优化RFID网络的含云生成算子的粒子群优化算法（英文）  

Particle swarm optimizer with cloud generators for optimizing RFID network

作　　者：高鹰[1] GAO Ying(School of Computer Science and Technology, Guangzhou University, Guangzhou 510006 , China)

机构地区：[1]广州大学计算机科学与教育软件学院,广东广州510006

出　　处：《广州大学学报（自然科学版）》2017年第2期82-88,共7页Journal of Guangzhou University:Natural Science Edition

基　　金：supported by Natural Science Foundation of Guangdong Province,China(2014A030313524 and 2014A030310349);Science and Technology Projects of Guangdong Province,China(2016B010127001,2015A010103020);Science and Technology Projects of Guangzhou(201607010191)

摘　　要：RFID网络规划问题是一个优化难题,文章给出一个含云生成算子的粒子群优化算法用于求解该问题.在该算法的子代生成框架中,新粒子通过云方式或PSO方式产生.(1)应用反向云生成算子,PSO认知种群被用于估计好解区域的期望、熵和超熵;(2)利用正向云生成算子,估计的期望、熵和超熵被用于生成云粒子;(3)来自PSO粒子的局部信息和来自云粒子的全局信息共同引导算法的下一步寻优.该算法优化文献中一些著名的RFID网络基准测试实例,实验结果显示该算法比原始的PSO有好的优化能力.RFID network planning is a hard optimization problem. In the paper, a particle（PSO） with cloud generators is introduced for optimizing RFID network. In the algorithm’s offspring generation scheme, new particles are generated in the cloud way or in the PSO way .①The cognitive population of PSO is firstly used to estimate Expectation, Entropy and Super-entropy of good solution regions by backward cloud gen-erator. ②And then the estimated Expectation, Entropy and Super-entropy are used to by positive cloud generator.③Both local information from PSO particles and the global particles are used to guide the next search. The proposed algorithm is applied RFID network benchmark instances used in the literature. The experimental results show that the algorithm hasbetter search ability than original PSO in the benchmark instances.

关 键 词：RFID网络 粒子群优化算法 反向云生成算子 正向云生成算子 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]