Learning to Branch: Accelerating Resource Allocation in Wireless Networks

Resource allocation in wireless networks, such as device-to-device (D2D) communications, is usually formulated as mixed integer nonlinear programming (MINLP) problems, which are generally NP-hard and difficult to get the optimal solutions. Traditional methods to solve these MINLP problems are all ba...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on vehicular technology Vol. 69; no. 1; pp. 958 - 970
Main Authors: Lee, Mengyuan, Yu, Guanding, Li, Geoffrey Ye
Format: Journal Article
Language:English
Published: New York IEEE 01.01.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Acceleration
Algorithms
Artificial neural networks
branch-and-bound algorithm
Complexity
Computational complexity
Computer simulation
Copper
device-to-device communicati-ons
Device-to-device communication
Dynamic control
imitation learning
Machine learning
Mixed integer
mixed integer nonlinear programming
Nonlinear programming
Optimization
Optimization techniques
Resource allocation
Resource management
Training
Wireless communications
Wireless networks
ISSN:0018-9545, 1939-9359
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Resource allocation in wireless networks, such as device-to-device (D2D) communications, is usually formulated as mixed integer nonlinear programming (MINLP) problems, which are generally NP-hard and difficult to get the optimal solutions. Traditional methods to solve these MINLP problems are all based on mathematical optimization techniques, such as the branch-and-bound (B&B) algorithm that converges slowly and has forbidding complexity for real-time implementation. Therefore, machine leaning (ML) has been used recently to address the MINLP problems in wireless communications. In this paper, we use imitation learning method to accelerate the B&B algorithm. With invariant problem-independent features and appropriate problem-dependent feature selection for D2D communications, a good auxiliary prune policy can be learned in a supervised manner to speed up the most time-consuming branch process of the B&B algorithm. Moreover, we develop a mixed training strategy to further reinforce the generalization ability and a deep neural network (DNN) with a novel loss function to achieve better dynamic control over optimality and computational complexity. Extensive simulation demonstrates that the proposed method can achieve good optimality and reduce computational complexity simultaneously.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0018-9545
1939-9359
DOI:10.1109/TVT.2019.2953724