Exploring self-star properties in cognitive sensor networking

Wireless sensor networks (WSNs) possess inherent tradeoffs among conflicting operational objectives such as data yield, data fidelity and power consumption. In order to address this challenge, this paper proposes a biologically-inspired framework to build cognitive WSN applications, which introspectively understand their conflicting objectives, find optimal tradeoffs with given constraints and autonomously adapt to dynamics of the network. The proposed framework, MONSOON, models an application as a decentralized group of software agents. This is analogous to a bee colony (application) consisting of bees (agents). Agents collect sensor data on individual nodes and carry the data to base stations. They perform this data collection functionality by autonomously sensing their local and surrounding network conditions and adaptively invoking biological behaviors such as pheromone emission, reproduction and migration. Each agent has its own behavior policy, as a gene, which defines how to invoke its behaviors. MONSOON allows agents to evolve their behavior policies via genetic operations such as crossover and mutation. Simulation results show that agents (WSN applications) exhibit the properties of self-configuration, self-optimization and self-healing and adapt to various dynamics of the network (e.g., node/link failures) by satisfying conflicting objectives under given constraints.