Determination of mobile sink path in wireless sensor networks using learning techniques

Abstract

This paper describes the network data transmission path finding techniques with mobile sink in wireless sensor networks. It also explores the ways to minimize energy consumption with sink due to communication with other sensor nodes. Congestion prevails in the Sensor nodes near to sink due to enormous data transfers from neighboring sensor nodes. Due to the heavy forwarding of data packets may led to a hotspot problem. By using mobile sink, it assimilates data by moving within the sensing region and balance the load of traffic to all sensor nodes in the network. To recede the delay due to the visit of more number of sensor nodes, some sensor nodes are considered as rendezvous points (RPs) and Mobile sink visits these points only. Source nodes forward their data to adjacent RPs. But it is more difficult to find the finest set of RPs and travelling path of mobile sink. This paper showcases the attempt to explore the ways to discover RPs and getting optimization in network data communication of sensor nodes through mobile sink. Social algorithms and Machine Learning techniques are the highly established efficient approaches to solve many complex optimization problems. The aim of this survey is to present a comprehensive study of applying Social algorithms in selecting finest set of RPs, to mitigate the challenges in Mobile sink path determination to extend network lifetime and exploring Machine Learning towards the energy conservation in WSN.