Skip to Main Content
QoS-aware Web service composition intends to maximize the global QoS of a composite service with local and global QoS constraints while selecting the independent candidate services from different providers. With the increasing number of candidate services emerging from the Internet, the network delays often greatly affect the performance of the composite service, which are usually difficult to be collected beforehand. One remedy is to predict them for the composition. However, there are some new issues in network delay predictions for the composition, including prediction accuracy, on-demand measures to new services and runtime overhead. In this paper, we try to tackle these critical challenges by taking advantage of the geolocations of candidate services. We firstly describe a network-aware service composition problem. Then, we present a novel geolocation-based NQoS prediction and reprediction approach for service composition. Furthermore, a geolocation-based service selection algorithm is presented to make use of our NQoS prediction approach for the composition. We have conducted extensive experiments on the real-world dataset collected from PlanetLab. Comparative experimental results demonstrate that our approach improves the prediction accuracy and predictability of the NQoS and reduces the runtime overheads in predicting the composition.