EU PVSEC Programme Online
EU PVSEC 2021, 6 - 10 September 2021
Presentation: 5BO.7.2 Spatio-Temporal Machine Learning Methods for Multi-Site PV Power Forecasting
Type: Oral
Date: Tuesday, 7th September 2021
10:30 - 12:00
Author(s): R.E. Carrillo Rangel, B. Schubnel, J. Simeunovic, R. Langou, P.-J. Alet
Presenter / Speaker: R.E. Carrillo Rangel, CSEM, Neuchâtel, Switzerland
Event: Conference Conference
Session: 5BO.7 Forecasting Solar Radiation and PV Power
Topic: 5. 1 Solar Resource and Forecasting
Keywords: Solar Radiation, Photovoltaic (PV), Forecasting, Machine Learning
Summary / Abstract: In this paper we present recent advances at CSEM in multi-site PV forecasting that rely entirely on past production data. The presented methods take a graph signal processing perspective and exploit the intuition that a dense network of PV stations provides enough information for short-term prediction horizons (up to six hours ahead) with a high temporal and spatial resolution. The proposed forecasting models are based on recent advances in graph machine learning to capture the spatio-temporal dependencies of the PV production data. The proposed methods were evaluated in two data sets for an entire year: 1) production data from 304 real PV systems, and 2) simulated production of 1000 PV systems, in both cases distributed over Switzerland. The best of the proposed methods achieves a daytime NRMSE (over all sites) of 15.5% for the real data set and 12% for the synthetic data set for 6 hours ahead prediction and 7.5% for the real data set and 3.5% for the synthetic data set for 15 minutes ahead prediction. Furthermore, the proposed nonlinear methods outperform state-of-the-art methods with NWP as inputs on time horizons between 0 h and 5 h.