Routing in wireless sensor networks using machine learning techniques: Challenges and opportunities

Energy conservation is the primary task in Wireless Sensor Networks (WSNs) as these tiny sensor nodes are the backbone of today's Internet of Things (IoT) applications. These nodes rely exclusively on battery power to maneuver in hazardous environments. So, there is a requirement to study and design efficient, robust communication protocols to handle the challenges of the WSNs to make the network operational for a long time. Although traditional technologies solve many issues in WSNs, it may not derive an accurate mathematical model for predicting system behavior. So, some challenging tasks like routing, data fusion, localization, and object tracking are handled by low complexity mathematical models to define system behavior. In this paper, an effort has been made to provide a big outlook to the current "researchers" on machine learning techniques that have been employed to handle various issues in WSNs, and special attention has been given to routing problems.