Knowledge Hub

Lei Zhang, Yingjun Ji, Xiaohui Li, Zhijia Huang, Dingsong Cui, Haibo Chen, Jingyu Gong, Fabian Breer, Mark Junker, Dirk Uwe Sauer,
Multi-objective charging scheduling for electric vehicles at charging stations with renewable energy generation,
Green Energy and Intelligent Transportation, Volume 4, Issue 4, 2025, 100283, ISSN 2773-1537,

https://doi.org/10.1016/j.geits.2025.100283.

Abstract: The rapid adoption of electric vehicles (EVs) in recent years has posed significant challenges to the safe operation of local grids, particularly due to massive charging operations at public charging stations. This paper proposes a real-time charging scheduling scheme to enable efficient Vehicle-to-Grid (V2G) interactions and facilitate renewable energy integration at public charging stations while accounting for real-world EV charging behaviors. First, an EV charging/discharging behavior database is developed to capture the temporal uncertainty and charging characteristics of both fast- and slow-charging operations on weekdays and weekends. Then a charging pile allocation mechanism is introduced to optimize the charging power distribution for each EV to maximize the operational efficiency of the studied charging station. A micro-grid system model is developed by incorporating efficient V2G interactions and renewable energy integration. Finally, a comprehensive charging scheduling scheme is proposed to achieve a balanced optimization of multiple objectives. Extensive simulation studies are conducted to evaluate the performance of the proposed scheduling method. The results demonstrate that the proposed scheme achieves strong performance across all three selected indicators.

Keywords: Electric vehicles; Charging stations; Micro-grid; V2G; Charging scheduling

Yitong Shang, Wen-Long Shang, Dingsong Cui, Peng Liu, Haibo Chen, Dongdong Zhang, Runsen Zhang, Chengcheng Xu, Ye Liu, Chenxi Wang, Mohannad Alhazmi, Spatio-temporal data fusion framework based on large language model for enhanced prediction of electric vehicle charging demand in smart grid management, Information Fusion, Volume 126, Part B, 2026, 103692, ISSN 1566-2535,

https://doi.org/10.1016/j.inffus.2025.103692.

Abstract: Accurate prediction of electric vehicle (EV) charging demand is pivotal for effective smart grid management and renewable energy integration. However, predicting spatio-temporal EV charging patterns remains challenging due to complex data fusion requirements arising from heterogeneous temporal, spatial, and contextual features, as well as difficulties in effectively integrating multiple modeling approaches. This paper introduces EV-STLLM, a novel spatio-temporal data fusion framework based on Large Language Model explicitly designed for accurate short-term EV charging demand forecasting through innovative integration of data-level and model-level fusion techniques. At the data level, a multi-source embedding module is developed to seamlessly fuse temporal features (e.g., time slots, weekdays), spatial heterogeneity (e.g., geographical location), and contextual charging behaviors into a unified representation via embedding convolutional network. At the model level, a large language model (LLM) is employed to capture global spatiotemporal dependencies, enhanced with Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning, substantially reducing computational costs while maintaining prediction robustness. Using a comprehensive real-world dataset comprising over 830,000 EV charging records across 16 districts and 331 subdistricts in Beijing, we validate EV-STLLM across multiple forecasting scenarios (district and subdistrict levels, one-step and two-step ahead predictions). Extensive comparative evaluations demonstrate that EV-STLLM consistently outperforms classical, graph-based, and deep learning baselines. Specifically, in one-step ahead district-level forecasting, EV-STLLM achieves up to a 15.41% reduction in MAE and a 53.51% reduction in MAPE compared to the leading baseline, underscoring its potential to significantly enhance data-driven smart grid operations.

Keywords: Electric vehicle; Charging demand prediction; Spatiotemporal data fusion; Large language models; Model fusion; Low-rank adaptation

L. Tziovani, L. Hadjidemetriou, S. Timotheou, Optimising the operating strategy of over-install renewable plants with battery storage systems,in Proc. IEEE ISGT Europe, Valletta, 2025, pp. 1-5.

https://doi.org/10.1109/ISGTEurope64741.2025.11305577

Abstract: Producers of renewable plants can enhance their profits by submitting accurate production profiles to the day-ahead energy markets. However, potential deviations between day-ahead forecasts and actual power generation result in power imbalances, which are penalized in the balancing market. To address this issue, this work proposes an operating strategy for over-installed renewable plants with battery energy storage systems (BESSs) to reduce power imbalances and thereby enhance the profits of producers. Specifically, a linear optimization scheme is developed to minimize power deficits during real-time operation by scheduling the charging and discharging power set-points of the BESS. The proposed scheme is implemented within a model predictive control framework using updated renewable forecasts. Moreover, a secondary controller is integrated into the proposed approach to store the renewable generation that exceeds the maximum export limits, eliminating power generation curtailments. The proposed strategy is applied to a wind power plant using real data. Simulation results demonstrate the capability of the proposed operating strategy to yield high-quality solutions under power generation uncertainty, enhancing profits by 4.2% and reducing power imbalances by 17.8%

Y. Wen, S. Timotheou, B. Chen, Multi-Regional Traffic Control with Traveland Charging Demand Co-Management,in Proc. IFAC WORLD CONGRESS, Busan, Republic of Korea, Aug. 2026, pp. 1-6

10.48550/arXiv.2605.00726

Abstract: Urban traffic management is essential for reducing congestion and supporting sustainable mobility. However, the task is becoming more challenging due to the growing penetration of electric vehicles and their charging demands. This paper presents a regional traffic coordination framework that combines route guidance and charging management to improve traffic network efficiency. Regional traffic dynamics are modeled by the macroscopic fundamental diagram, which allows for the analysis of congestion at the system level. The framework jointly optimizes routes and charging decisions, and it also uses demand management to regulate external inflows into the network. A case study on a 16-region urban network demonstrates the effectiveness of the proposed approach.

W-L. Shang, H. Chen, D. Cui, Z. Wang, D. Watling, W. Ochieng, Bi-directional charging of electric vehicles for sustainable energy management with distributed solar generation, Applied Energy, 424, Article 128478

https://doi.org/10.1016/j.apenergy.2026.128478 

Abstract: Electrifying road transport is essential for net-zero transitions, yet large-scale residential EV charging can intensify peaks in residential low-voltage distribution networks and increase technical losses. Prior studies show that bidirectional charging (V2G) can reduce peak demand and that distributed solar generation can offset local electricity use, but these resources are often analysed separately and rarely within an integrated framework that jointly quantifies peak impacts and converter-side and network-side efficiency penalties. This study develops a peak-minimisation optimisation model that coordinates EV charging and discharging while coupling V2G with distributed solar generation, including rooftop PV and vehicle-integrated PV. The model incorporates plug-in availability, daily mobility energy requirements, state-of-charge bounds, charging/discharging power limits, UK smart-meter household demand profiles, travel-behaviour-informed EV energy needs, home-availability patterns, and the IEEE European low-voltage test feeder. Four scenarios are compared: unidirectional charging, V2G, V2G with a grid-renewable setting, and V2G with distributed solar. Results show that V2G alone reduces peak demand by 5.72% at 50% EV penetration, whereas coupling V2G with distributed solar achieves a larger reduction of 14.62% and lowers feeder I²R losses, despite higher conversion losses from increased energy shifting. A Monte Carlo-based uncertainty analysis further confirms that these findings remain valid under combined weather variability and stochastic EV user behaviour. Under uncertainty, the PV-aware V2G scenario achieves the lowest mean peak demand, 21.73 kW, and the largest average peak reduction, 11.58%. These findings support PV-aware coordinated charging as a practical option for peak management, feeder-loss reduction and resilient residential low-voltage energy management.

Shang, W.-L., Chen, H., Cui, D., Wang, Z., Watling, D., & Ochieng, W., (2026) Short-term regional EV charging load forecasting based on GAT and GRU with trip distribution estimation, Applied Energy, 424, Article 128478

doi.org/10.1016/j.apenergy.2026.128478 

Abstract: Accurate forecasting of electric vehicle (EV) charging demand is crucial for developing coordinated charging strategies and reducing the negative impacts of large-scale, uncoordinated EV integration on power grid operations. Although previous studies have proposed predictive models using traffic simulations and machine learning with both dynamic and static features, most existing methods still fail to capture inter-nodal demand correlations, especially those involving long-distance nodes and heterogeneous data sources. To overcome these limitations, this study introduces STGR-Net, a novel short-term regional forecasting framework that integrates Graph Attention Networks (GAT), Gated Recurrent Units (GRU), and traffic distribution principles. The framework combines weekly aggregated charging data with fine-grained time series to extract spatio-temporal correlations, with particular focus on interactions among distant nodes. Based on these correlations, three matrices are constructed: (1) a dynamic gravity matrix from charging volume patterns, (2) a dynamic correlation matrix using inter-nodal Pearson coefficients, and (3) a static physical adjacency matrix. These components collectively form a novel triple-stream graph attention architecture. Temporal features are captured by parallel GRU encoders operating on three temporal sequences: recent, daily-periodic, and weekly-periodic. Each encoder is augmented with Reversible Instance Normalization (RevIN) to mitigate distributional shifts across different time periods. An adaptive gating mechanism further fuses temporal features with multi-dimensional spatial representations before prediction. Experiments on large-scale datasets from Beijing and Shenzhen show that STGR-Net achieves significant improvements in prediction accuracy over benchmark models. Ablation studies further confirm the contribution of the triple-stream graph architecture. The framework also shows strong practical utility for grid load management, charging service optimization, and infrastructure planning, supported by its efficient and accurate regional forecasting capability.

D. Cui et al. (2026) Understanding Electric Vehicle Refueling Demand and Parking Patterns in Forecasting, Planning, and Scheduling: A Literature Review, in IEEE Transactions on Intelligent Transportation Systems, vol. 27, no. 5, pp. 4967-4985

10.1109/TITS.2026.3652333 

Abstract: Vehicle electrification presents challenges and opportunities across multiple sectors, including the automotive, energy and infrastructure domains. Battery charging and swapping are the two primary technologies for refuelling electric vehicles (EVs). However, the involvement of multiple participants and various factors makes EV refuelling a complex and multi-domain issue. Since conventional conductive charging requires vehicles to remain stationary for a period of time, parking naturally provides opportunities for EV charging. Therefore, parking and EV charging are intrinsically connected in how they are organised and planned. This paper presents a comprehensive literature review on the features of EV refuelling demand and its relation to parking patterns. The review focuses on key study issues related to the interaction between EVs and the power grid, namely forecasting, planning, and scheduling. These issues are examined at three different scales: the individual, station, and regional levels. Based on the findings from the literature, an integrated framework is provided to capture the features and linkages between refuelling demand and parking patterns across the different study issues and scales. Finally, the paper proposes several open issues that could be explored in future studies from the perspective of integrating parking and refuelling analysis.