刘文博;傅旭华;王蕾;黄民翔;叶承晋;

• 1:浙江大学电气工程学院
• 2:国网浙江省电力公司经济技术研究院

摘要(Abstract)：

针对传统小波神经网络(wavelet neural network,WNN)应用于电力负荷预测时,存在网络组件无法对小波高频信号分量进行有效处理的问题,提出一种针对电力负荷高频信号的无迹卡尔曼滤波(unscented kalman filter,UKF)多频级WNN区间预测算法。首先,给定高频分量信号阈值,对三通道滤波器获取的中频信号分量进行深度划分,并利用UKF算法的无迹变换,获取电力信号高频小波分量均值产生的sigma特征点,将其作为神经网络输入进行训练和预测;其次,针对WNN输出低频信号分量方差的预测输出增量变换问题,利用区间预测估计算法实现高、低频方差预测输出融合,并作为网络输出评价指标;最后,通过实验对所提算法进行有效性验证,并给出高频信号分量阈值选取实验结果,为高频阈值选取提供依据。

关键词(KeyWords)： 电力负荷;无迹卡尔曼滤波;阈值;小波神经网络;区间预估

Abstract:

Keywords:

基金项目(Foundation): 国家电网公司科技项目(5211JY150016)~~

作者(Author): 刘文博;傅旭华;王蕾;黄民翔;叶承晋;

Email:

DOI: 10.13335/j.1000-3673.pst.2016.02.028

参考文献(References)：

• [1]Garulli A,Paoletti S,Vicino A.Models and techniques for electric load forecasting in the presence of demand re-sponse[J].IEEE Transactions on Control Systems Tech-nology,2015,23(3):1087-1097.
• [2]何永秀,陶卫君,杨卫红.基于解释结构模型的城市电力负荷预测[J].电力系统自动化,2009,33(20):37-42.He Yongxiu,Tao Weijun,Yang Weihong.Urban power load forecasting based on an interpretative structural model[J].Automation of Electric Power Systems,2009,33(20):37-42(in Chinese).
• [3]计鹿飞,江琦,唐昊.基于半马尔可夫控制过程的智能电网最优储能控制[J].电力系统自动化,2015,39(6):24-27.Ji Lufei,Jiang Qi,Tang Hao.Optimal energy storage control for smart grid based on semi-markov control processes[J].Automation of Electric Power Systems,2015,39(6):24-27(in Chinese).
• [4]万昆,柳瑞禹.区间时间序列向量自回归模型在电力负荷预测中的应用[J].电网技术,2012,36(11):77-81.Wan Kun,Liu Ruiyu.Application of interval time-series vector autoregressive model in short-term load forecasting[J].Power System Technology,2012,36(11):77-81(in Chinese).
• [5]He Yongxiu,He Haiying,Wang Yuejin.Forecasting model of residential load based on general regression neural net-work and PSO-Bayes least squares support vector ma-chine[J].Journal of Central South University of Technol-ogy,2011,18(4):1184-1192.
• [6]Ballini R,Yager R R.OWA filters and forecasting models applied to electric power load time series[J].Evolving Systems,2014,5(3):159-173.
• [7]Kab J H,Gwang W K.A short-term load forecasting expert system[J].IEEE Information Systems and Technologies,2001,17(4):112-116.
• [8]庞清乐.基于粗糙集理论的神经网络预测算法及其在短期负荷预测中的应用[J].电网技术,2010,34(12):168-173.Pang Qingle.A rough set based neuralnetwork load forecasting algorithm and its applicationin short-term load forecasting[J].Power System Technology,2010,34(12):168-173(in Chinese).
• [9]邰能灵,侯志俭,李涛.基于小波分析的电力系统短期负荷预测方法[J].中国电机工程学报,2003,23(1):45-50.Tai Nengling,Hou Zhijian,Li Tao.New principle based on wavelet transform for power system short-term load forecasting[J].Proceedings of the CSEE,2003,23(1):45-50(in Chinese).
• [10]葛少云,贾鸥莎,刘洪.基于遗传灰色神经网络模型的实时电价条件下电力负荷预测[J].电网技术,2012,36(1):224-229.Ge Shaoyun,Jia Ousha,Liu Hong.A gray neural network model improved by genetic algorithm for short-term load forecasting in price-sensitive environment[J].Power System Technology,2012,36(1):224-229(in Chinese).
• [11]Guan C,Laurent D M,Wang Y T.Very short-term load forecasting:wavelet neural networks with data pre-filtering[J].IEEE Transactions on Power System,2013,28(1):30-38.
• [12]Benaouda D,Murtagh F,Starck J L.Wavelet-based nonlinear multi-scale decomposition model for electricity load forecasting[J].Neurocomputing,2006,70(3):139-154.
• [13]Chen Y,Luh P B.Short-term load forecasting:similar day-based wavelet neural networks[J].IEEE Transactions on Power System,2010,25(1):322-330.
• [14]Farzad G J,Mohammad B,Ro-gayeh B.Erratum to:investigation of com-muting hamiltonian in quantum markov network[J].International Journal of Theoretical Physics,2014,53(12):4421-4430.
• [15]Yacine C,Patrick P,Lamine M.Electric load forecasting based on statistical robust methods[J].IEEE Transactions on Power System,2011,26(3):982-992.