An Unsupervised Deep Unrolling Framework for Constrained Optimization Problems in Wireless Networks

TL;DR

This paper introduces an unsupervised deep unrolling framework, UPGDNet, for efficiently solving complex constrained optimization problems in wireless networks, combining neural networks with projection methods.

Contribution

It proposes a novel deep unrolling framework that handles different types of constraints in wireless optimization problems, reducing computational complexity and improving generalization.

Findings

USRMNet achieves performance comparable to traditional methods.

USRMNet demonstrates low computational complexity.

USRMNet generalizes well across different user distributions.

Abstract

In wireless network, the optimization problems generally have complex constraints, and are usually solved via utilizing the traditional optimization methods that have high computational complexity and need to be executed repeatedly with the change of network environments. In this paper, to overcome these shortcomings, an unsupervised deep unrolling framework based on projection gradient descent, i.e., unrolled PGD network (UPGDNet), is designed to solve a family of constrained optimization problems. The set of constraints is divided into two categories according to the coupling relations among optimization variables and the convexity of constraints. One category of constraints includes convex constraints with decoupling among optimization variables, and the other category of constraints includes non-convex or convex constraints with coupling among optimization variables. Then, the first category of constraints is directly projected onto the feasible region, while the second category of constraints is projected onto the feasible region using neural network. Finally, an unrolled sum rate maximization network (USRMNet) is designed based on UPGDNet to solve the weighted SR maximization problem for the multiuser ultra-reliable low latency communication system. Numerical results show that USRMNet has a comparable performance with low computational complexity and an acceptable generalization ability in terms of the user distribution.