Unlock instant, AI-driven research and patent intelligence for your innovation.

Fluctuating wind velocity prediction method based on artificial bee colony optimized least square support vector machine (LSSVM)

A technology of artificial bee colony optimization and pulsating wind speed, which is applied to instruments, character and pattern recognition, computer components, etc., can solve the problems of low prediction accuracy and slow convergence speed of LSSVM

Inactive Publication Date: 2016-03-30
SHANGHAI UNIV
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a fluctuating wind speed prediction method based on artificial bee colony optimization LSSVM to solve the problems of low prediction accuracy and slow convergence speed of LSSVM

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fluctuating wind velocity prediction method based on artificial bee colony optimized least square support vector machine (LSSVM)
  • Fluctuating wind velocity prediction method based on artificial bee colony optimized least square support vector machine (LSSVM)
  • Fluctuating wind velocity prediction method based on artificial bee colony optimized least square support vector machine (LSSVM)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The implementation of the present invention will be further described in detail below with reference to the accompanying drawings.

[0054] Artificial Bee Colony (ABC) is a meta-heuristic intelligent algorithm, which is inspired by the foraging behavior of bees to solve numerical optimization problems. ABC is mainly composed of the following three parts: leading bees (EmployedBees), following bees (Onlookers) and scout bees (Scouts). In each cycle, the number of leading bees = the number of following bees = the number of solutions SN in the colony, and the number of scout bees is 1.

[0055] When the ABC algorithm solves the optimization problem, the location of the food source represents a feasible solution to the problem to be optimized, and the process of bees collecting honey is also the process of searching for the optimal solution. In the algorithm, firstly generate SN solutions, and each solution x i (i=1, 2, ... SN) are all D-dimensional vectors. At the begin...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a fluctuating wind velocity prediction method based on an artificial bee colony optimized least square support vector machine (LSSVM). The method comprises the steps of firstly, simulating and generating a fluctuating wind velocity time-histories sample at a vertical space point based on the ARMA numerical-simulation method, dividing the fluctuating wind velocity time-histories sample at the space point into two parts, namely a training set and a testing set, normalizing the two sets respectively, establishing a fluctuating wind velocity prediction model for an LSSVM, and enabling the prediction error of the model to be minimized through figuring out an optimal LSSVM model parameter combination based on the artificial bee colony algorithm. Meanwhile, the root-mean-square error, the coefficient of association, and the number of convergence are adopted as evaluation indexes. Moreover, a result obtained through the above method is compared with a result obtained through the LSSVM and particle swarm (PSO)-optimized PSO-LSSVM data driving technology.

Description

technical field [0001] The invention relates to a data-driven pulsating wind speed prediction method, in particular to a pulsating wind speed prediction method based on artificial bee colony optimization LSSVM (Least Squares Support Vector Machine, least squares support vector machine). Background technique [0002] Support Vector Machine (SVM) is a data-based machine learning algorithm developed based on the principle of VC dimension and structural risk minimization. It has the characteristics of small samples, nonlinearity, high dimension and high prediction accuracy. When dealing with function approximation or prediction problems, SVM describes the problem as a convex optimization problem, based on Mercer's theorem, through nonlinear mapping The input sample points are nonlinearly mapped from the input space to the high-dimensional feature space, and then the loss function is selected, and the minimum value of the loss function is solved in the high-dimensional feature s...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62
CPCG06F18/2411
Inventor 张永康李春祥
Owner SHANGHAI UNIV