摘要：

随着云计算环境中各种服务数量的急剧增长，如何从功能相同或相似的云服务中选择满足用户需求的服务成为云计算研究中亟待解决的关键问题。为此，建立带服务质量约束的多目标服务组合优化模型，针对传统多目标粒子群优化(MOPSO)算法中解的多样性差、易陷入局部最优等缺点，设计基于混沌多目标粒子群优化(CMOPSO)算法的云服务选择方法。采用信息熵理论来维护非支配解集，以保持解的多样性和分布的均匀性。当种群多样性丢失时，引入混沌扰动机制，以提高种群多样性和算法全局寻优能力，避免陷入局部最优。实验结果表明，与MOPSO算法相比，CMOPSO算法的收敛性和解集多样性均得到改善，能够更好地解决云计算环境下服务动态选择问题。

关键词: 云计算, 服务选择, 服务质量, 多目标粒子群优化算法, 信息熵, 混沌

Abstract:

With the explosive number growth of services in cloud computing environment, how to select the services that can meet user’s requirement from the services which have same or similar function becomes the key problem to be resolved in cloud computing. So a multi-objective service composition optimization model with Quality of Service(QoS) restriction is built, and since some disadvantages of the traditional Multi-objective Particle Swarm Optimization(MOPSO) algorithm, such as less diversity of solutions and falling into local extremum easily, a method of Chaotic MOPSO(CMOPSO) algorithm is proposed. This algorithm uses the information entropy theory to maintain non-dominated solution set so as to retain the diversity of solution and the uniformity of distribution. When the diversity of population disappears, it introduces chaotic disturbance mechanism to improve the diversity of population and the ability of global optimization algorithm to avoid falling into local extremum. Experimental result shows that the astringency and the diversity of solution set of CMOPSO algorithm are better than traditional MOPSO algorithm, and it can solve the problem of service dynamic selection under cloud computing environment more efficiently.

Key words: cloud computing, service selection, Quality of Service(QoS), Multi-objective Particle Swarm Optimization(MOPSO) algorithm, information entropy, chaotic

中图分类号: 

• TP391.9