B.K. Panigrahi et al. (Eds.): SEMCCO 2010, LNCS 6466, pp. 531–536, 2010. © Springer-Verlag Berlin Heidelberg 2010 Performance Evaluation of Particle Swarm Optimization Based Active Noise Control Algorithm Nirmal Kumar Rout 1 , Debi Prasad Das 2 , and Ganapati Panda 3 1 School of Electronics Engineering, KIIT University, Bhubaneswar, India routnirmal@rediffmail.com 2 PE&I Cell, IMMT (CSIR), Bhubaneswar, India debi_das_debi@yahoo.com 3 School of Electrical Sciences, IIT, Bhubaneswar, India ganapati.panda@gmail.com Abstract. Active noise control (ANC) has been used to control low-frequency acoustic noise. The ANC uses an adaptive filter algorithm and normally uses least mean square (LMS) algorithm. The gradient based LMS algorithm suffers from local minima problem. In this paper, particle swarm optimization (PSO) algorithm, which is a non-gradient but simple evolutionary computing type al- gorithm, is proposed for the ANC system. Detailed mathematical treatment is made and systematic computer simulation studies are carried out to evaluate the performance of the PSO based ANC algorithm. 1 Introduction Active noise control (ANC) is an electroacoustic or electromechanical system which cancels an acoustic noise based on the principle of destructive interference [1]. Dif- ferent types of ANC algorithms have been proposed to circumvent different issues linked with it such as nonlinear issues in [2]. In [3] genetic algorithm (GA) based al- gorithm is shown to be superior to the conventionally used least mean square (LMS) algorithm. Recently particle swarm optimization (PSO) has been proposed as an al- ternate useful and superior optimization algorithm to GA. Like GA, PSO also does not use derivative of the cost function for optimization of parameters and hence rela- tively free from local minima trap. The PSO is originally proposed by Kennedy et al. in [4] as an optimization tool. A single paper on PSO based adaptation of the weights of multilayer neural network as a nonlinear ANC algorithm has been reported in the literature [5]. In this paper, we present a systematic algorithm of the PSO based ANC system. The detailed analysis of the proposed algorithm through computer simulations would provide the merits and demerits of it. The paper is organized as follows. Section 2 describes the proposed method and deals with the advantages and the draw- backs of the PSO based ANC system. Section 3 presents the results of some computer simulations, and finally, Section 4 reports the conclusion of the findings. 2 Proposed Particle Swarm Optimization Based ANC System The proposed method involves separate training and testing phase of the ANC System.