PV Forecasting Using Support Vector Machine Learning in a Big Data Analytics Context
Renewable energy systems (RES) are reliable by nature; the sun and wind are theoretically endless resources. From the beginnings of the power systems, the concern was to know “how much” energy will be generated. Initially, there were voltmeters and power meters; nowadays, there are much more advance...
Gespeichert in:
Veröffentlicht in: | Symmetry (Basel) 2018-12, Vol.10 (12), p.748 |
---|---|
Hauptverfasser: | , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Renewable energy systems (RES) are reliable by nature; the sun and wind are theoretically endless resources. From the beginnings of the power systems, the concern was to know “how much” energy will be generated. Initially, there were voltmeters and power meters; nowadays, there are much more advanced solar controllers, with small displays and built-in modules that handle big data. Usually, large photovoltaic (PV)-battery systems have sophisticated energy management strategies in order to operate unattended. By adding the information collected by sensors managed with powerful technologies such as big data and analytics, the system is able to efficiently react to environmental factors and respond to consumers’ requirements in real time. According to the weather parameters, the output of PV could be symmetric, supplying an asymmetric electricity demand. Thus, a smart adaptive switching module that includes a forecasting component is proposed to improve the symmetry between the PV output and daily load curve. A scaling approach for smaller off-grid systems that provides an accurate forecast of the PV output based on data collected from sensors is developed. The proposed methodology is based on sensor implementation in RES operation and big data technologies are considered for data processing and analytics. In this respect, we analyze data captured from loggers and forecast the PV output with Support Vector Machine (SVM) and linear regression, finding that Root Mean Square Error (RMSE) for prediction is considerably improved when using more parameters in the machine learning process. |
---|---|
ISSN: | 2073-8994 2073-8994 |
DOI: | 10.3390/sym10120748 |