Adaptive LoRaWAN Transmission exploiting Reinforcement Learning: the Industrial Case

The Internet of Things is rapidly growing with the demand for low-power, long-range wireless communication technologies. Long Range Wide Area Network (LoRaWAN) is one such technology that has gained significant attention in recent years due to its ability to provide long-range communication with low power consumption. One of the main issues in LoRaWAN is the efficient utilization of radio resources (e.g., spreading factor and transmission power) by the end devices. To solve the resource allocation issue, machine learning (ML) methods have been used to improve the LoRaWAN network performance. The primary aim of this survey paper is to study and examine the issue of resource management in LoRaWAN that has been resolved through state-of-the-art ML methods. Further, this survey presents the publicly available LoRaWAN frameworks that could be utilized for dataset collection, discusses the required features for efficient resource management with suggested ML methods, and highlights the existing publicly available datasets. The survey also explores and evaluates the Network Simulator-3-based ML frameworks that can be leveraged for efficient resource management. Finally, future recommendations regarding the applicability of the ML applications for resource management in LoRaWAN are illustrated, providing a comprehensive guide for researchers and practitioners interested in applying ML to improve the performance of the LoRaWAN network.

“…RL approach has several advantages over traditional methods of optimizing LoRaWAN networks [ 129 , 152 , 153 , 154 , 155 ].…”

Section: Lorawan Meets MLmentioning

confidence: 99%

simulator [ 171 ], where the states are data extraction rate (DER) and SNR pairs.…”

Section: Lorawan Meets MLmentioning

confidence: 99%

LoRaWAN Meets ML: A Survey on Enhancing Performance with Machine Learning

Farhad

Pyun

2023

“…In the last years, Wi-Fi was also revealed to be promising to be applied in factory automation as, compared with the IEEE 802.15.4 solutions, it gives the possibility to cope with the timing requirements of the modern control systems and to perform a useful Rate Adaptation activity [136]. Indeed, for example, authors of [137] underlined the necessity of a minimum control frequency of 1 kHz for some specific application, not achievable by wirelessHART since it is characterized by a time slot of at least 10 ms. How to adapt emergent wireless technologies, such as 5G and Wi-Fi, to the strict requirements of the factory automation is an open research field [138][139][140][141], together with recent works concerning industrial LoRa networks [142]. Some works suggest the usage of hybrid wired/wireless networks, integrating ethernet TSN networks with both Wi-Fi [52] and 5G [143].…”

Section: Tsn Over Wi-fimentioning

confidence: 99%

A Comprehensive Review on Time Sensitive Networks with a Special Focus on Its Applicability to Industrial Smart and Distributed Measurement Systems

Fedullo

Morato

Tramarin

et al. 2022

Self Cite

The groundbreaking transformations triggered by the Industry 4.0 paradigm have dramatically reshaped the requirements for control and communication systems within the factory systems of the future. The aforementioned technological revolution strongly affects industrial smart and distributed measurement systems as well, pointing to ever more integrated and intelligent equipment devoted to derive accurate measurements. Moreover, as factory automation uses ever wider and complex smart distributed measurement systems, the well-known Internet of Things (IoT) paradigm finds its viability also in the industrial context, namely Industrial IoT (IIoT). In this context, communication networks and protocols play a key role, directly impacting on the measurement accuracy, causality, reliability and safety. The requirements coming both from Industry 4.0 and the IIoT, such as the coexistence of time-sensitive and best effort traffic, the need for enhanced horizontal and vertical integration, and interoperability between Information Technology (IT) and Operational Technology (OT), fostered the development of enhanced communication subsystems. Indeed, established technologies, such as Ethernet and Wi-Fi, widespread in the consumer and office fields, are intrinsically non-deterministic and unable to support critical traffic. In the last years, the IEEE 802.1 Working Group defined an extensive set of standards, comprehensively known as Time Sensitive Networking (TSN), aiming at reshaping the Ethernet standard to support for time-, mission- and safety-critical traffic. In this paper, a comprehensive overview of the TSN Working Group standardization activity is provided, while contextualizing TSN within the complex existing industrial technological panorama, particularly focusing on industrial distributed measurement systems. In particular, this paper has to be considered a technical review of the most important features of TSN, while underlining its applicability to the measurement field. Furthermore, the adoption of TSN within the Wi-Fi technology is addressed in the last part of the survey, since wireless communication represents an appealing opportunity in the industrial measurement context. In this respect, a test case is presented, to point out the need for wirelessly connected sensors networks. In particular, by reviewing some literature contributions it has been possible to show how wireless technologies offer the flexibility necessary to support advanced mobile IIoT applications.

“…Fedullo et al [ 23 ] used the SARSA algorithm for LoRaWAN management. SARSA is a table-based method, and so it is constrained to relatively small problem spaces.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Wireless Network Management with Multi-Agent Reinforcement Learning

Ivoghlian

Salčić

Wang

2022

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.