Energy efficient service embedding in IoT networks

The Internet of Things (IoT) is anticipated to participate in performing diverse and complex tasks in the near future. IoT objects capable of handling multiple sensing and actuating functions will be the corner stone of future IoT systems in smart cities. In this paper, we present an energy efficient service embedding framework in IoT network by using mixed integer linear programming (MILP). This framework addresses a set of metrics such as scalability, flexible resource allocation, cost reduction, and efficient use of resources. We consider the event-driven paradigm of Service Oriented Architecture (SOA) in our framework in order to provide service abstraction of basic services which can be composed into complex services and exploited by the upper application layer. The results show that our optimized network can save an average of 27% and 36% of the processing and network power consumption, respectively, compared to an energy unaware service embedding scheme.