In today’s context, urban flooding has emerged as a pervasive and significant global challenge, resulting in substantial economic losses spanning both human lives and property damage. With a concerning rise in urban flood-related fatalities and financial impacts, there’s an urgent call for enhanced flood risk management strategies. Although floods, as natural disasters, cannot be entirely prevented or eliminated, their catastrophic effects can be significantly reduced or mitigated. Cutting-edge technologies like the internet of things (IoT) and artificial Intelligence offer promising solutions for flood prediction. These advancements facilitate early warning systems, enabling pre-emptive evacuation measures to safeguard lives and minimize economic repercussions. This work aims to develop and implement a system leveraging IoT-derived data with an edge computing framework. It also uses machine learning techniques for fuzzy-based fused framework to provide rainfall prediction early flood warnings, focusing on risk mitigation as a proactive approach to address this pressing issue.
Wireless sensor networks (WSNs) are a decentralized kind of network which is equipped with sensor nodes and is rapidly being utilized to intelligently monitor different environmental conditions at a minimal cost. Sensor nodes are often battery-powered and the essential issue to address is how to decrease node energy consumption so that the network lifetime may be prolonged to realistic lengths. Routing is one of the primary operations performed within the network which consumes a sufficient amount of energy. Therefore, it is very much essential to consider the finest routing protocol so that it consumes less energy. In this article, we look at several routing protocols used in WSNs, including AODV, DSDV, DSR, OSLR and M-GEAR. Furthermore, we studied the execution of selected protocols based on network factors such as network latency, packet delivery ratio, and network throughput against multiple network sizes. The simulation findings show that protocol performance varies depending on network size and that selecting the optimum protocol based on network parameters is also crucial.