nabqr: Python package for improving probabilistic forecasts
This work addresses the need for more reliable probabilistic forecasts in renewable energy, specifically for wind power production, and is incremental as it builds on existing methods like LSTM networks and quantile regression.
The paper tackles the problem of improving probabilistic forecasts for wind power production by introducing the NABQR Python package, which corrects ensembles with LSTM networks and applies time-adaptive quantile regression, achieving up to 40% accuracy improvements in mean absolute terms for day-ahead forecasting in Denmark.
We introduce the open-source Python package NABQR: Neural Adaptive Basis for (time-adaptive) Quantile Regression that provides reliable probabilistic forecasts. NABQR corrects ensembles (scenarios) with LSTM networks and then applies time-adaptive quantile regression to the corrected ensembles to obtain improved and more reliable forecasts. With the suggested package, accuracy improvements of up to 40% in mean absolute terms can be achieved in day-ahead forecasting of onshore and offshore wind power production in Denmark.