Automated Service Composition and Routing in Networks with Data-Path Services

Advanced packet processing in the data path of networks is common in the current Internet and is expanding to next-generation networks. Dynamic composition of such "network services" allows networks to establish connections with customized communication characteristics to satisfy various application requirements. In these networks, there are two problems that need to be solved: finding the optimal composition of services to satisfy the communication requirements of a given connection ("service composition") and finding the optimal path for a given composition of services such that the required services are executed in sequence along the path ("service routing"). So far, these two problems have been studied separately. In our work, we combine both into a "service composition and routing" approach that can achieve better solutions than the current, separate approach. We present a novel decision making system that can determine the optimal or near-optimal solutions for the service composition and routing problem. We develop a synthetic benchmark for service requests to help comprehensively evaluate the performance of our systems. The results show that considering service composition and service routing jointly results in connections that have lower end-to-end delay while still meeting all service requirements.