Power system stabilization based on artificial intelligent techniques; A review

Abstract

This paper reviews new approaches in modern research using Artificial Intelligent (AI) techniques to develop power system stabilizer (PSS). These techniques are Artificial Neural Network (ANN), fuzzy logic, hybrid artificial intelligent, expert systems, and optimization techniques base AI such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Tabu Search (TS) algorithm, etc. Research showed controllers designed based on a conventional control theory, modern and adaptive control theories, suffer from some limitations. However, AI techniques proved to be able to overcome theses limits. Hence, more researchers preferred to utilize these approaches for the power systems. The review efforts geared towards PSS and excitation system stabilizer developed based on AI techniques, which effectively enhance both small signal stability and transient stability and equally provide superior performances. In addition, the dynamic performance of different AI based stabilizers are established and compared with other types of PSSs.

Improving Dynamic Stability of Power Systems by Using Avr, Power System Stabilizer

“…However, it has been used to denote different phenomena by different authors. In the North American literature, it has been used mostly to denote small-disturbance stability in the presence of automatic controls (particularly, the generation excitation controls) as distinct from the classical "steady-state stability" with no generator controls [1].…”

Modeling, simulation, and optimal design of power system stabilizers using ABC algorithm

“…Accordingly, novel modern control approaches, such as adaptive controllers and H ∞ control systems, have been employed for attaining operating performance superior to that of conventional stabilizers. However, the stabilizers depending upon modern control theory still have firm weaknesses, including completely essential information regarding the power system, high computing time for online parameter identification, and large implementation costs [8].…”

Untitled

“…Artificial intelligent techniques have been the focus of many researches [13]. In this paper a predictive controller based on two artificial neural networks is proposed.…”