A Federated Learning Framework for Smart Grids: Securing Power Traces in Collaborative Learning

TL;DR

This paper introduces a federated learning framework for smart grids that enables collaborative analysis of power data while preserving privacy, using encryption schemes like Paillier to ensure lossless and secure model training.

Contribution

It adapts federated learning to smart grid data, employing both horizontal and vertical schemes for privacy-preserving power consumption modeling.

Findings

Models are lossless and privacy-preserving with encryption.

Federated learning effectively captures power consumption patterns.

Framework applicable to various smart grid components.

Abstract

With the deployment of smart sensors and advancements in communication technologies, big data analytics have become vastly popular in the smart grid domain, informing stakeholders of the best power utilization strategy. However, these power-related data are stored and owned by different parties. For example, power consumption data are stored in numerous transformer stations across cities; mobility data of the population, which are important indicators of power consumption, are held by mobile companies. Direct data sharing might compromise party benefits, individual privacy and even national security. Inspired by the federated learning scheme from Google AI, we propose a federated learning framework for smart grids, which enables collaborative 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 the case with data scattered in the feature space. Case studies show that, with proper encryption schemes such as Paillier encryption, the machine learning models constructed from the proposed framework are lossless, privacy-preserving and effective. Finally, the promising future of federated learning in other facets of the smart grid is discussed, including electric vehicles, distributed generation/consumption and integrated energy systems.