Earticle

초록

영어

To evaluate short-term power load properly and efficiently, this paper proposes a modified DWT-QDE-LSSVM (Discrete wavelet transform (DWT) and least squares support vector machine (LSSVM) optimized by quantum differential evolution (QDE)) model combined with input selected. The load data series of the previous days are first decomposed into an approximation component and a detail component. Then LSSVM is built to model the approximation component and QDE algorithm is applied to overcome the problems faced by LSSVM in selecting parameters. In order to raise forecasting accuracy, this paper proposes the refinement of related factors. The empirical results show that the proposed DWT-QDE-LSSVM model is feasible and can satisfy the short-term load forecasting requirements in China.

목차

Abstract
 1. Introduction
 2. Methodology
  2.1. Discrete Wavelet Transform
  2.2. Least Squares Support Vector Machine
  2.3. Quantum Differential Evolution
 3. Approaches of DWT-QDE-LSSVM
 4. A Numeric Example and Results
  4.1. Data Preprocessing
  4.2. Selection of Input
  4.3. Statistic Measure to Determine the Accuracy of the Forecast
  4.4. DWT-QDE-LSSVM Results Analysis
  4.5. Comparative Analysis
 5. Conclusions
 References

키워드

저자

• Wei Sun [ Department of Business Administration, North China Electric Power University, China ]
• Jingyi Sun [ Department of Business Administration, North China Electric Power University, China ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Smart Home

• 간기

  격월간

• pISSN

  1975-4094

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605