Multi-objective Optimization in Partner Selection

It is a typical multi-objective optimization problem for the scientific decision of bidding to seek cooperating partner in virtual enterprise. With the optimization model proposed, partner selection is solved by the improved genetic algorithm. In the evolution process, individual survive rate is dynamic according to queue of individuals ´fitness values before roulette wheel selection, avoiding premature convergence. Crossover and mutation operators are accordingly adaptive to fitness value and iterative degree, which endows individuals with self- adaptability with the variation of the environment. Finally, the example demonstrates the validity of the adaptive genetic algorithm.