Multicell Power Control under Rate Constraints with Deep Learning

TL;DR

This paper introduces a deep learning approach with a projection layer for multicell power control, ensuring rate constraints are met efficiently for real-time sum rate maximization.

Contribution

It proposes a novel cascade DNN with a geometrically inspired projection block, enabling constraint satisfaction and direct sum rate maximization through unsupervised learning.

Findings

Outperforms existing deep learning and optimization methods in simulations.

Ensures per-user rate constraints are satisfied in power control.

Demonstrates robustness to model mismatch between training and testing.

Abstract

In the paper we study a deep learning based method to solve the multicell power control problem for sum rate maximization subject to per-user rate constraints and per-base station (BS) power constraints. The core difficulty of this problem is how to ensure that the learned power control results by the deep neural network (DNN) satisfy the per-user rate constraints. To tackle the difficulty, we propose to cascade a projection block after a traditional DNN, which projects the infeasible power control results onto the constraint set. The projection block is designed based on a geometrical interpretation of the constraints, which is of low complexity, meeting the real-time requirement of online applications. Explicit-form expression of the backpropagated gradient is derived for the proposed projection block, with which the DNN can be trained to directly maximize the sum rate via unsupervised learning. We also develop a heuristic implementation of the projection block to reduce the size of DNN. Simulation results demonstrate the advantages of the proposed method over existing deep learning and numerical optimization~methods, and show the robustness of the proposed method with the model mismatch between training and testing~datasets.