Re-Learning EXP3 Multi-Armed Bandit Algorithm for Enhancing the Massive IoT-LoRaWAN Network Performance

Almarzoqi, Samar Adel; Yahya, Ahmed; Matar, Zaki; Gomaa, Ibrahim

doi:10.3390/s22041603

Cited by 8 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, EXP3 requires an exceedingly large convergence time of around 200 k-hours of training, making it tedious and resource-consuming. In [31], the problem of long convergence time is addressed by modifying the algorithm selection pattern via switching of the parameters on the run. However, the convergence time still remained significantly long whereas it also decreased the overall throughput of the network since it used buffering.…”

Section: B Machine Learning-driven Techniquesmentioning

confidence: 99%

Intelligent Resource Allocation in LoRaWAN Using Machine Learning Techniques

et al. 2023

View full text Add to dashboard Cite

With the ubiquitous growth of Internet-of-things (IoT) devices, current low-power widearea network (LPWAN) technologies will inevitably face performance degradation due to congestion and interference. The rule-based approaches to assign and adapt the device parameters are insufficient in dynamic massive IoT scenarios. For example, the adaptive data rate (ADR) algorithm in LoRaWAN has been proven inefficient and outdated for large-scale IoT networks. Meanwhile, new solutions involving machine learning (ML) and reinforcement learning (RL) techniques are shown to be very effective in solving resource allocation in dense IoT networks. In this article, we propose a new concept of using two independent learning approaches for allocating spreading factor (SF) and transmission power to the devices using a combination of a decentralized and centralized approach. SF is allocated to the devices using RL for contextual bandit problem, while transmission power is assigned centrally by treating it as a supervised ML problem. We compare our approach with existing state-of-the-art algorithms, showing a significant improvement in both network level goodput and energy consumption, especially for large and highly congested networks.

show abstract

Section: B Machine Learning-driven Techniquesmentioning

confidence: 99%

Intelligent Resource Allocation in LoRaWAN Using Machine Learning Techniques

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Information technology has become essential in the daily lives of people and businesses and the Internet of Things (IoT) concept directly contributes to changes in everyday life [1][2][3][4][5][6][7]. The IoT is a communication paradigm in which objects communicate with each other and with users via network communication technologies, mostly wireless networks [8].…”

Section: Introductionmentioning

confidence: 99%

Planning and Optimization of Software-Defined and Virtualized IoT Gateway Deployment for Smart Campuses

Ferreira

Oliveira

Santos

et al. 2022

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) is based on objects or “things” that have the ability to communicate and transfer data. Due to the large number of connected objects and devices, there has been a rapid growth in the amount of data that are transferred over the Internet. To support this increase, the heterogeneity of devices and their geographical distributions, there is a need for IoT gateways that can cope with this demand. The SOFTWAY4IoT project, which was funded by the National Education and Research Network (RNP), has developed a software-defined and virtualized IoT gateway that supports multiple wireless communication technologies and fog/cloud environment integration. In this work, we propose a planning method that uses optimization models for the deployment of IoT gateways in smart campuses. The presented models aimed to quantify the minimum number of IoT gateways that is necessary to cover the desired area and their positions and to distribute IoT devices to the respective gateways. For this purpose, the communication technology range and the data link consumption were defined as the parameters for the optimization models. Three models are presented, which use LoRa, Wi-Fi, and BLE communication technologies. The gateway deployment problem was solved in two steps: first, the gateways were quantified using a linear programming model; second, the gateway positions and the distribution of IoT devices were calculated using the classical K-means clustering algorithm and the metaheuristic particle swarm optimization. Case studies and experiments were conducted at the Samambaia Campus of the Federal University of Goiás as an example. Finally, an analysis of the three models was performed, using metrics such as the silhouette coefficient. Non-parametric hypothesis tests were also applied to the performed experiments to verify that the proposed models did not produce results using the same population.

show abstract

Low power decentralized differentially private multi-armed bandit algorithm based performance improvement on long-range radio network

More,

Patel

2024

Wireless Netw

View full text Add to dashboard Cite

Re-Learning EXP3 Multi-Armed Bandit Algorithm for Enhancing the Massive IoT-LoRaWAN Network Performance

Cited by 8 publications

References 18 publications

Intelligent Resource Allocation in LoRaWAN Using Machine Learning Techniques

Intelligent Resource Allocation in LoRaWAN Using Machine Learning Techniques

Planning and Optimization of Software-Defined and Virtualized IoT Gateway Deployment for Smart Campuses

Low power decentralized differentially private multi-armed bandit algorithm based performance improvement on long-range radio network

Contact Info

Product

Resources

About