In a significant academic achievement, Dr Anirban Ghosh, Assistant Professor from the Department of Electronics and Communication Engineering along with Mr Naga Srinivasarao Chilamkurthy, PhD Scholar, and Mr Shaik Abdul Hakeem, an undergraduate student, have made a remarkable contribution to the field of communication engineering. Their paper, titled “Optimal Routing Protocol in LPWAN Using SWC: A Novel Reinforcement Learning Framework,” has been published in the esteemed IEEE Sensors Journal, with an impressive impact factor of 4.3.
This publication marks a milestone for the university and highlights the innovative research being conducted by its faculty and students. The paper delves into the development of an optimal routing protocol for Low-Power Wide-Area Network (LPWAN) using State-Wise Communication (SWC), employing a novel reinforcement learning framework to enhance network efficiency and performance.
This work will pave the way for advancements in LPWAN technologies, which are crucial for the Internet of Things (IoT) ecosystem. The university community celebrates this achievement and looks forward to the positive impact it will have on technology and society.
Abstract:
Low Power Wide Area Network (LPWAN) has emerged as a dominating communication technology that offers low-power and wide coverage for the Internet of Things (IoT) applications. However, the direct data transmission approach has a limited network lifetime. Even multi-hop data transmission experiences several difficulties including high data latency, poor bandwidth utilization, and reduced data throughput. To overcome these challenges, in this paper, a recent breakthrough in social networks known as Small-World Characteristics (SWC) is incorporated into LPWANs.
In particular, in this work, Small-World LPWANs (SW-LPWANs) are developed by using the Reinforcement Learning (RL) technique and using different node centrality measures like degree, betweenness, and closeness centrality. Further, the performance of the developed SW-LPWANs is evaluated in terms of energy efficiency (alive/dead devices, and network residual energy) and Quality-of-Service (average data latency, data throughput, and bandwidth utilization), and is compared with that of conventional multi-hop LPWAN. Finally, to validate the simulation results, similar analyses are performed on the real-field LPWAN testbed.
The obtained simulation results confirm that SW-LPWAN developed by the RL method performs better than other techniques, with 11% more alive devices, 5.5% higher residual energy, 2.4% improved data throughput, and 14% efficient bandwidth utilization compared to the next best method. A similar trend is observed with real-field LPWAN testbed data also.
Explanation of the Research in Layperson’s Terms
Social networks primarily revolve around establishing human connections, whereas LPWANs are designed for connecting IoT devices that have limited battery-driven power. In this context, the smart devices must communicate in an IoT setting to conserve the limited energy available to them. To achieve this, the concept at the core of social networking also known as small world characteristic is incorporated into LPWAN using the Q-learning technique.
Practical Implementation or the Social Implications of the Research
IoT applications such as remote healthcare, smart environmental monitoring, asset tracking, and smart traffic systems require low transmission delay and high network lifetime. The proposed research helps in achieving the above parameters.
Collaborations
Dr Om Jee Pandey, Assistant professor Department of Electronics Engineering, Indian Institute of Technology, (BHU), Varanasi. e-mail: omjee.ece@iitbhu.ac.in
Dr Linga Reddy Cenkeramaddi, Professor, Department of Information and Communication Technology, University of Agder, Norway. e-mail:linga.cenkeramaddi@uia.no
Future Research Plan
In the next phase of research, we will be interested in investigating how the energy efficiency and other quality of service of smart devices in an IoT setting can be improved if they are partially or completely mobile.