# A Learning Approach for Low-Complexity Optimization of Energy Efficiency in Multi-Carrier Wireless Networks

## TL;DR

This paper introduces a low-complexity, learning-based algorithm for optimizing energy efficiency in multi-carrier wireless networks, effectively balancing power and subcarrier allocation under constraints.

## Contribution

It presents a novel, computationally efficient framework combining fractional programming, learning, and game theory for energy-efficient resource allocation.

## Key findings

- Algorithm has linear complexity in users and subcarriers
- Performs comparably to more complex algorithms
- Provably convergent method

## Abstract

This paper proposes computationally efficient algorithms to maximize the energy efficiency in multi-carrier wireless interference networks, by a suitable allocation of the system radio resources, namely the transmit powers and subcarrier assignment. The problem is formulated as the maximization of the system Global Energy-Efficiency subject to both maximum power and minimum rate constraints. This leads to a challenging non-convex fractional problem, which is tackled through an interplay of fractional programming, learning, and game theory. The proposed algorithmic framework is provably convergent and has a complexity linear in both the number of users and subcarriers, whereas other available solutions can only guarantee a polynomial complexity in the number of users and subcarriers. Numerical results show that the proposed method performs similarly as other, more complex, algorithms.