Y. Tan et al. (Eds.): ICSI 2011, Part I, LNCS 6728, pp. 321–328, 2011. © Springer-Verlag Berlin Heidelberg 2011 Average-Inertia Weighted Cat Swarm Optimization Maysam Orouskhani 1,* , Mohammad Mansouri 2 , and Mohammad Teshnehlab 3 1 Msc Student, Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran orouskhani@ce.sharif.edu 2 Intelligent System Laboratory (ISLAB), faculty of Electrical Engineering, Control department, K.N. Toosi University of Technology, Tehran, Iran 3 Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran Abstract. For improving the convergence of Cat Swarm Optimization (CSO), we propose a new algorithm of CSO namely, Average-Inertia Weighted CSO (AICSO). For achieving this, we added a new parameter to the position update equation as an inertia weight and used a new form of the velocity update equation in the tracing mode ofalgorithm.Experimental results using Griewank,Rastrigin and Ackley functions demonstrate that the proposed algorithm has much better convergence than pure CSO. Keywords: Cat Swarm Optimization, Average-Inertia Weighted Cat Swarm Optimization, Swarm Intelligence. 1 Introduction Optimization and functionsminimization are very important problems. So there are many algorithms to solve these problems.Some of these optimization algorithms were developedbased on swarm intelligence bysimulating the intelligent behavior of animals, like AntColony Optimization (ACO) [1-6] which imitates the behavior ofants, Particle Swarm Optimization (PSO) [2] which imitates thebehavior of birds, Bee Colony Optimization (BCO)[3] which imitates the behavior of bees and the recent finding, Cat SwarmOptimization (CSO) [4] which imitates the behavior of cats. In order to solve the optimization problems, CSO models the behavior of cats into two sub-models namely seeking mode and tracing mode. In the cases of functions optimization, CSO is one ofthe best algorithms to find the best global solution. In comparison withother heuristic algorithms such as PSO and PSO with weighting factor [7], CSO usually achievesbetter result. But sometimes in some cases pure CSO takes a long time to find an acceptable solution. So it affects onperformance and convergence of the algorithm.Therefore high speed processor is needed for gettingreasonable result. In this article, our aim is to introduce a new version of CSO in order to improve the performance and achieve better convergence in less iteration. First we add a new * Corresponding author.