Adaptive Active Disturbance Rejection Load Frequency Control for Power System with Renewable Energies Using the Lyapunov Reward-Based Twin Delayed Deep Deterministic Policy Gradient Algorithm

The substitution of renewable energy sources (RESs) for conventional fossil fuels in electricity generation is essential in addressing environmental pollution and resource depletion. However, the integration of RESs in the load frequency control (LFC) of power systems can have a negative impact on f...

Full description

Saved in:
Bibliographic Details
Published in:Sustainability Vol. 15; no. 19; p. 14452
Main Authors: Zheng, Yuemin, Tao, Jin, Sun, Qinglin, Sun, Hao, Chen, Zengqiang, Sun, Mingwei
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.10.2023
Subjects:
Air-turbines
Algorithms
Alternative energy sources
Analysis
Controllers
Electric power production
Electric power systems
Electric power-plants
Energy resources
Optimization algorithms
Power plants
Renewable resources
Sustainability
Systems stability
Turbines
Wind power
ISSN:2071-1050, 2071-1050
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The substitution of renewable energy sources (RESs) for conventional fossil fuels in electricity generation is essential in addressing environmental pollution and resource depletion. However, the integration of RESs in the load frequency control (LFC) of power systems can have a negative impact on frequency deviation response, resulting in a decline in power quality. Moreover, load disturbances can also affect the stability of frequency deviation. Hence, this paper presents an LFC method that utilizes the Lyapunov reward-based twin delayed deep deterministic policy gradient (LTD3) algorithm to optimize the linear active disturbance rejection control (LADRC). With the advantages of being model-free and mitigating unknown disturbances, LADRC can regulate load disturbances and renewable energy deviations. Additionally, the LTD3 algorithm, based on the Lyapunov reward function, is employed to optimize controller parameters in real-time, resulting in enhanced control performance. Finally, the LADRC-LTD3 is evaluated using a power system containing two areas, comprising thermal, hydro, and gas power plants in each area, as well as RESs such as a noise-based wind turbine and photovoltaic (PV) system. A comparative analysis is conducted between the performance of the proposed controller and other control techniques, such as integral controller (IC), fractional-order proportional integral derivative (FOPID) controller, I-TD, ID-T, and TD3-optimized LADRC. The results indicate that the proposed method effectively addresses the LFC problem.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2071-1050
2071-1050
DOI:10.3390/su151914452