UNCORRECTED PROOF 1 2 Implementing soft computing techniques to solve economic 3 dispatch problem in power systems 4 H. Altun * , T. Yalcinoz 5 Department of Electrical and Electronic Engineering, Nigde University, Nigde 51100, Turkey 6 7 Abstract 8 Soft computing is the state-of-the-art approach to artificial intelligence and it has showed an excellent performance in solving the com- 9 bined optimization problems. In this paper, issues related to the implementation of the soft computing techniques are highlighted for a 10 successful application to solve economic dispatch (ED) problem, which is a constrained optimization problem in power systems. First of 11 all, a survey covering the basics of the techniques is presented and then implementation of the techniques in the ED problem is discussed. 12 The soft computing techniques, namely tabu search (TS), genetic algorithm (GA), Hopfield neural network (HNN) and multi-layered 13 perceptron (MLP) are applied to solve the ED problem. The techniques are tested on power systems consisting of 6 and 20 generating 14 units and the results are compared to highlight the performance of the soft computing techniques. Future directions and open-ended 15 problems in implementation of soft computing techniques for constrained optimization problems in power system are indicated. Sugges- 16 tions are presented to improve soft computing techniques. 17 Ó 2007 Published by Elsevier Ltd. 18 Keywords: Soft computing techniques; Constrained optimization; Economic dispatch; Tabu search; Genetic algorithm; Hopfield neural networks; MLP 19 neural networks 20 21 1. Introduction 22 The economic dispatch (ED) is a constrained optimiza- 23 tion problem and the nature of the problem is to find the 24 most economical schedule of the generating units while 25 satisfying load demand and operational constraints. The 26 problem has been tackled by many researchers in the past. 27 The economic dispatch problem using conventional meth- 28 ods are surveyed by Chowdhury and Rahman (1990) and 29 Talaq et al. (1994). Due to the network connection of power 30 systems and the further innovation in the electricity market, 31 the power systems become large scale non-linear dynamic 32 systems Q3 (Bai & Zhao, 1990). In consequence, conventional 33 techniques become very complicated when dealing with such 34 increasingly complex dynamic system to solve economic 35 dispatch problems, and are further limited by their lack of 36 robustness and efficiency in a number of practical applica- 37 tions. Thus developing a reliable, fast and efficient algorithm 38 is still an active area in power systems. In the last decay, the 39 success of artificial intelligence techniques in broad area of 40 optimization problems and promising research direction in 41 literature pave the way to employ artificial intelligence and 42 soft computing techniques to solve long standing power sys- 43 tem problems, such as economic dispatch (Hong & Li, 2002; 44 Kulkarni, Kothari, & Kothari, 2000; Roa-Sepulveda & Her- 45 rera, 2000; Song & Chou, 1997; Yalcinoz & Altun, 2005; 46 Yalcinoz & Altun, 2000; Yalcinoz & Short, 1997; Zhu & 47 Tomsovic, 2007), environmental/economical dispatch 48 (Chiang, 2007; Jayabarathi, 2003; Song, Wang, Wang, & 49 Johns, 1997), unit commitment (Dieu & Ongsakul, 2006; 50 Rajan, Christober, Mohan, & Manivannan, 2002; Rajan 51 & Mohan, 2003). 52 In this paper, a brief survey covering recent implementa- 53 tion of soft computing techniques in ED problem is pre- 54 sented. Then performance evaluation of a number of soft 55 computing techniques to solve the problem is elaborated. 0957-4174/$ - see front matter Ó 2007 Published by Elsevier Ltd. doi:10.1016/j.eswa.2007.08.066 * Corresponding author. Q2 Tel.: +90 388 225 2281; fax: +90 388 225 01 12. E-mail addresses: haltun@nigde.edu.tr (H. Altun), tyalcinoz@nigde.e- du.tr (T. Yalcinoz). www.elsevier.com/locate/eswa Expert Systems with Applications xxx (2007) xxx–xxx Expert Systems with Applications ESWA 2287 No. of Pages 11, Model 5+ 25 September 2007 Disk Used ARTICLE IN PRESS Please cite this article in press as: Altun, H. , & Yalcinoz, T., Implementing soft computing techniques to solve economic ..., Expert Systems with Applications (2007), doi:10.1016/j.eswa.2007.08.066