Operation-Adversarial Scenario Generation

TL;DR

This paper introduces an operation-adversarial cGAN model that generates realistic and stress-testing net load scenarios for power systems, improving dispatch decision robustness.

Contribution

The paper presents a novel OA-cGAN that internalizes power flow constraints and maximizes operational stress, enhancing scenario realism and system resilience.

Findings

Generated scenarios increase dispatch cost robustness.

Method outperforms traditional scenario generation.

Applicable to realistic power system models.

Abstract

This paper proposes a modified conditional generative adversarial network (cGAN) model to generate net load scenarios for power systems that are statistically credible, conditioned by given labels (e.g., seasons), and, at the same time, "stressful" to the system operations and dispatch decisions. The measure of stress used in this paper is based on the operating cost increases due to net load changes. The proposed operation-adversarial cGAN (OA-cGAN) internalizes a DC optimal power flow model and seeks to maximize the operating cost and achieve a worst-case data generation. The training and testing stages employed in the proposed OA-cGAN use historical day-ahead net load forecast errors and has been implemented for the realistic NYISO 11-zone system. Our numerical experiments demonstrate that the generated operation-adversarial forecast errors lead to more cost-effective and reliable dispatch decisions.