In the rapidly advancing domain of Intelligent Connected Vehicles (ICVs), multimodal Federated Learning (FL) presents a powerful methodology to harness diverse data sources, such as sensors, cameras, and Vehicle-to-Everything (V2X) communications, without compromising data privacy. Despite its potential, the presence of Byzantine adversaries–malicious participants who contribute incorrect or misleading updates–poses a significant challenge to the robustness and reliability of the FL process. This paper proposes a Byzantine-robust multimodal FL framework specifically designed for ICVs. Our framework integrates a robust aggregation mechanism to mitigate the influence of adversarial updates, a multimodal fusion strategy to effectively manage and combine heterogeneous input data, and a global optimization objective that accommodates the presence of Byzantine clients. The theoretical foundation of the framework is established through formal definitions and equations, demonstrating its ability to maintain reliable and accurate learning outcomes despite adversarial disruptions. Extensive experiments highlight the framework’s efficacy in preserving model performance and resilience in real-world ICV environments.
Electricity markets are intricate systems that facilitate efficient energy exchange within interconnected grids. With the rise of low-carbon transportation driven by environmental policies and tech advancements, energy trading has become crucial. This trend towards Electric Vehicles (EVs) is bolstered by the pivotal role played by EV charging operators in providing essential charging infrastructure and services for widespread EV adoption. This paper introduces a blockchain-assisted secure electricity trading framework between EV charging operators and the electricity market with renewable energy sources. We propose a single-leader, multi-follower Stackelberg game between the electricity market and EV charging operators. In the two-stage Stackelberg game, the electricity market acts as the leader, deciding the price of electric energy. The EV charging aggregator leverages blockchain technology to record and verify energy trading transactions securely. The EV charging operators, acting as followers, then decide their demand for electric energy based on the set price. To find the Stackelberg equilibrium, we employ a Deep Reinforcement Learning (DRL) algorithm that tackles non-stationary challenges through policy, action space, and reward function formulation. To optimize efficiency, we propose the integration of pruning techniques into DRL, referred to as Tiny DRL. Numerical results demonstrate that our proposed schemes outperform traditional approaches.
To achieve low carbon emissions in the power system and contribute to economic growth, a low-carbon optimization scheduling strategy for a power system, considering carbon responsibility sharing and electric vehicle demand response, is proposed based on the establishment of a flexible-load model guided by carbon potential. Firstly, utilizing the principle of proportional sharing to track carbon emission flow and establish a carbon emission flow model. Secondly, based on the Shapley value carbon responsibility allocation method, the reasonable range of carbon responsibility on each load side is calculated, and a hierarchical carbon price is established. A load aggregator demand response carbon emission model is established using the node carbon potential, and a dual-layer optimization scheduling model for the power system based on the node carbon potential demand response is constructed. The upper layer of the model is the optimal economic dispatch of the power grid operator, and the lower layer is the demand response economic dispatch of the load aggregator. Through numerical verification, the carbon trading model takes into account the system’s carbon emissions and overall operating costs while balancing the system’s low-carbon and economic aspects.
As the prevalence of electric vehicles (EVs) continues to surge, the precise forecasting of charging demands at individual charging stations becomes imperative for effective power distribution management. However, the charging demand of EVs is often related to various factors and exhibits strong randomness. This paper aims to explore the impact of climatic factors on the charging demand of electric vehicles at charging stations, and to study a prediction model based on the attention mechanism of LSTM for predicting the load of charging stations, providing important guidance for the scheduling of electric vehicles. By analysing the load data of a single charging station under different climatic conditions, the paper finds that climatic factors such as the highest temperature of the day, the lowest temperature, and the type of weather significantly affect the charging demand of electric vehicles. Utilizing the aforementioned characteristics, this paper studies a climate feature‐guided charging demand prediction model for a single charging station, which adopts the LSTM architecture and introduces the attention mechanism, incorporating the above‐mentioned important climatic features, and is ultimately able to accurately predict the future charging demand of the charging station. The experimental results show that, compared to other time series forecasting models, this model has significantly improved performance on the dataset tests, with its accuracy ratio (AR) indicator and qualified rate indicator both exceeding 0.85 and 0.95, respectively. This study not only offers a new perspective and method for predicting the demand for electric vehicle charging but also provides support for the development of electric vehicle scheduling.
2 September 2025 in International Journal of Computational Intelligence Systems
This study develops a centralized reinforcement learning framework, employing Q-learning, for efficient vehicle-to-grid (V2G) scheduling of large electric vehicle (EV) fleets. To address scalability challenges and inherent uncertainties in user behavior, the framework utilizes an aggregated state representation. This state captures the time-of-day, the distribution of the fleet’s state of charge (SOC) across discrete bins, and an estimated user adherence factor. The central agent learns a control policy based on this aggregated state to dynamically issue charging, discharging, or idle commands to EVs grouped within specific SOC bins. The primary objectives are to enhance power grid stability by minimizing the peak-to-average ratio (PAR) and to improve the economic viability of V2G participation for EV owners. Simulations conducted under a 40% EV penetration level (relative to a 300,000 vehicle base fleet) demonstrate the proposed method’s effectiveness: it reduced the grid PAR to 1.0683, compared to 1.0729 for a baseline uncontrolled charging scenario. Critically, the proposed method transformed the economic outcome, achieving positive average daily earnings of $1.17 per EV, in stark contrast to an average daily loss of $6.75 per EV under the baseline. These results validate the potential of the proposed intelligent, centralized control strategy using aggregated information to effectively manage large-scale V2G systems, enhance grid stability, and provide economic benefits under practical behavioral assumptions.
China’s power generation system has undergone reforms, leading to a competitive electricity market where independent producers participate through competitive bidding. With the rise of low-carbon policies, producers must optimize bidding strategies while reducing carbon emissions, creating complex interactions with local governments. Evolutionary game theory (EGT) is well-suited to analyze these dynamics. This study begins by summarizing the fundamental concepts of electricity trading markets, including transaction models, bidding mechanisms, and carbon reduction strategies. Existing research on the application of evolutionary game theory in power markets is reviewed, with a focus on theoretical constructs such as evolutionary stable strategies and replicator dynamics. Based on this foundation, the study conducts a detailed mathematical analysis of symmetric and asymmetric two-group evolutionary game models in general market scenarios. Building upon these models, a three-group evolutionary game framework is developed to analyze interactions within power producer groups and between producers and regulators under low-carbon mechanisms. A core innovation of this study is the incorporation of a case study based on China’s electricity market, which examines the evolutionary dynamics between local governments and power producers regarding carbon reduction strategies. This includes analyzing how regulatory incentives, market-clearing prices, and demand-side factors influence producers’ bidding and emission reduction behaviors. The study also provides a detailed analysis of the bidding strategies for small, medium, and large power producers, revealing the significant impact of carbon pricing and market-clearing prices on strategic decision-making. Specifically, the study finds that small producers tend to adopt more conservative bidding strategies, aligning closely with market-clearing prices, while large producers take advantage of economies of scale, adjusting their strategies at higher capacities. The study explores the conditions under which carbon emission reduction strategies achieve stable equilibrium, as well as the implications of these equilibria for both market efficiency and environmental sustainability. The study reveals that integrating carbon reduction strategies into power market dynamics significantly impacts bidding behaviors and long-term market stability, especially under the influence of governmental penalties and incentives. The findings provide actionable insights for both power producers and policymakers, contributing to the advancement of low-carbon market theories and supporting the global transition to sustainable energy systems.