Published on Fri Mar 26 2021

Deep Unsupervised Learning for Generalized Assignment Problems: A Case-Study of User-Association in Wireless Networks

Arjun Kaushik, Mehrazin Alizadeh, Omer Waqar, Hina Tabassum
0
0
0
Abstract

There exists many resource allocation problems in the field of wireless communications which can be formulated as the generalized assignment problems (GAP). GAP is a generic form of linear sum assignment problem (LSAP) and is more challenging to solve owing to the presence of both equality and inequality constraints. We propose a novel deep unsupervised learning (DUL) approach to solve GAP in a time-efficient manner. More specifically, we propose a new approach that facilitates to train a deep neural network (DNN) using a customized loss function. This customized loss function constitutes the objective function and penalty terms corresponding to both equality and inequality constraints. Furthermore, we propose to employ a Softmax activation function at the output of DNN along with tensor splitting which simplifies the customized loss function and guarantees to meet the equality constraint. As a case-study, we consider a typical user-association problem in a wireless network, formulate it as GAP, and consequently solve it using our proposed DUL approach. Numerical results demonstrate that the proposed DUL approach provides near-optimal results with significantly lower time-complexity.

Mon Mar 29 2021
Artificial Intelligence
Joint User Association and Power Allocation in Heterogeneous Ultra Dense Network via Semi-Supervised Representation Learning
0
0
0
Tue Dec 18 2018
Machine Learning
LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
Machine learning-based methods have emerged as a disruptive way to obtain near-optimal performance for MINLPs with affordable computational complexity. LORM learns the optimal pruning policy in the branch-and-bound algorithm via a sample-efficient method, namely, imitation learning.
0
0
0
Fri Nov 27 2020
Machine Learning
Deep Reinforcement Learning for Wireless Scheduling with Multiclass Services
Service providers have to schedule traffic destined to users with different classes of requirements and to allocate bandwidth resources over time. This is a highly intricate problem, in particular in wireless communication systems. We propose a deep deterministic policy gradient algorithm.
0
0
0
Tue Mar 03 2020
Machine Learning
Accelerating Generalized Benders Decomposition for Wireless Resource Allocation
Generalized Benders decomposition (GBD) is a globally optimal algorithm for mixed integer nonlinear programming (MINLP) problems. GBD decomposes an MINLP problem into a primal problem and a master problem. The main bottleneck is the high complexity of the master problem, which increases
0
0
0
Sat Oct 12 2019
Machine Learning
Generative Neural Network based Spectrum Sharing using Linear Sum Assignment Problems
Spectrum management and resource allocation (RA) problems are challenging and critical in a vast number of research areas. Traditional approaches for solving such problems usually consume time and memory. Recently different machine learning approaches have been considered as potential promising techniques for combinatorial optimization problems.
0
0
0
Wed Apr 15 2020
Machine Learning
Joint User Pairing and Association for Multicell NOMA: A Pointer Network-based Approach
In this paper, we investigate the joint user pairing and association problem for multicell non-orthogonal multiple access (NOMA) systems. The solution is found using an emerging deep learning architecture. The training phase of the PtrNet is based on deep reinforcement learning.
0
0
0