A PSO-SVM-based 24 Hours Power Load Forecasting Model
In order to improve the drawbacks of over-fitting and easily get stuck into local extremes of BACK propagation Neural Network, a new method of combination of wavelet transform and PSO-SVM (Particle Swarm Optimization- Support Vector Machine) power load forecasting model is proposed. By employing wav...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2015-01-01
|
| Series: | MATEC Web of Conferences |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1051/matecconf/20152501008 |
| id |
doaj-bc44b6369e0440a6988592e29facc7a7 |
|---|---|
| record_format |
Article |
| spelling |
doaj-bc44b6369e0440a6988592e29facc7a72021-02-02T00:47:22ZengEDP SciencesMATEC Web of Conferences2261-236X2015-01-01250100810.1051/matecconf/20152501008matecconf_emme2015_01008A PSO-SVM-based 24 Hours Power Load Forecasting ModelYu Xiaoxu0Ji Haisen1State Grid Liaoyang Electric Power Supply CompanyState Grid Liaoyang Electric Power Supply CompanyIn order to improve the drawbacks of over-fitting and easily get stuck into local extremes of BACK propagation Neural Network, a new method of combination of wavelet transform and PSO-SVM (Particle Swarm Optimization- Support Vector Machine) power load forecasting model is proposed. By employing wave-let transform, the authors decompose the time sequences of power load into high-frequency and low-frequency parts, namely the low-frequency part forecast with this model and the high-frequency part forecast with weighted average method. With PSO, which is a heuristic bionic optimization algorithm, the authors figure out the prefer-able parameters of SVM, and the model proposed in this paper is tested to be more accurately to forecast the 24h power load than BP model.http://dx.doi.org/10.1051/matecconf/20152501008wavelet transformparticle swarm optimizationsupport vector machine |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Yu Xiaoxu Ji Haisen |
| spellingShingle |
Yu Xiaoxu Ji Haisen A PSO-SVM-based 24 Hours Power Load Forecasting Model MATEC Web of Conferences wavelet transform particle swarm optimization support vector machine |
| author_facet |
Yu Xiaoxu Ji Haisen |
| author_sort |
Yu Xiaoxu |
| title |
A PSO-SVM-based 24 Hours Power Load Forecasting Model |
| title_short |
A PSO-SVM-based 24 Hours Power Load Forecasting Model |
| title_full |
A PSO-SVM-based 24 Hours Power Load Forecasting Model |
| title_fullStr |
A PSO-SVM-based 24 Hours Power Load Forecasting Model |
| title_full_unstemmed |
A PSO-SVM-based 24 Hours Power Load Forecasting Model |
| title_sort |
pso-svm-based 24 hours power load forecasting model |
| publisher |
EDP Sciences |
| series |
MATEC Web of Conferences |
| issn |
2261-236X |
| publishDate |
2015-01-01 |
| description |
In order to improve the drawbacks of over-fitting and easily get stuck into local extremes of BACK propagation Neural Network, a new method of combination of wavelet transform and PSO-SVM (Particle Swarm Optimization- Support Vector Machine) power load forecasting model is proposed. By employing wave-let transform, the authors decompose the time sequences of power load into high-frequency and low-frequency parts, namely the low-frequency part forecast with this model and the high-frequency part forecast with weighted average method. With PSO, which is a heuristic bionic optimization algorithm, the authors figure out the prefer-able parameters of SVM, and the model proposed in this paper is tested to be more accurately to forecast the 24h power load than BP model. |
| topic |
wavelet transform particle swarm optimization support vector machine |
| url |
http://dx.doi.org/10.1051/matecconf/20152501008 |
| work_keys_str_mv |
AT yuxiaoxu apsosvmbased24hourspowerloadforecastingmodel AT jihaisen apsosvmbased24hourspowerloadforecastingmodel AT yuxiaoxu psosvmbased24hourspowerloadforecastingmodel AT jihaisen psosvmbased24hourspowerloadforecastingmodel |
| _version_ |
1724313078439346176 |