Fog Analytics for Heterogeneous Green IoT
This project focuses on ensuring reliable connectivity and capacity through seamless handover between heterogeneous wireless networks for remote Green IoT nodes. A prime example of its application is the IoT landslide monitoring system. This system is equipped with a comprehensive sensor array, including rain gauges, pore pressure sensors, movement detectors, and inclinometers, all powered sustainably by solar energy. Funded by Amrita Vishwa Vidyapeetham in collaboration with the Ministry of Earth Sciences (MoES), the Department of Science & Technology (DST), and the European Union, the initiative aims to advance remote monitoring capabilities while prioritizing environmental sustainability.
Project Description
Providing reliable communications in a remotely monitored large-scale IoT deployment is a challenging task. We deal with such a deployment to monitor a landslide-prone zone where the nodes sense geological attributes essential for early warning. The deployment area is a hilly mountain with different demographic characteristics. Establishing network connectivity in this deployment site for real-time streaming of sensor data involves dealing with site-specific challenges such as asymmetric links, dynamic network conditions due to rough weather, inadequate solar power, network fail-over and re-connection problems etc. Our deployment makes use of only a few relay nodes for connecting the IoT nodes to an IoT gateway. The IoT gateway is equipped with Heterogenous wireless networks and seamlessly transmits data to the Data Management Center (DMC) which is situated 2500 km from the deployment sites. The IoT gateways employ fog analytics and use bandit-based reinforcement learning algorithms. This allows them to assess the performance of various networks and adaptively select the most efficient one. The system utilizes three types of bandit algorithms: approximate, contextual, and adversarial bandits. Approximate bandits implement the epsilon-greedy algorithm to make selections, contextual bandits rely on the Bayesian Upper Confidence Bound algorithm for decision-making, and adversarial bandits use the EXP3 algorithm. Together, these algorithms enable the system to optimize network selection, enhancing Quality of Service (QoS) and energy efficiency in heterogeneous connectivity environments for green IoT solutions.
Proposed Future Work Details : Future plans are to work with Odisha State Disaster Management Authority
Publication Details
- “QoS in Ultra-Low Memory Green IoT Nodes for Disaster Management Applications”, Kumar, Sangeeth, Gutjahr, Georg, IEEE Conference on Mobile Networks and Wireless Communications, Dec 2023
- “Reliable network connectivity in wireless sensor networks for remote monitoring of landslides.”, Kumar, Sangeeth, Subhasri Duttagupta, Venkat P. Rangan, and Maneesha Vinodini Ramesh. Wireless Networks 26 (2020)
- “Design and validation of wireless communication architecture for long term monitoring of landslides.”, Kumar, Sangeeth, P. Venkat Rangan, and Maneesha Vinodini Ramesh. In Advancing Culture of Living with Landslides: Volume 3 Advances in Landslide Technology, pp. 51-60. Springer International Publishing, 2017.
- “Scalable, secure, fail safe, and high performance architecture for storage, analysis, and alerts in a multi-site landslide monitoring system.” Guntha, Ramesh, Sangeeth Kumar, and Balaji Hariharan. In Advancing Culture of Living with Landslides: Volume 3 Advances in Landslide Technology, pp. 61-69. Springer International Publishing, 2017.
- Guntha, Ramesh, Sangeeth Kumar, and Balaji Hariharan. “Scalable, secure, fail safe, and high performance architecture for storage, analysis, and alerts in a multi-site landslide monitoring system.” In Advancing Culture of Living with Landslides: Volume 3 Advances in Landslide Technology, pp. 61-69. Springer International Publishing, 2017.
- Kumar, Sangeeth, P. Venkat Rangan, and Maneesha Vinodini Ramesh. “Pilot deployment of early warning system for landslides in Eastern Himalayas: Poster.” In Proceedings of the Tenth ACM International Workshop on Wireless Network Testbeds, Experimental Evaluation, and Characterization, pp. 97-99. 2016
