APPLICATION OF NOVEL REINFORCEMENT LEARNING AUTOMATA APPROACH IN POWER SYSTEM REGULATION

2009 ◽  
Vol 18 (08) ◽  
pp. 1609-1625 ◽  
Author(s):  
MOHAMMAD KASHKI ◽  
YOUSSEF L. ABDEL-MAGID ◽  
MOHAMMAD A. ABIDO
Keyword(s):  
Reinforcement Learning ◽  
Pid Controller ◽  
Controller Design ◽  
Learning Automata ◽  
Synchronous Generator ◽  
Optimization Method ◽  
Avr System ◽  
Pid Controller Design ◽  
Analytical System ◽  
Reinforcement Learning Automata

In this paper, a novel efficient optimization method based on reinforcement learning automata (RLA) for optimum parameters setting of conventional proportional-integral-derivative (PID) controller for AVR system of power synchronous generator is proposed. The proposed method is Combinatorial Discrete and Continuous Action Reinforcement Learning Automata (CDCARLA) which is able to explore and learn to improve control performance without the knowledge of the analytical system model. This paper demonstrates the full details of the CDCARLA technique and compares its performance with Particle Swarm Optimization (PSO) as an efficient evolutionary optimization method. The proposed method has been applied to PID controller design. The simulation results show the superior efficiency and robustness of the proposed method.

scholarly journals Enhanced Chaotic Grasshopper Optimization Algorithm Based PID Controller for Automatic Voltage Regulator System

2019 ◽  
Vol 8 (4) ◽  
pp. 348-354
Keyword(s):  
Optimization Algorithm ◽  
Pid Controller ◽  
Controller Design ◽  
System Response ◽  
Voltage Regulator ◽  
Minimum Error ◽  
Avr System ◽  
Grasshopper Optimization Algorithm ◽  
Pid Controller Design ◽  
Grasshopper Optimization

This work presents, the PID controller design for AVR system using Enhanced Chaotic Grasshopper Optimization Algorithm (ECGOA). The system response under the different settings are studied with PID controller for stable and minimum error operation. The gain of the controller revealed from traditional methods to recent optimization algorithm. The ECGOA will be implemented for AVR system with PID controller and the performance in-terms of transient response, robustness, stability and error is compared with existing optimization algorithm. The ECGOA based PID controller provides good response and examined upto ±50% of variation in several component of AVR system

Improved Jaya algorithm-based FOPID/PID for AVR system

2020 ◽  
Vol 39 (4) ◽  
pp. 775-790
Author(s):  
Jailsingh Bhookya ◽  
Ravi Kumar Jatoth
Keyword(s):  
Time Domain ◽  
Pid Controller ◽  
Controller Design ◽  
Optimal Controller ◽  
Jaya Algorithm ◽  
Proportional Integral Derivative ◽  
Content Type ◽  
Proportional Integral ◽  
Avr System ◽  
Pid Controller Design

Purpose This paper aims to get the optimal controller parameters of fractional order proportional integral derivative (FOPID)/proportional integral derivative (PID) i.e. Kp, Ki, Kd, λ and µ for designing controller in automatic voltage regulator (AVR) system. Design/methodology/approach A novel method is proposed to get the optimal controller parameters for designing controller in AVR system using improved Jaya algorithm (IJA). The time domain objective and regular integral error objectives are used to design the controller to estimate the performance of the AVR system based on optimal tuning FOPID/PID controller. Findings The proposed method captures time domain objective of the FOPID/PID controller design and demonstrates effective transient response and better control action. The efficient tuning of FOPID controller results in high superiority of control efforts. Practical implications The simulations of IJA-based FOPID/PID controller design method are performed in MatLab tool and compared with several methods in the recent state of the art and the same are observed to be robust for the AVR system. Originality/value The developed optimal FOPID/PID controller tuning using IJA optimization method is totally a new approach for the AVR system in the literature.

Sign in / Sign up

Export Citation Format

Share Document