Differential Evolution-Based Sensor Allocation for Target Tracking Application in Sensor-Cloud

摘要

In a sensor-cloud system, an optimal set of sensor nodes are generally allocated to complete the subsequent target tracking task. In this kind of system, allocation of an optimal number of sensor nodes for target tracking application is a NP-hard problem. In this paper, a meta-heuristic optimization-based scheme is used, called differential evolution-based sensor allocation scheme (DESA) for allocation of optimal sensor nodes to attain efficient target tracking. DESA uses a novel fitness function which comprises three parameters such as dwelling time, detection probability of the sensor node, and competency of the sensor. Simulation results show that proposed scheme allocates approximately 40-48% less number of sensor nodes for covering the target for its efficient tracking.