Dealing with these challenges at a small scale, before increasing the scope and
area, enables the understanding of the best way to do it and allows us to assess
the risks and benefits. Successful demonstration of the return on investment
business case will ultimately allow full-scale roll-out of smart DMAs. Successful
demonstration of the return on investment business case will ultimately allow
full-scale roll-out of smart DMAs.
The full possibilities of smart network technologies to deliver improved service
to customers and cost-effective performance improvements in the water industry
are yet to be realised. Smart metering technologies need to be able to support
decisions at both the household and utility levels [32]. Sensor technology and
the ‘big data’ they generate combined with advanced machine learning techniques
are providing exciting new opportunities for new scales of understanding of WDS.
With increased DMA flow and pressure measurements comes the possibility of
leak localisation at the sub-DMA level [33, 34]. AMR data expands information
availability even further and has the potential to be used for customer profiling at
the WSP side, allowing urban water planning and management based on consumer
types and for informing customers on their water end-use patterns. Nguyen et al. [35]
present a methodology using hidden Markov model and dynamic time warping
algorithm techniques disaggregating customer data into its end-use categories,
including for rapidly alerting consumers of occurring leak events. By utilising
AMR for demand forecasting, the possibility for reducing costs for treatment,
storage and distribution arises such as through optimisation of pump scheduling.
Candelieri et al. [36] present a data-driven, fully adaptive self-learning algorithm
for short-term water demand forecasting utilising AMR data. In the future, water
and energy use could be more efficiently managed through smart meter adoption and
changing the 24-h diurnal demand profile.
8 Use of Smart Meter Data
There is more to smart water metering than accurate billing, but the business
case for investing in smart meters and automatic meter reading is often complex.
The technological development and digitalization of the water industry show no
sign of slowing down, but the right tools can help water utilities decrease the
complexity of their daily work and transform their meter data into valuable
knowledge.
The concept of a smart city places citizens at the centre of services within a city.
This involves bringing together hard infrastructure, social capital including local
skills and community institutions and technologies to fuel sustainable economic
development and provide an attractive environment for all. For the water sector,
this means using technologies for optimising water resources and waste treatment,
monitoring and controlling water and providing real-time information to help water
companies and households manage their water better. The increasing use of smart
water metering technologies for monitoring networks in real time is providing water
Data Science Trends and Opportunities for Smart Water Utilities
19
area, enables the understanding of the best way to do it and allows us to assess
the risks and benefits. Successful demonstration of the return on investment
business case will ultimately allow full-scale roll-out of smart DMAs. Successful
demonstration of the return on investment business case will ultimately allow
full-scale roll-out of smart DMAs.
The full possibilities of smart network technologies to deliver improved service
to customers and cost-effective performance improvements in the water industry
are yet to be realised. Smart metering technologies need to be able to support
decisions at both the household and utility levels [32]. Sensor technology and
the ‘big data’ they generate combined with advanced machine learning techniques
are providing exciting new opportunities for new scales of understanding of WDS.
With increased DMA flow and pressure measurements comes the possibility of
leak localisation at the sub-DMA level [33, 34]. AMR data expands information
availability even further and has the potential to be used for customer profiling at
the WSP side, allowing urban water planning and management based on consumer
types and for informing customers on their water end-use patterns. Nguyen et al. [35]
present a methodology using hidden Markov model and dynamic time warping
algorithm techniques disaggregating customer data into its end-use categories,
including for rapidly alerting consumers of occurring leak events. By utilising
AMR for demand forecasting, the possibility for reducing costs for treatment,
storage and distribution arises such as through optimisation of pump scheduling.
Candelieri et al. [36] present a data-driven, fully adaptive self-learning algorithm
for short-term water demand forecasting utilising AMR data. In the future, water
and energy use could be more efficiently managed through smart meter adoption and
changing the 24-h diurnal demand profile.
8 Use of Smart Meter Data
There is more to smart water metering than accurate billing, but the business
case for investing in smart meters and automatic meter reading is often complex.
The technological development and digitalization of the water industry show no
sign of slowing down, but the right tools can help water utilities decrease the
complexity of their daily work and transform their meter data into valuable
knowledge.
The concept of a smart city places citizens at the centre of services within a city.
This involves bringing together hard infrastructure, social capital including local
skills and community institutions and technologies to fuel sustainable economic
development and provide an attractive environment for all. For the water sector,
this means using technologies for optimising water resources and waste treatment,
monitoring and controlling water and providing real-time information to help water
companies and households manage their water better. The increasing use of smart
water metering technologies for monitoring networks in real time is providing water
Data Science Trends and Opportunities for Smart Water Utilities
19