Advertisement

pp 1-26 | Cite as

Data Science Trends and Opportunities for Smart Water Utilities

  • Stephen R. MounceEmail author
Chapter
Part of the The Handbook of Environmental Chemistry book series

Abstract

We are witnessing an industry change which is transitioning to a more intelligent (or smarter) water network. In the UK a 5-year planning period and investment cycle called the Asset Management Plan (AMP) is the regulatory mechanism. This process is used to manage a water utility’s infrastructure and other assets to deliver an agreed standard of service. The challenge of AMP 6 and 7 (to 2025) and beyond is to maximise efficiency by moving from reactive to proactive management. This can be achieved by using data, information and (where possible) control of the system. The more intelligence that is captured, the more that can be learned and understood about the network and subsequently be predicted. Extra data provides new opportunities for asset maintenance and event analytics. Data science is an emerging discipline which combines analysis, programming and business knowledge and uses new and advanced techniques and technologies to work with complex data. The water sector needs to address the issue of ‘big data’ and obtaining ‘signal from the noise’. Primarily, the focus is on data to action by the application of data science.

The role of digitalisation for smart water networks is covered in this chapter, exploring issues of IoT, artificial intelligence, blockchain and other novel technologies. Reference to case studies demonstrates the type of applications which will become increasingly common place. Some recommendations based on future possibilities and opportunities are proposed.

Keywords

Blockchain Data science IoT Machine learning Smart networks 

References

  1. 1.
    Caffoor I (2010) Perspective: a vision of a low-carbon water sector in 2050. Proc Inst Civil Eng-Eng Sustain 163(1):9–14.  https://doi.org/10.1680/ensu.2010.163.1.9CrossRefGoogle Scholar
  2. 2.
    Boxall JB, Machell J, Dewis N, Gedman K and Saul A (2011) In: Dragan A. Savic and John K. Banyard (eds) Operation, maintenance and performance in water distribution systems, ICE, London. ISBN: 978-0-7277-4112-7.Google Scholar
  3. 3.
    SWIG (Sensors for Water Interest Group) (2007) ‘SCADA systems for future management of assets’ 24 Jan 2007Google Scholar
  4. 4.
    Bingi P, Sharma MK, Godla JK (1999) Critical issues affecting an ERP implementation. Inf Syst Manage 16(3):7Google Scholar
  5. 5.
    IBM (2014) Web ref. Retrieved from 30 Nov 2014Google Scholar
  6. 6.
    UKWIR (2019) Smart metering and smart networks for leakage management report. UK Water Industry Research, London – ISBN: 978-1-84057-880-5Google Scholar
  7. 7.
    Conroy P, De Rosa S (2015) Framework for expenditure decision making: development of service forecasting approaches. UK Water Industry Research Limited, LondonGoogle Scholar
  8. 8.
    Mounce SR, Douterelo I, Sharpe R, Boxall JB (2012) A bio-hydroinformatics application of self-organizing map neural networks for assessing microbial and physico-chemical water quality in distribution systems, Proceedings of 10th international conference on hydroinformatics, Hamburg, GermanyGoogle Scholar
  9. 9.
    Mounce SR, Jensen HJ, Boxall JB, Biggs CA (2012) Data mining T-RFLP profiles from water system sampling using self-organising maps. Proceedings of 8th international conference on natural computation and the 9th proceedings of international conference on fuzzy systems and knowledge discovery (IEEE), vol 1, pp 219–223.Google Scholar
  10. 10.
    Mounce SR, Sharpe R, Speight V, Holden B, Boxall JB (2014) Knowledge discovery from large disparate corporate databases using self-organising maps to help ensure supply of high quality potable water. Proceedings of 11th international conference on hydroinformatics, New York, USAGoogle Scholar
  11. 11.
    Ellis K, Mounce SR, Edwards J, Speight V, Jakomis N, Boxall JB (2015) Interpreting and estimating the risk of iron failures, Computing and Control for the Water Industry (CCWI2015). Procedia Eng 119:299–308Google Scholar
  12. 12.
    Blokker EJM, Furnass WR, Machell J, Mounce SR, Schaap PG, Boxall JB (2016) Relating water quality and age in drinking water distribution systems using self-organising maps. Environments 3(2):10.  https://doi.org/10.3390/environments3020010CrossRefGoogle Scholar
  13. 13.
    Mounce SR, Blokker EJM, Husband SP, Furnass WR, Schaap PG, Boxall JB (2016) Multivariate data mining for estimating the rate of discoloration material accumulation in drinking water distribution systems. IWA J Hydroinf 18(1):96–114Google Scholar
  14. 14.
    Mackey T, Mounce SR, Boxall JB, Cashman A (2017) A multivariate geospatial data-driven approach to descriptive modelling of burst behaviour in a small island context. Proceedings of computing and control for the water industry (CCWI2017), Sheffield, UKGoogle Scholar
  15. 15.
    Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480. http://www-01.ibm.com/software/data/bigdata/what-is-big-data.htmlGoogle Scholar
  16. 16.
    Sharpe RL, Smith CJ, Biggs CA and Boxall JB, (2010) Pilot scale laboratory investigations into the impact of steady state conditioning hydraulics on potable water discolouration. Proceedings of 11th annual international symposium on water distribution systems analysis, Arizona, USA, SeptemberGoogle Scholar
  17. 17.
    Ester M, Kriegel HP, Sander J, Xu X (1996) Simoudis E, Han J, Fayyad UM (eds) A density-based algorithm for discovering clusters in large spatial databases with noise. AAAI Press, Palo Alto, pp 226–231Google Scholar
  18. 18.
    Sammon JW (1969) A nonlinear mapping for data structure analysis. IEEE Trans Comput C-18(5):401–409Google Scholar
  19. 19.
    van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605Google Scholar
  20. 20.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444Google Scholar
  21. 21.
    Mounce SR (2017) Visualising smart water meter dataset clustering with parametric t-distributed stochastic neighbour embedding. Proceedings of 13th international conference on natural computation, fuzzy systems and knowledge discovery (IEEE). Guilin, China. vol 1, pp. 1940–1945. ISBN: 978-1-5386-2165-3Google Scholar
  22. 22.
    UKWIR (2013) Cost Benefit Analysis of Ubiquitous Data Collection in Water Distribution – CBA Scenarios. 13/DW/12/2 – ISBN: 1 84057 692 8Google Scholar
  23. 23.
  24. 24.
    Nakamoto S (2009) Bitcoin: a peer-to-peer electronic cash system. Cryptography Mailing list at. https://metzdowd.com.
  25. 25.
    IWA (Source) (2018) How Bitcoin’s footprint is impacting water use. https://www.thesourcemagazine.org/how-bitcoins-footprint-is-impacting-water-use/. Accessed 18 Mar 2019
  26. 26.
    Bull R, Azennoud M (2016) Smart citizens for smart cities: participating in the future. Proc Inst Civil Eng-Energy 169(3):93–101.  https://doi.org/10.1680/jener.15.00030CrossRefGoogle Scholar
  27. 27.
    Cahn A (2014) An overview of smart water networks. J Am Water Works Ass 106(7):68–74Google Scholar
  28. 28.
    Mounce SR, Mounce RB, Jackson T, Austin J, Boxall JB (2014) Associative neural networks for pattern matching and novelty detection in water distribution system time series data. IWA J Hydroinf 16(3):617–632Google Scholar
  29. 29.
    Wu Y, Liu S (2017) A review of data-driven approaches for burst detection in water distribution systems. Urban Water J 14(9):972–983.  https://doi.org/10.1080/1573062X.2017.1279191CrossRefGoogle Scholar
  30. 30.
    Mounce, S. R. and Boxall, J. B., (2011). Chapter 9: online monitoring and detection, water loss reduction. Bentley Institute Press, Exton Ed. Zheng Wu, ISBN: 978-1-934493-08-3.Google Scholar
  31. 31.
    Mounce SR, Fargus A, Weeks M, Young J, Jackson T, Goya E, Boxall JB (2017) Online advanced uncertain reasoning architecture with binomial event discriminator system for novelty detection in smart water networks, Proceedings of computing and control for the water industry (CCWI2017), Sheffield, UK, 5th to 7th September 2017Google Scholar
  32. 32.
    Savić D, Vamvakeridou-Lyroudia L, Kapelan Z (2014) Smart meters, smart water, smart societies: the iWIDGET project. Procedia Eng 89:1105–1112Google Scholar
  33. 33.
    Farley B, Mounce SR, Boxall JB (2013) Development and field validation of a burst localization methodology. ASCE J Water Resour Plann Manage 139(6):604–613Google Scholar
  34. 34.
    Romano M, Kapelan Z, Savic DA (2013) Geostatistical techniques for approximate location of pipe burst events in water distribution systems. J Hydroinf 15(3):634–651Google Scholar
  35. 35.
    Nguyen KA, Stewart RA, Zhang H (2013) An intelligent pattern recognition model to automate the categorisation of residential water end-use events. J Environ Modell Software 47:108–127Google Scholar
  36. 36.
    Candelieri A, Soldi D, Archetti F (2015) Short-term forecasting of hourly water consumption by using automatic metering readers data. Proceedings of CCWI 2015, Leicester, UK, 2nd–4th SeptemberGoogle Scholar
  37. 37.
    Stewart RA, Nguyen K, Beal C, Zhang H, Sahin O, Bertone E, Vieira AS (2018) Integrated intelligent water-energy metering systems and informatics: visioning a digital multi-utility service provider. Environ Model Software 105:94–117.  https://doi.org/10.1016/j.envsoft.2018.03.006CrossRefGoogle Scholar
  38. 38.
    Stewart RA, Willis R, Giurco D, Panuwatwanich K, Capati G (2010) Web-based knowledge management system: linking smart metering to the future of urban water planning. Aust Planner 47:66e74Google Scholar
  39. 39.
    Vitorinoa D, Loureirob D, Alegreb H, Coelhob S, Mamadeb A (2014) In defense of the demand pattern, a software approach. Procedia Eng. 89:982–989Google Scholar
  40. 40.
    Rani S, Sikka G (2012) Recent techniques of clustering of time series data: a survey. Int J Comput Appl 52(15):1–9Google Scholar
  41. 41.
    McKennaa SA, Fuscoa F, Ecka BJ (2014) Water demand pattern classification from smart meter data. Procedia Eng 70(2014):1121–1130Google Scholar
  42. 42.
    García D, Gonzalez D, Quevedo J, Puig V, Saludes J (2015) Water demand estimation and outlier detection from smart meter data using classification and Big Data methods. In: Proceedings of 2nd IWA new developments in IT and water conference, Rotterdam, February 2015Google Scholar
  43. 43.
    Mounce SR, Furnass WR, Goya E, Hawkins M, Boxall JB (2016) Clustering and classification of aggregated smart meter data to better understand how demand patterns relate to customer type, Proceedings of computing and control for the water industry (CCWI2016), Amsterdam, Netherlands, 7th to 9th November 2016Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Civil and Structural EngineeringUniversity of SheffieldSheffieldUK
  2. 2.Mounce HydroSmartBeverleyUK

Personalised recommendations