Sensor Topology Optimization in Dense IoT Environments by Applying Neural Network Configuration

In dense IoT deployments of wireless sensor networks (WSNs), sensor placement, coverage, connectivity, and energy constraints determine the overall network lifetime. In large-size WSNs, it is difficult to maintain a trade-off among these conflicting constraints and, thus, scaling is difficult. In the related research literature, various solutions are proposed that attempt to address near-optimal behavior in polynomial time, the majority of which relies on heuristics. In this paper, we formulate a topology control and lifetime extension problem regarding sensor placement, under coverage and energy constraints, and solve it by applying and testing several neural network configurations. To do so, the neural network dynamically proposes and handles sensor placement coordinates in a 2D plane, having the ultimate goal to extend network lifetime. Simulation results show that our proposed algorithm improves network lifetime, while maintaining communication and energy constraints, for medium- and large-scale deployments.