基于PSO信息传递模式的混合算法

粒子群优化算法（Particle Swarm Optimization，PSO）是一种基于群智能（Swarm Intelligence）的随机优化计算技术。PSO和遗传算法这两种算法相比较，PSO收敛快速准确，但编码形式单一，局限于解决实优化问题，而遗传算法编码形式灵活，解决问题广泛，但执行效率低于PS00。将粒子群算法的信息传递模式与遗传算法的编码和遗传操作相结合，提出一种混合算法。并推导了两个算法之间的密切联系。并通过组合优化和函数优化的基准测试集对算法进行测试，试验结果表明，该算法在收敛精度和速度优于传统遗传算法。同时，也观察到该算法取得了与粒子群算法一致的收敛现象。

A HYBRID ALGORITHM INSPIRED BY THE PSO IDEA

This paper presents a hybrid PSO-based algorithm(HPSO) combining the idea of the particle swarm(PSO) with genetic algorithm(GA).Another reason is that PSO does not resolve combinatorial optimization better,for examples,Travel salesman problem(TSP),Minimum Spanning Tree(MST).We hybrid the way that each particle exploits information of its own experience to search the solution space with the crossover operator of GA,we prescribe a new algorithm to resolve Combinatorial Optimization and other optimization with discrete encoding.The PSGA outperforms the basic GA with faster convergence and better solution on MST and function optimization with discrete encoding,to some extend,we also answer why PSO is faster than GA on convergence speed.