23 January 2017 Super short term forecasting of photovoltaic power generation output in micro grid
Author Affiliations +
Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103223V (2017) https://doi.org/10.1117/12.2266068
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China
Abstract
The prediction model combining data mining and support vector machine (SVM) was built. Which provide information of photovoltaic (PV) power generation output for economic operation and optimal control of micro gird, and which reduce influence of power system from PV fluctuation. Because of the characteristic which output of PV rely on radiation intensity, ambient temperature, cloudiness, etc., so data mining was brought in. This technology can deal with large amounts of historical data and eliminate superfluous data, by using fuzzy classifier of daily type and grey related degree. The model of SVM was built, which can dock with information from data mining. Based on measured data from a small PV station, the prediction model was tested. The numerical example shows that the prediction model is fast and accurate.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cheng Gong, Longfei Ma, Zhongjun Chi, Baoqun Zhang, Ran Jiao, Bing Yang, Jianshu Chen, Shuang Zeng, "Super short term forecasting of photovoltaic power generation output in micro grid", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103223V (23 January 2017); doi: 10.1117/12.2266068; https://doi.org/10.1117/12.2266068
PROCEEDINGS
7 PAGES


SHARE
Back to Top