LoRaDRL: Deep Reinforcement Learning Based Adaptive PHY Layer Transmission Parameters Selection for LoRaWAN

Ilahi, Inaam; Usama, Muhammad; Farooq, Muhammad Omer; Janjua, Muhammad Umar; Qadir, Junaid

doi:10.1109/lcn48667.2020.9314772

Cited by 22 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous work [7], we showed that the performance deteriorates in a LoRa-MAB based system when EDs are mobile. The major cause of this poor performance is the reduced action space for LoRa EDs that are placed far from the gateway at the start of the simulation.…”

Section: B Related Workmentioning

confidence: 94%

“…The intelligent selection of parameters not only reduces the impact of frequency jamming attacks but also causes a significant drop in power usage because of fewer re-transmissions required due to lost or collided packets. For this purpose, we proposed a deep reinforcement learning (DRL)-based PHY-layer parameters selection scheme for dense LoRa networks in our previous work [7].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we build upon our previous work [7] and perform extensive additional experiments in nonuniformly distributed network scenarios and in networks having EDs moving with high velocities. To support dense networks, the algorithm needs to support multiplechannels as the channels are orthogonal to each other and do not interfere with each other.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Intelligent Resource Allocation in Dense LoRa Networks using Deep Reinforcement Learning

Ilahi¹,

Usama²,

Farooq³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The anticipated increase in the count of IoT devices in the coming years motivates the development of efficient algorithms that can help in their effective management while keeping the power consumption low. In this paper, we propose LoRaDRL and provide a detailed performance evaluation. We propose a multi-channel scheme for LoRaDRL. We perform extensive experiments, and our results demonstrate that the proposed algorithm not only significantly improves long-range wide area network (LoRaWAN)'s packet delivery ratio (PDR) but is also able to support mobile end-devices (EDs) while ensuring lower power consumption. Most previous works focus on proposing different MAC protocols for improving the network capacity. We show that through the use of LoRaDRL, we can achieve the same efficiency with ALOHA while moving the complexity from EDs to the gateway thus making the EDs simpler and cheaper. Furthermore, we test the performance of LoRaDRL under large-scale frequency jamming attacks and show its adaptiveness to the changes in the environment. We show that LoRaDRL's output improves the performance of state-of-the-art techniques resulting in some cases an improvement of more than 500% in terms of PDR compared to learning-based techniques.

show abstract

Section: B Related Workmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Resource Allocation in Dense LoRa Networks using Deep Reinforcement Learning

Ilahi¹,

Usama²,

Farooq³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ilahi et al [ 19 ] proposed using deep RL (specifically double DQN) to configure the SF and TXP of nodes at runtime. As in this study, the action space consisted of two adjustable parameters, SF and TXP.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Wireless Network Management with Multi-Agent Reinforcement Learning

Ivoghlian

Salčić

Wang

2022

Sensors

View full text Add to dashboard Cite

Wireless networks are trending towards large scale systems, containing thousands of nodes, with multiple co-existing applications. Congestion is an inevitable consequence of this scale and complexity, which leads to inefficient use of the network capacity. This paper proposes an autonomous and adaptive wireless network management framework, utilising multi-agent deep reinforcement learning, to achieve efficient use of the network. Its novel reward function incorporates application awareness and fairness to address both node and network level objectives. Our experimental results demonstrate the proposed approach’s ability to be optimised for application-specific requirements, while optimising the fairness of the network. The results reveal significant performance benefits in terms of adaptive data rate and an increase in responsiveness compared to a single-agent approach. Some significant qualitative benefits of the multi-agent approach—network size independence, node-led priorities, variable iteration length, and reduced search space—are also presented and discussed.

show abstract

“…These approaches are optimized in a static environment that depends on a formulated mathematical model. Recently, machine-learning-based resource management schemes for IoT networks have been proposed [14]- [19] by applying reinforcement learning, such as Q-learning [20] and multiarmed bandit learning [21]. Reinforcement learning can realize dynamic resource allocation in response to the environment because the learning process calculates the reward based on feedback from the environment [22].…”

Section: Introductionmentioning

confidence: 99%

Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN

et al. 2021

View full text Add to dashboard Cite

In recent years, owing to research on, and development of, the Internet-of-Things (IoT) and machine-to-machine (M2M) communication, wireless sensor networks have attracted considerable attention. Among these networks, low power wide area networks (LPWANs), which realize low power, low data rate, and wide communication area, are most commonly used for long-range communication. These networks adopt asynchronous random access protocols, such as the pure ALOHA (additive links on-line Hawaii area) protocol in the medium access control (MAC) sublayer. Thus, there is a high possibility that multiple nodes transmit packets simultaneously on the common frequency channel, resulting in packet collisions. Carriersense multiple access/collision avoidance (CSMA/CA) and centralized resource allocation are effective for avoiding packet collisions. However, these schemes increase the energy consumption of battery-powered LPWAN nodes. In addition, LPWAN has a large coverage area; hence, there is a high possibility that the carrier sense may not work successfully. Thus, this paper proposes a simple but effective machine-learningbased scheme that tackles the packet collision problem by offsetting the transmission timings and avoiding unnecessary packet transmission in an autonomous decentralized manner. Each LPWAN node adjusts the transmission probability and timing using the Q-learning technique. The proposed scheme provides effective packet collision avoidance for LPWAN nodes without the need for an additional control signal. The computer simulation results show that the proposed scheme can improve the average packet delivery ratio (PDR) by 60% compared to the pure ALOHA protocol.INDEX TERMS Internet of Things (IoT), low power wide area networks (LPWAN), LoRaWAN , machine learning, resource allocation.

show abstract

LoRaDRL: Deep Reinforcement Learning Based Adaptive PHY Layer Transmission Parameters Selection for LoRaWAN

Cited by 22 publications

References 5 publications

Intelligent Resource Allocation in Dense LoRa Networks using Deep Reinforcement Learning

Intelligent Resource Allocation in Dense LoRa Networks using Deep Reinforcement Learning

Adaptive Wireless Network Management with Multi-Agent Reinforcement Learning

Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN

Contact Info

Product

Resources

About