The Risk Programming of Virtual Enterprises Based on Algorithms of Min / Max / Mean / Random-PSO

The classical particle swarm optimization (PSO) is an effective method to find the extreme values of continuous functions, however its application in discrete space is still premature. In this text, four algorithms of PSO are proposed to solve the problem of combinatorial optimization. They are designed according to the different reactions between particle extremum and overall extremum and help to solve the problem of risk programming of virtual enterprises. Among these four algorithms of PSO, namely min-PSO, max-PSO, mean-PSO, and random-PSO, random-PSO is concluded as the best after comparisons. Meanwhile, multi-level fuzzy synthetic evaluation is integrated to assess the overall risk level. Simulation analysis suggested that PSO is a simple but effective algorithm to solve the problem of combinatorial optimization