Web service composition technique based on a service graph and particle swarm optimization

This paper presents a new technique for semantic Web service composition inspired by the swarm behavior. The proposed technique combines a service composition graph model with a hybrid particle swarm optimization algorithm to identify the optimal composition solution. The following criteria are considered to select the optimal composition solution: the QoS attributes of the services and the semantic quality of the connections between the services involved in a composition solution. The semantic quality is evaluated using a set of metrics which adapt the learning accuracy measure.