Shaping a Sustainable Future with IoT and AI for Water Distribution Networks

This thesis addresses both environmental and technical challenges in developing sustainable systems for critical infrastructures, with a particular focus on Water Distribution Networks (WDNs). By leveraging Internet of Things (IoT), Artificial Intelligence (AI), particularly Machine Learning (ML), and Low Power Wide Area Networks (LPWANs) technologies, specifically Long Range Wide Area Network (LoRaWAN), this research aims to optimize and enhance the resilience of WDNs amidst rising global water demands and climate change. With a projected 40% global water deficit by 2030, improving the efficiency of WDNs is essential for sustainable water management. Additionally, the increasing complexity of modern WDNs, driven by urbanization, fluctuating consumer demands, and limited resources, makes their management more challenging. Beyond these environmental and managerial concerns, this work also addresses the security vulnerabilities associated with the rapid expansion of these interconnected systems, which are often constrained by limited computational resources and minimal security, posing significant risks to critical infrastructure.