基于集合经验模态分解和ARIMA-GRNN的负荷预测方法

doi:10.16180/j.cnki.issn1007-7820.2021.12.008

摘要/Abstract

摘要：

针对传统负荷预测方法难以兼顾电力负荷内在线性特征量与非线性特征量的问题,文中提出一种基于EEMD和ARIMA-GRNN的混合负荷预测模型方法。该方法采用EEMD法,将负荷数据分解成不存在模态混叠的IMF分量和余项。运用ARIMA模型算法对每个IMF分量进行线性预测,得到时间序列预测分量,并将其与原始数据相减得到其中的非线性分量。通过GRNN神经网络算法对非线性分量进行预测得到非线性分量的预测值,并将求得的线性预测分量和非线性预测分量相加得到最终的预测值。仿真实验表明,文中提出的基于EEMD和ARIMA-GRNN 的混合预测模型在预测精度和性能上均优于采用单一算法的负荷预测方法。

关键词: 负荷预测, 集合经验模态分解, ARIMA-GRNN, 混合模型, IMF, 神经网络算法, 非线性, 时间序列

Abstract:

In view of the problem that traditional load forecasting methods hardly take into account the inherent linear and nonlinear characteristics of power load, this study proposes a hybrid load forecasting model based on EEMD and ARIMA-GRNN. In this method, EEMD method is used to decompose the load data into IMF components and residual terms without modal aliasing. ARIMA model algorithm is used to make linear prediction for each IMF component to obtain the time series prediction component, and subtract it from the original data to obtain the non-linear component. The non-linear component is predicted by the GRNN neural network algorithm to obtain the predicted value of the non-linear component. The obtained linear and the nonlinear predicted components are added to obtain the final predicted value. The simulation results show that the hybrid forecasting model based on EEMD and ARIMA-GRNN proposed in the present study is superior to the load forecasting method using a single algorithm in terms of forecasting accuracy and performance.

Key words: load forecasting, EEMD, ARIMA-GRNN, hybrid model, IMF, neural network algorithm, nonlinear, time series

中图分类号:

TP13

王洪亮,陈新源,赵雨梦. 基于集合经验模态分解和ARIMA-GRNN的负荷预测方法[J]. 电子科技, 2021, 34(12): 42-48.

WANG Hongliang,CHEN Xinyuan,ZHAO Yumeng. Load Forecasting Method Based on Ensemble Empirical Mode Decomposition and ARIMA-GRNN[J]. Electronic Science and Technology, 2021, 34(12): 42-48.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

表1

参考文献 19

[1]	Sayyidmousavi A, Bougherara H, Fawaz Z. A micromechanical approach for the fatigue failure prediction of unidirectional polymer matrix composites in off-axis loading including the effect of viscoelasticity[J]. Advanced Composite Materials, 2015, 24(1):65-77. doi: 10.1080/09243046.2014.941189
[2]	陈丽娜, 马龙, 安树怀, 等. 计及储能调度因素的电力系统短期负荷预测模型[J]. 青岛大学学报(工程技术版), 2018, 33(4):45-50.
	Chen Lina, Ma long, An Shuhuai, et al. Study on short-term load forecasting of power system considering energy storage dispatching under real-time price[J]. Journal of Qingdao University(Engineering & Technology Edition), 2018, 33(4):45-50.
[3]	刁家伟. 基于ARIMA-BPNN的负荷预测方法研究与应用[D]. 广州:广东工业大学, 2018.
	Diao Jiawei. Research and implementation of load forecasting method based on ARIMA-BPNN model[D]. Guangzhou:Guangdong University of Technology, 2018.
[4]	丁磊明, 杨晓雷, 黄金波, 等. 基于BP神经网络优化的改进灰色模型在电量预测中的应用[J]. 机电信息, 2019(36):36-39.
	Ding Leiming, Yang Xiaolei, Huang Jinbo, et al. Application of improved grey model based on BP neural network optimization in power forecasting[J]. Mechanical and Electrical Information, 2019(36):36-39.
[5]	陈卓. 残差自修正深度学习集成神经网络在短期电力负荷预测中的应用[D]. 杭州:浙江大学, 2018.
	Chen Zhuo. Application of residual self-correction deep-learning integrated neural network in short-term load forecasting[D]. Hangzhou:Zhejiang University, 2018.
[6]	马立新, 郑晓栋, 尹晶晶. 基于粗糙特征量的短期电力负荷预测[J]. 电子科技, 2016, 29(1):40-43.
	Ma Lixin, Zheng Xiaodong, Yin Jingjing. Short-term load forecasting based on rough characteristic-component algorithm[J]. Electronic Science and Technology, 2016, 29(1):40-43.
[7]	王增平, 赵兵, 纪维佳, 等. 基于GRU-NN模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(5):53-62.
	Wang Zengping, Zhao Bing, Ji Weijia, et al. Short-term load forecasting method based on GRU-NN model[J]. Automation of Electric Power Systems, 2019, 43(5):53-62.
[8]	Melodi O Adegoke, Olatunji M Adeyanju. Specific system random load forecasts for nigerian 330 kV 38-bus transmission grid[J]. International Journal of Engineering Research in Africa, 2016, 45(9):87-94.
[9]	陈卓, 孙龙祥. 基于深度学习LSTM网络的短期电力负荷预测方法[J]. 电子技术, 2018, 47(1):39-41.
	Chen Zhuo, Sun Longxiang. Short-term electrical load forecasting based on deep learning LSTM networks[J]. Electronic Technology, 2018, 47(1):39-41.
[10]	Paggi M, Corrado M, Berardone I. A global/local approach for the prediction of the electric response of cracked solar cells in photovoltaic modules under the action of mechanical loads[J]. Engineering Fracture Mechanics, 2016, 16(8):40-57.
[11]	Shi H, Xu M H, Ma Q Y, et al. A whole system assessment of novel deep learning approach on short-term load forecasting [C].Cardiff:Proceedings of the Ninth International Conference on Applied Energy, 2017.
[12]	祝学昌. 基于IFOA-GRNN的短期电力负荷预测方法研究[J]. 电力系统保护与控制, 2020, 48(9):121-127.
	Zhu Xuechang. Research on short-term power load forecasting method based on IFOA-GRNN[J]. Power System Protection and Control, 2020, 48(9):121-127.
[13]	Duarte G R, Fonseca L G, Goliatt P V Z C, et al. Comparison of machine learning techniques for predicting energy loads in buildings[J]. Ambiente Construído, 2017, 17(3):103-115. doi: 10.1590/s1678-86212017000300165
[14]	刘翊枫, 周国鹏, 刘昕, 等. 基于智能相似日识别及偏差校正的短期负荷预测方法[J]. 电力系统保护与控制, 2019, 47(12):138-145.
	Liu Yifeng, Zhou Guopeng, Liu Xin, et al. A short-term load forecasting method based on intelligent similar day recognition and deviation correction[J]. Power System Protection and Control, 2019, 47(12):138-145.
[15]	陈亮, 王震, 王刚. 深度学习框架下LSTM网络在短期电力负荷预测中的应用[J]电力信息与通信技术, 2017, 15(5):8-11.
	Chen Liang, Wang Zhen, Wang Gang. Application of LSTM network in short-term power load forecasting under the deep learning framework[J]. Electric Power Information and Communication Technology, 2017, 15(5):8-11.
[16]	袁超. 短期电力负荷混合预测模型研究[D]. 兰州:兰州大学, 2015.
	Yuan Chao. Research on hybrid forecasting model of short-term electricity demand[D]. Lanzhou:Lanzhou University, 2015.
[17]	金山红, 朱想, 赫卫国, 等. 基于相空间重构ARIMA和SVR的母线净负荷预测[J]. 电力需求侧管理, 2018, 20(2):20-24.
	Jin Shanhong, Zhu Xiang, He Weiguo, et al. Forecasting of bus-bar net load based on PSR-ARIMA and SVR[J]. Power Demand Side Management, 2018, 20(2):20-24.
[18]	马立新, 尹晶晶, 郑晓栋. 基于特征提取相似日的ELM短期负荷预测研究[J]. 电子科技, 2015, 28(12):22-25.
	Ma Lixin, Yin Jingjing, Zheng Xiaodong. Short-term load forecasting based on daily feature extraction of similar days and ELM[J]. Electronic Science and Technology, 2015, 28(12):22-25.
[19]	周先春, 嵇亚婷. 基于EEMD算法在信号去噪中的应用[J]. 电子设计工程, 2014, 22(8):12-14.
	Zhou Xianchun, Ji Yating. Methods based on EEMD in signal denosing[J]. Electronic Design Engineering, 2014, 22(8):12-14.

预测算法	均方差误差	平均绝对误差	平均绝对百分误差/%
ARIMA	482.296 0	366.669 1	7.567 5
GRNN	1 110.241 8	793.501 7	18.048 6
ARIMA-GRNN	453.438 1	291.757 7	6.399 2
EEMD-ARIMA-GRNN	394.327 8	266.089 6	5.564 2