Artificial intelligence can provide value to natural gas utilities and customers, a National Association of Regulatory Utility Commissioners (NARUC) primer states.
The primer from the US regulatory non-profit is aimed to improve awareness of artificial intelligence tools and practices, with a focus on the potential to enhance natural gas utility performance.
It zeroes in on the three most common challenges being faced. These are ageing distribution infrastructure, excavator damage to underground infrastructure and customer participation in energy efficiency programmes.
Regarding ageing infrastructure, artificial intelligence can assist in identifying and prioritising repair and replacement programmes. It can also reduce operational and maintenance expenditures by predicting infrastructure that is likely to develop a methane leak.
Traditionally gas utilities have detected leaks using handheld devices, which is slow and prone to error. As an example of the latter, a smart leak detection system has been developed deploying optical sensors to provide images from across the system. Algorithms are able to differentiate between the chemical properties of various hydrocarbons and non-hazardous substances such as puddles of water on the images.
Third-party excavation is the leading cause of damage to gas distribution pipes in the US, causing $1.5 billion in costs to utilities annually. National Grid and NiSource are examples of two northeastern gas distribution utilities that have used predictive analytics to decrease third-party excavation damages by drawing on data including street names, towns, map grids, company names and type of work being performed.
The Gas Technology Institute has developed an excavation notification system that deploys a custom-built device in the cab of construction equipment to alert operators when digging is occurring close to the natural gas system.
Many gas utilities or third parties offer energy efficiency programmes to customers with annual spending on such programmes reaching $1.37 billion in 2017. WGL is an example of a utility that has used artificial intelligence to improve its energy efficiency and awareness programmes.
Southern California Gas is another, reporting savings of 286,540 therms between December 2019 and February 2020 after deploying Bidgely’s AI-driven home energy report programme.
“There are many documented examples of artificial intelligence deployment by electric utilities, but comparatively few resources examining the potential for natural gas utilities,” says NARUC Center for Partnerships & Innovation Director, Danielle Sass Byrnett, of the primer.
The publication also highlights the main artificial intelligence implementation challenges, viz lack of expertise, cost recovery from customers and data governance issues.
“Artificial intelligence has a broad range of current and potential applications for natural gas utilities. However, using these capabilities to provide valuable, actionable insights to utilities and benefit customers requires attention and action from regulators and utilities,” the publication concludes.
Stating artificial intelligence to be “a transformative technology with vast potential in the natural gas industry”, continued communication and collaboration is encouraged among regulators, gas utilities and other stakeholders “to pilot, evaluate and improve the deployment of responsible artificial intelligence innovations for natural gas utilities”.