Virtual Inertia Optimization of Wind Power System and Its Significance for Sustainable Development

Biyao Liu ()
Additional contact information
Biyao Liu: Guangdong University of Technology, School of International Education

A chapter in Proceedings of the 2025 4th International Conference on Public Service, Economic Management and Sustainable Development (PESD 2025), 2025, pp 258-264 from Springer

Abstract: Abstract A virtual inertia optimization framework based on improved deep Q network (DQN) is proposed to solve inertia attenuation and frequency instability problems caused by high proportion wind power grid integration. By integrating dynamic perception and decision-making mechanism of deep reinforcement learning, the model maps power grid state information (frequency deviation, inertia gap and tie-line power) into virtual inertia parameter adjustment instructions, and optimizes the training process by using competition architecture, L1 regularization and multi-level experience playback. simulation result show that that improved DQN algorithm has significant effect on the RMS value of frequency fluctuation (0.12 Hz, 42.9% lower than PSO, 36.8% lower than ACO), response time (0.86 seconds, 36.3%-43.4% increase) and absolute value of power fluctuation (0.08 pu) are significantly better than particle swarm optimization (PSO) and ant colony algorithm (ACO), especially in load mutation scenarios, showing stronger robustness and real-time adjustment ability, providing key technical support for stable operation of high permeability new energy grid.

Keywords: Wind Power System; Virtual Inertia Optimization; Improved Deep Q Network; Particle Swarm Optimization (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-916-2_30

Ordering information: This item can be ordered from
http://www.springer.com/9789464639162

DOI: 10.2991/978-94-6463-916-2_30

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().