Missing data estimation and IoT-based flyby monitoring of a water distribution system: Conceptual and experimental validation

Achieving uninterrupted water supply to the consumer node is considered to be the significant aspect for urban water distribution system (WDS). Under circumstances such as sensor failures or large sampling interval, the intermittent vital data are ignored, which lead to the missing data problem. In this work, an enhanced version of Kalman filter (KF) is proposed termed to be customized KF (CKF). The proposed CKF is equipped to handle the state- and input-dependent noises, which are amplified based on the input and states in WDS. These noises corrupt the measured response from the WDS added to the conventional sensor and model uncertainties. In this case, a real-world-existing WDS is considered to test the credibility of the proposed algorithm. This reduces the complexity of the computation and the sampling rate of the measured head level, and the flows are considered to be random. The study indicates that the proposed CKF performs better in estimating the missing data voids with the noise-corrupted measurements. To have the continuous monitoring accessible in remote sections, the vital parameters are monitored through Internet of Things (IoT) in android platform. The estimated data from the MATLAB and the sensor data of the consumer demands are monitored through user-defined android application. This technique provides the advantage of monitoring the WDS in flyby condition and also even in the presence of any sensor failures, which also helps to localize the fault location.