Knowledge extraction from raw data in water networks: application to the Barcelona supramunicipal water transport network

Abstract

Critical Infrastructure Systems (CIS) such as the case of potable water transport network are complex large-scale systems, geographically distributed and decentralized with a hierarchical structure, requiring highly sophisticated supervisory and real-time control (RTC) schemes to ensure high performance achievement and maintenance when conditions are non-favorable due to e.g. sensor malfunctions (drifts, offsets, problems of batteries, communications problems,...). Once the data are reliable, a process to transform these validated data into useful information and knowledge is key for the operating plan in real time (RTC). And moreover, but no less important, it allows extracting useful knowledge about the assets and instrumentation (sectors of pipes and reservoirs, flowmeters, level sensors, ...) of the network for short, medium and large term management plans. In this work, an overall analysis of the results of the application of a methodology for sensor data validation/reconstruction to the ATLL water network in the city of Barcelona and the surrounding metropolitan area since 2008 until 2013 is described. This methodology is very important for assessing the economic and hydraulic efficiency of the network.