Cyber-Attack Detection in Water Distribution Systems Based on Blind Sources Separation Technique

Service quality and efficiency of urban systems have been dramatically boosted by various high technologies for real-time monitoring remote control, also gained privileged space in water distribution. Monitored hydraulic parameters are crucial data developing planning, operation security analyses networks, which makes them increasingly reliable. However, devices control increase the possibilities failure cyber-attacks systems, can severely impair system and, extreme cases, collapse service. This paper proposes an automatic two-step methodology cyber-attack detection distribution systems. The first step is based on signal-processing theory, applies a fast Independent Component Analysis (fastICA) algorithm to time series (e.g., pressure, flow, tank level), separates into independent components. These components then processed statistical abrupt changes, from attacks may be disclosed. applied case study provided Battle Attack Detection Algorithms (BATADAL) results compared with seven other approaches, showing excellent results, this reliable early-warning approach.