Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning

The reduction of maintenance costs in agricultural wireless sensor networks (WSNs) requires reducing energy consumption. At the same time, care should be taken not to affect communication quality and network lifetime. This paper studies a joint optimization algorithm for transmitted power and channe...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xiao Han, Huarui Wu, Huaji Zhu, Cheng Chen
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/8e3b6abacdcb482aa59f16f05f6ccd0f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8e3b6abacdcb482aa59f16f05f6ccd0f
record_format dspace
spelling oai:doaj.org-article:8e3b6abacdcb482aa59f16f05f6ccd0f2021-11-25T18:50:26ZJoint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning10.3390/pr91119192227-9717https://doaj.org/article/8e3b6abacdcb482aa59f16f05f6ccd0f2021-10-01T00:00:00Zhttps://www.mdpi.com/2227-9717/9/11/1919https://doaj.org/toc/2227-9717The reduction of maintenance costs in agricultural wireless sensor networks (WSNs) requires reducing energy consumption. At the same time, care should be taken not to affect communication quality and network lifetime. This paper studies a joint optimization algorithm for transmitted power and channel allocation based on deep reinforcement learning. First, an optimization model to measure network reward was established under the constraint of the signal-to-interference plus-noise-ratio (SINR) threshold, which includes continuous power variables and discrete channel variables. Secondly, considering the dynamic changes of agricultural WSNs, the network control is described as a Markov decision process with continuous state and action space. A deep deterministic policy gradient (DDPG) reinforcement learning scheme suitable for mixed variables was designed. This method could obtain a control scheme that maximizes network reward by means of black-box optimization for continuous transmitted power and discrete channel allocation. Experimental results indicated that the studied algorithm has stable convergence. Compared with traditional protocols, it can better control the transmitted power and allocate channels. The joint power and channel optimization provides a reference solution for constructing an energy-balanced network.Xiao HanHuarui WuHuaji ZhuCheng ChenMDPI AGarticlepower controlchannel allocationDDPGmixed variableChemical technologyTP1-1185ChemistryQD1-999ENProcesses, Vol 9, Iss 1919, p 1919 (2021)
institution DOAJ
collection DOAJ
language EN
topic power control
channel allocation
DDPG
mixed variable
Chemical technology
TP1-1185
Chemistry
QD1-999
spellingShingle power control
channel allocation
DDPG
mixed variable
Chemical technology
TP1-1185
Chemistry
QD1-999
Xiao Han
Huarui Wu
Huaji Zhu
Cheng Chen
Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
description The reduction of maintenance costs in agricultural wireless sensor networks (WSNs) requires reducing energy consumption. At the same time, care should be taken not to affect communication quality and network lifetime. This paper studies a joint optimization algorithm for transmitted power and channel allocation based on deep reinforcement learning. First, an optimization model to measure network reward was established under the constraint of the signal-to-interference plus-noise-ratio (SINR) threshold, which includes continuous power variables and discrete channel variables. Secondly, considering the dynamic changes of agricultural WSNs, the network control is described as a Markov decision process with continuous state and action space. A deep deterministic policy gradient (DDPG) reinforcement learning scheme suitable for mixed variables was designed. This method could obtain a control scheme that maximizes network reward by means of black-box optimization for continuous transmitted power and discrete channel allocation. Experimental results indicated that the studied algorithm has stable convergence. Compared with traditional protocols, it can better control the transmitted power and allocate channels. The joint power and channel optimization provides a reference solution for constructing an energy-balanced network.
format article
author Xiao Han
Huarui Wu
Huaji Zhu
Cheng Chen
author_facet Xiao Han
Huarui Wu
Huaji Zhu
Cheng Chen
author_sort Xiao Han
title Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
title_short Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
title_full Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
title_fullStr Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
title_full_unstemmed Joint Power and Channel Optimization of Agricultural Wireless Sensor Networks Based on Hybrid Deep Reinforcement Learning
title_sort joint power and channel optimization of agricultural wireless sensor networks based on hybrid deep reinforcement learning
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/8e3b6abacdcb482aa59f16f05f6ccd0f
work_keys_str_mv AT xiaohan jointpowerandchanneloptimizationofagriculturalwirelesssensornetworksbasedonhybriddeepreinforcementlearning
AT huaruiwu jointpowerandchanneloptimizationofagriculturalwirelesssensornetworksbasedonhybriddeepreinforcementlearning
AT huajizhu jointpowerandchanneloptimizationofagriculturalwirelesssensornetworksbasedonhybriddeepreinforcementlearning
AT chengchen jointpowerandchanneloptimizationofagriculturalwirelesssensornetworksbasedonhybriddeepreinforcementlearning
_version_ 1718410658810167296