Centralized & Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization

TL;DR

This paper introduces centralized and distributed deep reinforcement learning methods for optimizing downlink sum-rate in multi-cell networks, achieving higher efficiency and faster execution than traditional algorithms.

Contribution

It presents novel trust region-based DRL algorithms for multi-agent and single-agent settings, improving convergence and enabling distributed optimization with limited CSI.

Findings

Higher spectral efficiency than WMMSE and FP algorithms

Execution times over 100 times faster than traditional methods

Decentralized DRL approaches with limited CSI perform competitively

Abstract

For a multi-cell, multi-user, cellular network downlink sum-rate maximization through power allocation is a nonconvex and NP-hard optimization problem. In this paper, we present an effective approach to solving this problem through single- and multi-agent actor-critic deep reinforcement learning (DRL). Specifically, we use finite-horizon trust region optimization. Through extensive simulations, we show that we can simultaneously achieve higher spectral efficiency than state-of-the-art optimization algorithms like weighted minimum mean-squared error (WMMSE) and fractional programming (FP), while offering execution times more than two orders of magnitude faster than these approaches. Additionally, the proposed trust region methods demonstrate superior performance and convergence properties than the Advantage Actor-Critic (A2C) DRL algorithm. In contrast to prior approaches, the proposed decentralized DRL approaches allow for distributed optimization with limited CSI and controllable information exchange between BSs while offering competitive performance and reduced training times.