Energy trading, retail and resilience will all be boosted by artificial intelligence, explains Neil Pennington

It is the nature of the human condition that we constantly seek out new ways to make our lives easier and to do things more efficiently. Whether it be the discovery of the wheel or electricity, people across the globe discover, develop and use technology to find new ways of doing things; such things are mostly for good, but can have unintended consequences.

Take for instance the industrial revolution. Delivering rapid advances in efficiency, bringing electricity and heating to common use, and creating new sources of economic value, it also helped widen the gap between rich and poor as well as accelerating our journey to the cliff edge of climate change.

Even now, with absolute knowledge that we need radical change, our inability and inertia to give up fossil fuels and fundamentally redesign the energy system is not helping the fight against runaway climate change.

As an industry, we stand at the edge of another revolution. Sometimes known as the fourth industrial revolution, the advent of technologies such as the Internet of Things (IoT), blockchain, nanotechnology, machine learning and artificial intelligence (AI) are already changing the relationship between human and machine, changing the nature of work and bringing entirely new possibilities that could be as radical as eradicating disease and decarbonising the planet; it is in our hands to make this a force for good.

What do we mean by AI?

Arguably, within the utility industry, the technology creating the most excitement and offering the biggest potential for change is AI.

Artificial intelligence today is properly known as narrow AI (or weak AI), in that it is designed to perform a narrow task (for example, predicting behavioural patterns, facial recognition, internet searches or driving a car).

However, the long-term goal of many researchers is to create general AI (AGI, or strong AI).

While narrow AI may outperform humans at whatever its specific task is, such as playing chess or solving equations, AGI would outperform humans at nearly every cognitive task. Although not yet invented, its advent is hailed as a defining moment for the human race.

What’s in it for utilities?

When we look at the utility sector, there are a number of areas that are being transformed through the application of AI.

Retail: the increasing use of chatbots utilising natural language processing is transforming customer service; machine learning is also being used to understand patterns of customer behaviour, to attract and retain customers and even to predict bill (non)-payment.

At the end of 2018, South Staffs Water announced its intention to use AI in its collections system. AI solutions are also gaining traction within the connected home space with devices such as Amazon’s Alexa, which enable the customer to seamlessly interact with their thermostat and control systems (such as Centrica’s Hive and Google’s Nest).

Energy trading: aggregating platforms such as Origami Energy use machine learning to predict asset availability and market prices in near real time, enabling them to successfully bid into markets such as frequency response.

Operational optimisation: fault prediction and dynamic maintenance is one of the clearest uses of AI, enabling operators to predict equipment failures. It does this by using sensor data from various units, and significantly reduces their costs of downtime and maintenance. Shell (as set out at its site Shell.ai) has developed models for searching and identifying common geological features to help find oil and gas resources quicker than traditional methods.

At the consumer household end of the market, Verv is offering a service through demand disaggregation that identifies individual home appliances to predict faults and create alerts when devices are accidentally left on.

Where AI is perhaps set to make the biggest impact is in the area of mobility and the transactive, decentralised grid of the future.

Google’s self-driving car combines lidar, radar and wheel-based sensors, along with data from cameras and Google street view, to combine real-time data with advanced notice of potential events. Further applied to solving the issue of charging, settlement and interoperability between currently proprietary charging infrastructures, and the management of the decentralised grid of the future, AI combined with other technologies such as blockchain will have game-changing consequences.

Dr Neil Pennington is working with a number of organisations, including Rivetz, DISC, Grid Singularity and the Energy Web Foundation, to develop blockchain and digital identity for use in micropayments, messaging and decentralised energy. He is a former smart programme director and UK innovation director at RWE.

This interview first appeared in Flex, issue 3. Read the full issue of Flex here