Mathematical Model of Asynchronous Parallel Evolutionary Algorithm to Analyze Influence of Evaluation Time Bias

This paper proposes a mathematical model to analyze the behavior of an asynchronous parallel evolutionary algorithm (APEA) and demonstrates its validity through the comparison of the theoretical result with the simulation one. The proposed model considers the transition of the probability density of solutions in the population and the slave nodes in the parallel computing environment during the optimization process of an APEA. This paper demonstrates the convergence state of the population and the slave nodes on the flat fitness landscape by using the proposed model. From the result of the comparison between the theoretical result acquired by the proposed model and the simulation one, the validity of the proposed model is confirmed. Additionally, it is revealed that an APEA is necessarily biased toward the search area having a shorter evaluation time regardless of the fitness landscape. This paper finally shows a possible attempt to avoid the evaluation time bias on APEAs and demonstrates its effectiveness in the simulation experiment.

[1]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[2]  Enrique Alba,et al.  Parallelism and evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

[3]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[4]  Ludovic Duponchel,et al.  Simultaneous data pre-processing and SVM classification model selection based on a parallel genetic algorithm applied to spectroscopic data of olive oils. , 2014, Food chemistry.

[5]  Günter Rudolph,et al.  Comparing Asynchronous and Synchronous Parallelization of the SMS-EMOA , 2016, PPSN.

[6]  Byung-Il Koh,et al.  Parallel asynchronous particle swarm optimization , 2006, International journal for numerical methods in engineering.

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

[8]  V. Bajic,et al.  DWFS: A Wrapper Feature Selection Tool Based on a Parallel Genetic Algorithm , 2015, PloS one.

[9]  Jack B A Davis,et al.  The Birmingham parallel genetic algorithm and its application to the direct DFT global optimisation of Ir(N) (N = 10-20) clusters. , 2015, Nanoscale.

[10]  Enrique Alba,et al.  Parallel metaheuristics: recent advances and new trends , 2012, Int. Trans. Oper. Res..

[11]  Keiki Takadama,et al.  Asynchronously evolving solutions with excessively different evaluation time by reference-based evaluation , 2014, GECCO.

[12]  Mikhail Zhabitsky,et al.  Asynchronous Differential Evolution with Restart , 2012, NAA.

[13]  Vincent Roberge,et al.  Strategies to Accelerate Harmonic Minimization in Multilevel Inverters Using a Parallel Genetic Algorithm on Graphical Processing Unit , 2014, IEEE Transactions on Power Electronics.

[14]  A Shayeghi,et al.  Pool-BCGA: a parallelised generation-free genetic algorithm for the ab initio global optimisation of nanoalloy clusters. , 2015, Physical chemistry chemical physics : PCCP.

[15]  Shigeru Obayashi,et al.  Multi-Objective Design Exploration and its Applications , 2010 .

[16]  Akira Oyama,et al.  Simultaneous structure design optimization of multiple car models using the K computer , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[17]  Matjaz Depolli,et al.  Asynchronous Master-Slave Parallelization of Differential Evolution for Multi-Objective Optimization , 2013, Evolutionary Computation.

[18]  Gregory Miller,et al.  The effect of evaluation time variance on asynchronous Particle Swarm Optimization , 2017, 2017 IEEE Congress on Evolutionary Computation (CEC).

[19]  Kenneth A. De Jong,et al.  Evaluation-Time Bias in Asynchronous Evolutionary Algorithms , 2015, GECCO.

[20]  Roman Neruda,et al.  Parallel evolutionary algorithm with interleaving generations , 2017, GECCO.

[21]  Kenneth A. De Jong,et al.  Understanding Simple Asynchronous Evolutionary Algorithms , 2015, FOGA.

[22]  Andrew Lewis,et al.  Asynchronous Multi-Objective Optimisation in Unreliable Distributed Environments , 2009 .

[23]  Keiki Takadama,et al.  Asynchronous Evaluation Based Genetic Programming: Comparison of Asynchronous and Synchronous Evaluation and Its Analysis , 2013, EuroGP.