Comparison of widely-used models for multifactoral short-term photovoltaic generation forecast

The paper presents a comparative analysis of three common methods of forecasting time series for short-term forecasting of the generation of photovoltaic power plants with different horizons. The models were built using real data of the photovoltaic power plant and the local meteorological station....

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE 8th International Conference on Energy Smart Systems (ESS) pp. 123 - 126
Main Authors Loskutov, S., Miroshnyk, V., Blinov, I.
Format Conference Proceeding
LanguageEnglish
Published IEEE 12.10.2022
Subjects
gradient boosting
Multilayer perceptrons
neural network
Photovoltaic systems
PVSPP
regression
renewable energy
Sensitivity
Short-term generation forecasting
Temperature distribution
Temperature sensors
Time series analysis
Wind speed
Online AccessGet full text

Cover

More Information
Summary:The paper presents a comparative analysis of three common methods of forecasting time series for short-term forecasting of the generation of photovoltaic power plants with different horizons. The models were built using real data of the photovoltaic power plant and the local meteorological station. Meteorological data include solar irradiation, ambient temperature, humidity, wind speed and cloud cover. The results of the forecast of gradient boosting, elastic regression and multilayer perceptron for horizons 1 and 24 hours were compared. Sensitivity to input factors was investigated using SHAP value.
DOI:10.1109/ESS57819.2022.9969270