关键词: 面向服务架构, 服务查找, 分布性, 负载均衡, 系统吞吐率

Abstract: Service discovery is a very important part in Service-Oriented Architecture (SOA). However, current service discovery algorithms do not take account of the load balancing of the service discovery nodes, so they can not meet the requirements of search efficiency in frequent requests. To solve this problem, a distributed request routing algorithm for service discovery named HaFA, considering the node capacity and network latency, was proposed for a distributed service registry center in SOA. This algorithm measured the node's computation power using the load on the node to solve the problem that the tasks may still be assigned to the node which has weak capacity after balancing of the load degree, and can improve the utilization of computation resources in the service registry center. It used the load fluctuation rate of the node to estimate the load degree of the next discrete-time point to solve the problem that the load fluctuation during the network delay has impact on the load balancing. The experimental results show that HaFA algorithm can effectively improve the system throughput in distributed service discovery and shorten the average waiting time for response.

Key words: SOA, Service Discovery, Distribution, Load Balancing, System Throughput