Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach
This addresses privacy concerns in renewable energy data sharing for power system decision-makers, but it is incremental as it combines existing federated learning and LSGAN techniques.
The paper tackled the problem of generating renewable energy scenarios for power systems by proposing Fed-LSGAN, a federated deep generative learning framework that preserves privacy without sacrificing quality, and it outperformed state-of-the-art centralized methods in simulations.
Scenario generation is a fundamental and crucial tool for decision-making in power systems with high-penetration renewables. Based on big historical data, a novel federated deep generative learning framework, called Fed-LSGAN, is proposed by integrating federated learning and least square generative adversarial networks (LSGANs) for renewable scenario generation. Specifically, federated learning learns a shared global model in a central server from renewable sites at network edges, which enables the Fed-LSGAN to generate scenarios in a privacy-preserving manner without sacrificing the generation quality by transferring model parameters, rather than all data. Meanwhile, the LSGANs-based deep generative model generates scenarios that conform to the distribution of historical data through fully capturing the spatial-temporal characteristics of renewable powers, which leverages the least squares loss function to improve the training stability and generation quality. The simulation results demonstrate that the proposal manages to generate high-quality renewable scenarios and outperforms the state-of-the-art centralized methods. Besides, an experiment with different federated learning settings is designed and conducted to verify the robustness of our method.