Grid Raven's management team comes from the Transmission System Operator world. We combine sector know-how with proven competences in machine learning.
Grid Raven's story began when we noticed that renewable energy developers consistently pointed out that they're having difficulty obtaining grid connections. In sunny and windy places the grid is full, yet at the same time neighboring regions continue to burn fossil fuels. The energy transition has barely started, but power grids are already becoming a bottleneck.
We knew that the existing power grid is not used to its maximum potential. It's possible to safely transmit up to one third more power through the existing network by accounting with real-time and forecast conditions along the line.
The insight that prompted us to launch the Grid Raven was that machine learning can be used to predict wind with sufficient accuracy for Dynamic Line Ratings. The key is to predict weather conditions down to the meter-level but at the scale of national power grids. The result is an accurate prediction of line ratings, helping increase grid capacity by 30% globally by 2030.
Previously co-founder and Data Science Lead at Mind Titan, a machine learning agency. Has built over 100 machine learning solutions from the architecture and code down to the physical servers.
Previously Head of the Smart Grid Unit at Elering, Estonia's national grid, and founder of Sympower, a demand response aggregator with over 1.5GW of flexibility in the portfolio.
Previously Digitalisation Team Lead at Elering, responsible among other things for condition assessment of overhead lines, grid modeling and data acquisition. PhD in transmission overhead lines.
We love finding stuff out and to get to the bottom of things. We take ownership for what we do and do things well. We can easily admit mistakes, especially if we can laugh about it.