Real-Time Alum Dosage Optimization Using IoT-Enabled Water Quality Sensing Device

Ensuring the safety and cleanliness of water for consumption and other applications requires the removal of impurities, contaminants, and hazardous substances through water treatment processes. A critical step in these processes is the addition of Aluminum Sulfate (Alum), which facilitates the removal of suspended particulate matter, such as mud, from raw water. All water treatment plants in Sri Lanka rely on manual laboratory testing, specifically the "Jar Test," to determine the appropriate Alum dosage based on raw water quality parameters. This paper proposes an automated system designed to optimize this process. The proposed system integrates an IoT-enabled sensing device, a machine learning model, and a userfriendly web interface to calculate the optimal Alum dosage. The IoT sensing device is installed in the distribution chamber and continuously monitors water quality parameters in real time. These parameters are transmitted to a centralized server and displayed on the web interface. The machine learning model analyzes the data and provides precise Alum dosage recommendations, enhancing decision-making. By automating this critical aspect of water treatment, the system reduces human error, operational time, and energy consumption, thereby improving the overall efficiency and accuracy of the treatment process. This innovative approach has the potential to transform water treatment operations, ensuring consistent and reliable water quality management.