基于SVM与相似日的短期电力负荷预测

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (918 KB)
输出: BibTeX | EndNote (RIS)

摘要对受多种不确定性因素影响的短期电力负荷预测,提出了一种基于模糊聚类选取相似日的短期电力负荷预测方法。该方法首先针对气象类型的不确定性因素,将气象因素细分为气温、气压、风速、阴雨等情况,和星期类型、日期类型一起构成相似日的影响因素,通过模糊规则建立模糊系数特征映射表,实现了影响因素的量化。然后再采用模糊聚类方法进行分类,根据聚类水平选取相似日,从而达到减少样本数量,加快选取速度的目的。接着针对获取的相似日负荷数据中含有非高斯噪声的问题,利用小波变换获取其低频分量,从而有效地消除了非高斯噪声的影响。再采用PSO优化的支持向量机实现短期电力负荷低频部分的预测,采用加权平均方法实现高频部分的预测,提高了预测精度。最后利用上海市某电网的负荷数据进行应用研究,不但在平时日,而且在周末和节假日,都取得了较好的预测效果。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	于龙
	郑益慧
	王昕
	李立学
	周荔丹
	陈洪涛

关键词 ：短期电力负荷预测, 模糊聚类, 相似日, 小波变换, 粒子群优化, 支持向量机

Abstract：As to the short-term electric power load forecasting, its accuracy is affected by many uncertain influence factors. To solve this problem, a novel method using Similar Days based on fuzzy clustering analysis was proposed in this paper. Firstly it categorized weather factors as temperature, air pressure, wind speed, overcast and rainy etc, then together with week type and day type they consist of the influence items. According to the items above, fuzzy rules were applied to establish the mapping table to get the factors quantized. Next cluster technology was utilized to classify the content in the mapping table, and the similar days are chosen out based on the clustering level, which is to reduce the numbers of samples and accelerate the speed of selection. Secondly aiming to eliminating non-gaussian noise contained in the similar day’s power load, wavelet transform was adopted to extract the low sequence components. Finally a SVM(Support Vector Machine), which was optimized by PSO(particle swarm optimization)algorithm, was designed to predict the low frequency part, while, mean square weighted method was used to predict the high frequency part. The simulation results show this approach is encouraging.

Key words： keywords：Short-term power load forecasting fuzzy clustering analysis similar days wavelet transform particle swarm optimization support vector machine

收稿日期: 2012-09-20 出版日期: 2013-12-12

PACS:

TM714

作者简介: 于龙男，1986年生，硕士研究生，研究方向为短期电力负荷预测。郑益慧男，1971年生，博士，副教授，研究方向为电力电子装置、电能质量及电工电子技术。

引用本文:

于龙, 郑益慧, 王昕, 李立学, 周荔丹, 陈洪涛. 基于SVM与相似日的短期电力负荷预测[J]. 电工技术学报, 2013, 28(1增): 217-223. Yu Long, Zheng Yihui, Wang Xin, Li Lixue, Zhou Lidan, Chen Hongtao. Short Term Load Forecasting Based on SVM and Similar Days. Transactions of China Electrotechnical Society, 2013, 28(1增): 217-223.

链接本文:

http://dgjsxb.ces-transaction.com/CN/Y2013/V28/I1增/217

[1] 郭创新, 游家训, 彭明伟, 等. 基于面向元件神经网络与模糊积分融合技术的电网故障智能诊断[J]. 电工技术学报, 2010, 9(25): 183-190.
Guo Chuangxin, You Jiaxun, Peng Mingwei, et al . A fault intelligent diagnosis approach based on element-oriented artificial neural networks and fuzzy integral fusion[J]. Transactions of China Eelectrote- chenical Society, 2010, 9(25): 183-190.
[2] 黄南天, 徐殿国, 刘晓胜. 基于S变换与SVM的电能质量复合扰动识别[J]. 电工技术学报, 2011, 10(26): 23-30.
Huang Nantian, Xu Dianguo, Liu Xiaosheng. Identification of power quality complex disturbances based on S-transform and SVM[J]. Transactions of China Eelectrotechnical Society, 2011, 10(26): 23-30.
[3] 谢宏, 魏江平, 刘鹤立. 短期负荷预测中支持向量机模型的参数选取和优化方法[J]. 中国电机工程学报, 2006, 26(22): 17-22.
Xie Hong, Wei Jiangping, Liu Heli. Parameter selection and optimization method of SVM model for short-term load forecasting [J]. Proceedings of the CSEE, 2006, 26(22): 17-22.
[4] 杨毅, 韦钢, 周冰, 等. 基于模糊期望值模型的配电网网架规划[J]. 电工技术学报, 2011, 4(26): 200- 206.
Yang Yi, Wei Gang, Zhou Bing, et al. Distribution network planning based on fuzzy expected value model [J]. Transactions of China Eelectrotechenical Society, 2011, 4(26): 200-206.
[5] 鲁波涌, 黄文清. 结合小波变换和能量算子的电压暂降检测方法[J]. 电工技术学报, 2011, 5(26): 171-177.
Lu Boyong, Huang Wenqing. Hybrid wavelet-energy operator method for voltage sag detection [J]. Transactions of China Eelectrotechenical Society, 2011, 5(26): 171-177.
[6] 谢宏, 陈志业, 牛东晓, 等. 基于小波分解与气象因素影响的电力系统日负荷预测模型研究[J]. 中国电机工程学报, 2001, 21(5): 5-10.
Xie Hong, Chen Zhiye, Niu Dongxiao, et al．The research of daily load forecasting model based on wavelet decomposing and climatic influence [J]. Proceedings of the CSEE, 2001, 21(5): 5-10.
[7] Chen Ying, Luh P B, Guan Che, et al. Short-term load forecasting: similar day-based wavelet neural networks [J]. IEEE Transactions on Power Systems, 2010, 25(1): 322-330.
[8] Mohamed A A, Naresh S K. Short-term load demand modeling and forecasting: a review[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1982, 12(3): 370-382.
[9] 李昌, 罗国阳. 结合支持向量机的卡尔曼预测算法在VRLA蓄电池状态监测中的应用[J]. 电工技术学报, 2011, 11(26): 168-174.
Li Chang, Luo Guoyang. Application of Kalman prediction algorithm combined with SVM in monitoring states of VRLA battery[J]. Transactions of China Eelectrotechenical Society, 2011, 11(26): 168-174.
[10] 金海峰, 熊信艮, 吴耀武. 基于相似性原理的短期负荷预测方法[J]. 电力系统自动化, 2001, 25(23): 45-48.
Jin Haifeng, Xiong Xingen, Wu Yaowu. Short-term load forecasting based on analogous theory [J]. Automation of Electric Power Systems, 2001, 25(23): 45-48.
[11] 莫维仁, 张伯明, 孙宏斌, 等. 短期负荷预测中选择相似日的探讨[J]. 清华大学学报: 自然科学版, 2004, 44(1): 106-109.
Mo Weiren, Zhang Boming, Sun Hongbin, et al. Method to select similar days for short-term load forecasting[J]. Journal of Tsinghua University: Natural Sciences, 2004, 44(1): 106-109.
[12] 刘晶, 朱锋峰, 林辉, 等. 基于相似日负荷修正算法的短期负荷预测[J]. 计算机工程与设计, 2010, 31(6): 1279-1282.
Liu Jing, Zhu Fengfeng, Lin Hui, et al. Short-term load forecasting based on algorithm of similar days’ load modification[J]. Computer Engineering and Design, 2010, 31(6): 1279-1282.
[13] 黎灿兵, 李晓辉, 赵瑞, 等. 电力短期负荷预测相似日选取算法[J]. 电力系统自动化, 2008, 32(9): 69- 73.
Li Canbing, Li Xiaohui, Zhao Rui, et al. A novel algorithm of selecting similar days for short-term power load forecasting[J]. Automation of Electric Power Systems, 2008, 32(9): 69-73.
[14] Tomonobu S, Hitoshi T, Katsumi U, et al. One- hour-ahead load forecasting using neural network[J]. IEEE Transactions on Power Systems, 2002, 17(1): 113-118.
[15] Henrique S H, Charlos E P, Reinaldo C S. Neural networks for short-term load forecasting: a review and evaluation[J]. IEEE Transactions on Power Systems, 2001, 16(1): 44-55.
[16] 史德明, 李林川, 宋建文. 基于灰色预测和神经网络的电力系统负荷预测[J]. 电网技术, 2001, 25(12): 14-17.
Shi Deming, Li Linchuan, Song Jianwen. Power system load forecasting based upon combination of grey forecast and artificial neural network[J]. Power System Technology, 2001, 25(12):14-17.
[17] Amjady N, Keynia F, Zareipour H. Short-term load forecast of microgrids by a new bilevel prediction strategy[J]. IEEE Transactions on Smart Grid, 2010, 1(3): 286-294.
[18] Rejc M, Pantos M. Short-term transmission-loss forecast for the slovenian transmission power system based on a fuzzy-logic decision approach [J]. IEEE Transactions on Power Systems, 2011, 26(3): 1511- 1521.
[19] Shu Fan, Hyndman R J. Short-term load forecasting based on a semi-parametric additive model[J]. IEEE Transactions on Power Systems, 2012, 27(1): 134- 141.
[20] Amjady N, Daraeepour A. Midterm demand prediction of electrical power systems using a new hybrid forecast technique[J]. IEEE Transactions on Power Systems, 2011, 26(2): 755-765.
[21] Amjady N. Short-term bus load forecasting of power systems by a new hybrid method[J]. IEEE Transac- tions on Power Systems, 2007, 22(1): 333-341.
[22] Cadenase, Rivera W. Wind speed forecasting in the south coast of Oaxaca, Mexico[J]. Renewable Energy, 2007, 32(12): 2116-2128.
[23] Mota L T M, Mota A A, Morelato A. Load behaviour prediction under blackout conditions using a fuzzy expert system[J]. IET Generation, Transmission & Distribution, 2007, 1(3): 379-387.
[24] Fan Shu, Chen Luonan, Lee WeiJen, et al. Short- term load forecasting using comprehensive combination based on multimeteorological information[J]. IEEE Transactions on Industry Applications, 2009, 45(4): 1460-1466.
[25] Taylor J W. Short-term load forecasting with exponentially weighted methods[J]. IEEE Transactions on Power Systems, 2012, 27(1): 458- 464.