Personalized Federated Learning With Cost-Oriented Load Forecasting for Home Energy Management Systems
Open Access
- 17 September 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 61 (1) , 1410-1419
Abstract
Accurate day-ahead demand forecasting is crucial for optimizing the performance of home energy management systems. Traditional forecasting methods often decouple the forecasting task and the subsequent decision marking, resulting in imbalanced economic penalties from load deviations. Furthermore, the rise of digitization has led to a massive increase in fine-grained smart meter data stored daily, posing significant challenges to customers' data privacy and security. To address these technical challenges, this study proposes a personalized federated learning methodology that incorporates a cost-oriented loss function. This methodology is designed to learn end-user-specific patterns, reduce penalization costs, and preserve customer privacy. Comparative analyses reveal that the proposed method, which utilizes a cost-oriented loss function and $L^{2}$ regularization, outperforms traditional symmetric loss functions in terms of efficiency and economic benefits. The results confirm that this personalized federated learning approach consistently achieves the lowest error rates and penalization costs compared to other methods. Additionally, sensitivity analyses indicate that even households with limited historical consumption data can achieve accurate load predictions using the personalized federated learning approach.Keywords
Funding Information
- ATLAS Digitalization (PID2021-128101OB-I00)
- Ministry of Science
- Universities of Spain (MCIN/AEI/10.13039/501100011033)
- European Regional Development Fund
This publication has 24 references indexed in Scilit:
- A review of federated learning in renewable energy applications: Potential, challenges, and future directionsEnergy and AI, 2024
- Model optimization techniques in personalized federated learning: A surveyExpert Systems with Applications, 2023
- Semi-asynchronous personalized federated learning for short-term photovoltaic power forecastingDigital Communications and Networks, 2023
- Privacy-preserving federated learning for residential short-term load forecastingApplied Energy, 2022
- Federated learning review: Fundamentals, enabling technologies, and future applicationsInformation Processing & Management, 2022
- Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural NetworksInternational Journal of Electrical Power & Energy Systems, 2022
- Cost-oriented load forecastingElectric Power Systems Research, 2022
- Support vector regression with asymmetric loss for optimal electric load forecastingEnergy, 2021
- Federated Learning for Distributed Reasoning on Edge ComputingProcedia Computer Science, 2021
- Outline of forecast theory using generalized cost functionsSpanish Economic Review, 1999