원문정보
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
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