Data Processing Automation for Bulk Water Supply Monitoring
Water as a resource is becoming more scarce with South Africa having several provinces being struck with droughts. Up to 30% of water is lost through leaks in water distribution networks. It is common practice to monitor water usage in large water distrib
- PDF / 988,523 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 13 Downloads / 211 Views
and Francois Mouton3,4(&)
1
University of Pretoria, Pretoria, South Africa [email protected] 2 North-West University, Potchefstroom, South Africa 3 Noroff University College, Oslo, Norway [email protected] 4 University of the Western Cape, Belville, South Africa
Abstract. Water as a resource is becoming more scarce with South Africa having several provinces being struck with droughts. Up to 30% of water is lost through leaks in water distribution networks. It is common practice to monitor water usage in large water distribution networks. These monitoring systems unfortunately lack the ability to alert on high flow rates and detect water leaks unless the data is reviewed manually. The paper will explore statistical and Artificial Intelligence approaches to test the viability to detect leaks. This will can then be used as an alerting team to improve operational efficiencies of small teams and reduce repair time of leaks and thus reduces water lost through leaks. Keywords: Artificial Intelligence Automation Big data Critical infrastructure Data optimization Leak detection Water management
1 Introduction Water as a resource has become more scarce with 40% of the world’s population living in water stressed areas - Guppy and Anderson, 2017. Fresh water has reduced by 55% from the 1960’s and the forecast is that it will increase by another 50% by 2030 [4]. Economic impact equates to US$ 500 billion per annum due to water insecurity Guppy and Anderson, 2017. Sustainability Development Goal 6 (SDG6) has been developed due to this scarcity and projections by the United Nations (UN) to work towards water security to the world that is affordable to the masses [8]. South Africa as a region has been struck with droughts over several of its provinces [2, 10]. This in turn has forced introductions of water restrictions with the hope that water supply can be maintained to the communities. The unfortunate fact is that around 30% of water losses occur from leaks in distribution networks [4, 8, 9]. Reduction in these water losses can assist in alleviating water supply in all ready stressed water regions. An additional benefit can be realized on utilities bill savings if leaks is reduced on the client side. This paper focuses on a specific client site, a University Campus, model development to make use of water monitoring data to detect water leaks and increase reaction time. Currently the site has a monitoring system in place, however, in its © IFIP International Federation for Information Processing 2020 Published by Springer Nature Switzerland AG 2020 D. Kreps et al. (Eds.): HCC14 2020, IFIP AICT 590, pp. 193–202, 2020. https://doi.org/10.1007/978-3-030-62803-1_16
194
A. de Coning and F. Mouton
current state it does not perform early leak detection without excessive manual work. The current monitoring system has been installed to collect usage data per hour and can be displayed on a web interface. This system has around 300 monitoring station reporting to a central server but the large amount of information requi
Data Loading...
