Research Article
Enhancing Flood Disaster Response Through Real-Time Monitoring and IoT: The Case of SentryLeaf
Issue:
Volume 13, Issue 1, March 2025
Pages:
1-14
Received:
11 March 2025
Accepted:
25 March 2025
Published:
12 April 2025
Abstract: Floods are among the greatest natural disasters, causing immense destruction, particularly in flood-prone regions like Bangladesh. This study introduces SentryLeaf, an innovative IoT-based network for real-time flood monitoring and disaster response. The system integrates water-level sensors, environmental sensors, and communication modules to facilitate continuous monitoring, enabling quick identification of high-risk areas. The major findings of this research include the system's high accuracy in data collection, with water-level sensors providing measurements accurate to ±2 cm under ideal conditions. Additionally, SentryLeaf ensures real-time data transmission and reliable communication even in the absence of traditional networks, thanks to its decentralized architecture. The communication network remained stable over distances of 200 meters, despite obstructions, and the peer-to-peer communication protocol exhibited resilience under harsh conditions. Furthermore, the system’s user interface received positive feedback for its intuitive design and responsiveness, allowing emergency responders to make informed decisions quickly. Overall, SentryLeaf significantly enhances Bangladesh’s disaster preparedness and response capabilities, offering a scalable, cost-effective, and resilient solution for mitigating flood-related damages.
Abstract: Floods are among the greatest natural disasters, causing immense destruction, particularly in flood-prone regions like Bangladesh. This study introduces SentryLeaf, an innovative IoT-based network for real-time flood monitoring and disaster response. The system integrates water-level sensors, environmental sensors, and communication modules to faci...
Show More
Research Article
QoS-Aware Task Scheduling Using Reinforcement Learning in Long Rage Wide Area Network IoT Application
Ermias Melku Tadesse*
,
Haimanot Edmealem,
Tesfaye Belay,
Abubeker Girma
Issue:
Volume 13, Issue 1, March 2025
Pages:
15-27
Received:
10 March 2025
Accepted:
26 March 2025
Published:
19 April 2025
DOI:
10.11648/j.iotcc.20251301.12
Downloads:
Views:
Abstract: In order to solve the problems of effective resource allocation in low-power wide-area networks, this thesis investigates the scheduling of end devices in Internet of Things applications using LoRaWAN technology. The main goal of this research is to use RL to improve QoS measures including energy efficiency, throughput, latency, and dependability. This was accomplished by using a simulation-based approach that evaluated the effectiveness of the RL-based scheduling algorithm using NS3 simulations. The main findings show that, in comparison to current scheduling practices, the RL agent greatly improves data transmission reliability and improves network throughput. Furthermore, the suggested approach efficiently lowers average system latency and overall energy usage, improving network resource utilization. These findings imply that using reinforcement learning (RL) for job scheduling in LoRaWAN networks can offer a reliable and expandable solution to present problems, resulting in more intelligent and environmentally friendly IoT systems. In the end, this study finds that using RL-based techniques can help improve resource management in contexts that are dynamic and resource-constrained.
Abstract: In order to solve the problems of effective resource allocation in low-power wide-area networks, this thesis investigates the scheduling of end devices in Internet of Things applications using LoRaWAN technology. The main goal of this research is to use RL to improve QoS measures including energy efficiency, throughput, latency, and dependability. ...
Show More
