Prediction study and application of wind power development based on filtering error threshold

Publisher: John Wiley & Sons Inc

E-ISSN: 1944-7450|34|5|1536-1546

ISSN: 1944-7442

Source: ENVIRONMENTAL PROGRESS AND SUSTAINABLE ENERGY, Vol.34, Iss.5, 2015-08, pp. : 1536-1546

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

As a clean and renewable energy source, wind energy has been increasingly gaining global attention. Wind speed forecasting is of great significance for wind energy domain: planning and design of wind farms, wind farm operation control, wind power prediction, power grid operation scheduling, and more. Many wind speed forecasting algorithms have been proposed to improve forecast accuracy. In terms of such factors, in this article, a novel hybrid wind speed forecasting method was proposed based on Kalman filter and Generalized regression neural network as well as the idea of filtering error threshold in data preprocessing. The proposed models can implement long‐term wind speed forecasting with higher precision and reliability compared with single method and conventional approach, as demonstrated by several cases study using daily average wind speed samples collected in western China in a given year. © 2015 American Institute of Chemical Engineers Environ Prog, 34: 1536–1546, 2015