How AI can help meet global energy demand; Verv featured in AI report in The Times
We’re delighted to have been included in Raconteur’s latest report on artificial intelligence, featured in The Times newspaper! The report provides an in-depth look into how AI is penetrating and propelling forward different sectors, driving innovation not previously possible.
In the energy section of the report, artificial intelligence is highlighted as a key driver in enabling the growth of low carbon, green electricity with an absolutely huge potential impact. It’s great to see that industry leading reports like this one align with exactly what we are doing in the energy space! Our VLUX token is the next step in this journey.
You can read more here!
Intrigued as to how we use machine learning and AI within our energy trading platform? Find out more about how our algorithms are designed to optimise energy trading and get consumers the cheapest energy prices….
Advances in machine learning and AI have over the past few years transformed many industries, improving predictive capabilities and providing better models of human behaviour. For example, the development of complex machine learning algorithms has enabled retailers to predict customer activity, understand trends in consumer purchasing behaviour, and adapt advertisements and content for customers’ individual preferences.
Applying AI & machine learning to the energy sector
And we want to apply these advances to the energy sector as well, using AI algorithms to disaggregate electricity data about appliance usage, in turn providing better predictions about energy use behaviour. And it’s this information that will become a critical enabler for energy trading and the balancing of supply and demand of electricity.
Our embedded AI has been designed to build on IoT’s passive sensing and control functionality, through deriving patterns and relationships from multiple datasets, to guide the flow of energy in its most economical (i.e at the best price for the consumer) and sustainable form.
The datasets Verv’s AI hub has been designed to draw from include:
- Granular detail on household electrical activity, both on i) appliances and ii) microgeneration/storage assets (capacity, performance, state of charge).
2. External factors influencing electricity generation or consumption, specifically weather forecast data, geolocation data and satellite data on cloud coverage and opacity.
We’ve designed the system to process these data feeds with neural networks, which are being trained to identify interconnected patterns so that our forecasts for generation, consumption, and battery activity can be continuously improved. The goal of this is the efficient utilisation of electrical infrastructure and a provided assurance that the generated kWhs will be traded at the right time for the best economic return. To achieve this, the Verv home hub has leveraged key developments in machine learning, particularly deep learning.
The Verv home hub’s existing presence in households means that Verv has an extensive dataset of detailed appliance-level energy usage, enabling it to train powerful models of consumption behaviour.
Furthermore, our AI algorithms have been designed to learn not only customers’ electricity consumption behaviour, but also their patterns of engagement with energy trading. Rather than requiring ongoing input and decisions from the user, the algorithms have been designed to learn how the user interacts with the platform to provide a customised experience that ensures long-term, sustainable customer engagement.
