A polar coordinate particle swarm optimiser

The Particle Swarm Optimisation (PSO) algorithm consists of a population (or swarm) of particles that are ''flown'' through an n-dimensional space in search of a global best solution to an optimisation problem. PSO operates in Cartesian space, producing Cartesian solution vectors. By making use of an appropriate mapping function the algorithm can be modified to search in polar space. This mapping function is used to convert the position vectors (now defined in polar space) to Cartesian space such that the fitness value of each particle can be calculated accordingly. This paper introduces the polar PSO algorithm that is able to search in polar space. This new algorithm is compared to its Cartesian counterpart on a number of benchmark functions. Experimental results show that the polar PSO outperforms the Cartesian PSO in low dimensions when both algorithms are applied to the search for eigenvectors of different nxn square matrices. Performance of the polar PSO on general unconstrained functions is not as good as the Cartesian PSO, which emphasizes the main conclusion of this paper, namely that the PSO is not an efficient search algorithm for general unconstrained optimisation problems defined in polar space.

[1]  R. Eberhart,et al.  Comparing inertia weights and constriction factors in particle swarm optimization , 2000, Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512).

[2]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[3]  Xiao-Feng Xie,et al.  Handling boundary constraints for numerical optimization by particle swarm flying in periodic search space , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[4]  N. Franken,et al.  Combining particle swarm optimisation with angle modulation to solve binary problems , 2005, 2005 IEEE Congress on Evolutionary Computation.

[5]  Kathleen Steinhöfel,et al.  Proc. IEEE Congress on Evolutionary Computation , 2008, CEC 2008.

[6]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[7]  Rolf Wanka,et al.  Particle Swarm Optimization in High-Dimensional Bounded Search Spaces , 2007, 2007 IEEE Swarm Intelligence Symposium.

[8]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[9]  Russell C. Eberhart,et al.  A discrete binary version of the particle swarm algorithm , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[10]  Tian Hou Seow,et al.  Particle swarm inspired evolutionary algorithm (PS-EA) for multiobjective optimization problems , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[11]  Alejandro Sierra,et al.  The polar evolution strategy , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[12]  Frans van den Bergh,et al.  An analysis of particle swarm optimizers , 2002 .

[13]  Maurice G. Kendall,et al.  A Course in the Geometry of n Dimensions , 1962 .

[14]  Dipti Srinivasan,et al.  Particle Swarm Inspired Evolutionary Algorithm (PS-EA) for Multi-Criteria Optimization Problems , 2003, Evolutionary Multiobjective Optimization.

[15]  Andries Petrus Engelbrecht,et al.  Binary Differential Evolution , 2006, 2006 IEEE International Conference on Evolutionary Computation.