Parallel Evolution Algorithm Research And Application

In this paper a novel class of parallel evolutionary computation technique-Swarm Intelligence. Algorithm and application is discussed, among which the Quantum-behaved Particle Swarm Optimization (QPSO) algorithm is a recently proposed approach and is a variant of original Particle Swarm Optimization (PSO). QPSO is global convergent and will be a promising solver for complex optimization problem, which is shown by some previous work. Thus, the research of this paper will be of somewhat significance in evolutionary computation area and parallel area.On the base of genetic algorithm, particle swarm algorithm, quantum-behaved particle swarm algorithm and some other parallel algorithm, we put forward a new parallel method on particle swarm algorithm and quantum-behaved particle swarm algorithm by the influence of the implement of genetic algorithm. The main idea is introducing the concepts of island model and changing arithmetic operators. In the cluster environment, the optimal algorithm increasing global searching ability by maintaining diversity,using changing arithmetic operators to communicate with each other.Due to the long time for communication, bottleneck will appear on parallel tests. We amend communication by reducing the communication cycle according to descending numeral array. We set examples by some basic testing case to describe the design idea and the implement process and we provide many testing results and comparison with other serial and parallel results. The results indicate that both searching ability and running time are better and it's a useful means for solving complex optimization problems. In this paper, we present a decision-making process that incorporates Parallel Particle Swarm Optimization (PPSO) Algorithm into multi-stage portfolio optimization system. The objective function is to maximize one's economic utility or end-of-period wealth. Experiments are conducted to compare performance of the portfolios optimized by different objective functions in terms of expected return and standard derivation.