一种面向多类型服务的动态负载均衡算法

A dynamic load balancing algorithm for multi-type services

针对航空物流ILink数据平台交易复杂性高、服务种类多、业务规模大等特点,提出一种面向多类型服务的动态负载均衡算法。通过分析四种基本服务类型以及实时采集四种服务类型的资源消耗,根据用户服务请求类型的不同动态调整各服务器的负载,引入了过载服务器节点缓冲机制缓冲负载过重节点,有效解决了航空物流ILink数据平台可能出现的用户等待时间过长、局部负载过重、甚至个别服务器节点崩溃的问题,达到了集群的负载均衡。仿真实验结果表明,提出的算法在系统吞吐量、系统响应时间、负载率等关键指标上优于经典的比率算法和遗传算法。

A dynamic load balancing algorithm for multi?type services is proposed to suit aviation logistics ILink data platform to complex transaction,multi?type service and large?scale business.The four fundamental service types were analyzed and resource consumption of the four service types was acquired in real time.The algorithm can update the load balance weight of every service according to the types of users′service requests.A node buffer mechanism for overload servers was imported to solve the problems of long time waiting of users,over?heavy local load and even the breakdown of individual server node possibly appearing on the aviation logistics ILink data platform,so as to achieve the load balancing.The simulation results show that the algorithm is superior to the classic ratio algorithm and genetic algorithm in system throughout,responding time and load efficiency.