Reading Time: 13 minutes

‘Nothing is softer or more flexible than water, yet nothing can resist it.”

Lao Tzu

For over a decade we have all heard about or actually have installed smart electric meters. Some may have even learned about smart grids. Electricity was prioritized to bring IoT, big data, and analytics to as a means to better manage the production, distribution, and consumption.

Now, water is rising to the top and is finally getting the attention that it warrants. Smart water has a distinct advantage over smart electricity in so much as it is able to taken advantage of the developments and innovations from the electricity deployments that went ahead of it. As a next generation technology, there is the opportunity to do water even smarter than electricity. And, since water distribution is different compared to electricity distribution, it can offer features and capabilities that better match the needs for this essential, life-giving resource.

A smart water meter not only measures water flow, but uses wireless communication to connect to local or wide area networks, allowing remote location monitoring and infrastructure maintenance through leak detection as a minimum functionality. But, it can do so much more if duly equipped.

Utility companies are responsible for determining the price of water and managing the day-to-day delivery of safe drinking water. Historically, utility operations were labourious and required extensive measurement and action by field personnel.

Many popular smart meters have successfully leveraged IoT sensors and radio devices to deploy a wireless-based water system throughout a city and the surrounding areas. It is not uncommon for a municipality to have identified and repaired thousands of water leaks, achieved a ten percent or better increase in water network efficiency, and saved over one million cubic meters of water due to the distribution network’s improved performance.  

Non-Revenue Water Losses

In this day and age of widespread, long-term droughts, impacts from climate change, and rapidly increasing rates of urbanization as cities around the world explode in size and number, water loss is a critical issue. Some cities have experienced water losses as high as 70%. But even small losses that accumulate over time can have significant financial impacts on community water departments and economic impacts on water customers. The question then becomes, who picks up the tab? Who actually pays for these losses, how are these water costs covered in current budgets, and how do communities afford the necessary improvements needed to minimize water losses?

Simply put, non-revenue water loss is water that does not make it from point A (the source of the water distribution system) to point B (the end user) because it got lost along the way due to leakage, wastage, or theft. These losses can be real, physical losses (caused by leaks, breaks, spills, etc.) or only apparent losses that occur as a result of broken or tampered meters, poor meter reading, inaccurate record keeping, or outright water theft. Even relatively small amounts of water loss can add up over time to represent a significant financial drain on the water utility (due to lost revenue from customers). The leaks and breaks that allow water to escape can also allow impurities to enter the distribution system, impairing the quality of the water itself.

Total non-revenue water loss is measured by the volume of the water lost (in liters or gallons) as a percentage or share of the total water supplied during the same time period. The rate of water loss can also be expressed as the volume of lost water per length (measured as kilometers or miles) of the pipes making up the water distribution system. These numbers will vary according to location and age of the water supply system. Developing nations face a serious problem with water losses for their rapidly expanding urban areas. But developed nations also face significant issues resulting from old and underfunded water infrastructure. In both cases, significant cost savings and efficiencies are possible, provided the money and will are available.

A distinction should be made between non-revenue water loss and unaccounted for water. The terms are sometimes used interchangeably, but are actually quite different. Non-revenue water includes authorized but unbilled water use (such as for firefighting) while unaccounted for water does not.

There are many credible solutions from a variety of vendors to help resolve and better manage these non-revenue loss and to be more informed regarding unaccounted water loss.

Future Smart Water Solutions

Today, we bolt-on a radio device to read meters. We may have some simple analytics to try to make sense of these reads. In some cases, we may send communications back to the consumers to notify about alerts or to inquire about irregular water consumption rates. But, for the most part, these existing smart water meter solutions are a smaller improvement over the older manually read water meters, but do not drive sufficient value to provide the return on investments (ROI) that were hoped for at the refresh away from the manual options.

In 2020, we are now at the cusp of a major reinvention of smart water. The hundred year old plus water industry is about to meet artificial intelligence, big data, elastic cloud resources, and the Internet of Things head-on.

We are at the advent of bringing advanced data science to the Utility water industry.

Artificial Intelligence

Stephen Hawking has said, “Every aspect of our lives will be transformed [by AI],” and it could be “the biggest event in the history of our civilization.”

We are not quite there yet, but it is only a matter of time. So what would AI mean for the Utility business and the municipal leadership, and how does advance analytics using machine learning, neural networks, and deep learning come into play?

It is now possible to get the real-time insights you need to stay relevant, safe, and effective for today, and tomorrow. With deep expertise and an end-to-end supply chain, Utilities can now design and deliver solutions that deliver meaningful value to ratepayers and are ready to deploy. And with modular high-performance computing (HPC) solutions from exascale to everyscale, Utilities can now make sure that advanced compute power necessary to drive AI is the least of your concerns.

In simple terms, artificial intelligence is the theory and development of computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.

Every Canadian touches or comes in contact with AI every single day, but they rarely are aware of this interaction since the modern AI platforms are so good they defy detection. When you use Amazon, Facebook, chatbots, or even drive your car, you are drawing upon artificial intelligence to assist you.

We are seeing Industry 4.0 technology companies providing AI based solutions that allow Utilities to make the most of the data deluge that results from the digitization of the water sector. Far from replacing human operators, AI is being used to enhance decision-making by extending people’s cognitive powers. Operators are required to make decisions with increasing amounts of complex data inputs. At a minimum, machine learning (ML) enables operators to make informed decisions based on actionable insights. The predictive capabilities of ML are based on processing collected information, learning from the data, and providing possible outcomes. ML technology tackles the predictive and prescriptive phases of AI transformation. The decision-making and action taking is in the hands of human operators who can decide what actions to take based on intelligently repurposed and distilled information.

In the future, we expect full blown automation to be added to the sequence of AI transformation, enabling people to shift into higher value added jobs within Utilities.

AI is currently used in water utilities for intelligent control, process optimization, asset monitoring and proactive management, event detection, and infrastructure planning. Predictive modelling and prescriptive suggestions enables a shift from reactive and static to proactive and dynamic management. Providing operators with AI augmented decision-making for intelligent control of their systems leads to optimized scheduling that can drastically reduce energy costs, chemical inputs, and water use, as well as enable better allocation of staff time.

While AI is used today by only the largest water Utilities, it is now becoming available to every Utility regardless of size. Even unincorporated communities can access affordable AI to help remedy their water distribution issues.

Big Data

“Millions of points of data are being collected every minute about our environment, our economy, and how people interact with their city and surrounding environment, from transportation to water use,” said Mark Fisher, president and chief executive officer of the Council of the Great Lakes Region. “By connecting this data and analyzing it at incredibly fast speeds using smart computing technology, we can generate profound insights about what is happening in our watersheds, now and in the future, that will help governments, businesses, and civil society make better decisions regarding economic development, land use, and protecting the environment.”

Big Data is the ability to process all of the data available and in near real-time. Before big data, we were forced to analyze a statistically significant represented sample of the data set. So, the results were not ideal nor reflective of the actual knowledge and information within the data. Today, we can analyze all of the data. The result is far deeper insights and keener situational awareness of what is happening inside the water distribution systems. From these insights and awareness we can make faster and better decisions. The outcome is a shift from reactive responses to proactive actions to better management of the municipalities water resources.

Elastic Cloud Resources

In future smart water networks, the big data will flow to elastic cloud resources. An elastic cloud solution brings together a variety of cloud-based capabilities to best serve the needs of the water Utility. These resources normally include compute, storage, analytics, and artificial intelligence capabilities. However, these are all available upon demand and scale for the task. If you need a thousand servers to run your invoicing at the end of the month, you simply buy it for the few hours necessary to run the process and then you hand these resources back until the next month. Elastic cloud makes so much economic sense.

These major resources are billed to the Utility based upon consumption of these resources. So, rather than capitalize a private cloud solution owned and operated by the Utility at great expense, the Utility can access key resources when and where they are needed. This dynamic cloud solution can cut costs to the Utility by as much as 50% over owned and operated clouds.

In addition, the burden of running a data centre including the major challenges for cyber security, software patch updates, server break / fix, AC power, cooling, infrastructure, and more, all fall on to a hyper-scale provider who can deliver these underpinning and very costly needs at a fraction of the expense compared to a private cloud.

Now, some Utilities are nervous about placing all of their essential resources in the hands of a third-party, cloud service provider. But, IT departments have been doing this successfully for over ten years already and major cloud service providers like AWS, Google, Microsoft, and IBM can be trusted to deliver robust, backed-up, redundant elastic cloud services.

Data Residency

Where your data is stored is often a regulated attribute that needs to be respected. In Canada today, there are sufficient cloud resources to ensure domestic data residency. Many service providers operate multiple cloud data centres in Canada to ensure that your customer data is not shipped out of the country where you cannot be assured that it is misused or beyond your legal control. It is even possible to keep data resident within the same Province in some, but not all cases. Quebec, Ontario, and British Columbia can all use local resources that are virtualized and redundant today.

Data Privacy

Big data needs to be protected. Utilities have a trusted role with the ratepayers to ensure that the consumers private information is duly protected. A hybrid cloud may be desired to place anonymized data on the public cloud while keeping identifiable data on the private cloud.

Other approaches can work too, such as strong encryption of personal information on the public cloud to ensure that even if an attack happens that this PI is protected and unavailable. It is foolish to assume that there is no risk. There is always risk in all scenarios – private and public – with perhaps far less risk in hyper-scale public cloud compared to municipal owned and operated data centres. A level of healthy paranoia is warranted when it comes to protecting privacy.

Internet of Things

The adoption of cellular technology in water metering solutions is opening the door to new opportunities and greater flexibility for utilities. Most cities — large and small — already have cellular infrastructure in place. By implementing Internet of Things (IoT)-enabled cellular networks, cities can benefit from longer battery lifespan, greater scalability, and increased mobility as well as easier integration of smart sensors for water, parking meters, lights, transportation and more without duplicating infrastructure.

While public wireless networks are beneficial, they are also very expensive to operate. So, private networks are desired to capitalize the network investments, lower operating costs, and to mitigate ROI risks by sharing these private networks with other municipal departments to form a Smart City solution that integrates capabilities and adds intelligence to street lights, waste water, storm sewers, traffic lights, and garbage collection to name but a few.

The major advantage to these new IoT networks is the diversity, volume, and placement of sensors. It is no longer sufficient to place sensors only at the source and the destination – at the water plant and the consumer’s homes. We need sensors throughout the supply chain to monitor the holistic system and to create a comprehensive point of view of the end to end systems.

Smarter solutions, powered by cellular and IoT-based technologies, are rapidly transforming the water metering industry and helping water utilities face the challenges ahead.


Implementing cybersecurity best practices is critical for water and wastewater utilities. Cyber-attacks are a growing threat to critical infrastructure sectors, including water and wastewater systems. Many critical infrastructure facilities have experienced cybersecurity incidents that led to the disruption of a business process or critical operation. The good news is that cybersecurity best practices can be very effective in eliminating the vulnerabilities that cyber-attacks exploit. Implementing a basic cybersecurity program can:

  • Ensure the integrity of process control systems;
  • Protect sensitive utility and customer information;
  • Reduce legal liabilities if customer or employee personal information is stolen; and
  • Maintain customer confidence.

Many water and wastewater utilities, particularly small systems, lack the resources for information technology (IT) and security specialists to assist them with starting a cybersecurity program. Utility personnel may believe that cyber-attacks do not present a risk to their systems or feel that they lack the technical capability to improve their cybersecurity. However, external resources can be relied upon and trusted to deliver superior security protection when applied by the respected hyper-scale cloud providers in Canada, such as AWS, Google, Microsoft Azure, and IBM.

Outsourcing security to a third-party does not release the local Utilities of responsibility for security, the exact opposite is true. Utilities remain steadfastly in control, but now have qualified technical personnel available to help them best manage this ever-present threat to a municipality. Utilities must remain vigilant. It is not a matter of ‘if’ you will get attacked, it is a matter of what you do ‘when’ you are attacked.


The next generation of smart water management will be built upon artificial intelligence, big data, elastic cloud, and the Internet of Things. These emerging technologies are coalescing to bring new capabilities to Utilities of all sizes and scale.

Data residency and data privacy are essential attributes to take full advantage of these new innovations. Placing the ratepayers at the front of mind will ensure a welcome deployment for the next generation of smart water management solutions.

Security must be seamlessly woven into your water management systems at every point. You can be certain that you will be attacked. It is how you respond to these attacks that will determine your risk. By being well prepared and ready for the expected attacks, you can better manage exploits by absorbing, reflecting, or refracting them for minimal affect to your upstream, mid-stream, and downstream systems, and most importantly, your valued customers.

————————–MJM ————————–


Chatta, S. (2019). New Report on Water Management and Big Data Analytics. Water Canada. Retrieved on October 28, 2020 from,

Duffy, D. (2016). Non-Revenue Water Loss: Its Causes and Cures. WaterWorld Magazine, Endeavor Business Media, LLC. Retrieved on October 28, 2020 from,

EPA. (2020). Water Sector Cybersecurity Brief for States. Environmental Protection Agency. Retrieved on October 28, 2020 from,

Unknown. (2020). Four Trends Shaping Water Metering in 2020. Water Finance and Management. Retrieved on October 28, 2020 from,

Unknown. (2020). The new reality of water management: Industry 4.0. iAgua, Smart Water Magazine. Retrieved on October 28, 2020 from,

Weisbord, E. (2019). AI basics for advanced water wise utilities – Part 1. International Water Association. Retrieved on October 28, 2020 from,

————————–MJM ————————–

About the Author:

Michael Martin has more than 35 years of experience in systems design for applications that use broadband networks, optical fibre, wireless, and digital communications technologies. He is a business and technology consultant. He offers his services on a contracting basis. Over the past 15 years with IBM, he has worked in the GBS Global Center of Competency for Energy and Utilities and the GTS Global Center of Excellence for Energy and Utilities. He is a founding partner and President of MICAN Communications and before that was President of Comlink Systems Limited and Ensat Broadcast Services, Inc., both divisions of Cygnal Technologies Corporation (CYN: TSX). Martin currently serves on the Board of Directors for TeraGo Inc (TGO: TSX) and previously served on the Board of Directors for Avante Logixx Inc. (XX: TSX.V).  He has served as a Member, SCC ISO-IEC JTC 1/SC-41 – Internet of Things and related technologies, ISO – International Organization for Standardization, and as a member of the NIST SP 500-325 Fog Computing Conceptual Model, National Institute of Standards and Technology. He served on the Board of Governors of the University of Ontario Institute of Technology (UOIT) [now OntarioTech University] and on the Board of Advisers of five different Colleges in Ontario.  For 16 years he served on the Board of the Society of Motion Picture and Television Engineers (SMPTE), Toronto Section.  He holds three master’s degrees, in business (MBA), communication (MA), and education (MEd). As well, he has three undergraduate diplomas and five certifications in business, computer programming, internetworking, project management, media, photography, and communication technology. He has earned 20 badges in next generation MOOC continuous education in IoT, Cloud, AI and Cognitive systems, Blockchain, Agile, Big Data, Design Thinking, Security, and more.