About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
ECML-PKDD-DCs 2017
Conference paper
Multi-plant photovoltaic energy forecasting challenge with regression tree ensembles and hourly average forecasts
Abstract
In this paper, we present the winning solution to the ECML-PKDD Discovery Challenge 2017 on Multi-Plant Photovoltaic (PV) Energy Forecasting. The goal of the challenge is to utilize the historic data of three different PV plants in Italy regarding meteorological conditions and production in order to forecast their energy production. A major problem is that the data contains many missing value for most sensors and especially for the period of the year for which predictions shall be made in the subsequent year. We investigate two approaches: a regression tree ensemble whose hyperparameters where tuned via Bayesian optimization and a simple rule that just predicts the hourly averages that were observed during the previous year. The latter approach is the winning solution of the challenge.