A Real‐Time Scheduling Strategy for Virtual Power Plants Based on TCN‐SPPO
International Journal of Energy Research · 2026-01 · 2026 (1)
DOI: 10.1155/er/7300156 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Energy Research, online erschienen am 27.07.2026. Verfasst von Qiang Xing und 5 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
The virtual power plant (VPP) provides a new model for the integration and management of distributed energy resources. This paper proposes a real‐time scheduling strategy for VPPs based on temporal convolutional network‐safe proximal policy optimization (TCN‐SPPO). First, an optimal scheduling model aiming to reduce the comprehensive operation cost of VPP is constructed and converted into a real‐time scheduling model based on a constrained Markov decision process (CMDP), which explicitly incorporates safety constraints into the optimization framework of deep reinforcement learning (DRL). Second, an agent feature perception enhancement strategy based on a TCN is proposed to deeply explore local patterns and long‐term dependencies in operational data. Then, a TCN‐SPPO training paradigm based on mechanisms such as Lagrangian relaxation and delayed storage is proposed to realize efficient learning and optimization of VPP real‐time scheduling strategies. Finally, a case simulation is conducted based on distributed energy data from a region in Qinghai, China, to verify the effectiveness of the proposed TCN‐SPPO method.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Xing, Q., Yang, Q., Wang, M., Wu, M., Ni, Y., & Wu, J. (2026). A Real‐Time Scheduling Strategy for Virtual Power Plants Based on TCN‐SPPO. International Journal of Energy Research, 2026(1). https://doi.org/10.1155/er/7300156
Vancouver
Xing Q, Yang Q, Wang M, Wu M, Ni Y, Wu J. A Real‐Time Scheduling Strategy for Virtual Power Plants Based on TCN‐SPPO. International Journal of Energy Research. 2026;2026(1). doi:10.1155/er/7300156
BibTeX
@article{Xing2026,
author = {Xing, Qiang and Yang, Qiming and Wang, Mingshen and Wu, Mingming and Ni, Yiming and Wu, Jiayu},
title = {A Real‐Time Scheduling Strategy for Virtual Power Plants Based on TCN‐SPPO},
journal = {International Journal of Energy Research},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/er/7300156}
}
EUVIMED