多尺度分析与数据互迁移相结合的短期电力负荷预测方法

doi:10.11896／j.issn.1002-137X.2018.07.053

计算机科学 ›› 2018, Vol. 45 ›› Issue (7): 315-321.doi: 10.11896／j.issn.1002-137X.2018.07.053

• 交叉与前沿 • 上一篇

多尺度分析与数据互迁移相结合的短期电力负荷预测方法

刘世昌,金敏

湖南大学信息科学与工程学院长沙410006

收稿日期:2017-05-18 出版日期:2018-07-30 发布日期:2018-07-30
作者简介:刘世昌(1991-),男,硕士生,主要研究方向为电力负荷预测,E-mail:ilscobject@hnu.edu.cn;金敏(1973-),女,博士,教授,主要研究方向为电力负荷预测,E-mail:jinmin@hnu.edu.cn(通信作者)。
基金资助:
本文受国家自然科学基金项目(61374172)资助

Short-term Load Forecasting Method Combining Multi-scale Analysis with Data Co-transfer

LIU Shi-chang, JIN Min

College of Computer Science and Electronic Engineering,Hunan University,Changsha 410006,China

Received:2017-05-18 Online:2018-07-30 Published:2018-07-30

摘要/Abstract

摘要： 为了提升短期电力负荷的预测效果,提出一种多尺度分析与数据互迁移相结合的短期电力负荷预测方法。一方面,针对多尺度分析预测法中分解得到的子序列在建模和预测的过程中没有对原序列中的隐含相关信息加以利用的问题,采用互信息特征选择法选取合适的原负荷序列历史值并将其加入到原负荷序列近似分量的特征集合中,通过特征扩充为学习器提供更多的信息,进而提高近似分量的预测精度。另一方面,针对不同类型的数据在学习过程中会相互影响的问题,采用了一种基于核岭回归的数据互迁移学习方法,将其他几种类型中与待预测类型日相似的数据迁移到待预测类型日的数据中,既利用了这些数据的相似性,又兼顾了这些数据的差异性。测试案例显示,所提方法在MAPE,MAE和RMSE这3个误差评价指标上相对于单模型方法分别降低了6.2%,3.4%和5.5%。

关键词: 短期电力负荷预测, 多尺度分析, 核岭回归, 数据互迁移, 特征扩充

Abstract: In order to improve the performance of short-term load forecasting,this paper proposed a short-term load forecasting method combining multi-scale analysis with data co-transfer.On the one hand,aiming at the problem that the hidden information in the original series which is related to the subseries isn’t fully utilized in the modeling and prediction of subseries in multi-scale analysis forecasting method,this paper used mutual information feature selection method to select appropriate past loads and introduced them into the feature set of the approximation component of original load series.By expanding feature set,more information can be provided for learning algorithm,which can further improve the forecasting accuracy of the approximate component.On the other hand,aiming at the problem thatdifferent kinds of data can influence model’s performance,this paper proposed a transfer learning method based on kernel ridge regression to transfer similar data to data corresponding to days to be forecasted.By doing this,the similarity of these data was used and the difference of these data was taken into account during modeling.Case study shows that the proposed me-thod outperforms in MAPE,MAE and RMSE which are decreased by 6.2%,3.4% and 5.5% respectivelywhen compared with single model forecasting method.

Key words: Data co-transfer, Feature-expanding, Kernel ridge regression, Multi-scale analysis, Short-term load forecasting

中图分类号:

TM734

刘世昌,金敏. 多尺度分析与数据互迁移相结合的短期电力负荷预测方法[J]. 计算机科学, 2018, 45(7): 315-321. https://doi.org/10.11896／j.issn.1002-137X.2018.07.053

LIU Shi-chang, JIN Min. Short-term Load Forecasting Method Combining Multi-scale Analysis with Data Co-transfer[J]. Computer Science, 2018, 45(7): 315-321. https://doi.org/10.11896／j.issn.1002-137X.2018.07.053

参考文献

[1]MALLAT S G.A theory for multiresolution signal decomposition:the wavelet representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693.
[2]MOAZZAMI M,KHODABAKHSHIAN A,HOOSHMAND R.A new hybrid day-ahead peak load forecasting method for Iran’sNational Grid[J].Applied Energy,2013,101:489-501.
[3]GHOFRANI M,GHAYEKHLOO M,ARABALI A,et al.A hybrid short-term load forecasting with a new input selection framework[J].Energy,2015,81:777-786.
[4]LI S,GOEL L,WANG P.An ensemble approach for short-term load forecasting by extreme learning machine[J].Applied Energy,2016,170:22-29.
[5]MASTOROCOSTAS P A,THEOCHARIS J B,BAKIRTZIS A G.Fuzzy modeling for short term load forecasting using the orthogonal least squares method[J].IEEE Transactions on Power Systems,1999,14(1):29-36.
[6]BAKIRTZLS A G,PETRIDLS V,KLARTZIS S J,et al.A neural network short term load forecasting model for the Greek power system[J].IEEE Transactions on Power Systems,1996,11(2):858-863.
[7]MANDAL P,SENJYU T,FUNABASHI T.Neural networks approach to forecast several hour ahead electricity prices and loads in deregulated market[J].Energy Conversion and Mana-gement,2006,47(15-16):2128-2142.
[8]WU C H,TZENG G H,LIN R H.A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J].Expert Systems with Applications,2009,36(3):4725-4735.
[9]DOUAK F,MELGANI F,BENOUDJIT N.Kernel ridge regression with active learning for wind speed prediction[J].Applied Energy,2013,103:328-340.
[10]EXTERKATE P,GROENEN P J F,HEIJ C,et al.Nonlinear forecasting with many predictors using kernel ridge regression[J].International Journal of Forecasting,2016,32(3):736-753.
[11]KIM H H,SWANSON N R.Forecasting financial and macroeconomic variables using data reduction methods:New empirical evidence[J].Journal of Econometrics,2014,178:352-367.
[12]ZHANG Y L,LUO G M.Short term power load prediction with knowledge transfer[J].Information Systems,2015,53:161-169.
[13]KOPRINSKA I,RANA M,AGELIDIS V G.Correlation and instance based feature selection for electricity load forecasting[J].Knowledge-Based Systems,2015,82:29-40.
[14]DAI W,YANG Q,XUE G R,et al.Boosting for transfer lear-ning[C]∥Proceedings of the 24th International Conference on Machine Learning.2007:193-200.
[15]PARDOE D,STONE P.Boosting for Regression Transfer[C]∥Proceedings of the 27th International Conference on Machine Learning (ICML-10).2010:863-870.
[16]REIS A J R,DA SILVA A P A.Feature extraction via multire-solution analysis for short-term load forecasting[J].IEEE Tran-sactions on Power Systems,2005,20(1):189-198.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

多尺度分析与数据互迁移相结合的短期电力负荷预测方法

Short-term Load Forecasting Method Combining Multi-scale Analysis with Data Co-transfer

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	庄世杰, 於志勇, 郭文忠, 黄昉菀. 基于Zoneout的跨尺度循环神经网络及其在短期电力负荷预测中的应用 Short Term Load Forecasting via Zoneout-based Multi-time Scale Recurrent Neural Network 计算机科学, 2020, 47(9): 105-109. https://doi.org/10.11896/jsjkx.190800030
[2]	孟凡喜,屈鸿,侯孟书. 基于GA和SVM的电力负荷预测方法研究 Method of Short-term Load Forecasting Based on GA and SVM 计算机科学, 2014, 41(Z6): 91-93.
[3]	耿佳佳，康晓东，王昊，刘玲玲，郭军. 联合Labor和分形的医学影像图像局部特征描述 Description for Partial Characteristics of Medical Image by Uniting Gabor and Fractal Dimension 计算机科学, 2012, 39(Z11): 381-383.
[4]	王忠林. 基于多尺度句子信息的语义距离计算 Semantic Calculation Framework Based on Multiscale Analysis 计算机科学, 2011, 38(8): 239-241.
[5]	翟俊海，王华超，翟梦尧，王熙照. 基于小波多尺度奇异值分解的人脸识别 Face Recognition Based on Wavelet Multiscale Singular-value Decomposition 计算机科学, 2011, 38(6): 283-285.
[6]	刘光帅，李柏林，何朝明. 离散点云原始形状及边界曲线提取算法 Extracting Methods of Primitive Shapes and Boundary Curves from Scattered Point Set 计算机科学, 2011, 38(5): 279-282.
[7]	杨红菊,张艳,曹付元. 一种基于颜色矩和多尺度纹理特征的彩色图像检索方法 Color Image Retrieval Approach Based on Color Moments and Multi-scale Texture Features 计算机科学, 2009, 36(9): 273-277.