Machine learning & IoT based water distribution system for reservoirs in Sri Lanka

Abstract

Water resource management in Sri Lanka is hindered by inefficient water distribution systems in reservoirs and tanks, resulting in water scarcity, wastage, and negative impacts on agriculture, hydropower generation, and drinking water. Despite the global progress in Machine Learning (ML)-based predictive models for hydrological forecasting, Sri Lanka lacks the application of such techniques in its reservoir water management systems. This work proposes a novel approach that integrates ML and Internet of Things (IoT) technologies to develop a demand prediction and smart water distribution system tailored to the Sri Lankan context. The proposed system employs a hybrid model combining Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) networks to accurately predict reservoir inflow, release, and water levels. Sensory data from ESP32 microcontrollers is collected and transmitted to a cloud-based storage system, enabling real-time predictions and adaptive water distribution control. Our work process includes training the ML model, tuning hyperparameters, and optimizing the prediction framework to ensure robustness and reliability. Comparative analysis is conducted by benchmarking the hybrid ANN-LSTM model against other models, such as Random Forest, Support Vector Regression (SVR), XGBoost, and Multi-Layer Perceptron (MLP). The results demonstrate the superiority of the hybrid approach in accurately forecasting water levels and facilitating efficient water resource management. This study offers a scalable and adaptable framework for smart water management in Sri Lanka by leveraging real-time data acquisition and predictive analytics. The research concludes with recommendations for enhancing the proposed system, including real-time adaptive control mechanisms and further application to other hydrological forecasting systems