Parameters Selection of Twin Support Vector Regression Based on Cloud Particle Swarm Optimization

2020 ◽  
pp. 388-399
Author(s):  
Xiuxi Wei ◽  
Huajuan Huang ◽  
Weidong Tang
Keyword(s):  
Particle Swarm Optimization ◽  
Support Vector Regression ◽  
Particle Swarm ◽  
Support Vector ◽  
Twin Support Vector Regression ◽  
Cloud Particle ◽  
Swarm Optimization ◽  
Parameters Selection ◽  
Selection Of

Particle Swarm Optimization-Enhanced Twin Support Vector Regression for Wind Speed Forecasting

2017 ◽  
Vol 28 (5) ◽  
pp. 905-914 ◽  
Author(s):  
Essam H. Houssein
Keyword(s):  
Particle Swarm Optimization ◽  
Wind Speed ◽  
Support Vector Regression ◽  
Renewable Energy Sources ◽  
Particle Swarm ◽  
Support Vector ◽  
Twin Support Vector Regression ◽  
Swarm Optimization ◽  
Suggested Approach ◽  
Forecasting Accuracy

Abstract Wind energy is considered one of the renewable energy sources that minimize the cost of electricity production. This article proposes a hybrid approach based on particle swarm optimization (PSO) and twin support vector regression (TSVR) for forecasting wind speed (PSO-TSVR). To enhance the forecasting accuracy, TSVR was utilized to forecast the wind speed, and the optimal settings of TSVR parameters were optimized by PSO carefully. Moreover, to estimate the performance of the suggested approach, three wind speed benchmark data of OpenEI were used as a case study. The experimental results revealed that the optimized PSO-TSVR approach is able to forecast wind speed with an accuracy of 98.9%. Further, the PSO-TSVR approach has been compared with two well-known algorithms such as genetic algorithm with TSVR and the native TSVR using radial basis kernel function. The computational results proved that the proposed approach achieved better forecasting accuracy and outperformed the comparison algorithms.

Sign in / Sign up

Export Citation Format

Share Document