TY - JOUR
T1 - Operation-adversarial scenario generation
AU - Liang, Zhirui
AU - Mieth, Robert
AU - Dvorkin, Yury
N1 - Funding Information:
This work was supported by the US DOE ARPA-e under Grant DE-AR0001300 .
Publisher Copyright:
© 2022 Elsevier B.V.
PY - 2022/11
Y1 - 2022/11
N2 - 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.
AB - 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.
KW - Conditional generative adversarial network (cGAN)
KW - DC optimal power flow (OPF)
KW - Operation-adversarial learning
UR - http://www.scopus.com/inward/record.url?scp=85134739157&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85134739157&partnerID=8YFLogxK
U2 - 10.1016/j.epsr.2022.108451
DO - 10.1016/j.epsr.2022.108451
M3 - Article
AN - SCOPUS:85134739157
SN - 0378-7796
VL - 212
JO - Electric Power Systems Research
JF - Electric Power Systems Research
M1 - 108451
ER -