Welcome to the InfoSci Platform
Reference Hub1
A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System

A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System

Ahmad Mozaffari, Moein Mohammadpour, Alireza Fathi, Mofid Gorji-Bandpy
Copyright: © 2014 |Volume: 5 |Issue: 3 |Pages: 14
ISSN: 1947-8283|EISSN: 1947-8291|EISBN13: 9781466652637|DOI: 10.4018/ijamc.2014070102
Cite Article Cite Article

MLA

Mozaffari, Ahmad, et al. "A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System." IJAMC vol.5, no.3 2014: pp.9-22. http://doi.org/10.4018/ijamc.2014070102

APA

Mozaffari, A., Mohammadpour, M., Fathi, A., & Gorji-Bandpy, M. (2014). A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System. International Journal of Applied Metaheuristic Computing (IJAMC), 5(3), 9-22. http://doi.org/10.4018/ijamc.2014070102

Chicago

Mozaffari, Ahmad, et al. "A Fuzzy Model with Thermodynamic Based Consequents and a Niching Swarm-Based Supervisor to Capture the Uncertainties of Damavand Power System," International Journal of Applied Metaheuristic Computing (IJAMC) 5, no.3: 9-22. http://doi.org/10.4018/ijamc.2014070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In this investigation, a novel fuzzy mathematical program based on thermodynamic principles is implemented to capture the uncertainties of a practical power system, known as Damavand power plant. The proposed intelligent machine takes the advantages of a niching bio-inspired learning mechanism to be reconciled to the requirements of the problem at hand. The aim of the bio-inspired fuzzy based intelligent system is to yield a model capable of recognizing different operating parameters of Damavand power system under different operating conditions. To justify the privileges of using a niching metaheuristic over gradient descend methods, the authors use the data, derived through data acquisition, together with a machine learning based approach to estimate the multi-modality associated with the training of the proposed fuzzy model. Moreover, the niching bio-inspired metaheuristic, niching particle swarm optimization (NPSO), is compared to canonical PSO (CPSO), stochastic social PSO (SSPSO), unified PSO (UPSO), comprehensive learning PSO (CLPSO), PSO with constriction factor (PSOCF) and fully informed PSO (FIPSO). Through experiments and analysis of the characteristics of the problem being optimized, it is proved that NPSO is not only able to tackle the deficiencies of the learning process, but also can effectively adjust the fuzzy approach to conduct the identification process with a high degree of robustness and accuracy.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.