Enhancing PV feed-in power forecasting through federated learning with differential privacy using LSTM and GRU

Given the inherent fluctuation of photovoltaic (PV) generation, accurately forecasting solar power output and grid feed-in is crucial for optimizing grid operations. Data-driven methods facilitate efficient supply and demand management in smart grids, but predicting solar power remains challenging due to weather dependence and data privacy restrictions. Traditional deep learning (DL) approaches require access to centralized training data, leading to security and privacy risks. To navigate these challenges, this study utilizes federated learning (FL) to forecast feed-in power for the low-voltage grid. We propose a bottom-up, privacy-preserving prediction method using differential privacy (DP) to enhance data privacy for energy analytics on the customer side. This study aims at proving the viability of an enhanced FL approach by employing three years of meter data from three residential PV systems installed in a southern city of Germany, incorporating irradiance weather data for accurate PV power generation predictions. For the experiments, the DL models long short-term memory (LSTM) and gated recurrent unit (GRU) are federated and integrated with DP. Consequently, federated LSTM and GRU models are compared with centralized and local baseline models using rolling 5-fold cross-validation to evaluate their respective performances. By leveraging advanced FL algorithms such as FedYogi and FedAdam, we propose a method that not only predicts sequential energy data with high accuracy, achieving an R2 of 97.68%, but also adheres to stringent privacy standards, offering a scalable solution for the challenges of smart grids analytics, thus clearly showing that the proposed approach is promising and worth being pursued further. •Federated learning with long short-term memories and gated recurrent units for electrical feed-in power forecasting.•Training on energy data from real residential households with PV-systems connected to the low-voltage grid.•Proposing a federated-driven method with differential privacy for the privacy-preserving prediction of the feed-in power.•Advanced federated aggregation strategies to mitigate adverse data distributions on the model performance.•Model performance comparison and analysis of different training methods.