Dexter Energy: Using AI to optimize the forecast and trade of renewable energy
About Dexter Energy
Dexter Energy was started with the idea of using machine learning to accelerate the transition toward a fully renewable power system. The company now employs 40 people and achieved a turnover of €2.7 million in 2022. In April 2023, it announced a new €10.5M series B investment.
Tell us your challenge. We're here to help.
Contact us
About Xebia
Xebia is an IT Consultancy and Software Development Company that helps the top 250 companies worldwide embrace innovation, adopt the latest technologies, and implement the most successful business models.
This specialist in power forecasting and energy trade optimization for the renewable energy market chose Google Cloud to develop innovative, scalable, high-performance, and easy-to-administer AI models.
Google Cloud results
- Simplified administration and development thanks to managed services, open source software standards, and BigQuery's integrated approach
- Reduced infrastructure and operating costs, thanks to event-driven programming in particular
- Inherent scalability in GKE's combined approach, in terms of serverless computing and the native elasticity of Google Cloud in general
- Performance and reliability in terms of real-time processing on large volumes of data, including through streaming
Making the most of renewable energy with AI
The company is on a mission to help renewable energy companies lead the way toward a cleaner and more affordable energy future by offering AI-powered forecast and trade optimization services for the short-term trading cycle. Notable clients include Greenchoice, Axpo, Giga Storage, and Luminus.
At the core of Dexter Energy's products is its ability to accurately forecast the power generated by renewable assets, such as wind and solar parks, as well as the ability to forecast the electricity prices on short-term energy markets. This is in no way an easy task and requires significant resources, as pointed out by Fons de Leeuw, the company's Principal Engineer.
"In addition to fluctuating production depending on weather conditions, we must take into account a large number of parameters related to demand and the energy market so we can offer green electricity to our customers at the best price."
—Fons de Leeuw, Principal Engineer at Dexter Energy"We have to be able to estimate the production of a wind farm or solar panels in advance. In addition to fluctuating production depending on weather conditions, we must take into account a large number of parameters related to demand and the energy market."
The main challenge is that the energy supply needs to be equal to the energy demand every single moment. And this is made even more complex by the fact that currently, storing large amounts of excess electricity is still very difficult. So, the electricity needs to be consumed instantly. If at any time the power system is not in balance, meaning supply does not equal demand, it can generate overvoltage on the network, leading to power outages.
Analyzing and planning in real time
To help accelerate the energy transition toward a fully renewable power system the company developed a set of algorithms that allow it to accurately predict the volume of generated power as well as the energy price, for the Day Ahead, Intraday, and Imbalance markets.
Founded in 2017, Dexter Energy opted for Google Cloud from the very beginning to ensure it had a scalable infrastructure and innovative solutions at its disposal for implementing its AI-based algorithms and very detailed market analysis. The data comes from just about everywhere: customers, the energy market, weather, producers. A large part is in motion: the data is processed in just-in-time flow (data streaming).
AI-based algorithms and detailed market analysis
The data comes from just about anywhere: customers, the energy market, the weather, producers. A lot of it is dynamic: data is processed on a just-in-time basis (data streaming).
"Overall, we store over 200 terabytes, and process over 2,000 workloads and 250 gigabytes of data daily," explains Danny Bennett, DevOps and MLOps Engineer at Dexter Energy. "The analysis and planning are done in real time. In other words, the slightest latency or malfunction could be catastrophic for our business. So we need reliability, a large processing capacity, and also scalability to cope with possible peaks in traffic."
This infrastructure scalability is all the more important as Dexter Energy has big ambitions when it comes to future growth. Founded in the Netherlands, the company is currently active in The Netherlands, Belgium, and Germany, currently expanding to Italy. In the near future, it is looking to expand to the UK and some other European countries. "And that's just the start!" says Fons de Leeuw.
Developing quickly, easily, and in a scalable way
Opting for a cloud provider with the same, evident commitment to sustainable development was a no-brainer for Dexter Energy. But this was not the only reason for the company's decision. Among its selection criteria, technological synergy clearly played an important role, as Danny Bennett points out. "We share Google Cloud's approach to AI. Google's research in this area is clearly in line with what we are looking to implement. What's more, Google Cloud solutions are known for just how easy they are to familiarize yourself with, especially since they're well documented. These solutions are based on open source software, which is a very important factor for us because it means they rely on standards and tools we enjoy using, while allowing us to remain in control of what we build."
"BigQuery was essentially the 'killer app' for us. It allowed us—and continues to allow us—to store and query large amounts of data quickly and easily."
—Danny Bennett, DevOps and MLOps Engineer at Dexter EnergySo it's no surprise Google Kubernetes Engine (GKE) became one of the technological building blocks that caught Dexter's attention. Goal: to build an intrinsically scalable architecture by capitalizing on GKE's containers and features to simplify and optimize management. The company also uses serverless technologies and event-driven programming to reduce administration requirements and maximize costs. "But if we had to pick just one reason, BigQuery was essentially the 'killer app' for us," says Danny Bennett.
"BigQuery allowed us—and continues to allow us—to store and query large amounts of data quickly and easily. In addition, given the complex balance we're working with, it's clearly a big plus to be able to capitalize on Google Cloud's integrated approach, whether it's storage, analytics, ML, AI, or the acceleration of processing queries in real time for all types of data, without forgetting the scalability and serverless computing that save us time and money, and provides flexibility."
"Another example of open source technology working well with Google Cloud is our use of the TileDB library on top of Google Cloud Storage, this allows us to scale storage of large amounts of historical data with a different use case from BigQuery," adds Fons de Leeuw.
An innovative and highly competitive service
Natively designed around Google Cloud's infrastructure from the outset, Dexter Energy's IT architecture has been constantly improving over the years, making ever more intensive use of GKE and BigQuery. "Between Google Cloud and ourselves, it's more than a question of technology," Fons de Leeuw explains. "We share the same culture with a strong commitment to renewable energy on both sides. From the very beginning, we benefited from Google Cloud's support as well as support from Xebia since 2022, a service provider who guided us through the implementation of our environment."
"Google Cloud, and more specifically its managed services, save us time and money while offering us performance and reliability, two critical factors for a company like ours that does real-time analysis on large volumes of data."
—Fons de Leeuw, Principal Engineer at Dexter EnergyThe combined innovative force of Google Cloud and Dexter Energy has enabled the development of AI models that are so groundbreaking, that they allow energy market suppliers to reduce their balancing costs by up to 35%. Danny Bennett also believes the company has made hugely significant savings in development and operating costs thanks to Google Cloud.
"Since our infrastructure was designed natively in Google Cloud, we obviously don't have a before and after comparison. But my experience at companies with similar requirements before coming to Dexter Energy means I can confidently say the savings are huge, if only down to the many managed services we use. They save us valuable time in terms of development and administration. They also guarantee us flexibility and reliability, which are particularly critical factors for a company that does real-time analysis."
Tell us your challenge. We're here to help.
Contact us
About Dexter Energy
Dexter Energy was started with the idea of using machine learning to accelerate the transition toward a fully renewable power system. The company now employs 40 people and achieved a turnover of €2.7 million in 2022. In April 2023, it announced a new €10.5M series B investment.
About Xebia
Xebia is an IT Consultancy and Software Development Company that helps the top 250 companies worldwide embrace innovation, adopt the latest technologies, and implement the most successful business models.