Forecasting Energy Availability in Local Energy Communities via LSTM Federated Learning
This study addresses the challenge of achieving accurate energy availability forecasting in local energy communities, where privacy concerns often restrict access to individual electricity consumption data, thereby hindering the deployment of high-precision predictive models. To overcome this limitation, the work proposes a novel decentralized forecasting framework that integrates Long Short-Term Memory (LSTM) networks with federated learning, enabling collaborative model training without sharing raw user data. Experimental results demonstrate that the proposed approach effectively preserves user privacy while still delivering prediction accuracy sufficient for practical applications. This method offers a viable and innovative technical pathway for intelligent energy management in privacy-sensitive environments.