Knowledge driven modeling improves failure predictions in complex water networks
Composable, Knowledge-Driven Disservice Propagation for Complex Interdependent Services with a Flow-Allocation Module Validated Against Hydraulic Simulation
Computational Engineering, Finance, and Science
Summary
Predicting how problems spread in interconnected infrastructure like water systems is hard because simple maps omit important details and detailed simulators are complex to use. The authors propose a new method that categorizes parts of networks to model failure spread while considering the amount of resource flow. They test their model against a detailed water simulation tool and find it better at identifying critical points missed by simpler methods. Their approach runs through steps guaranteeing a final, stable prediction.
What this means in practice
- •For infrastructure resilience planners: Identify critical nodes in water networks to prioritize upgrades and responses to failures more accurately than simple connectivity checks.
- •For pipeline network operators: Use the flow-aware propagation model to better anticipate service disruptions during attacks or component failures and improve emergency responses.
Authors
Cristian Curaba, Stefano Grimaz
Abstract
Modeling cascading failure across interdependent critical infrastructure requires either a composable physical simulator per domain or a topological abstraction that discards quantity awareness. Simulators are costly, data-hungry, and require detailed calibration per domain; topological abstractions stay data-parsimonious while missing quantity-based behaviors that govern real dynamics. We present, instead, a knowledge-driven propagation architecture in which heterogeneous service dependencies are identified by categories: a general logical propagation resolves multi-dependency and redundancy structures purely from how nodes are categorized, while quantity-aware categories plug in dedicated mechanisms - here, a max-min fair-share flow module for water distribution. Both share one discrete functionality scale and a monotonic update algorithm guaranteeing convergence in finitely many rounds. We assess the flow module by comparing its results with those we get from preexisting pressure-driven simulation with WNTR (Water Network Tool for Resilience) on eight realistic networks across four failure families (clustered damage, capacity-targeted attack, source failure, tank loss). Under capacity-targeted attack and source failure a topological-reachability baseline misses 46% of the truly critical junctions, where the flow module misses 10% and 8% at an average critical-class precision of 0.73. Supplementary materials, code and results are available at: https://github.com/cascade-platform-org/CASCADE