Time-Based Node Deployment Policies for Reliable Wireless Sensor Networks

Abstract

Wireless sensor networks (WSNs) are commonly used to monitor a remote environment over an extended period of time. One important design consideration is the WSN's reliability of area coverage, as sensors fail over time and functionality of the network degrades. When the WSN no longer sufficiently covers the region, maintenance actions may consider repairing failed nodes or deploying new sensors to re-establish network capability. Toward identifying an optimal maintenance policy, specifically the deployment of new sensors, in this article, we present an optimization model formulated using the network destruction spectrum (D-spectrum), which seeks to determine a time-based deployment policy balancing cost and reliability. While the benefits of using the D-spectrum in reliability are widely researched, the application of the D-spectrum to enable the modeling and solving of an optimization problem is new. With the complexity already present in estimating reliability, the significance of this optimization model is that it decouples the complexity of estimating the D-spectrum from the estimation of network reliability in the presence of a given deployment policy. This key feature allows us to quickly evaluate a wide range of time-based deployment policies. Additionally, we present an efficient destruction algorithm that performs a vital subroutine in estimating the D-spectrum, allowing for a large number of replications to be performed in the Monte Carlo simulation, thereby reducing the variance of the resulting reliability estimate. Finally, the optimization model is illustrated through a numerical example.