RF energy modelling using machine learning for energy harvesting communications systems. (24th November 2020)

• Record Type: Journal Article
• Authors: Ye, Youjie; Azmat, Freeha; Adenopo, Idris; Chen, Yunfei; Shi, Rui
• Is Part Of: International journal of communication systems. Volume 34:Number 3(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2020-11-24
• Subjects: energy harvesting -- machine learning -- modelling -- prediction algorithms -- radio frequency; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.4688
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: Machine learning (ML) theories and methods are mainly based on probability theory and statistics. It is a very powerful tool for data modelling. On the other hand, energy harvesting has been regarded as a viable solution to extending battery lifetime of wireless sensor network. Motivated by these, modelling of the radio frequency (RF) energy available to the wireless nodes is required for efficient operation of wireless networks. In this work, we will use different ML algorithms to model the RF energy data for efficient operation of energy harvesting communication systems. Four ML algorithms are studied and compared in terms of the accuracy for RF energy modelling using the energy data in the band between 1805 and 1880 MHz. The results show that linear regression (LR) has the highest accuracy and the most stable performance, while decision tree is the worst model. Also, in terms of the operation efficiency of the system, LR has the best performance, followed by support vector machine and random forest algorithm. Abstract : In this article, four different ML algorithms are compared in terms of the accuracy for RF energy modelling using the energy data for efficient operation of energy harvesting communication systems. The results show that, linear regression(LR) has the highest accuracy and the most stable performance, while decision tree is the worst model. Also, in terms of the operation efficiency of the system, LR has the best performance, followed by support vector machine and random forest algorithm.