Skip to main content

A Machine Learning Framework for Resource Allocation Assisted by Cloud Computing

Wang, Jun-Bo, Wang, Junyuan, Wu, Yongpeng, Wang, Jin-Yuan, Zhu, Huiling, Lin, Min, Wang, Jiangzhou (2018) A Machine Learning Framework for Resource Allocation Assisted by Cloud Computing. IEEE Network, 32 (2). pp. 144-151. ISSN 0890-8044. (doi:10.1109/MNET.2018.1700293) (KAR id:67037)

PDF Author's Accepted Manuscript
Language: English
Download (548kB) Preview
[thumbnail of Proof.pdf]
Preview
This file may not be suitable for users of assistive technology.
Request an accessible format
Official URL
https://doi.org/10.1109/MNET.2018.1700293

Abstract

Conventionally, the resource allocation is formulated as an optimization problem and solved online with

are very difficult to be obtained in real time. Lagrangian relaxation or greedy methods are then often employed,

challenges to meet the ever-increasing QoS requirements of users with scarce radio resource. Assisted by cloud

using machine learning. Moreover, optimal or near-optimal solutions of historical scenarios can be searched offline

historical scenarios to find the most similar one. Then, the optimal or near-optimal solution in the most similar

of new design philosophy, a machine learning framework is proposed for resource allocation assisted by cloud

shows that the proposed machine-learning based resource allocation outperforms conventional methods.

Item Type: Article
DOI/Identification number: 10.1109/MNET.2018.1700293
Uncontrolled keywords: Resource allocation, machine learning, cloud computing, k-nearest neighbour (k-NN), beam allocation algorithm, massive MIMO
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Engineering and Digital Arts
Depositing User: Jiangzhou Wang
Date Deposited: 15 May 2018 14:38 UTC
Last Modified: 16 Feb 2021 13:54 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/67037 (The current URI for this page, for reference purposes)
Wang, Jiangzhou: https://orcid.org/0000-0003-0881-3594
  • Depositors only (login required):

Downloads

Downloads per month over past year