An Intuitive Remote Monitoring Framework for Water Quality in Fish Pond using Cloud Computing

Abstract

Accuracy in prediction of water quality is a recent research domain gaining popularity in smart aquaculture. In aquaculture, the modifications in water quality parameters possess nonlinearity, dynamicity, unstableness and complexity due to the open environment with its surroundings. Conventional prediction methods have several disadvantages like poor generalization, lower accuracy and high time complexity. By considering these issues, a Novel water quality prediction method interfaced with (IoT)Internet of Things termed as Low-Cost Real-Time Monitoring System (LCRTMS) is proposed to predict water temperature, pH, DO, and Ammonia. Multi-sensors and Blynk private cloud integrated framework are used for collecting data in real-time and enhancing the remote monitoring capabilities. Experimental results indicate that the accuracy in predicting temperature, DO, pH and ammonia can attain 98.56% in 0.257 seconds and 98.97% in 0.301seconds in the short-term prediction.