A Federated Learning Framework in Smart Grid: Securing Power Traces in Collaborative Learning

With the deployment of smart sensors and advancements in communication technologies, big data analytics have become vastly popular in the smart grid domain, which inform stakeholders of the best power utilization strategy. However, these power-related data are typically scattered among different parties. Direct data sharing might compromise party benefits, individual privacy and even national security. Inspired by the federated learning scheme of Google AI, we hereby propose a federated learning framework in smart grid, which enables collaborative machine learning of power consumption patterns without leaking individual power traces. Horizontal federated learning is employed when data are scattered in the sample space; vertical federated learning, on the other hand, is designed for data scattered in the feature space. Case studies show that, with proper encryption schemes such as Paillier, the machine learning models constructed from the proposed framework are lossless, privacy-preserving and effective.