Volume 9 - Issue 4
Supervised learning-based Lifetime Extension of Wireless Sensor Network Nodes
- Jaewoong Kang
Department of Industrial Enginnering, Sungkyunkwan University, Suwan, Korea
kjw1727@skku.edu
- Jongmo Kim
Department of Industrial Enginnering, Sungkyunkwan University, Suwan, Korea
dignityc@skku.edu
- Mye Sohn
Department of Industrial Enginnering, Sungkyunkwan University, Suwan, Korea
myesohn@skku.edu
Keywords: Sustainability, Wireless Sensor Network, Interval Determination, Machine Learning
Abstract
In this paper, we propose a new approach to increase the sustainability of the Wireless Sensor Network
(WSN) nodes by extending their lifetimes. To do so, we attempt to find the optimal values of
the collection interval and the transmission interval for each task that can maximize the lifetime of
the WSN nodes by applying machine learning techniques. As a preprocessing for finding the optimal
value of two parameters, we first determine the combination of nodes necessary to perform each
task using the wrapper method. In addition, we applied Simulated Annealing (SA) to find the values
of two parameter that lower power consumption without being significantly affected by the WSN’s
performance. To prove the superiority of the method, we perform two kinds of experiments. Finally,
we prove the reduction of energy consumption using our framework.