云计算环境中基于朴素贝叶斯算法的负载均衡技术  

Load balancing technology based on naive Bayes algorithm in cloud computing environment

作　　者：蔡嵩[1,2] 张建明[1] 陈继明[1,2] 潘金贵[2] 

机构地区：[1]江苏大学计算机科学与通信工程学院,江苏镇江212013 [2]计算机软件新技术国家重点实验室(南京大学),南京210093

出　　处：《计算机应用》2014年第2期360-364,共5页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61170126;61202474);江苏省自然科学基金资助项目(BK20130528);江苏省高校自然科学基金资助项目(11KJB520003)

摘　　要：针对云计算环境中任务调度算法复杂度高、任务分配不够合理等问题,提出一种基于朴素贝叶斯分类的负载均衡技术。该技术利用云计算环境的心跳机制全面地收集各节点负载信息,并采用朴素贝叶斯算法对各节点负载状态进行分类;然后,根据节点状态分类结果,实现任务和资源分配的合理调度。实验结果表明,基于朴素贝叶斯算法的负载均衡技术能提高任务的分配效率,避免任务在各节点间频繁迁移,快速有效地实现云计算环境中各节点间的负载均衡。For the the heavy complexity of scheduling algorithm and the misallocation of assignment occurring in the cloud computing environment, a load balancing technology based on naive Bayes algorithm was proposed. This technology made use of the heartbeat mechanism to gather every node＇s load information comprehensively, so as to classify the load state of all nodes based on naive Bayes algorithm. Then, according to the classification, it achieved reasonable dispatch of the task and resource for each node. The results of the experiments show that, this load balancing technology improves the efficiency of the allocation of tasks and avoids the frequent migration between nodes, so that it can achieve the purpose of balancing the load rapidly and effectively.

关 键 词：云计算环境 负载均衡 朴素贝叶斯 负载信息 任务调度 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]