Imbalance Price Forecasting in Belgium under the European Balancing Platform

Abstract

This research work describes the development and application of several forecasting techniques to try to predict the belgian imbalance price. The imbalance price is a price that gets applied to certain large actors of the power grid when they are not consuming or producing the expected amount of power. Since this price gets settled ex post when the overall grid imbalance is known, grid actors can benefit from predicting it. This way they can make adjustements before the price gets settled. This is done using machine learning and other forecasting techniques. By design, ELIA, the Belgian transmission system operator wants these actors to adjust their positions to help balance the grid. The problem is that the European Union imposed to its members to join their common balancing platforms. These platforms allow countries to work together when it comes to balancing but this adds a layer of complexity for balancing and also forecasting the imbalance price. The objectives of this work are to see how the regulation changes affect the forecasts and to develop an algorithm that works with these new platforms. To do this, thorough research on the new platforms was done to understand how they work, what they bring and what they will impact. The literature of imbalance price forecasting and surrounding domains was also reviewed. Then, with the help of Flexide’s expertise, the development of forecasting methods began by selecting features in the data, comparing algorithm performances and finally selecting the XGBoost tree ensemble method in the end. This method was then further tuned with different approaches. Finally, the results are presented using a battery simulation that charges and discharges depending on the predicted imbalance price. This gives a first idea of the gains achievable by forecasting. The methods developed in this work managed to slightly outperform the benchmark method that was previously used by Flexide. In conclusion, forecasting the imbalance price may seem like it comes down to predicting chaos at first, but in the right context, forecasts have proven to be good enough to be useful and they are a key to improving the grid balance in the future.