A Machine Learning Assisted Method for Coverage Optimization in a Network of Mobile Sensors

In this work, efficient algorithms are developed to increase the area covered by a network of mobile sensors. The sensors are divided into k sets, and then the proposed algorithms perform iteratively to increase the area covered by at least k sensors as much as possible. Since the performance of the algorithms highly depends on the initial positions of sensors, we use the K-means clustering technique for partitioning the sensors into k sets. Simulation results confirm the effectiveness of the proposed algorithms. They also show that using the K-means clustering technique improves the performance of the algorithms in terms of energy consumption, covered area, and convergence time.