Sustainable green networking: exploiting degrees of freedom towards energy-efficient 5G systems

摘要

The carbon footprint concern in the development and deployment of 5G new radio systems has drawn the attention to several stakeholders. In this article, we analyze the critical power consuming component of all candidate 5G system architecturesthe power amplifier (PA)and propose PA-centric resource management solutions for green 5G communications. We discuss the impact of ongoing trends in cellular communications on sustainable green networking and analyze two communications architectures that allow exploiting the extra degrees-of-freedom from multi-antenna and massive antenna deployments: small cells/distributed antenna network and massive MIMO. For small cell systems with a moderate number of antennas, we propose a peak to average power ratio-aware resource allocation scheme for joint orthogonal frequency and space division multiple access. For massive MIMO systems, we develop a highly parallel recurrent neural network for energy-efficient precoding. Simulation results for representative 5G deployment scenarios demonstrate an energy efficiency improvement of one order of magnitude or higher with respect to current state-of-the-art solutions.