IoT aware Energy Indexed Theil-Sen Linear Regressive Time instantaneous Data Transmission in WSN

Abstract

Wireless Sensor Network is self-organizing multi-hop sensor nodes that communicate with each other through wireless communication. The sensor node monitors the environmental conditions and collects the data transmitting and receiving the data from/to several nodes.  During the data transmission, energy is the most important parameter to enhance the overall network lifespan. In general, the sensor nodes have low energy but big data transmission causes a major problem in WSN.

A novel machine learning technique called IoT aware Energy Indexed Theil-Sen Linear Regressive Time Instantaneous Data transmission (IoT-ETLR) is introduced to improve the network lifetime in WSN. Theil-Sen Linear Regression Analysis is carried out in IoT-ETLR to analyze the residual energy of the sensor nodes based on Camargo's index. Theil-Sen regression analysis is a machine learning method used for estimating the relationship between one or more variables. The regression analysis is linear regression that identifies the higher energy-efficient sensor nodes. After that, the route path discovery between the source and sink node via neighboring higher energy sensor nodes is based on the Time difference of the arrival method. Finally, the route path gets constructed and data transmission is carried out in efficient manner. Experimental evaluation is carried out on factors such as energy consumption, packet delivery ratio, packet loss rate, end to end delay with respect to the different number of sensor nodes and data packets. The observed results indicate that our proposed IoT-ETLR technique provides a better results in energy-aware data transmission with a higher delivery ratio and lesser delay than the state-of-the-art works.