22 February 2012 A distributed big data storage and data mining framework for solar-generated electricity quantity forecasting
Author Affiliations +
Proceedings Volume 8333, Photonics and Optoelectronics Meetings (POEM) 2011: Optoelectronic Devices and Integration; 83330S (2012); doi: 10.1117/12.919640
Event: Photonics and Optoelectronics Meetings 2011, 2011, Wuhan, China
Abstract
Photovoltaic is a method of generating electrical power by converting solar radiation into direct current electricity using semiconductors that exhibit the photovoltaic effect. Photovoltaic power generation employs solar panels composed of a number of solar cells containing a photovoltaic material. Due to the growing demand for renewable energy sources, the manufacturing of solar cells and photovoltaic arrays has advanced considerably in recent years. Solar photovoltaics are growing rapidly, albeit from a small base, to a total global capacity of 40,000 MW at the end of 2010. More than 100 countries use solar photovoltaics. Driven by advances in technology and increases in manufacturing scale and sophistication, the cost of photovoltaic has declined steadily since the first solar cells were manufactured. Net metering and financial incentives, such as preferential feed-in tariffs for solar-generated electricity; have supported solar photovoltaics installations in many countries. However, the power that generated by solar photovoltaics is affected by the weather and other natural factors dramatically. To predict the photovoltaic energy accurately is of importance for the entire power intelligent dispatch in order to reduce the energy dissipation and maintain the security of power grid. In this paper, we have proposed a big data system--the Solar Photovoltaic Power Forecasting System, called SPPFS to calculate and predict the power according the real-time conditions. In this system, we utilized the distributed mixed database to speed up the rate of collecting, storing and analysis the meteorological data. In order to improve the accuracy of power prediction, the given neural network algorithm has been imported into SPPFS.By adopting abundant experiments, we shows that the framework can provide higher forecast accuracy-error rate less than 15% and obtain low latency of computing by deploying the mixed distributed database architecture for solar-generated electricity.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianzong Wang, Yanjun Chen, Rui Hua, Peng Wang, Jia Fu, "A distributed big data storage and data mining framework for solar-generated electricity quantity forecasting", Proc. SPIE 8333, Photonics and Optoelectronics Meetings (POEM) 2011: Optoelectronic Devices and Integration, 83330S (22 February 2012); doi: 10.1117/12.919640; https://doi.org/10.1117/12.919640
PROCEEDINGS
7 PAGES


SHARE
KEYWORDS
Photovoltaics

Data storage

Solar cells

Databases

Data mining

Neural networks

Solar energy

RELATED CONTENT

Embedded digital oilfield model
Proceedings of SPIE (October 05 2017)
A data mining algorithm based on the rough sets theory...
Proceedings of SPIE (December 02 2005)
Manufacturing Experience With GaAs Solar Cells
Proceedings of SPIE (November 20 1986)
A fuzzy neural network for intelligent data processing
Proceedings of SPIE (March 28 2005)

Back to Top