Identifying power consumption signatures in LTE conformance tests using machine learning

Considering that recent mobile smartphones are energy-hungry battery-powered devices and radio frequency (RF) conformance tests are currently executed with no current drain measurements, the objective of this paper is to propose a machine learning approach to identify power consumption signatures (PCSs) of smartphones under Long Term Evolution (LTE) user equipment RF conformance tests. Experimental results show that the proposed methodology can be used to build an operating history with PCSs for potential use cases.