A Multi-objective Optimization Approach for Data Fusion in Mobile Agent Based Distributed Sensor Networks

A recent approach for data fusion in wireless sensor networks involves the use of mobile agents that selectively visit the sensors and incrementally fuse the data, thereby eliminating the unnecessary transmission of irrelevant or non-critical data. The order of sensors visited along the route determines the quality of the fused data and the communication cost. The computation of mobile agent routes involves tradeoffs between energy consumption, path loss, and detection accuracy. For instance, as the number of sensors in the route increases, the quality of fused data improves but the energy consumption and path loss increase. This paper models the mobile agent routing problem as a multi-objective optimization problem, maximizing the total detected signal energy while minimizing the energy consumption and path loss. A recently developed multi-objective evolutionary algorithm called the evolutionary multi-objective crowding algorithm (EMOCA) is employed for obtaining the mobile agent routes. The performance of EMOCA is compared with a recently proposed combinatorial optimization approach. Simulation results show that EMOCA outperforms the combinatorial optimization approach for different network sizes clearly demonstrating the advantage of a multi-objective optimization approach.