A Parameter Self-Adjusting Optimization Model to Simulate and Forecast Short-Term Wind Speed Based on Least Square Support Vector Machine Regression Algorithm and Parameter Cross Validation Method
Abstract:The wind speed forecast of wind power farms is very important to the power system steady operation, economic load dispatching, operational efficiency and the market competition ability. To forecast the short-term wind speed scientifically and accurately, this paper proposes a novel parameter self-adjusting optimization intelligent model based on least square support vector machine (LS-SVM) regression algorithm and parameter cross validation (PCV) method. The model maps the wind speed sample point to the high dimension characteristics space through the nonlinear transformation, and seeks for the wind speed forecast regression function in the space. This method not only can exert the unique advantages of quick training speed, global convergence and good generalization ability of the LS-SVM, but realize multiparameter union optimization using PCV to improve the LS-SVM regression precision. The 10 minutes later wind speed forecast results based on the actual wind speed sample data show that the model is simple and feasible, and increases the forecast precision and operating speed greatly.
Document Type: Research Article
Publication date: March 1, 2012
More about this publication?
- ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- ingentaconnect is not responsible for the content or availability of external websites