Research on Short-Term Forecasting of Multiple Loads in Integrated Energy Systems Based on Composite Correlation Coefficients

doi:10.12096/j.2096-4528.pgt.24047

Abstract

Abstract:

Objectives To ensure the stable operation of the power grid, it is crucial to accurately predict the multivariate loads within an integrated energy system. To address the issues of low prediction accuracy and the coupling between multivariate loads in current algorithms, a predictive algorithm based on the composite correlation coefficient (CCC) is proposed. Methods The Savitzky-Golay (SG) filter and sparrow search algorithm (SSA) are used to optimize variational mode decomposition (VMD) for processing the characteristics of raw data. Subsequently, the CCC is utilized to analyze coupling, and highly correlated features are manually extracted and input into a gated recurrent unit (GRU) neural network combined with an encoder-decoder (ED) structure to obtain multivariate load prediction results. Finally, based on the aforementioned algorithm, experimental verification is carried out using numerical examples. Results Compared with traditional GRU, long short-term memory network, and bidirectional GRU prediction models, the proposed algorithm reduces the prediction errors of electric load by 0.55%, 0.49%, and 0.17%, respectively. The prediction errors of cooling load are reduced by 0.71%, 0.54%, and 0.19%, respectively. The prediction errors of heat load are reduced by 0.62%, 0.55%, and 0.19%, respectively. Conclusions The proposed algorithm model captures key information more effectively, demonstrates certain advantages over other algorithms, and improves prediction accuracy.

Key words: integrated energy systems, multivariate load prediction, energy coupling, composite correlation coefficient, encoder-decoder, gated recurrent unit, filtering

CLC Number:

TK 01

Weiquan TU, Hui LI, Zheng WAN. Research on Short-Term Forecasting of Multiple Loads in Integrated Energy Systems Based on Composite Correlation Coefficients[J]. Power Generation Technology, 2025, 46(1): 9-18.

Figures/Tables 10

Fig. 1 EDGRU structure

Fig. 2 SSVCEG structure

Tab. 1 Results after filtering with different parameters

负荷	参数	RMSE
电负荷/kW	$n = 5,$ $w = 7$	259.29
	$n = 5,$ $w = 9$	383.63
	$n = 3,$ $w = 7$	457.51
冷负荷/kW	$n = 5,$ $w = 7$	259.84
	$n = 5,$ $w = 9$	352.52
	$n = 3,$ $w = 7$	422.42
热负荷/MJ	$n = 5,$ $w = 7$	94.94
	$n = 5,$ $w = 9$	137.15
	$n = 3,$ $w = 7$	158.25

Tab. 1 Results after filtering with different parameters

负荷	参数	RMSE
电负荷/kW	$n = 5,$ $w = 7$	259.29
	$n = 5,$ $w = 9$	383.63
	$n = 3,$ $w = 7$	457.51
冷负荷/kW	$n = 5,$ $w = 7$	259.84
	$n = 5,$ $w = 9$	352.52
	$n = 3,$ $w = 7$	422.42
热负荷/MJ	$n = 5,$ $w = 7$	94.94
	$n = 5,$ $w = 9$	137.15
	$n = 3,$ $w = 7$	158.25

Tab. 2 Correlation indicators of different loads and their features

负荷类型	不同特征	相关性指标
负荷类型	不同特征	Person	GRA	UIC	CCC
电负荷	月	-0.089	0.674	0.348	0.371
	日	-0.043	0.641	0.018	0.234
	小时	0.029	0.629	0.031	0.229
	云型	-0.038	0.562	0.013	0.204
	露点	0.536	0.694	0.173	0.468
	地面反射率	0.203	0.705	0.072	0.327
	风速	0.124	0.679	0.013	0.272
	降水量	0.645	0.658	0.213	0.505
	风向	0.253	0.713	0.026	0.331
	湿度	-0.256	0.681	0.042	0.326
	温度	0.686	0.691	0.276	0.551
	气压	-0.466	0.707	0.139	0.437
	冷负荷	0.813	0.689	0.405	0.636
	热负荷	-0.544	0.645	0.316	0.502
冷负荷	月	0.191	0.713	0.422	0.442
	日	-0.011	0.638	0.013	0.221
	小时	0.178	0.661	0.072	0.304
	云型	-0.088	0.612	0.018	0.239
	露点	0.488	0.615	0.182	0.428
	地面反射率	0.292	0.665	0.134	0.364
	风速	0.217	0.691	0.019	0.309
	降水量	0.705	0.711	0.318	0.578
	风向	0.383	0.682	0.037	0.367
	湿度	-0.496	0.626	0.106	0.409
	温度	-0.496	0.554	0.489	0.652
	气压	-0.561	0.654	0.218	0.478
	电负荷	0.813	0.689	0.405	0.636
	热负荷	-0.775	0.627	0.448	0.617
热负荷	月	-0.212	0.542	0.461	0.405
	日	-0.029	0.621	0.025	0.225
	小时	-0.119	0.606	0.047	0.257
	云型	0.048	0.697	0.017	0.254
	露点	-0.459	0.603	0.154	0.405
	地面反射率	-0.401	0.597	0.163	0.387
	风速	-0.072	0.751	0.018	0.281
	降水量	-0.565	0.699	0.218	0.494
	风向	-0.453	0.581	0.072	0.369
	湿度	0.485	0.745	0.129	0.453
	温度	-0.816	0.591	0.576	0.661
	气压	0.641	0.551	0.303	0.498
	电负荷	-0.544	0.645	0.316	0.502
	冷负荷	-0.775	0.627	0.448	0.617

Fig. 3 Diagram of composite correlation coefficients

Tab. 3 Prediction results of different feature selection inputs

实验方法	电负荷		冷负荷		热负荷
实验方法	MAPE/%	RMSE/kW	MAPE/%	RMSE/kW	MAPE/%	RMSE/MJ
E1	4.16	1 188.62	4.75	1 203.93	4.31	464.20
E2	3.61	1 013.47	4.33	1 122.77	4.08	443.10
E3	3.14	902.13	4.07	1 041.39	3.43	411.45
E4	2.85	849.72	3.68	1 008.11	2.92	379.80
E5	3.72	1 051.59	4.03	1 066.31	3.96	443.10
E6	2.62	761.05	3.27	834.16	2.84	369.25

Tab. 4 Prediction results of multivariate loads of different models

方法实验	电负荷		冷负荷		热负荷
方法实验	MAPE/%	RMSE/kW	MAPE/%	RMSE/kW	MAPE%	RMSE/MJ
GRU	3.17	905.62	3.98	995.65	3.46	411.45
LSTM	3.11	903.45	3.81	970.87	3.39	411.45
BiGRU	2.79	819.13	3.46	898.87	3.03	379.80
SSVCEG	2.62	761.05	3.27	834.16	2.84	369.25

Fig. 4 Prediction results of electric load

Fig. 5 Prediction results of cooling load

Fig. 6 Prediction results of heat load

References 22

1	韩肖清，李廷钧，张东霞，等．双碳目标下的新型电力系统规划新问题及关键技术[J]．高电压技术，2021，47(9)：3036-3046．
	HAN X Q， LI T J， ZHANG D X，et al ．New issues and key technologies of new power system planning under double carbon goals[J]．High Voltage Engineering，2021，47(9)：3036-3046．
2	黄超，卜思齐，陈麒宇，等．元电力：新一代智能电网[J]．发电技术，2022，43(2)：287-304． doi:10.12096/j.2096-4528.pgt.22058
	HUANG C， BU S Q， CHEN Q Y，et al ．Meta-power：next-generation smart grid[J]．Power Generation Technology，2022，43(2)：287-304． doi:10.12096/j.2096-4528.pgt.22058
3	朱继忠，董瀚江，李盛林，等．数据驱动的综合能源系统负荷预测综述[J]．中国电机工程学报，2021，41(23)：7905-7923．
	ZHU J Z， DONG H J， LI S L，et al ．Review of data-driven load forecasting for integrated energy system[J]．Proceedings of the CSEE，2021，41(23)：7905-7923．
4	吴军英，路欣，刘宏，等．基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]．中国电力，2024，57(6)：131-140．
	WU J Y， LU X， LIU H，et al ．Ultra-short-term multi-region power load forecasting based on spearman-GCN-GRU model[J]．Electric Power，2024，57(6)：131-140．
5	李云松，张智晟．考虑综合需求响应的Transformer-图神经网络综合能源系统多元负荷短期预测[J]．电工技术学报，2024，39(19)：6119-6128．
	LI Y S， ZHANG Z S ．Transformer based multi load short-term forecasting of integrated energy system considering integrated demand response[J]．Transactions of China Electrotechnical Society，2024，39(19)：6119-6128．
6	吕忠麟，顾洁，孟璐．基于耦合特征与多任务学习的综合能源系统短期负荷预测[J]．电力系统自动化，2022，46(11)：58-66．
	LÜ Z L， GU J， MENG L ．Short-term load forecasting for integrated energy system based on coupling features and multi-task learning[J]．Automation of Electric Power Systems，2022，46(11)：58-66．
7	余帆，王磊，江巧永，等．基于特征筛选的VMD-MIC-SSA-Informer短期负荷预测[J]．陕西科技大学学报，2022，40(5)：191-196．
	YU F， WANG L， JIANG Q Y，et al ．VMD-MIC-SSA-Informer short-term load prediction based on feature selection[J]．Journal of Shaanxi University of Science & Technology，2022，40(5)：191-196．
8	封钰，宋佑斌，金晟，等．基于随机森林算法和粗糙集理论的改进型深度学习短期负荷预测模型[J]．发电技术，2023，44(6)：889-895． doi:10.12096/j.2096-4528.pgt.23013
	FENG Y， SONG Y B， JIN S，et al ．Improved deep learning model for forecasting short-term load based on random forest algorithm and rough set theory[J]．Power Generation Technology，2023，44(6)：889-895． doi:10.12096/j.2096-4528.pgt.23013
9	李云松，张智晟．基于GRU-TGTransformer的综合能源系统多元负荷短期预测[J]．电力系统保护与控制，2023，51(15)：33-41．
	LI Y S， ZHANG Z S ．Multi load short-term forecasting of an integrated energy system based on a GRU-TGTransformer[J]．Power System Protection and Control，2023，51(15)：33-41．
10	杨秀，胡钟毓，田英杰，等．基于Attention机制的CNN-GRU配网线路重过载短期预测方法[J]．电力科学与技术学报，2023，38(1)：201-209．
	YANG X， HU Z Y， TIAN Y J，et al ．Short-term heavy overload forecasting method of distribution net line based on CNN-GRU with Attention mechanism[J]．Journal of Electric Power Science and Technology，2023，38(1)：201-209．
11	ZHANG L， SHI J， WANG L，et al ．Electricity，heat，and gas load forecasting based on deep multitask learning in industrial-park integrated energy system[J]．Entropy，2020，22(12)：1355． doi:10.3390/e22121355
12	王凇瑶，张智晟．基于量子加权多层级GRU神经网络的综合能源系统多元负荷短期预测[J]．电力系统保护与控制，2022，50(23)：85-93．
	WANG S Y， ZHANG Z S ．Short-term multivariate load forecasting of an integrated energy system based on a quantum weighted multi-hierarchy gated recurrent unit neural network[J]．Power System Protection and Control，2022，50(23)：85-93．
13	陈锦鹏，胡志坚，陈纬楠，等．二次模态分解组合DBiLSTM-MLR的综合能源系统负荷预测[J]．电力系统自动化，2021，45(13)：85-94．
	CHEN J P， HU Z J， CHEN W N，et al ．Load prediction of integrated energy system based on combination of quadratic modal decomposition and deep bidirectional long short-term memory and multiple linear regression[J]．Automation of Electric Power Systems，2021，45(13)：85-94．
14	刘新宇，蒲欣雨，李继方，等．基于贝叶斯优化的VMD-GRU短期风电功率预测[J]．电力系统保护与控制，2023，51(21)：158-165．
	LIU X Y， PU X Y， LI J F，et al ．Short-term wind power prediction of a VMD-GRU based on Bayesian optimization[J]．Power System Protection and Control，2023，51(21)：158-165．
15	闫红艳，Hwang Jin Kwon，高艳丰．基于类噪声数据的电力系统低频振荡模态参数辨识[J]．发电技术，2022，43(1)：19-31．
	YAN H Y， KWON H J， GAO Y F ．Modal parameter identification of low frequency oscillation in power system based on ambient data[J]．Power Generation Technology，2022，43(1)：19-31．
16	姜飞，林政阳，王文烨，等．考虑最小平均包络熵负荷分解的最优Bagging集成超短期多元负荷预测[J]．中国电机工程学报，2024，44(5)：1777-1788．
	JIANG F， LIN Z Y， WANG W Y，et al ．Optimal bagging ensemble ultra short term multi-energy load forecasting considering least average envelope entropy load decomposition[J]．Proceedings of the CSEE，2024，44(5)：1777-1788．
17	武文栋，施保华，郑传良，等．基于改进麻雀搜索算法优化RBF神经网络的光伏阵列故障诊断[J]．智慧电力，2023，51(2)：77-83．
	WU W D， SHI B H， ZHENG C L，et al ．Fault diagnosis of photovoltaic array based on improved sparrow search algorithm optimized RBF neural network[J]．Smart Power，2023，51(2)：77-83．
18	侯健敏，孟莹，李志，等．基于综合相关性指标与SA-BiGRU的综合能源系统多元负荷预测[J]．电力建设，2024，45(5)：118-130．
	HOU J M， MENG Y， LI Z，et al ．Multi-energy load forecasting in integrated energy systems based on comprehensive correlation index and SA-BiGRU network[J]．Electric Power Construction，2024，45(5)：118-130．
19	申洪涛，李飞，史轮，等．基于气象数据降维与混合深度学习的短期电力负荷预测[J]．电力建设，2024，45(1)：13-21．
	SHEN H T， LI F， SHI L，et al ．Short-term power load forecasting based on reduction of meteorological data dimensionality and hybrid deep learning[J]．Electric Power Construction，2024，45(1)：13-21．
20	周纲，黄瑞，刘度度，等．基于改进K-means聚类和皮尔逊相关系数户变关系异常诊断[J]．电测与仪表，2024，61(3)：76-82．
	ZHOU G， HUANG R， LIU D D，et al ．Abnormal diagnosis of household variable relationship based on improved K-means clustering and Pearson correlation coefficient[J]．Electrical Measurement & Instrumentation，2024，61(3)：76-82．
21	袁建华，李洪强，谢斌斌，等．基于特征因素选取的IVMD-GLSSVM光伏出力短期预测[J]．电子测量技术，2023，46(12)：77-83．
	YUAN J H， LI H Q， XIE B B，et al ．Short term forecasting of photovoltaic output based on feature factor selection and IVMD-GLSSVM[J]．Electronic Measurement Technology，2023，46(12)：77-83．
22	MOUSAVI A， BARANIUK R G ．Uniform partitioning of data grid for association detection[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，44(2)：1098-1107． doi:10.1109/tpami.2020.3029487

[1]	Sha LIU, Zhe SUN, Zifeng QIU, Yan HU. Unmanned Aerial Vehicle Image Dehazing Algorithm Based on Simple Linear Iterative Clustering Optimization and Its Application in Wind Farm [J]. Power Generation Technology, 2020, 41(6): 608-616.
[2]	Chao CHEN,Haibin LIU,Jing GE,Xuejun QIU,Lei CHEN,Xinbao WANG,Junbo FU. Wind Power Fluctuation Suppression by Doubly-fed Variable-speed Pumped Storage Unit [J]. Power Generation Technology, 2020, 41(4): 452-460.
[3]	Hao WU,Jun CHAI,Shuai AN,Shu XIA. Application of SCA-VMD in Noise Reduction of Transformer Sound Signal [J]. Power Generation Technology, 2020, 41(2): 186-189.