Abstract :

The Increasing Complexity Of Modern Water Distribution Systems And The Growing Risk Of Cyber-physical Attacks Have Created A Strong Need For Intelligent Monitoring And Prediction Mechanisms. The Traditional Water Monitoring System Relies On Manual Observation And Threshold-based Techniques, Which Are Inefficient In Detecting Anomalies And Predicting System Behavior Accurately. These Systems Lack Automation, Real-time Analysis, And The Ability To Handle Large-scale Sensor Data, Leading To Delayed Responses And Potential Failures. The Major Problem Addressed In This Project Is The Accurate Detection Of Abnormal Conditions And Prediction Of Critical System Parameters In Water Distribution Networks Using Data-driven Approaches. The Traditional System Fails To Capture Complex Relationships Among Sensor Readings Such As Tank Levels, Flow Rates, Pump Status, And Pressure Variations. This Highlights The Need For An Advanced System Capable Of Performing One Classification And Four Regression Tree (1CA4RT) Efficiently. To Address These Challenges, The System Implements Restricted Boltzmann Machine (RBM) With Logistic Regression (LR) For Classification And Ridge Regressor (RR) For Regression, Along With Adaptive Boosting (AB) And Natural Gradient Boosting (NGB) As Baseline Models. A Hybrid Model, Variational Quantum Probabilistic Tree Ensemble (VQPTE), Integrating Variational Quantum Neural Network (VQNN), Probabilistic Output Representation Transformation (PORT), And Random Forest (RF), Is Proposed. The System Classifies Normal And Attack Conditions And Predicts Parameters Such As Average Tank Level, Pump Status, Flow Rate, And Pressure. The VQPTE Model Achieves 97.35% Accuracy And High R² Scores (0.9758, 0.9913, 0.9954, 0.9826), Enabling Accurate, Reliable, And Real-time Monitoring.

Published:

09-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2148-2161

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite