility GPS traces. To achieve this, we first transformed the dynamic vehicular environment based on vehicular capacity into its equivalent urban single snapshot. We then obtained the various traffic zone distributions by initially utilizing k-means clustering to allow flexibility in the total number of wanted traffic zones in each dataset. In each traffic zone, iterative clustering techniques employing Density-based Spatial Clustering of Applications with Noise (DBSCAN) or clustering by fast search and find of density peaks (CFS) revealed various area separation where EV chargers were needed. Finally, to find the exact location of the EV charging station, we last ran k-means to locate centroids, depending on the constraint on how many EV chargers were needed. Extensive simulations revealed the strengths and weaknesses of the clustering methods when applied to our datasets. We utilized the silhouette and Calinski–Harabasz indices to measure the validity of cluster formations. We also measured the inter-station distances to understand the closeness of the locations of EV chargers. Our study shows how CFS + k-means clustering techniques are able to pinpoint EV charger locations. However, when utilizing DBSCAN initially, the results did not present any notable outcome.

Renewable sources-based efficient electric vehicle charging system through power forecasting and charge scheduling

Renewable sources-based efficient electric vehicle charging system through power forecasting and charge scheduling