Test results show that the proposed hybrid forecasting method outperforms traditional algorithms in forecasting accuracy, convergence speed, and robustness under extreme conditions such as data missing, and it can effectively quantify the impact of load fluctuations on the voltage of distribution networks.
Abstract
To address the challenges that traditional single models have in balancing high-dimensional spatio-temporal correlation, long-sequence dynamic dependence, and a lack of a multi-station coordination mechanism in electric vehicle (EV) charging load forecasting, a hybrid forecasting method based on long short-term memory-graph reinforcement learning (LGRL) is proposed in this paper. First, a spatio-temporal feature decoupling architecture is constructed. The graph attention network (GAT) is used to dynamically aggregate high-order spatial features of neighboring nodes via adaptive attention coefficients, thereby characterizing the topological correlations of the charging station road network. Meanwhile, residual connections and a gated noise suppression mechanism are introduced into the long short-term memory network (LSTM) to adaptively filter irregular load disturbances, which enables accurate capture and noise-resistant extraction of non-linear temporal evolution laws. Second, a multi-agent coordinated forecasting framework based on value decomposition (QMIX) is established. Each charging station is modeled as an independent agent, and the global forecasting objective is decomposed into a decentralized local decision-making process in a lossless manner by introducing monotonicity constraints. A two-layer network structure comprising local and global mixing layers is designed. A parameterized hypernetwork is employed to fit the non-linear mapping between global states and local action value functions, thus achieving multi-station coordinated forecasting while ensuring the optimal performance of the global system. Third, a robust optimization strategy integrated with prioritized experience replay (PER) is designed. Key load samples are reweighted and trained according to temporal difference errors, which solves the problems of difficult algorithm convergence and weak generalization ability to extreme samples in dynamic heterogeneous scenarios. Finally, a case study is conducted based on the actual power grid topology of Fengxian District, Shanghai. Test results show that the proposed method outperforms traditional algorithms in forecasting accuracy, convergence speed, and robustness under extreme conditions such as data missing, and it can effectively quantify the impact of load fluctuations on the voltage of distribution networks.
This survey presents a comprehensive review of deep learning-based approaches for EV charging load forecasting, categorizing them into point and probabilistic forecasting paradigms, and differentiates single-architecture models, hybrid architectures, and ensemble learning models within each paradigm.
Chong-Ren Sun, Bassem Mikhail, Felix Chen et al.· IEEE Open Journal of Intelli...· 0 citations
A short-term EV charging load forecasting model that integrates Sample Entropy (SE) with a TCN-BiGRU hybrid network that outperforms GRU, BiGRU, and TCN-GRU across all seasons.
A multi-domain machine learning framework that integrates spatio-temporal charging demand, station-level infrastructure characteristics, land-use information, and graph-based network relationships for EV charging prediction and infrastructure siting is proposed.
B. Thango, G. K. Ayetor· World Electric Vehicle Journ...· 0 citations
Accurate electric vehicle (EV) charging load forecasting is important for grid dispatch, peak-load management, and charging infrastructure planning. However, residential EV charging loads exhibit both multi-scale periodicity and stochastic fluctuations, making it difficult for fixed-window models to capture dynamic tem...
Jingyue Zhang, Jing-Hua Wang, Peng-Tao Su et al.· Proceedings of the Instituti...· 0 citations
Reliably forecasting how much energy electric vehicles (EVs) will require at public chargers is a prerequisite for infrastructure planning and matching available capacity to real-world usage. This study compares two representative approaches, Random Forest and Long Short-Term Memory (LSTM), to forecast hourly charging...
Hao-Ran Luo· ITM Web of Conferences· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 9, 2026