Automatic maintenance route planning of large-scale sensor networks

The growing market for wireless sensor networks causes challenges and opportunities for their maintenance in the future. In various applications, sensor networks spread out to wide areas, and therefore their maintenance is costly. This paper studies application of the quality assurance knowledge of observations for the sensor network maintenance. Firstly, quality assurance techniques determine whether observations are correct or suspicious. Secondly, specially designed performance indices are applied to describe the observation history. The key is to determine the accuracy of observations and if all of them are available in the database as they are supposed to. Thirdly, maintenance routes are determined based on performance indices. Since this route-planning problem is close to the travelling salesman problem, routes are solved using either heuristic or evolutionary computing methods using somewhat similar ideas. This paper demonstrates the approach using surface weather stations.