DDPG-ADRC-Based Load Frequency Control for Multi-Region Power Systems with Renewable Energy Sources and Energy Storage Equipment

Zhenlan Dou, Chunyan Zhang, Xichao Zhou, Dan Gao and Xinghua Liu ()
Additional contact information
Zhenlan Dou: State Grid Shanghai Municipal Electric Power Company, Shanghai 200120, China
Chunyan Zhang: State Grid Shanghai Municipal Electric Power Company, Shanghai 200120, China
Xichao Zhou: State Grid Integrated Energy Services Group Co., Ltd., Beijing 100032, China
Dan Gao: School of Electrical Engineering, Xi’an University of Technology, Xi’an 710048, China
Xinghua Liu: School of Electrical Engineering, Xi’an University of Technology, Xi’an 710048, China

Energies, 2025, vol. 18, issue 14, 1-21

Abstract: A scheme of load frequency control (LFC) is proposed based on the deep deterministic policy gradient (DDPG) and active disturbance rejection control (ADRC) for multi-region interconnected power systems considering the renewable energy sources (RESs) and energy storage (ES). The dynamic models of multi-region interconnected power systems are analyzed, which provides a basis for the subsequent RES access. Superconducting magnetic energy storage (SMES) and capacitor energy storage (CES) are adopted due to their rapid response capabilities and fast charge–discharge characteristics. To stabilize the frequency fluctuation, a first-order ADRC is designed, utilizing the anti-perturbation estimation capability of the first-order ADRC to achieve effective control. In addition, the system states are estimated using a linear expansion state observer. Based on the output of the observer, the appropriate feedback control law is selected. The DDPG-ADRC parameter optimization model is constructed to adaptively adjust the control parameters of ADRC based on the target frequency deviation and power deviation. The actor and critic networks are continuously updated according to the actual system response to ensure stable system operation. Finally, the experiment demonstrated that the proposed method outperforms traditional methods across all performance indicators, particularly excelling in reducing adjustment time (45.8% decrease) and overshoot (60% reduction).

Keywords: multi-region interconnected power system; energy storage equipment; load frequency control; first-order active disturbance rejection controller; deep deterministic policy gradient algorithm (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/14/3610/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/14/3610/ (text/html)

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:gam:jeners:v:18:y:2025:i:14:p:3610-:d:1697456

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().