A Homogeneous Distributed Computing Framework for Multi-objective Evolutionary Algorithm

This paper proposes a homogeneous distributed computing (HDC) framework for multi-objective evolutionary algorithm (MOEA). In this framework, multiple processors divide a work into several pieces and carry them out in parallel. Every processor does its task in a homogeneous way so that the overall procedure becomes not only faster but also fault-tolerant and independent to the number of processors. To implement this framework into an evolutionary algorithm, the evolutionary process of multi-objective particle swarm optimization (MOPSO) is employed. The effectiveness of the proposed framework is demonstrated by empirical comparisons between the results with the different numbers of processors, one and four. Seven DTLZ functions are used as benchmark functions and hypervolume, diversity, and evaluation time are used as comparison metrics. The results indicate that the evaluation time is significantly reduced by the proposed framework without any loss of overall solution quality and diversity.

[1]  Kalyanmoy Deb,et al.  Distributed Computing of Pareto-Optimal Solutions with Evolutionary Algorithms , 2003, EMO.

[2]  Yang Yang,et al.  A distributed cooperative coevolutionary algorithm for multiobjective optimization , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[3]  Marco Laumanns,et al.  Scalable multi-objective optimization test problems , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[4]  Wilson Rivera,et al.  Scalable Parallel Genetic Algorithms , 2001, Artificial Intelligence Review.

[5]  Ki-Baek Lee,et al.  Mass-spring-damper motion dynamics-based particle swarm optimization , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[6]  Qingfu Zhang,et al.  Hybrid Estimation of Distribution Algorithm for Multiobjective Knapsack Problem , 2004, EvoCOP.

[7]  C.A. Coello Coello,et al.  MOPSO: a proposal for multiple objective particle swarm optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[8]  Prospero C. Naval,et al.  An effective use of crowding distance in multiobjective particle swarm optimization , 2005, GECCO '05.

[9]  Ki-Baek Lee,et al.  Multi-objective particle swarm optimization with preference-based sorting , 2011, 2011 IEEE Congress of Evolutionary Computation (CEC).

[10]  Eckart Zitzler,et al.  Evolutionary algorithms for multiobjective optimization: methods and applications , 1999 .

[11]  Jong-Hwan Kim,et al.  Quantum-inspired Multiobjective Evolutionary Algorithm for Multiobjective 0/1 Knapsack Problems , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[12]  Jens Gottlieb,et al.  Evolutionary Computation in Combinatorial Optimization , 2006, Lecture Notes in Computer Science.

[13]  Ki-Baek Lee,et al.  Particle Swarm Optimization driven by Evolving Elite Group , 2009, 2009 IEEE Congress on Evolutionary Computation.