State-of-the-art forecasting systems are often based on single machine learning models that have been trained for individual wind farms. The data of a each wind farm is typically used exclusively for its ”own” model. This article presents two approaches with deep neural networks to make the data usable across wind farms with transfer learning. In the first case, the adaptation to individual wind farms is achieved by an separate output layer for each wind farm. With the second approach, a Bayesian wind farm embedding is proposed. An experiment with realistic forecast conditions based on power measurements and weather forecasts of 19 wind farms is carried out. The proposed techniques are compared to established single wind farm models such as random forests, gradient boosted regression trees, and simple multi layer perceptrons. Our results indicate that a significant improvement in prediction quality can be achieved using multi-task learning, especially with a short time span of historical training data.
In order to reduce the dependence on fuel imports as well as CO2-emissions, islands are switching from diesel to renewable generation. Energy storage systems are used to avoid curtailment of the renewable generation as well as to reduce cycling of the diesel generator. This paper evaluates the operation of a modular, low temperature adiabatic compressed air system (KompEx LTA-CAES ®) on El Hierro using mixed integer linear programming. Optimal dimensions for charging power and storage capacity are determined and a sensitivity analysis concerning fuel prices and storage efﬁciency is presented. The economic situation is assessed for the KompEx LTA-CAES as well as for the existing pumped hydro storage.