Water Distribution Systems (WDSs) are crucial for urban infrastructure but struggle with challenges such as significant water losses, with up to 40% lost due to leaks and inefficiencies. Our study harnesses the power of smart technologies, including IoT sensors and machine learning, to transition WDS from reactive to proactive management. Incorporating both hydrometeorological data and advanced Early Warning Systems (EWSs), we enhance system responsiveness to potential threats such as water leaks. This research evaluates the efficacy of using raw versus transformed data (anomaly scores) in predicting and managing system malfunctions. Our findings suggest that integrating sophisticated, data-driven solutions into WDS can reduce malfunctions and improve operational efficiency, offering a detailed analysis of the impact of both internal and external factors on system performance.