Approaching Globally Optimal Energy Efficiency in Interference Networks via Machine Learning

TL;DR

This paper introduces a machine learning framework with a specialized neural network architecture to efficiently approximate the globally optimal energy efficiency in multi-cell wireless networks, balancing performance and computational complexity.

Contribution

It proposes a novel permutation-equivariant neural network and an objective function for non-convex optimization, enabling near-optimal energy efficiency with low computational cost.

Findings

Achieves energy efficiency close to global optimum

Requires significantly less computation than traditional methods

Demonstrates effectiveness on multi-cell network scenarios

Abstract

This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple but suboptimal approaches or optimal methods with high complexity and poor scalability are proposed. In contrast, we propose a machine learning framework to approach the global optimum. While the neural network (NN) training takes moderate time, application with the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on stochastic actions to solve the non-convex optimization problem. Besides, we design a dedicated NN architecture for the multi-cell network optimization problems that is permutation-equivariant. It classifies channels according to their roles in the EE computation. In this way, we encode our domain knowledge into the NN design and shed light into the black box of machine learning. Training and testing results show that the proposed method without supervision and with reasonable computational effort achieves an EE close to the global optimum found by the branch-and-bound algorithm. Hence, the proposed approach balances between computational complexity and performance.