Short Term Load Forecasting Using A Hybrid Model Based On Support Vector Regression
Journal: International Journal of Scientific & Technology Research (Vol.4, No. 5)Publication Date: 2015-05-15
Authors : Aliasghar Baziar; Abdollah Kavousi-Fard;
Page : 189-195
Keywords : Index Terms Support Vector Regression SVM; Krill Herd KH Algorithm; Short Term Load Forecasting STLF.;
Abstract
Abstract This paper proposes a new hybrid method based on support vector regression SVR to predict the load value of power systems accurately. The proposed method will use the SVR to overcome some deficiencies such as overfitting and complicated structure that exist in the neural network. In order to find the optimal values of the parameters krill herd KH algorithm is used as the optimizer. The KH algorithm can explore the problem search space for reaching the best structure for the SVR when training. In order to check the performance and accuracy of the proposed hybrid method the empirical load data from the Fars Regional Company are used as the test data. The simulations show the high reliable and accuracy of the proposed method.
Other Latest Articles
- Strategic Planning And Performance Of Commercial Banks In Nigeria
- Estimating Energy Conservation Potential Of Local Metal Casting Units In Uganda Using Data Envelopment Analysis
- An Integrated Framework Of Web 2.0 Technology And A Collaborative Learning
- Mycoflora Of Barley Hordeum Vulgare L. At Different Locations In Hail Area- Saudi Arabia
- New Concept For Calculating The Age Of A Fossil Bone By Uranium-Series Method
Last modified: 2015-06-28 04:10:46