Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting
| Autor: | Christos K. Simoglou, G. I. Chouliaras, Evaggelos G. Kardakos, Anastasios G. Bakirtzis, Stylianos I. Vagropoulos |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Engineering
Artificial neural network Mean squared error Pv generation business.industry 020209 energy Photovoltaic system Weather forecasting 02 engineering and technology computer.software_genre Term (time) 0202 electrical engineering electronic engineering information engineering Econometrics Autoregressive integrated moving average Time series business computer |
| Zdroj: | 2016 IEEE International Energy Conference (ENERGYCON). |
| DOI: | 10.1109/energycon.2016.7514029 |
| Popis: | This paper compares four practical methods for electricity generation forecasting of grid-connected Photovoltaic (PV) plants, namely Seasonal Autoregressive Integrated Moving Average (SARIMA) modeling, SARIMAX modeling (SARIMA modeling with exogenous factor), modified SARIMA modeling, as a result of an a posteriori modification of the SARIMA model, and ANN-based modeling. Interesting results regarding the necessity and the advantages of using exogenous factors in a time series model are concluded from this comparison. Finally, intra-day forecasts updates are implemented to evaluate the forecasting errors of the SARIMA and the SARIMAX models. Their comparison highlights differences in accuracy between the two models. All models are compared in terms of the Normalized (with respect to the PV installed capacity) Root Mean Square Error (NRMSE) criterion. Simulation results from the application of the forecasting models in a PV plant in Greece using real-world data are presented. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|