Energy Sustainable Mobile Networks via Energy Routing, Learning and Foresighted Optimization

TL;DR

This paper proposes a novel framework for energy self-sustainable mobile networks using energy routing, Gaussian Process-based forecasting, and model predictive control to optimize energy transfer and consumption, significantly reducing grid energy use.

Contribution

It introduces an integrated optimization approach combining energy routing, forecasting, and foresighted control for sustainable base station operation.

Findings

Substantial energy self-sustainability improvements

Near-zero outage probability in most cases

More than 50% reduction in grid energy purchase

Abstract

The design of self-sustainable base station (BS) deployments is addressed in this paper: BSs have energy harvesting and storage capabilities, they can use ambient energy to serve the local traffic or store it for later use. A dedicated power packet grid allows energy transfer across BSs, compensating for imbalance in the harvested energy or in the traffic load. Some BSs are offgrid, i.e., they can only use the locally harvested energy and that transferred from other BSs, whereas others are ongrid, i.e., they can also purchase energy from the power grid. Within this setup, an optimization problem is formulated where: energy harvested and traffic processes are estimated at the BSs through Gaussian Processes (GPs), and a Model Predictive Control (MPC) framework is devised for the computation of energy allocation and transfer schedules. Numerical results, obtained using real energy harvesting and traffic profiles, show substantial improvements in terms of energy self-sustainability of the system, outage probability (zero in most cases), and in the amount of energy purchased from the power grid, which is of more than halved with respect to the case where the optimization does not consider GP forecasting and MPC.