Journal of Shanghai University（Natural Science Edition） ›› 2018, Vol. 24 ›› Issue (4): 627-633.doi: 10.12066/j.issn.1007-2861.1819
• Research Articles • Previous Articles Next Articles
XU Yanqin, LI Chunxiang()
Received:
Online:
Published:
Contact:
Abstract:
With linear combination operation on B-spline kernel functions including B1, B3, and B5 and radial basis function (RBF) kernel functions, combined kernel functions (referred to as the B-RBF function) are proposed. Further, least squares support vector machines (LSSVM) using particle swarm optimization (PSO) based B-RBF functions are developed, termed PSO-B-RBF. To predict fluctuating wind velocity, optimization is implemented on penalty parameters and kernel parameters using the PSO algorithm. For comparison, prediction results of PSO-RBF-LSSVM are also taken into consideration. The numerical analyses demonstrate that PSO-B3-RBF-LSSVM has better performance in predicting fluctuating wind velocity with respect to PSO-B1-RBF-LSSVM, PSO-B5-RBF-LSSVM, and PSO-RBF-LSSVM.
Key words: B-spline kernel function, combined kernel function, least squares support vector machine, particle swarm optimization, fluctuating wind velocity
CLC Number:
TU311
XU Yanqin, LI Chunxiang. Predicting fluctuating wind velocity using optimized combined kernel functions based LSSVM[J]. Journal of Shanghai University（Natural Science Edition）, 2018, 24(4): 627-633.
0 / / Recommend
Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks
URL: https://www.journal.shu.edu.cn/EN/10.12066/j.issn.1007-2861.1819
https://www.journal.shu.edu.cn/EN/Y2018/V24/I4/627
Fig. 1
Flow chart of PSO-B-RBF-LSSVM"
Fig. 2
Simulation of fluctuating wind speed time-history series"
Fig. 3
Comparison of forecast wind speed and actual wind speed at 60 m"
Fig. 4
Comparison of forecast wind speed and actual wind speed at 130 m"
Table 1
Prediction performance index of fluctuating wind velocity at 60 m"
Table 2
Prediction performance index of fluctuating wind velocity at 130 m"
)
