A review study of Edge Computing Architecture For Predicting and Monitoring Water Quality in IOT System

Clean water is crucial not only for drinking but also for cooking, washing, and personal hygiene. It helps prevent infections and promotes overall health. Manual tools and techniques used for monitoring quality of water are not sufficient to measure the quality of water in real-time. With the development of computing technology the monitoring of water quality indicators accurately are possible but not in real-time. The development of advance ICT devices and artificial intelligence, it's been possible to build potential and predictive models for monitoring and controlling pollution based on the real-time data. An intelligent water quality monitoring model is built on the real-time data available can predict the values of environment pollutants in real time. IOT based water sensors are embedded in water to measure the water quality indicators. By using the smart monitoring devices and machine learning techniques, the current level of pollution at the location is sent to users for information in real time. Machine learning model is used for the prediction of pollution level in the environment based on the previous data and the current data obtained by the sensors. In this review study, our aim to focus on the combination of machine learning and the edge computing paradigm in IOT environment. The presented research commences with the topic of edge computing, its benefits, such as reduced data transmission, improved scalability, and reduced latency, as well as the challenges associated with this computing paradigm, like energy consumption, constrained devices, security, and device fleet management strikes shortcomings of existing framework. It explores the areas of improvement and move towards a better and efficient model which allows data from environment sensors to be stored and processed locally at the edge and warns the users real-time. It implementation near the monitoring station saves network traffic and computing resources while ensuring the accuracy, privacy, security of data, low latency and lowering reliance on centralized cloud.