An Agent-based Integrated Self-evolving Service Composition Approach in Networked Environments

Service composition is an important research problem in service computing systems, which combines simple and individual services into composite services to fulfill users’ complex requirements. Service composition usually consists of four stages, i.e., service discovery, candidate selection, service negotiation and task execution. In self-organising systems, there is the fifth stage of service composition: self-evolution. Most of existing works study only some of the five stages. However, these five stages should be systematically studied so as to develop an integrated and efficient service composition approach. Against this background, this paper proposes an agent-based integrated self-evolving service composition approach. This approach systematically takes the five stages of service composition into consideration. It is also decentralised and self-evolvable. Experimental results demonstrate that the proposed approach can achieve almost the same success rates while uses much less communication overhead and time consumption in comparison with three existing representative approaches.