Reinforcement learning-based intelligent resource allocation for integrated VLCP systems

In this letter, an intelligent resource allocation framework based on model-free reinforcement learning (RL) is first presented for multi-user integrated visible light communication and positioning (VLCP) systems, in order to maximize the sum rate of users while guaranteeing the users' minimum...

Full description

Saved in:

Bibliographic Details
Main Authors:	Yang, Helin, Du, Pengfei, Zhong, Wen-De, Chen, Chen, Alphones, Arokiaswami, Zhang, Sheng
Other Authors:	School of Electrical and Electronic Engineering
Format:	Article
Language:	English
Published:	2020
Subjects:	Engineering::Electrical and electronic engineering Visible Light Communication and Positioning Intelligent Resource Allocation
Online Access:	https://hdl.handle.net/10356/142886
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Nanyang Technological University
Language:	English

id	sg-ntu-dr.10356-142886
record_format	dspace
spelling	sg-ntu-dr.10356-1428862020-07-07T04:34:40Z Reinforcement learning-based intelligent resource allocation for integrated VLCP systems Yang, Helin Du, Pengfei Zhong, Wen-De Chen, Chen Alphones, Arokiaswami Zhang, Sheng School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Visible Light Communication and Positioning Intelligent Resource Allocation In this letter, an intelligent resource allocation framework based on model-free reinforcement learning (RL) is first presented for multi-user integrated visible light communication and positioning (VLCP) systems, in order to maximize the sum rate of users while guaranteeing the users' minimum data rates and positioning accuracy constraints. The learning framework can learn the optimal policy under unknown environment's dynamics and the continuous-valued space, and a reward function is proposed to take into account the strict communication and positioning constraints. Moreover, a modified experience replay actor-critic (MERAC) RL approach is proposed to improve the learning efficiency and convergence speed, which efficiently collects the reliable experience and utilizes the most useful knowledge from the memory. Numerical results show that the MERAC approach can effectively learn to satisfy the strict constraints and achieve the fast convergence speed. NRF (Natl Research Foundation, S’pore) Accepted version 2020-07-07T03:20:17Z 2020-07-07T03:20:17Z 2019 Journal Article Yang, H., Du, P., Zhong, W.-D., Chen, C., Alphones, A., & Zhang, S. (2019). Reinforcement learning-based intelligent resource allocation for integrated VLCP systems. IEEE Wireless Communications Letters, 8(4), 1204-1207. doi:10.1109/lwc.2019.2911682 2162-2337 https://hdl.handle.net/10356/142886 10.1109/lwc.2019.2911682 4 8 1204 1207 en SMA-RP6 IEEE Wireless Communications Letters © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/lwc.2019.2911682 application/pdf
institution	Nanyang Technological University
building	NTU Library
country	Singapore
collection	DR-NTU
language	English
topic	Engineering::Electrical and electronic engineering Visible Light Communication and Positioning Intelligent Resource Allocation
spellingShingle	Engineering::Electrical and electronic engineering Visible Light Communication and Positioning Intelligent Resource Allocation Yang, Helin Du, Pengfei Zhong, Wen-De Chen, Chen Alphones, Arokiaswami Zhang, Sheng Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
description	In this letter, an intelligent resource allocation framework based on model-free reinforcement learning (RL) is first presented for multi-user integrated visible light communication and positioning (VLCP) systems, in order to maximize the sum rate of users while guaranteeing the users' minimum data rates and positioning accuracy constraints. The learning framework can learn the optimal policy under unknown environment's dynamics and the continuous-valued space, and a reward function is proposed to take into account the strict communication and positioning constraints. Moreover, a modified experience replay actor-critic (MERAC) RL approach is proposed to improve the learning efficiency and convergence speed, which efficiently collects the reliable experience and utilizes the most useful knowledge from the memory. Numerical results show that the MERAC approach can effectively learn to satisfy the strict constraints and achieve the fast convergence speed.
author2	School of Electrical and Electronic Engineering
author_facet	School of Electrical and Electronic Engineering Yang, Helin Du, Pengfei Zhong, Wen-De Chen, Chen Alphones, Arokiaswami Zhang, Sheng
format	Article
author	Yang, Helin Du, Pengfei Zhong, Wen-De Chen, Chen Alphones, Arokiaswami Zhang, Sheng
author_sort	Yang, Helin
title	Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
title_short	Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
title_full	Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
title_fullStr	Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
title_full_unstemmed	Reinforcement learning-based intelligent resource allocation for integrated VLCP systems
title_sort	reinforcement learning-based intelligent resource allocation for integrated vlcp systems
publishDate	2020
url	https://hdl.handle.net/10356/142886
_version_	1681058759069138944

Reinforcement learning-based intelligent resource allocation for integrated VLCP systems

Similar Items