An Efficient QoS Preference Oriented Recommendation Scheme for the Internet of Services

Internet of services provides the services capabilities to interact and collaborate. Users are able to create, share and access services by means of heterogeneous devices and interaction channels, in extremely personalized ways. However, in the dynamic and ever-growing scenario, lacks of customization and flexibility have become more and more crucial. In this paper, a QoS preference oriented service recommendation scheme is proposed. First, the customer's preference is well described by a matrix model, which can be updated dynamically with customer's feedback evaluation. Entropy evaluation method is introduced to measure the weight coefficient of each QoS attribute. Furthermore, ant colony optimization algorithm is used to seek optimal service compositions. This recommending procedure will be repeated until the customer's requirement is satisfied, also can be restarted whenever the service process is blocked in execution. Theoretical analysis and numerical simulation indicate that the proposed scheme can satisfy the customer's requirements effectively and flexibly.