Consumer's privacy is a main concern in Smart Grids (SGs) due to the sensitivity of energy data, particularly when used to train machine learning models for different services. These data-driven models often require huge amounts of data to achieve acceptable performance leading in most cases to risks of privacy leakage. By pushing the training to the edge, Federated Learning (FL) offers a good compromise between privacy preservation and the predictive performance of these models. The current paper presents an overview of FL applications in SGs while discussing their advantages and drawbacks, mainly in load forecasting, electric vehicles, fault diagnoses, load disaggregation and renewable energies. In addition, an analysis of main design trends and possible taxonomies is provided considering data partitioning, the communication topology, and security mechanisms. Towards the end, an overview of main challenges facing this technology and potential future directions is presented.

翻译：消费者隐私是智能电网（SG）中的核心关切，源于能源数据的敏感性，尤其是在将其用于训练不同服务的机器学习模型时。这些数据驱动模型通常需要海量数据才能达到可接受的性能，这在多数情况下会引发隐私泄露风险。联邦学习（FL）通过将训练过程推向边缘，在隐私保护与模型预测性能之间取得了良好平衡。本文综述了FL在智能电网中的应用，重点讨论了其在负荷预测、电动汽车、故障诊断、负荷分解及可再生能源等领域的优势与不足。此外，基于数据划分、通信拓扑及安全机制，本文分析了主要设计趋势与可能的分类体系。最后，概述了该技术面临的主要挑战及未来潜在研究方向。