基于相空间重构和随机配置网络的电力负荷短期预测

doi:10.12204/j.issn.1000-7229.2021.09.013

电力建设 ›› 2021, Vol. 42 ›› Issue (9): 120-128.doi: 10.12204/j.issn.1000-7229.2021.09.013

基于相空间重构和随机配置网络的电力负荷短期预测

赵允文¹^,², 李鹏¹^,², 孙煜皓³, 沈鑫⁴, 杨晓华⁴

1.云南大学信息学院,昆明市 650500
2.云南省高校物联网技术及应用重点实验室,昆明市 650500
3.中科智能(深圳)科技有限公司,广东省深圳市 518000
4.云南电网有限责任公司,昆明市 650217

收稿日期:2020-12-16 出版日期:2021-09-01 发布日期:2021-09-02
通讯作者: 李鹏
作者简介:赵允文(1997),男,硕士研究生,从事电力大数据分析与建模、智能信息处理研究工作|孙煜皓(1985),男,博士,硕士生导师,从事窄带电力线通讯能耗优化、电力线通讯系统组建、电力线信道估计研究工作|沈鑫(1981),男,博士,教授级高级工程师,从事智能配电网、计量自动化研究工作|杨晓华(1988),男,工学学士,工程师,从事电力计量技术研究工作。
基金资助:
国家自然科学基金项目(61763049);云南省应用基础研究计划重点项目(2018FA032)

Short-Term Power Load Forecasting Based on Phase Space Reconstruction and Stochastic Configuration Networks

ZHAO Yunwen¹^,², LI Peng¹^,², SUN Yuhao³, SHEN Xin⁴, YANG Xiaohua⁴

1. School of Information, Yunnan University, Kunming 650500, China
2. Internet of Things Technology and Application Key Laboratory of Universities in Yunnan, Kunming 650500, China
3. CTC Intelligence (Shenzhen) Tech Co., Ltd., Shenzhen 518000, Guangdong Province, China
4. Yunnan Power Grid Co., Ltd., Kunming 650217, China

Received:2020-12-16 Online:2021-09-01 Published:2021-09-02
Contact: LI Peng
Supported by:
National Natural Science Foundation of China(61763049)

摘要/Abstract

摘要：

针对配电网负荷随时间空间变化的非线性特征导致短期负荷预测精度低和模型训练时间成本高的问题,设计了一种基于相空间重构(phase space reconstruction, PSR)和随机配置网络(stochastic configuration networks, SCN)的电力负荷短期预测模型。首先将配电网数据中与负荷相关的气象数据通过主元分析法(principal component analysis, PCA)进行数据降维,并与负荷序列组合成多变量的时间序列,运用混沌时间序列理论,通过互信息法和虚假近邻法求取参数并重构相空间,最后使用随机配置网络预测电力负荷。采用欧洲电网公开数据集的历史负荷和气象数据验证所提方法,结果表明,与网格搜索法优化的支持向量机(support vector machines, SVM)、反向传播神经网络(back propagation neural networks, BP)、长短期记忆网络(long short-term memory network, LSTM)和整合移动平均自回归(autoregressive integrated moving average, ARIMA)相比,所设计方法具有智能化水平高、运算高效的特点,有一定的实用价值。

关键词: 配电网, 短期负荷预测, 相空间重构(PSR), 主元分析法(PCA), 随机配置网络(SCN)

Abstract:

Aiming at the problem of the non-linear characteristics of the distribution network load changing with time and space, the short-term load forecasting accuracy is insufficient and the model training time cost is high. In this paper, a short-term load forecasting model based on phase space reconstruction (PSR) and stochastic configuration network (SCN) is designed. Firstly, the meteorological data related to the load in the distribution network data is reduced by principal component analysis (PCA), and is combined with the load sequence to form a multivariable time series. Using chaotic time series theory, the paper reconstructs the phase space through mutual information method and false nearest neighbor method, and finally uses stochastic configuration network to predict power load. The proposed method is verified with historical load and meteorological data of public data sets of European power grid. The results show that, compared with the support vector machine (SVM) optimized by the grid search method, backpropagation neural network (BP), long and short-term memory network (LSTM), and autoregressive integrated moving average (ARIMA), the proposed method can complete load forecasting relatively, accurately and efficiently. The analysis of the calculation example verifies that the proposed method has the characteristics of high level of intelligence and efficient operation, and has certain practical value.

Key words: distribution network, short-term load forecasting, phase space reconstruction (PSR), principal component analysis (PCA), stochastic configuration network(SCN)

中图分类号:

TM715

赵允文, 李鹏, 孙煜皓, 沈鑫, 杨晓华. 基于相空间重构和随机配置网络的电力负荷短期预测[J]. 电力建设, 2021, 42(9): 120-128.

ZHAO Yunwen, LI Peng, SUN Yuhao, SHEN Xin, YANG Xiaohua. Short-Term Power Load Forecasting Based on Phase Space Reconstruction and Stochastic Configuration Networks[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(9): 120-128.

图/表 14

图1 随机配置网络模型

Fig.1 Model of SCN

图2 PCA算法流程

Fig.2 Algorithm flowchart of PCA

表1 气象序列累积贡献率

Table 1 Cumulative contribution rate of each sequence

表2 数据序列最大Lyapunov指数

Table 2 Maximum Lyapunov exponent of data series

表3 最佳延迟时间

Table 3 Optimal delay time in each sequence

表4 最小嵌入维数

Table 4 Minimum embedding dimension in each sequence

图3 负荷预测流程

Fig.3 Flowchart of the load forecasting

表5 SCN算法伪代码

Table 5 Pseudo code of SCN algorithm

图4 负荷序列

Fig.4 Load series

图5 部分预测结果

Fig.5 Forecast result

图6 预测负荷的相对误差比较

Fig.6 Comparison of the relative errors of load prediction

表6 第94号样本相对误差

Table 6 Relative error of the 94th sample

表7 预测误差和训练时间比较

Table 7 Comparison of prediction error and training time

表8 需人工确定的参数

Table 8 Parameters need to be manually determined

参考文献 21

[1]	魏骜, 茅大钧, 韩万里, 等. 基于EMD和长短期记忆网络的短期电力负荷预测研究[J]. 热能动力工程, 2020, 35(4):203-209.
	WEI Ao, MAO Dajun, HAN Wanli, et al. Short-term load forecasting based on EMD and long short-term memory neural networks[J]. Journal of Engineering for Thermal Energy and Power, 2020, 35(4):203-209.
[2]	魏腾飞, 潘庭龙. 基于改进PSO优化LSTM网络的短期电力负荷预测[J/OL]. 系统仿真学报. (2020-09-11) [2020-11-11]. http://kns.cnki.net/kcms/detail/11.3092.V.20200910.1734.013.html.
	WEI Tengfei, PAN Tinglong. Short-term power load forecasting based on LSTM neural network optimized by improved PSO[J/OL]. Journal of System Simulation. (2020-09-11) [2020-11-11]. http://kns.cnki.net/kcms/detail/11.3092.V.20200910.1734.013.html.
[3]	赵冬梅, 马泰屹, 王闯. 基于相空间重构和长短期记忆算法的电力系统无功负荷预测模型[J]. 现代电力, 2020, 37(5):470-477.
	ZHAO Dongmei, MA Taiyi, WANG Chuang. Reactive load forecasting model based on PSR-LSTM in power system[J]. Modern Electric Power, 2020, 37(5):470-477.
[4]	MEI F, WU Q L, SHI T, et al. An ultrashort-term net load forecasting model based on phase space reconstruction and deep neural network[J]. Applied Sciences, 2019, 9(7):1487. doi: 10.3390/app9071487 URL
[5]	杨捷, 罗成臣, 张思路, 等. 相空间重构和SVR耦合的短期电力负荷预测[J]. 电测与仪表, 2020, 57(16):96-100.
	YANG Jie, LUO Chengchen, ZHANG Silu, et al. Short-term load forecasting based on phase space reconstruction and SVR coupling model[J]. Electrical Measurement & Instrumentation, 2020, 57(16):96-100.
[6]	蔡舒平, 闫静, 刘国海, 等. 基于Fisher信息和在线SVR的智能电网气象敏感负荷预测动态建模技术[J]. 中国电机工程学报, 2020, 40(11):3441-3452.
	CAI Shuping, YAN Jing, LIU Guohai, et al. A dynamic modeling methodology based on fisher information and on-line SVR for smart grids weather sensitive load forecasting[J]. Proceedings of the CSEE, 2020, 40(11):3441-3452.
[7]	陈吕鹏, 殷林飞, 余涛, 等. 基于深度森林算法的电力系统短期负荷预测[J]. 电力建设, 2018, 39(11):42-50.
	CHEN Lüpeng, YIN Linfei, YU Tao, et al. Short-term power load forecasting based on deep forest algorithm[J]. Electric Power Construction, 2018, 39(11):42-50.
[8]	孔祥玉, 李闯, 郑锋, 等. 基于经验模态分解与特征相关分析的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(5):46-52.
	KONG Xiangyu, LI Chuang, ZHENG Feng, et al. Short-term load forecasting method based on empirical mode decomposition and feature correlation analysis[J]. Automation of Electric Power Systems, 2019, 43(5):46-52.
[9]	苏适, 周立栋, 万筱钟, 等. 计及气象因素的用电负荷短期分时分类预测模型与方法[J]. 电力建设, 2017, 38(10):76-83.
	SU Shi, ZHOU Lidong, WAN Xiaozhong, et al. Time-sharing and classified prediction model for Short Term load considering meteorological factors[J]. Electric Power Construction, 2017, 38(10):76-83.
[10]	MORENO-CARBONELL S, SÁNCHEZ-ÚBEDA E F, MUÑOZ A. Rethinking weather station selection for electric load forecasting using genetic algorithms[J]. International Journal of Forecasting, 2020, 36(2):695-712. doi: 10.1016/j.ijforecast.2019.08.008 URL
[11]	LI B, LU M Z, ZHANG Y Y, et al. A weekend load forecasting model based on semi-parametric regression analysis considering weather and load interaction[J]. Energies, 2019, 12(20):3820. doi: 10.3390/en12203820 URL
[12]	PEI S Q, QIN H, YAO L Q, et al. Multi-step ahead short-term load forecasting using hybrid feature selection and improved long short-term memory network[J]. Energies, 2020, 13(16):4121. doi: 10.3390/en13164121 URL
[13]	周松林, 茆美琴, 苏建徽. 基于主成分分析与人工神经网络的风电功率预测[J]. 电网技术, 2011, 35(9):128-132.
	ZHOU Songlin, MAO Meiqin, SU Jianhui. Prediction of wind power based on principal component analysis and artificial neural network[J]. Power System Technology, 2011, 35(9):128-132.
[14]	黄伟建, 李永涛, 黄远. 基于混合神经网络和注意力机制的混沌时间序列预测[J]. 物理学报, 2021, 70(1):235-243.
	HUANG Weijian, LI Yongtao, HUANG Yuan. Prediction of chaotic time series using hybrid neural network and attention mechanism[J]. Acta Physica Sinica, 2021, 70(1):235-243.
[15]	WOLF A, SWIFT J B, SWINNEY H L, et al. Determining Lyapunov exponents from a time series[J]. Physica D: Nonlinear Phenomena, 1985, 16(3):285-317. doi: 10.1016/0167-2789(85)90011-9 URL
[16]	CAO L Y. Practical method for determining the minimum embedding dimension of a scalar time series[J]. Physica D: Nonlinear Phenomena, 1997, 110(1/2):43-50. doi: 10.1016/S0167-2789(97)00118-8 URL
[17]	FATHIMA T A, JOTHIPRAKASH V. Behavioural analysis of a time series-A chaotic approach[J]. Sadhana, 2014, 39(3):659-676. doi: 10.1007/s12046-014-0249-2 URL
[18]	龚祝平. 制造质量信息系统重构相空间延迟时间计算方法的对比[J]. 系统工程, 2011, 29(3):81-85.
	GONG Zhuping. Comparison of the calculating methods of delay time in the reconstructed phase space of manufacturing quality information system[J]. Systems Engineering, 2011, 29(3):81-85.
[19]	吕小青, 曹彪, 曾敏, 等. 确定延迟时间互信息法的一种算法[J]. 计算物理, 2006, 23(2):184-188.
	LÜ Xiaoqing, CAO Biao, ZENG Min, et al. An algorithm of selecting delay time in the mutual information method[J]. Chinese Journal of Computational Physics, 2006, 23(2):184-188.
[20]	GHORBANI M A, KISI O, AALINEZHAD M. A probe into the chaotic nature of daily streamflow time series by correlation dimension and largest Lyapunov methods[J]. Applied Mathematical Modelling, 2010, 34(12):4050-4057. doi: 10.1016/j.apm.2010.03.036 URL
[21]	WANG D H, LI M. Stochastic configuration networks: Fundamentals and algorithms[J]. IEEE Transactions on Cybernetics, 2017, 47(10):3466-3479. doi: 10.1109/TCYB.2017.2734043 URL

基于相空间重构和随机配置网络的电力负荷短期预测

Short-Term Power Load Forecasting Based on Phase Space Reconstruction and Stochastic Configuration Networks

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	邓靖微, 李华强, 温丰瑞, 王俊翔, 谢康胜, 金智博. 计及虚拟电厂市场交易的主动配电网两阶段优化调度[J]. 电力建设, 2021, 42(9): 22-31.
[2]	谢康胜, 李华强, 王俊翔, 邓靖微. 考虑输配电网协同的源荷储资源统筹规划[J]. 电力建设, 2021, 42(9): 41-52.
[3]	张林垚, 郑洁云, 胡志坚, 倪识远, 吴桂联, 翁菖宏, 陈志, 陈锦鹏. 基于混合用户均衡理论和充放电管理的快/慢充电站规划[J]. 电力建设, 2021, 42(8): 99-109.
[4]	孟祥坤, 韩民晓, 张夏辉, 曹文远, 缪惠宇. 开环运行直流配用电系统安全域模型建立与应用[J]. 电力建设, 2021, 42(7): 48-57.
[5]	焦昊, 陈锦铭, 刘伟, 王海林, 董树锋, 郭雅娟. 基于Infomap算法的配电网边缘划分方法[J]. 电力建设, 2021, 42(7): 65-72.
[6]	黄冬梅, 庄兴科, 胡安铎, 孙锦中, 时帅, 孙园, 唐振. 基于灰色关联分析和K均值聚类的短期负荷预测[J]. 电力建设, 2021, 42(7): 110-117.
[7]	李桂鑫, 徐科, 刘英英, 吕永青, 窦晓波, 迟福建. 基于分布式模型预测控制的含分布式储能有源配电网动态电压控制[J]. 电力建设, 2021, 42(6): 116-126.
[8]	孙建梅, 胡嘉栋, 蔚芳. 考虑利益主体合作的分布式电源运营商电源优化配置[J]. 电力建设, 2021, 42(6): 127-134.
[9]	李穆寅, 曹志远, 李佳旭, 马佳骏, 许寅, 刘家妤, 张琪祁. 计及供电-供水系统耦合关系的配电网故障恢复优化决策方法[J]. 电力建设, 2021, 42(3): 54-60.
[10]	王珺, 田恩东, 马建, 窦晓波, 刘之涵. 基于数据驱动的非全实时观测配电网无功优化方法[J]. 电力建设, 2021, 42(2): 68-76.
[11]	陈刚, 黄杨, 丁理杰, 柳维衡, 魏巍, 曾宇, 刘友波. 考虑高压配电网转供能力的储能电站双层规划模型[J]. 电力建设, 2021, 42(1): 85-95.
[12]	王天霖, 高崇, 张俊潇, 曹华珍, 欧阳森, 杨墨缘. 直流配电网规划技术的新需求及其在一次规划的体现[J]. 电力建设, 2020, 41(9): 102-114.
[13]	黄家祺，张宇威，贺继锋，颜炯，朱旭，杨军. 一种考虑极限场景的配电网鲁棒扩展规划方法[J]. 电力建设, 2020, 41(7): 67-74.
[14]	刘家妤，马佳骏，王颖，许寅. 多源协同的智能配电网故障恢复次序优化决策方法[J]. 电力建设, 2020, 41(6): 100-106.
[15]	高崇，曾广璇，张俊潇，曹华珍，唐俊熙，余涛. 基于成功流法的配电信息物理系统可靠性评估[J]. 电力建设, 2020, 41(5): 58-65.