北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2009, Vol. 32 ›› Issue (2): 1-4.doi: 10.13190/jbupt.200902.1.lij

• 论文 •    下一篇

一种基于混合遗传算法的双边多议题协商

李剑 牛少彰   

  1. 北京邮电大学 北京邮电大学信息安全中心
  • 收稿日期:2008-09-18 修回日期:1900-01-01 出版日期:2009-04-28 发布日期:2009-04-28
  • 通讯作者: 李剑

A Bilateral Multi-Issue Negotiation Based on Hybrid Genetic Algorithm

LI Jian   

  • Received:2008-09-18 Revised:1900-01-01 Online:2009-04-28 Published:2009-04-28
  • Contact: LI Jian

摘要:

为了提高基于智能体电子商务双边多议题协商当中agent协商的效率,提出了一种agent的协商模型,并且将混合遗传算法HGA应用于这种模型当中,来提高模型中agent协商的效率。分别对4种遗传算法各进行1000次的实验。结果表明,它们同样达到协商最优解时,标准遗传算法SGA平均需要218次协商,基于Metropolis准则的遗传算法MGA平均需要184次协商,自适应遗传算法AGA平均需要152次协商,而混合遗传算法HGA平均仅需要121次协商。这说明,在求解双边多议题协商问题的时候,HGA可以使得协商当中的agent高效达到协商的最优解。

关键词: 电子商务, 双边多议题协商, 混合遗传算法, 智能体

Abstract:

To make the agents negotiate more efficient in bilateral multi-issue negotiation in multi-agent based e-commerce, an agent negotiation model is presented,。A hybrid genetic algorithm (HGA) is applied in the model to enhance the negotiation efficiency. Experiments are done for 1000 times for four kinds of agents to gain the satisfying result, Standard Genetic Algorithm(SGA) averagely needs 218 runs negotiation , Genetic Algorithm based on Metropolis rule(MGA) averagely needs 184 runs, adaptive genetic algorithm(AGA)averagely needs 152 runs while the hybrid genetic algorithm(HGA) averagely 121 runs. Experimentals show that the HGA can gain the optimal negotiation result more efficiently than other three kinds of genetic algorithms in bilateral multi-issue negotiation.

Key words: e-commerce, bilateral multi-issue negotiation, hybrid genetic algorithm, agent