Overcoming Data Scarcity at the Edge: A Federated Learning Approach with GAN-Based Data Augmentation
Andreas El Saer, Petrina Troulitaki, Eirini Bageorgou, Sevasti Politi, Konstantinos Lieros · 2025
Renewable energy forecasting—particularly for distributed solar power—is vital for ensuring grid reliability and efficient resource management. However, traditional centralized forecasting approaches often come with drawbacks like high communication overhead, privacy issues, and limited scalability. Federated Learning (FL), consists of a decentralized machine learning framework that allows edge devices to collaboratively train models without disclosing raw data. Yet, FL struggles when devices have limited or sparse data, leading to cold-start problems and weaker model performance. To mitigate these challenges, this work introduces a method that incorporates GAN-based data augmentation to enrich local datasets with synthetic time-series samples during the initialization phase of the federated training process. Specifically, we benchmark a Long Short-Term Memory network for local -at the edge- forecasting tasks, while CopulaGAN is employed to generate realistic synthetic solar energy data. Experimental results—using real-world solar datasets in a federated environment—show that this GAN-enhanced FL-LSTM approach significantly boosts both forecasting accuracy and training convergence compared to standard FL setups without data augmentation.