Federated Learning for Short-term Residential Load Forecasting

Briggs, Christopher; Fan, Zhong; Andras, Peter

Abstract

Load forecasting is an essential task performed within the energy industry to help balance supply with demand and maintain a stable load on the electricity grid. As supply transitions towards less reliable renewable energy generation, smart meters will prove a vital component to facilitate these forecasting tasks. However, smart meter adoption is low among privacy-conscious consumers that fear intrusion upon their fine-grained consumption data. In this work we propose and explore a federated learning (FL) based approach for training forecasting models in a distributed, collaborative manner whilst retaining the privacy of the underlying data. We compare two approaches: FL, and a clustered variant, FL+HC against a non-private, centralised learning approach and a fully private, localised learning approach. Within these approaches, we measure model performance using RMSE and computational efficiency. In addition, we suggest the FL strategies are followed by a personalisation step and show that model performance can be improved by doing so. We show that FL+HC followed by personalisation can achieve a ~5% improvement in model performance with a ~10x reduction in computation compared to localised learning. Finally we provide advice on private aggregation of predictions for building a private end-to-end load forecasting application.

Citation

Briggs, C., Fan, Z., & Andras, P. (2022). Federated Learning for Short-term Residential Load Forecasting. IEEE Open Access Journal of Power and Energy, 9, 573-583. https://doi.org/10.1109/oajpe.2022.3206220

• Journal Article Type: Article
• Acceptance Date: Sep 7, 2022
• Online Publication Date: Sep 12, 2022
• Publication Date: 2022
• Deposit Date: Nov 15, 2022
• Publicly Available Date: Feb 15, 2023
• Journal: IEEE Open Access Journal of Power and Energy
• Print ISSN: 2687-7910
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 9
• Pages: 573-583
• DOI: https://doi.org/10.1109/oajpe.2022.3206220
• Keywords: federated learning, load forecasting, distributed machine learning, deep learning, data privacy, internet-of-things
• Public URL: http://researchrepository.napier.ac.uk/Output/2957896