An Event Prediction-based IP Multimedia Subsystem Service Exposure

Exposure of relevant services aligned with user's needs is nowadays not only a guarantee of the latter's satisfaction but above all, a way for service providers to stand apart from competitors. In this context, the IP Multimedia Subsystem (IMS), which is an implementation of the Next Generation Network (NGN) concept, aims to provide a seamless access to a rich and varied range of services regardless the access technology employed by the service requestor. Moreover, the multitude of existing services makes service exposure a challenging exercise. To meet this challenge, in this paper we propose a service exposure approach based on event prediction. Our approach is proactive and based on an online service recommendation implicitly initiated by the service requestor. Our work is compared to the classic service exposure approach and to the predictive collaborative service exposure approach we proposed in our previous work. The obtained results illustrate the good performance of our approach in terms of response time, CPU utilization, memory use; but poorer performance in terms of service targeting accuracy compared to the aforementioned approaches.