Title :
Gas load prediction based on DE-SVM algorithm
Author :
Sun, Yong ; Yang, Guoli ; Wang, Limin ; Shi, Yongjiang ; Yongqiang Wu
Author_Institution :
Dept. of Urban Constr., Hebei Inst. of Archit. & Civil Eng., Zhangjiakou, China
Abstract :
In order to improve the prediction accuracy, in accordance with the influence factors and characteristics of gas load, a model based on SVM (Support Vector Machine) has been established. In order to optimize the behavior of SVM, DE (Differential Evolution) algorithm was introduced into classic SVM. Using the algorithm to predict a real example and compare with SVM model optimization method based on GA (Genetic Algorithm), ACO (Ant Colony Optimization) and POS (Partial Swarm Optimization) demonstrate an improvement of generalization performance.
Keywords :
gas industry; genetic algorithms; particle swarm optimisation; support vector machines; ant colony optimization; differential evolution algorithm; gas load prediction; genetic algorithm; partial swarm optimization; support vector machine; Accuracy; Ant colony optimization; Cities and towns; Civil engineering; Electronic mail; Equations; Optimization methods; Prediction algorithms; Predictive models; Support vector machines; DE; Gas Load; Prediction; SVM;
Conference_Titel :
Future Computer and Communication (ICFCC), 2010 2nd International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5821-9
DOI :
10.1109/ICFCC.2010.5497814
