A distributed big data storage and data mining framework for solar-generated electricity quantity forecasting

Jianzong Wang; Yanjun Chen; Rui Hua; Peng Wang; Jia Fu

doi:10.1117/12.919640

22 February 2012 A distributed big data storage and data mining framework for solar-generated electricity quantity forecasting

Jianzong Wang, Yanjun Chen, Rui Hua, Peng Wang, Jia Fu

Author Affiliations +

Proceedings Volume 8333, Photonics and Optoelectronics Meetings (POEM) 2011: Optoelectronic Devices and Integration; 83330S (2012) https://doi.org/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.

Citation Download Citation

Jianzong Wang, Yanjun Chen, Rui Hua, Peng Wang, and 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); https://doi.org/10.1117/12.919640

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available