Adaptive edge analytics for distributed networked control of water systems

Over the last decade, there has been a trend where water utility companies aim to make water distribution networks more intelligent in order to improve their quality of service, reduce water waste, minimize maintenance costs etc., by incorporating IoT technologies. Current state of the art solutions use expensive power hungry deployments to monitor and transmit water network states periodically in order to detect anomalous behaviors such as water leakage and bursts. However, more than 97% of water network assets are remote away from power and are often in geographically remote underpopulated areas, facts that make current approaches unsuitable for next generation more dynamic adaptive water networks. Battery-driven wireless sensor/actuator based solutions are theoretically the perfect choice to support next generation water distribution. In this paper, we present an end-to-end water leak localization system, which exploits edge processing and enables the use of battery-driven sensor nodes. Our system combines a lightweight edge anomaly detection algorithm based on compression rates and an efficient localization algorithm based on graph theory. The edge anomaly detection and localization elements of the systems produce a timely and accurate localization result and reduce the communication by 99% compared to the traditional periodic communication. We evaluated our schemes by deploying non-intrusive sensors measuring vibrational data on a real-world water test rig that have had controlled leakage and burst scenarios implemented.

Influencing water consumption at South Staffordshire Water PLC : a disaggregated behavioural analysis of contributory factors

This research identifies factors which influence the consumption of potable water supplied to customers' property. A complete spectrum of the customer base is examined including household, commercial and industrial properties. The research considers information from around the world, particularly demand management and tariff related projects from North America. A device termed the Flow Moderator was developed and proven, with extensive trials, to conserve water at a rate equivalent to 40 litres/property/day whilst maintaining standards-of-service considerably in excess of Regulatory requirements. A detailed appraisal of the Moderator underlines the costs and benefits available to the industry through deliberate application of even mild demand management. More radically the concept of a charging policy utilising the Moderator is developed and appraised. Advantages include the lower costs of conventional fixed-price charging systems coupled with the conservation and equitability aspects associated with metering. Explanatory models were developed linking consumption to a range of variables demonstrated that households served by a communal water service-pipe (known in the UK as a shared supply) are subject to associated restrictions equivalent to -180 litres/property/day. The research confirmed that occupancy levels were a significant predictive element for household, commercial and industrial customers. The occurrence of on-property leakage was also demonstrated to be a significant factor recorded as an event which offers considerable scope for demand management in its own right.