有限理性公平数据交换协议的设计与仿真  

Design and Simulation of Fair Data Exchange Protocol with Bounded Rationality

作　　者：陆正福[1] 普艳红 倪盛斌 许辰铭[1] 杨春尧[1] LU Zheng-fu;PU Yan-hong;NI Sheng-bin;XU Chen-ming;YANG Chun-yao(School of Mathematics and Statistics,Yunnan University,Kunming 650500,China)

机构地区：[1]云南大学数学与统计学院,昆明650500

出　　处：《计算机科学》2018年第11期115-123,共9页Computer Science

基　　金：国家自然科学基金项目(10861012);云南省教育厅科学研究基金项目(09Y0347);云南大学理(工)科校级科研基金项目(YNUY201368);云南大学中青年骨干教师培养计划专项经费基金项目(XT412003)资助

摘　　要：理性交换协议(REP)因使用了理想化的理性假设,在现实中有可能失效。为解决此协议失效的问题,基于与现实更为接近的有限理性假设(BRH),定义了有限理性公平概念,并首次基于BRH设计了有限理性公平数据交换协议(FDEP-BR)。理论分析表明,与REP相比,FDEP-BR虽然牺牲了一定效率(轮复杂度为O(l*v)),但具有容错性和有限理性公平性,能够抵抗非合作攻击。对FDEP-BR构造自动机模型,并改进经验加权吸引(EWA)学习模型的决策方式,设计了EWA学习决策算法;在此基础上,基于Jade-Repast集成平台对FDEP-BR进行了仿真,仿真结果表明FDEP-BR的均衡状态与预期具有一致性。Rational exchange protocol may fail in reality because of the use of the idealized rationality hypothesis.In order to solve the protocol failure problem,based on bounded rationality hypothesis which is more consistent with the reality,the concept of bounded rational fairness was defined and fair data exchange protocol with bounded rationality(FDEP-BR)was designed for the first time.The theoretical analysis shows that the FDEP-BR can resist non-cooperative attack because of its fault-tolerance and bounded rationality fairness at the cost of round complexityΟ(l*v)compared with the rational exchange protocol.A finite automata model for FDEP-BR was constructed,the decision-making method for experiential weighted attraction(EWA)learning model was improved,and the EWA learning decision algorithm was designed.Then the FDEP-BR was simulated on the Jade-Repast integration platform.The simulation results show that the equilibrium state of the FDEP-BR is consistent with expectations.

关 键 词：有限理性 有限自动机 有限理性公平 公平数据交换协议 协议仿真 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]