基于PSO的组合拍卖模型及其Swarm仿真

通过放松竞买人对拍卖物品的替代性或互补性的一致性认识假设,在组合拍卖机制设计的基础上建立了基于竞买人报价的组合拍卖模型.为了高效率地获得物品的最优分配方式,运用particle swarm optimization(PSO)算法模拟物品分配方式的寻优过程,在此基础上构建了基于PSO算法的组合拍卖模型.在Swarm仿真平台上对基于PSO算法的组合拍卖模型进行设计与实现,并通过一个具体的组合拍卖算例进行仿真验证,结果分析表明基于PSO算法的组合拍卖模型能够有效地解决多个物品的分配问题,并能实现卖主收益的最大化.学习能力参数分析表明,与自我学习能力相比,社会学习能力对卖主收益的优化更加重要.本文的研究结果对组合拍卖的理论研究和实际应用具有一定的借鉴价值.

Swarm simulation of combinatorial auction model based on PSO

By easing the consistency hypothesis of alternative or complementary auction items for bidders, this paper establishes a combinational auction model according to bidders' bid on the basis of combinatorial auction mechanism design. In order to efficiently obtain the optimal allocation of multiple items, particle swarm optimization (PSO) algorithm is used to simulate the optimization process of allocation, and then the combinatorial auction model based on PSO algorithm is constructed. The paper designs and implements the combinatorial auction model based on PSO algorithm on swarm simulation platform, and verifies the simulation validation through a specific combinational auction example. The analysis of simulation results shows that the combinatorial auction model based on PSO algorithm can effectively solve the problem of the distribution of multiple items, and can maximize the benefit of the vendor. The parameter analysis of learning ability shows that compared with self-learning ability, social learning ability is more important to the optimization of seller's return. This paper will have certain reference value to both the theoretical research and practical application of combinatorial auction.