When Smart Meters Become Detectives: Putting an End to Energy Theft

In its AMI global forecast 2020-2025, Wood Mackenzie Power & Renewables Energy Research predicts that 1.3 billion smart meters will be installed globally by 2025. Those billions of smart meters are producing trillions of granular data points that the energy providers we work with around the world are leveraging to realize meaningful ROI. The value of AMI data spans business units and strategic imperatives, including accelerating transportation electrification, improving customer engagement, advancing decarbonisation and enabling bottom-up grid planning for greater resiliency and reliability.

This week, I’ve been on the ground working with utilities in India. In India alone, they are targeting 250M smart meters and a myriad of use cases around EV and electrification, grid modernisation and personalised customer experience. But by far, the biggest business case for smart meter adoption is revenue protection. The idea of leveraging customer energy use data to improve collections is obvious. But what is more exciting to energy providers is the potential to curb energy theft.??

It is estimated that $80 to $100 billion is lost globally to energy theft each year.?

Beyond the substantial economic impact, theft impacts grid reliability by manipulating local area supply, which can lead to transformer overloading, blackouts, damage to utility assets, poor customer experience and safety vulnerabilities.

Historically, theft countermeasures have relied largely upon labour-intensive premises inspections and account auditing — even for tamper alerts originating from meter hardware. For example, an energy provider might measure the amount of power travelling through low voltage transformers at the neighborhood level and subtract the combined energy usage for all customers served by that transformer to identify a subset of customers — perhaps 200 homes — within which theft might be occurring. Beyond that, there has been no consistently accurate means to pinpoint exactly which of those 200 customers are bad actors.?

Until now, of course.?

We’re here in India talking with utilities about how they can apply AI-powered analytics to smart meter data for a much more effective approach. Rather than pursue theft only at the transformer level, Bidgely’s patented AI technology makes it possible for them to conduct theft analysis home-by-home, at the appliance level. Anomalies in appliance-level consumption patterns accurately reveal theft via meter bypassing, meter tampering, tariff misuse and more.

AI-enabled data science can, like a detective, provide a clear, data-driven picture of exactly what is happening, and empower utilities with better intelligence that they can use to take more effective action.?

Accurately Detecting and Categorizing Theft

By analysing historical AMI data and correlating it with external factors like weather, AI-derived occupancy, and appliance/lifestyle profiling, it is possible to identify consumption-related anomalies that signal theft has or is occurring.

For example, in the case of meter tampering in which electricity thieves take steps to prevent energy consumption from being recorded, AI algorithms leverage energy consumption patterns, technical parameters of phase currents, neutral currents, voltages, power factors and available smart meter events to identify where and how meter tampering is most likely to have taken place. Tampering patterns include notable drops in consumption with corresponding electric anomalies.

When it comes to direct theft in which a consumer bypasses the meter using an illegal connection mechanism, consumption patterns might flag such anomalies as when there is a change in outside temperature but no corresponding change in electrical use — i.e. when a heat wave occurs but there is no increase in cooling-related electrical use. Analysis also looks at characteristic energy use for all homes with similar sanctioned/connected loads to identify significant outlier homes.

To flag tariff misuse, because smart meter data analytics isolate appliance-level signatures, it is possible to accurately distinguish between residential appliance behaviour and commercial appliance behaviour and identify patterns indicative of commercial activity on a residential tariff.?

Strategically Target Bad Actors

Beyond smart theft detection, our advanced data science is able to categorise theft incidents and bad actors as high, medium or low probability and estimate how much energy loss occurred during an anomaly period. Analytics also reveal the duration of theft activity and how many times the behaviour was repeated – information a theft inspector cannot determine in a visit to a tampering site. This loss analysis enables utilities to focus mitigation efforts on the most significant violators to ensure the highest possible return on investment. High probability and high value cases can be prioritised for immediate action, and energy providers are able to proceed with greater confidence before engaging with customers over potential theft claims.

Looking Forward

It’s been incredibly exciting to engage with utilities here in India and explore all the ways Bidgely’s?Energy Theft Detection Solution can equip energy providers with precise tools to discover, understand, and remedy theft quickly.

Looking ahead, Bidgely has been selected by REC Ltd., a CPSE under MoP, GoI to participate in Ministry of Power, GoI Technology Incubation Challenge Powerthon 2022, which was organised in collaboration with SINE incubation lab of IIT Bombay. Our category is AI/ML based data analytics of consumer power consumption/ behaviour and detection of theft for energy in support of the National Revamped Distribution Sector Scheme (RDSS) to reduce losses of State DISCOMs in India to 12-15% by 2025.

Through this challenge, we will engage in a 4-month theft detection effort with a state utility to further demonstrate how AI-enabled data analytics can detect and resolve India’s energy misuse issues. At the same time, we’re working with a large utility in central India – in collaboration with the World Bank – to further prove theft detection analytics use cases.

With billions of dollars and long-term grid reliability at stake, it’s energising to be delivering a future-ready solution not only for India – but also much more of the South Asian, Middle East and African world.?

To learn more about Bidgely’s Energy Theft Solution for detecting energy misuse, visit?bidgely.com/solutions/energy-theft-detection.