AloA Optimized RLNN controller for LFC of deregulated two-area power system /
No Thumbnail Available
Date
2021-07-20
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Informatics Publishing Limited
Abstract
The performance of the ant lion optimization algorithm (AloA) optimized RLNN controllers are analysed in this work for LFC of two-area deregulation power system. The comparisons are performed for time domain performances of AloA optimized RLNN controllers with traditional PID controllers. The input of PID and RLNN controllers are used area control error (ACE) and controllers’ gains are adjusted through online for RLNN controllers. The performance analyses are also studied to check the controllers’ robustness with variation in parameters of the system and loads. The analysis exposes that AloA optimized RLNN controllers significantly improve the time domain performances of the considered power system compared to PID controllers.
Description
Keywords
Reinforced Learning Neural Network (RLNN), Load Frequency Control (LFC), Area Control Error, Ant Lion Optimization Algorithm.