Asynchronous federated learning with partial weights aggregation for energy consumption forecasting

Privacy-preserving load forecasting in smart grids using federated learning: a comparative analysis of aggregation strategies

Experimental results on real-world energy consumption datasets demonstrate that the proposed FL framework achieves competitive forecasting accuracy while preserving client data privacy, and a rigorous comparative analysis reveals that FedProx and FedTrimmedAvg consistently outperform FedAvg under non-IID conditions.

Initialization Is Critical: Advancing Federated Short-Term Load Forecasting under Load Heterogeneity via Model Initialization

Short-term load forecasting (STLF) provides essential information for numerous applications in modern power systems. However, accurate STLF often relies on fine-grained smart-meter data from distributed users, raising increasing concerns about data privacy. Federated learning (FL) has therefore emerged as a promising privacy-preserving paradigm for STLF. Nevertheless, this paper reveals structured heterogeneity in clients'load data. Specifically, clients exhibit different responses to exogenous factors and distinct temporal load profiles, which can degrade forecasting performance in FL. To mitigate these issues, this paper studies the role of model initialization in federated STLF, and proposes two initialization strategies from global and local perspectives. For global model initialization, when auxiliary public load data are available, a pretrained initialization strategy is developed to initialize the global model before federated training, thereby reducing client drift during the training process. For local model initialization, we propose SLIAvg, a sequential local initialization strategy that promotes a more consistent training process by allowing participating clients to start from progressively adapted models within each communication round. Since the proposed strategies only modify the initialization process, they are compatible with most existing FL frameworks and privacy-enhancing techniques. Experiments on real smart-meter data with two representative forecasting architectures demonstrate that the proposed strategies effectively improve forecasting performance, as evidenced by reduced client drift, improved convergence behavior, and lower forecasting errors.

Entropy-Regularized Weighted Federated Meta-Learning Approach for Power Load Forecasting in Non-IID Scenarios

Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination

It is demonstrated that lightweight aggregation strategies can substantially improve empirical safety in federated reinforcement learning while preserving standard communication protocols.

Dynamic Information Fusion for Personalized Federated Learning

The Internet of Things generates vast amounts of decentralized data, where data heterogeneity presents a significant challenge in federated learning. Many existing personalized federated learning (pFL) approaches prioritize local model accuracy at the expense of global generalization, leading to reduced cost-effectiveness. To address this issue, a federated learning algorithm called Dynamic Information Fusion for Personalized Federated Learning (FedIF) is proposed. Two model heads carrying different information are fused by FedIF to obtain a personalized model fitting local data better. The personalization steps of FedIF are performed after local training in each round of the FedAvg algorithm. This design allows FedIF to be combined with other algorithms that improved FedAvg based algorithms. Comparative and ablation experiments are conducted between FedIF and other state-of-the-art personalized federated learning algorithms. Experimental results indicate that the FedIF achieves competitive performance in most evaluated heterogeneous settings.

Gradient-Complementary Asynchronous Federated Learning for Multi-Task Anomaly Detection in Smart Grid

The increasing deployment of heterogeneous IoT devices has transformed smart grids into large-scale distributed cyber–physical systems, where anomaly detection becomes a critical yet challenging computational intelligence problem. In such environments, anomaly knowledge is sparse, fragmented, and highly non-independent across users, while device participation is asynchronous and communication-constrained. This paper proposes a gradient-complementary asynchronous federated learning (GC-AFL) framework, which explicitly models gradient complementarity as a distributed intelligence fusion mechanism for multi-task anomaly detection. Unlike conventional federated aggregation that suppresses heterogeneity, GC-AFL exploits dissimilar gradient information to preserve task-specific anomaly knowledge. The framework further integrates a communication-aware collaboration strategy and a staleness-compensated aggregation scheme to ensure efficiency and long-term fairness under asynchronous updates. Extensive experiments demonstrate that GC-AFL consistently outperforms state-of-the-art synchronous and asynchronous federated learning methods in terms of detection accuracy, robustness to Non-IID data, anomaly recall, and communication efficiency. The results validate the effectiveness of gradient complementarity as a general computational intelligence principle for distributed anomaly detection.