Cognitive approaches in Wireless Sensor Networks: A survey

Wireless Sensor Networks are believed to be the enabling technology for Ambient Intelligence. They hold the promise of delivering to a smart communication paradigm where applications evolve from user requirements. Cognitive agents capable of making proactive decisions based on learning, reasoning and information sharing when interspersed in sensor networks may help achieve end-to-end goals of the network, even in the presence of multiple constraints and optimization objectives. Cognitive radio at the physical layer of such agents might be able to enable the opportunistic use of the heterogeneous environment in which the sensor network is deployed. A framework used in Cognitive Networks that can be applied to application-specific sensor networks is discussed. The main contribution of this paper is providing a comparative study of the different cognitive techniques applied to sensor network applications in recent times, (including one by the authors) and evaluating their effectiveness in achieving the network's end-to-end goals.