A Survey on Energy-Efficient Routing in Wireless Sensor Networks Using Machine Learning Algorithms

Abstract

Wireless sensor network (WSN) consists of sparsely distributed, low energy, and bandwidth sensor nodes that collect sensed data. In WSNs, these data are initially converted from analog to digital signals and transmitted to base stations. Routing in WSNs is the process of determining the most efficient path for data transmission among various sensor nodes. In routing, small sensor nodes use limited network bandwidth and energy to capture and transmit a limited amount of data. However, with the advancement of big data and IoT, large-scale sensors are used to route massive amounts of data. Routing with this huge data consumes a lot of network bandwidth and energy and thus reduces the lifespan of the network. Thus, for energy-efficient routing (EER), there is a need for data optimization that can be achieved by many machine learning (ML) algorithms. Many researchers have devised various noteworthy works related to ML to have an EER in WSNs. This chapter reviews the existing ML-based routing algorithms in WSNs.