Multi-Lateral Multi-Issue Negotiation Based on Hybrid Genetic Algorithm and Its Application in E-Commerce

To enable agents negotiate more efficiently in multi-lateral multi-issue cooperative negotiations in multi-agent based e-commerce, a hybrid genetic algorithm (HGA) is presented. After 1000 times of experiments for four kinds of agents to gain satisfying result, standard genetic algorithm(SGA) averagely needs negotiation of 185 runs, genetic algorithm based on Metropolis rule(MGA) averagely needs 176 runs, adaptive genetic algorithm(AGA) averagely needs 169 runs, while the HGA averagely needs only 153 runs. Experimental results showed that the HGA can gain optimal negotiation result more efficiently than the other three kinds of genetic algorithms in multi-lateral multi-issue cooperation negotiation.