Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

TL;DR

This paper introduces Fed-LSGAN, a federated deep generative learning framework that generates privacy-preserving renewable energy scenarios by combining federated learning with LSGANs, capturing spatial-temporal data characteristics.

Contribution

It presents a novel federated deep generative model that preserves data privacy while accurately modeling renewable energy scenarios using LSGANs.

Findings

Outperforms state-of-the-art centralized methods in scenario quality

Successfully generates high-quality renewable energy scenarios

Demonstrates robustness across different federated learning settings

Abstract

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.