Cyberattack Diagnosis in Water Distribution Networks Combining Data-Driven and Structural Analysis Methods

Most scientific contributions addressing cybersecurity issues in water distribution networks (WDNs) propose detection systems without considering the location problem. A methodology for and of cyberattacks WDNs is proposed this paper. Structural analysis neural are effectively combined with control chart adaptive exponential weighted moving average (AEWMA). The framework requires only data from normal operating conditions knowledge about behavioral model system. validity was demonstrated widely known case study Battle Attack Detection Algorithms (BATADAL). method detected all attacks a false positive rate (false alarm rate) below 5% true (TPR) (i.e., higher than 95%. presents consistent diagnosis results while guaranteeing that district metering area under attack always identified.