Learning Non-myopic Power Allocation in Constrained Scenarios

TL;DR

This paper introduces a learning-based approach for non-myopic power allocation in wireless networks, optimizing long-term utility under constraints using an actor-critic method, outperforming previous myopic algorithms.

Contribution

It formulates the power allocation as a constrained sequential decision problem and applies an actor-critic algorithm to achieve better long-term utility while respecting constraints.

Findings

Superior episodic network utility performance

Efficient in time and computational complexity

Effective constraint-aware power regulation

Abstract

We propose a learning-based framework for efficient power allocation in ad hoc interference networks under episodic constraints. The problem of optimal power allocation -- for maximizing a given network utility metric -- under instantaneous constraints has recently gained significant popularity. Several learnable algorithms have been proposed to obtain fast, effective, and near-optimal performance. However, a more realistic scenario arises when the utility metric has to be optimized for an entire episode under time-coupled constraints. In this case, the instantaneous power needs to be regulated so that the given utility can be optimized over an entire sequence of wireless network realizations while satisfying the constraint at all times. Solving each instance independently will be myopic as the long-term constraint cannot modulate such a solution. Instead, we frame this as a constrained and sequential decision-making problem, and employ an actor-critic algorithm to obtain the constraint-aware power allocation at each step. We present experimental analyses to illustrate the effectiveness of our method in terms of superior episodic network-utility performance and its efficiency in terms of time and computational complexity.