实时多任务异构云计算平台负载均衡算法

Real-time multitask load balance algorithm for heterogeneous cloud computing platforms

针对组成云计算平台各节点之间软件环境存在异构性及数据分布不均匀等原因而导致云计算平台在处理大量任务时往往出现节点负载不均衡的问题,提出了解决异构云计算平台负载均衡方法与相关算法.研究首先统计云计算平台提供的各类服务的平均资源消耗,结合任务分配给指定节点后运行时长和资源占用情况,预测评估某一时刻节点上任务剩余资源消耗需求总量既剩余负载总量;各节点按周期反馈实际任务负载情况,及时修正任务负载信息;最后综合考虑节点各项性能,预测各节点负载评估值,并将待分配任务分发给最适合的节点.实验结果表明,该算法具有可行性并在实时多任务异构云计算平台负载均衡方面具有一定优势.

A load-balancing algorithm applying in heterogeneous cloud Computing Platform handling real-time multitasks was proposed. Average hardware resource consumption of jobs running on nodes was measured.Balancing server receive load status of each node in the cluster periodically. A load status vector that reflects the quantity of resources required to finish allocated jobs of each node can be estimated according to the latest load status report and other parameters. As a request is submitted to the cluster,Balancing Server calculates the load status estimation vector of each node,and then dispatches it to the node that possesses the minimal load status estimation value. Experiment results proved that this dynamic load balancing algorithm is reasonable and effective.