Three ways energy and utilities organizations can harness the power of AI, ML, and big data – now and in the future

But as these organizations grapple with growing demand, erratic temperatures, aging infrastructure, and the threat of cyberattacks, many struggle to maintain a high level of service in an uncertain and unpredictable landscape.

Artificial intelligence (AI) and machine learning (ML), as powered by big data, have the potential to modernize energy and utilities organizations by identifying ways to reduce waste and redundancy, protect and manage assets, and detect performance anomalies – all while realizing valuable cost savings, both for the organization and the customer. In this blog, we explore the three main areas where AI is making a mark on the energy and utilities sector today and how such investments may impact the future.

Reducing waste and redundancy

Today: Pinpointing leaks to save time, money, and natural resources

Each year in the U.S. alone, trillions of gallons of water are lost due to aging pipes, broken water mains, and faulty meters. Replacing the entire system would be massively expensive, time-consuming, and impractical, which means that utility companies must take a localized approach to repairs. However, doing so may prove difficult as utilities have millions upon millions of miles of pipes and mains to consider.

This complex problem has resulted in many solutions. For example, in the UK, one water company uses sniffer dogs that can smell chlorine to detect leaks. Increasingly, however, companies are turning to more technological leak-detection tools, such as the SmartBall, which can be deployed to identify pipeline leaks along with advanced acoustic technology and hydroponic sensors. Similarly, a team at the Massachusetts Institute of Technology (MIT) recently developed a robotic solution that is capable of detecting small variations in water pressure as the device contracts and expands to the size of the pipe.

Capgemini has applied a wide variety of solutions, including AI and ML techniques, to solve the leakage problem. These AI-enabled solutions can help water companies detect and identify the source of leaks faster and with more accuracy than traditional methods by leveraging the data they own. For example, one client, a leading water company in the UK, was able to detect leaks at least 15 days sooner and locate them 60 percent faster using AI and ML as compared to existing tools and processes. Importantly, these tools don’t just translate into time and money, but also into the  conservation of valuable natural resources.

Tomorrow: Taking a proactive approach to system upgrades and repairs

Looking to the future, water companies can deploy AI and ML solutions to help plan main replacement activities by identifying and replacing assets that have a higher propensity to fail. These systems can also provide a higher level of situational awareness in network planning to help mitigate the risk of extreme weather conditions, fluctuations in demand, and even cyberattacks.

Protecting and managing assets

Today: Using data and imagery to predict network failures and avoid customer interruptions

Because outages can be caused by any number of factors – from equipment failure to severe storms to squirrels – they can be hard to predict and expensive to prevent. The good news is that utilities have meticulously gathered outage data over the years. The even better news is that AI and ML can help turn that information into actionable insights that can help predict network failures, plan timely interventions, and avoid customer interruptions.

For example, one client, an electricity operator in Australia, uses computer vision and AI techniques to analyze a photos and historical data taken during inspections to predict failure of components such as link boxes and circuit breakers [based on their age, surrounding location, and signs of damage or decay]. Another electricity distribution operator in Canada analyses satellite imagery, weather data, and light detection and ranging (LIDAR) data to calculate the risk posed by vegetation growing near power lines and to conduct early intervention, such as tree trimming.

Tomorrow: Enabling automation to avoid outages and promote self-healing capabilities

In April, the US Department of Energy (DOE) announced a $20 million R&D investment for AI and ML in the energy sector. The goal of this program is to develop faster grid analytics and modeling, better grid asset management, and sub-second automatic control actions that will help system operators avoid grid outages, improve operations, and reduce costs. In addition, many organizations are working on applications that will improve the grid’s self-healing capabilities. While these capabilities will be instrumental in increasing overall reliability, its true value may rest in the ability to detect and respond to cyberattacks quickly.

Customer service

Today: Leveraging conversational AI to improve customer service speed, accuracy, and efficiency

Like most organizations, utility providers struggle to provide high-quality customer service. However, utilities may have an advantage in developing a solution. Unlike retail or healthcare providers, utility customers typically call service lines for a very limited number of reasons, the most common being to report an outage or dispute a bill. This relatively short list of requests puts utilities in a prime position to automate their customer service function.

For example, one popular scenario we’ve seen among companies is the use of conversational AI or chatbots to navigate common customer queries. When a customer visits the FAQ section of the website, a chat window opens automatically and prompts the user to type a question. The AI-enabled tool then finds and shares the answer based on existing content or directs the request to another resource. These conversational AI applications significantly reduce the cost of customer service for organizations by reducing the need for call centers or other service stations. In addition, the quality of service is much improved for the user, often resulting in faster, more accurate information and, by extension, a better customer experience.

Another valuable use for AI in customer service is improving compliance and quality assurance in call centers. For example, our company worked with a large telco to build an AI solution that measures the compliance of unscripted and natural customer interaction based on 238 features and one million sample calls. This has improved the customer experience substantially by standardizing answers to common questions, anticipating customer issues and reactions, and identifying training opportunities for employees.

Tomorrow: Integrating the customer experience to improve connectivity for all customers

Looking to the future, utility customers can leverage third-party voice assistants such as Siri and Alexa to get information about their accounts, track their balance, and troubleshoot common issues. These applications may be particularly helpful for niche customer groups, including hearing or visually impaired, people with disabilities, those who are homebound, or the elderly.

While the value of AI and ML is clear, most energy and utilities organizations have yet to tap into its full potential. Our recent research, Intelligent Automation in Energy and Utilities: The next digital wave, revealed that only 15 percent of energy and utilities organizations have deployed multiple automation use cases at scale. What’s more, our research also found that the sector can save up to $813 billion from intelligent automation at scale. That’s a powerful consideration for today – with a huge implications for tomorrow.

To learn how we can help you with your Intelligent Automation journey, do not hesitate to reach out to me directly.