Upper Confidence Bound Based Communication Parameters Selection to Improve Scalability of LoRa@FIIT Communication

Valach, Alexander; Macko, Dominik

doi:10.1109/jsen.2022.3174663

Cited by 4 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors show experimentally that selfish UCB, which consists in each player independently playing UCB [4], i.e., a classic commonly-used MAB algorithm, works surprisingly well. This experimental result has been confirmed in the case of LoRa networks using stochastic and non-stochastic multi-armed bandits in [15], [16] or in the case of the IEEE 802.15.4 time-slotted channel hopping protocol [17]. Despite its good experimental performance, this algorithm has no theoretical guarantees, and it has been shown that selfish UCB can fail badly on some cases [18].…”

Section: Introductionmentioning

confidence: 90%

“…For instance, a user's device can interact with its environment in real-time, to get a green light when the user faces a crossroad, an ad when the user is in front of a shop, a ticket when getting on the bus, and more critical applications such as healthcare ones. Such packets has to be sent and processed as soon as possible, and therefore the authors in [16] suggest a modification in the LoRA@FIIT [24] link-layer protocol, so such emergency packets are given the priority to be retransmitted in case of failure over other types of normal packets in order to guarantee QoS in LoRa networks. In this work, in order to model the packets' delivery rate, we assume that each player has a probability of sending a packet at each time step.…”

Section: A Underlying Assumptionsmentioning

confidence: 99%

See 1 more Smart Citation

Massive multi-player multi-armed bandits for IoT networks: An application on LoRa networks

Dakdouk,

Féraud,

Varsier

et al. 2023

Ad Hoc Networks

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 90%

Section: A Underlying Assumptionsmentioning

confidence: 99%

Massive multi-player multi-armed bandits for IoT networks: An application on LoRa networks

Dakdouk,

Féraud,

Varsier

et al. 2023

Ad Hoc Networks

View full text Add to dashboard Cite

“…In addition, the MAB-based SF-selection methods can achieve a higher FSR than the random-based selection method, indicating that the distributed reinforcement learning approaches were effective. Moreover, compared to the existing studies on decentralized parameter selection using UCB1 in [27,32] and -greedy in [3], the ToW dynamics algorithm can achieve a higher FSR. A comparison of the FSR values showed that, as the number of LoRa devices increased, the difference between the ToW and the other MAB-based methods increased, which indicated that the ToW algorithm is more suitable for large-scale LoRa systems.…”

Section: Performance Evaluation Of the Sf Selectionmentioning

confidence: 95%

“…Some other methods that allocate the SF based on channel gain and the Signal-to-Noise Ratio (SNR) were proposed in [ 25 , 26 ], respectively. In [ 27 ], a modification of the existing LoRa@FIIT protocol was proposed, ensuring energy-efficient, QoS-supporting, and reliable communication over the LoRa technology by selecting an appropriate SF and transmission power. In [ 28 ], a deep-reinforcement-learning-based adaptive PHY layer transmission-parameter-selection algorithm was proposed to select the SF and power.…”

Section: Related Workmentioning

confidence: 99%

“…Using the implemented LoRa system, we evaluated the performance of the (i)

-greedy-based, (ii) UCB1-based, (iii) ToW-dynamics-based joint channel and SF selection in the combinatorial and independent MAB-based channel–SF-selection methods, and (iv) the random channel–SF selection. Among the compared methods, the UCB1-based method was introduced in [ 27 , 32 ], while the MAB-based independent methods were proposed in [ 19 ]. By comparing the recently published results, we aimed to justify that the proposed ToW-dynamics-based combinatorial transmission selection method has advanced the state-of-the-art in this field.…”

Section: Implementation and Performance Evaluation Of The Mab-based C...mentioning

confidence: 99%

See 1 more Smart Citation

Combinatorial MAB-Based Joint Channel and Spreading Factor Selection for LoRa Devices

Urabe

Fujisawa

et al. 2023

Sensors

View full text Add to dashboard Cite

Long-Range (LoRa) devices have been deployed in many Internet of Things (IoT) applications due to their ability to communicate over long distances with low power consumption. The scalability and communication performance of the LoRa systems are highly dependent on the spreading factor (SF) and channel allocations. In particular, it is important to set the SF appropriately according to the distance between the LoRa device and the gateway since the signal reception sensitivity and bit rate depend on the used SF, which are in a trade-off relationship. In addition, considering the surge in the number of LoRa devices recently, the scalability of LoRa systems is also greatly affected by the channels that the LoRa devices use for communications. It was demonstrated that the lightweight decentralized learning-based joint channel and SF-selection methods can make appropriate decisions with low computational complexity and power consumption in our previous study. However, the effect of the location situation of the LoRa devices on the communication performance in a practical larger-scale LoRa system has not been studied. Hence, to clarify the effect of the location situation of the LoRa devices on the communication performance in LoRa systems, in this paper, we implemented and evaluated the learning-based joint channel and SF-selection methods in a practical LoRa system. In the learning-based methods, the channel and SF are decided only based on the ACKnowledge information. The learning methods evaluated in this paper were the Tug of War dynamics, Upper Confidence Bound 1, and ϵ-greedy algorithms. Moreover, to consider the relevance of the channel and SF, we propose a combinational multi-armed bandit-based joint channel and SF-selection method. Compared with the independent methods, the combinations of the channel and SF are set as arms. Conversely, the SF and channel are set as independent arms in the independent methods that are evaluated in our previous work. From the experimental results, we can see the following points. First, the combinatorial methods can achieve a higher frame success rate and fairness than the independent methods. In addition, the FSR can be improved by joint channel and SF selection compared to SF selection only. Moreover, the channel and SF selection dependents on the location situation to a great extent.

show abstract

Energy-efficient multi-hop LoRa broadcasting with reinforcement learning for IoT networks

Chen,

Mao,

et al. 2025

Ad Hoc Networks

View full text Add to dashboard Cite

Upper Confidence Bound Based Communication Parameters Selection to Improve Scalability of LoRa@FIIT Communication

Cited by 4 publications

References 38 publications

Massive multi-player multi-armed bandits for IoT networks: An application on LoRa networks

Massive multi-player multi-armed bandits for IoT networks: An application on LoRa networks

Combinatorial MAB-Based Joint Channel and Spreading Factor Selection for LoRa Devices

Energy-efficient multi-hop LoRa broadcasting with reinforcement learning for IoT networks

Contact Info

Product

Resources

About