Performance Analysis Of Parallel Mind Evolutionary Computation

Genetic Algorithm (GA) was firstly proposed in 1960's by professor Holland who came from Michigan State University. It is a computational model that simulates evolutionary process in nature. During the passed 30 years, the theoretical study and application of GA has been most active, and has rapidly become a highlight in the fields of international academy. However, there are many shortcomings in GA, which should not be neglected. In the early stage, researchers have noticed the problem of GA's prematurely. Another crucial problem is computing efficiency of GA, due to non-directionality of its evolutionary mechanism.Mind Evolutionary Computation (MEC) is a new approach of Evolutionary Computation (EC) proposed by Chengyi Sun in 1998. It comes from the consideration of the existing problems of Genetic Algorithm (GA) and the analysis of the mind progress of humanity. It imitates two phenomena of human society -similartaxis and dissimilation.MEC is of parallelity inherent and development of large-scale parallel computer is rapidly. These make us begin to study parallel problem of MEC. MEC integrates with parallel computer can promote research and development of MEC.In this thesis, based on the review of EC, MEC and Parallel Genetic Algorithms (PGAs), we analyze many factors of affecting performance of PMEC. The theoretic analysis and experimental results show that PMEC has good parallel performance. This enriches the framework of MEC. The originalities in this thesis are as follows:Firstly, we compare Parallel Mind Evolution Algorithms with Master Slave Parallel Genetic Algorithms and Coarse Parallel Genetic Algorithms .Secondly, many factors of affecting performance of PMEC are analyzed in theory. We conduct experiments in order to verify the analysis. Studies on its theoiy and experiment show that MEC is suitable to paralleling.