Nowadays, optimal sensor placement (OSP) for leakage detection in water distribution networks is a lively field of research, and a challenge for water utilities in terms of network control, management, and maintenance. How many sensors to install and where to install them are crucial decisions to make for those utilities to reach a trade-off between efficiency and economy. In this paper, we address the where-to-install-them part of the OSP through the following elements: nodes’ sensitivity to leakage, uncertainty of information, and redundancy through conditional entropy maximisation. We evaluate relationships among candidate sensors in a network to get a picture of the mutual influence among the nodes. This analysis is performed within a multi-criteria decision-making approach: specifically, a herein proposed variant of DEMATEL, which uses fuzzy logic and builds comparison matrices derived from information obtained through leakage simulations of the network. We apply the proposal first to a toy example to show how the approach works, and then to a real-world case study.

While operating a water distribution network (WDN), it is essential to prepare the system to face with intentional (e.g., cyber-physical attack) or unintentional (e.g., pipe leakage/burst) adverse events or other drivers such as the effects of climate change. Increasing the network’s preparedness to deal with anomalous events is an effective manner to improve the system’s resilience, reducing the negative impacts of events. In this paper, leakage/burst events, and ordinary network operation, are captured by both sensors and expert knowledge in a WDN in Spain. Event-driven and data-driven approaches are used to characterise the system behaviour, in particular when it is operating under the effects of an anomalous event, based on the resilience phases (i.e., absorptive, adaptive, restorative) for the collected dataset. The relationship of clustering pressure head time series based on their potential state in a particular resilience phase, in three random cases of short-term leakage events, was explored. This paper focuses on capturing the behaviour of the system, through the exploration of the hydraulic parameters of WDNs (in particular the pressure head) before, during, and after a leakage event, by means of a spatial-temporal analysis. It was observed that the network behaviour could be categorised into 1) ordinary operation and 2) during the event, which would allow to characterise the system behaviour when influenced by leakage/burst event and also explore its adaptability to resilience phases. The results show that it is possible to extract relevant patterns (i.e., feature maps) and generate an anomaly indicator from the pressure head heatmaps that facilitate the characterisation of anomalous events for WDNs.

Water distribution systems (WDSs) are large complex infrastructures made from pipes, valves, pumps, tanks and other elements designed and erected to transport water of sufficient quality from water sources to consumers. The amount of the above elements, which can reach up to tens of thousands of links and junctions, their frequently wide spatial dispersion and the WDS characteristic of being very dynamic structures make the management of real WDSs a complex problem [1-4]. However, although the main objective is to supply water in the quantity and quality required, other requirements are essential, namely maintaining conditions far from failure scenarios [5,6], ability to quickly detect sources of contamination intrusion [7,8], minimization of leaks [9-10], etc. Advances in low powered sensors and data transmission are making their way on the creation of smarter water networks. Despite prices are getting attractive, the return on investment is far from being clear for many water company managers in the water distribution industry. To be prepared to arouse in these managers a real interest in the need for the implementation of an adequate lattice of sensors in their water distribution networks, and to provide them with convincing arguments for their rapid implementation three important questions should be first answered that should be clearly perceived as main support elements in ad hoc decision-making: firstly, how many sensors are needed; secondly, where sensors should be located in order to get the most out of them; and, finally, what to do with the measurements in terms of improving operation and customer services. This contribution addresses the third of these questions without forgetting the other two and present a pilot project at early stage. There are three aspects crucially important for water utilities and where the correct use of measurements makes the difference on what the company can achieve: reduction of non-revenue water, network operation optimization and provisioning of a quality service. This contribution presents the development of a platform for Smarter Water Network Operation and Management specifically aimed to support the three mentioned aspects. It uses a water network analysis engine to estimate the state of the water network based on measurements taken from the field combined with a mathematical model of the water distribution network. The estimation of the network state is done starting J. Beyerer et al. (Eds.