基于Transformer算法的园区综合能源需求预测

doi:10.3969/j.issn.2097-0706.2023.10.008

综合智慧能源 ›› 2023, Vol. 45 ›› Issue (10): 61-69.doi: 10.3969/j.issn.2097-0706.2023.10.008

基于Transformer算法的园区综合能源需求预测

尹宇晨¹(), 刘宇杭¹(), 马愿谦¹^,^*(), 雷一²()

1.浙江理工大学信息科学与工程学院，杭州 310018
2.清华四川能源互联网研究院，成都 610200

收稿日期:2023-03-20 修回日期:2023-05-19 出版日期:2023-10-25 发布日期:2023-06-06
通讯作者: *马愿谦（1991），女，讲师，博士，从事电能质量、电能扰动方面的研究，mayq666@qq.com。
作者简介:尹宇晨（2002），男，在读硕士研究生，从事电能质量、电能扰动方面的研究，1227253991@qq.com；
刘宇杭（2002），男，在读硕士研究生，从事电能质量、电能扰动方面的研究，614190172@qq.com；
雷一（1985），男，正高级工程师，博士，从事电能质量、电能扰动方面的研究，leiyi@tsinghua-eiri.org。
基金资助:
浙江省自然科学基金项目(LQ22E070009);浙江理工大学科研业务费专项资金资助项目(23222130-Y)

Integrated energy demand forecasting for the park based on the Transformer algorithm

YIN Yuchen¹(), LIU Yuhang¹(), MA Yuanqian¹^,^*(), LEI Yi²()

1. School of Information Science and Engineering，Zhejiang Sci-Tech University，Hangzhou 310018，China
2. Tsinghua Sichuan Energy Internet Research Institute，Chengdu 610200，China

Received:2023-03-20 Revised:2023-05-19 Online:2023-10-25 Published:2023-06-06
Supported by:
The Natural Science Foundation of Zhejiang Province(LQ22E070009);Fundamental Research Funds of Zhejiang Sci-Tech University(23222130-Y)

摘要/Abstract

摘要：

准确的综合能源需求预测是区域综合能源系统调度和能效评估的基础。在综合能源需求预测方面，影响因素众多、设计参数复杂、计算效率较低，且在长序列预测上仍有较大优化空间，因此提出了一种基于Transformer算法的园区综合能源需求预测方法。建立了园区冷热电负荷影响因素的筛选模型，为数据预处理后筛选适当的影响因素提供基础；建立了基于欧氏距离的综合相似度的相似日选取方法，为综合能源的预测奠定了基础；建立了基于Transformer算法的冷热电负荷预测模型，以实现园区综合能源需求预测；以中国东部某园区为对象进行算例分析，预测园区综合能源需求。结果表明，所提预测方法能有效提高预测精度，具有较高的准确度和实用性。

关键词: 园区综合能源, Transformer算法, 能源需求预测, 相似日, 冷热电负荷

Abstract:

Accurate forecasting on integrated energy demands will be the basis for the scheduling and energy efficiency assessment of regional integrated energy systems. Integrated energy demand forecasting is infected by multiple factors. And being hampered by complex design parameters and low calculation efficiency，there is plenty of room for the optimization of current long series prediction method. Therefore，an integrated energy demand forecasting method based on Transformer algorithm is proposed. Firstly，influencing factors are screened from pre-processed data by the influence factor selection model for the cooling，heating and electricity loads in a park. Secondly，similar days are categorized based on the Euclidean distance，which lays a foundation for the integrated energy prediction. Then，a forecasting model for cooling，heating and electricity loads based on Transformer algorithm is established to predict the integrated energy demand in the park. Finally，the proposed forecasting model is tested on a park located in eastern China，and the results verified its prediction accuracy and effectiveness.

Key words: integrated energy in parks, Transformer algorithm, energy demand forecasting, similar day, cooling, heating and electricity loads

中图分类号:

TK01

尹宇晨, 刘宇杭, 马愿谦, 雷一. 基于Transformer算法的园区综合能源需求预测[J]. 综合智慧能源, 2023, 45(10): 61-69.

YIN Yuchen, LIU Yuhang, MA Yuanqian, LEI Yi. Integrated energy demand forecasting for the park based on the Transformer algorithm[J]. Integrated Intelligent Energy, 2023, 45(10): 61-69.

图/表 13

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

图11

表4

综合能量预测结果评估

负荷类型	评价指标 $M A P E$
负荷类型	随机森林	Transformer	BP
冷负荷	5.281	1.016	8.958
热负荷	0.649	0.320	0.519
电负荷	0.496	0.486	3.485

表4

参考文献 24

[1]	LEI Z, XUAN W B, WANG K, et al. Research on power demand forecasting based on the relationship between economic development and power demand[C]// 2018 China International Conference on Electricity Distribution (CICED). IEEE, 2018: 2710-2713.
[2]	CHEN B, WANG Y. Short-term electric load forecasting of integrated energy system considering nonlinear synergy between different loads[J]. IEEE Access, 2021, 9: 43562-43573. doi: 10.1109/ACCESS.2021.3066915
[3]	吕昊, 何益鸣, 田浩, 等. 基于物联网的园区综合能源系统快速通信网络建模与仿真[J]. 中国电力, 2022, 55(5): 166-173.
	LV Hao, HE Yiming, TIAN Hao, et al. Modeling and simulation of fast communication network for park integrated energy system based on IoT[J]. Electric Power, 2022, 55(5): 166-173.
[4]	JIA H J, WANG D, XU X D, et al. Research on some key problems related to integrated energy systems[J]. Automation of Electric Power Systems, 2015, 39(7): 198-207.
[5]	李丹, 张远航, 李黄强, 等. 基于精准气象数据的地区电网短期负荷智能预测系统设计[J]. 中国电力, 2022, 55(7): 128-133.
	LI Dan, ZHANG Yuanhang, LI Huangqiang, et al. Design of a short-term load intelligent forecasting system for regional power grid based on accurate weather data[J]. Electric Power, 2022, 55(7): 128-133.
[6]	ELJAZZAR M M, HEMAYED E E. Impact of economic, social and meteorological factors on load forecasting in different timeframes—A Survey[C]// 2020 5th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE). IEEE, 2020.
[7]	陈厚合, 王杨, 张儒峰, 等. 考虑源荷协调的风电并网系统旋转备用容量优化[J]. 电力自动化设备, 2017, 37(8):185-192.
	CHEN Houhe, WANG Yang, ZHANG Rufeng, et al. Spinning reserve capacity optimization considering coordination between source and load for power system with wind power[J]. Electric Power Automation Equipment, 2017, 37(8):185-192.
[8]	CUI J, YU R Z, ZHAO D B, et al. Intelligent load pattern modeling and denoising using improved variational mode decomposition for various calendar periods[J]. Applied Energy, 2019, 247:480-491. doi: 10.1016/j.apenergy.2019.03.163
[9]	叶震, 张国忠. AR与T-S混合模型在负荷预测中的应用[J]. 电力自动化设备, 2002, 22(10):43-46.
	YE Zhen, ZHANG Guozhong. Application of modeling method combining AR with fuzzy-neural system to power dam load forecasting[J]. Electric Power Automation Equipment, 2002, 22(10):43-46.
[10]	朱剑飞, 陈文刚, 宰洪涛, 等. 基于ARIMA与LSTM在电力负荷预测中的对比讨论[J]. 电气应用, 2022, 41(2):27-31.
	ZHU, Jianfei, CHEN Wengang, ZAI Hongtao, et al. Comparative discussion on power load forecasting based on ARIMA and LSTM[J]. Electrotechnical Application, 2022, 41(2):27-31.
[11]	JIANG H Y, REN Y R, LIU Z H, et al. Evaluations of failure initiation criteria for predicting damages of composite structures under crushing loading[J]. Journal of Reinforced Plastics and Composites, 2018, 37(21):1279-1303. doi: 10.1177/0731684418783847
[12]	邵建浩, 张婷. 基于BP神经网络的SCARA机器人故障诊断[J]. 机床与液压, 2022, 50(14):166-170. doi: 10.3969/j.issn.1001-3881.2022.14.030
	SHAO Jianhao, ZHANG Ting. Fault diagnosis of SCARA robot based on BP neural network[J]. Machine Tool & Hydraulics, 2022, 50(14):166-170.
[13]	邵凯旋, 吴映涵, 梅钢. 随机森林算法在气象与空气质量分析中的应用[J]. 山西建筑, 2021, 47(24):122-126.
	SHAO Kaixuan, WU Yinghan, MEI Gang. Application of random forest algorithm in analysis of meteorological conditions and air quality[J]. Shanxi Architecture, 2021, 47(24):122-126.
[14]	宋英华, 刘子奇, 刘丹, 等. 基于模糊贝叶斯网络的化工园区火灾爆炸事故情景推演[J]. 安全与环境工程, 2022, 29(3) :86-93.
	SONG Yinghua, LIU Ziqi, LIU Dan, et al. Scenario deduction of fire and explosion accidents in chemical industry parks based on Fuzzy Bayesian network[J]. Safety and Environmental Engineering, 2022, 29(3) :86-93.
[15]	BARGHINIA S, KAMANKESH S, MAHDAVI N, et al. A combination method for short term load forecasting used in Iran electricity market by Neuro Fuzzy, Bayesian and finding similar days methods[C]// 2008 5th International Conference on the European Electricity Market. IEEE, 2008: 1-6.
[16]	陈文鼎, 赵哲身. 基于BP神经网络的空调负荷预测[J]. 节能技术, 2010, 28(1):15-17,24.
	CHEN Wending, ZHAO Zheshen. Prediction of air conditioning load based on BP neural network[J]. Energy Conservation Technology, 2010, 28(1):15-17,24.
[17]	王琦, 杨超杰, 李丽锋. 改进Elman神经网络在短期热负荷预测中的应用[J]. 工业仪表与自动化装置, 2020(1):50-53.
	WANG Qi, YANG Chaojie, LI Lifeng. Application of improved Elman neural network in short-term thermal load forecasting[J]. Industrial Instrumentation & Automation, 2020(1):50-53.
[18]	骆小满, 皇甫成, 阮江军, 等. 基于神经网络的热电联产机组热负荷和电负荷预测[J]. 热力发电, 2019, 48(9):46-50.
	LUO Xiaoman, HUANGFU Cheng, RUAN Jiangjun, et al. Prediction of heat and electric load of cogeneration unit based on neural network[J]. Thermal Power Generation, 2019, 48(9):46-50.
[19]	RAO Z Y, ZHANG Y X. Transformer-based power system energy prediction model[C]// 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). IEEE, 2020.
[20]	LI W S, WU K H, FENG L, et al. A Region-level integrated energy load forecasting method based on CNN-LSTM model with user energy label differentiation[C]// 2020 5th International Conference on Power and Renewable Energy (ICPRE). 2020.
[21]	TANG Y, LIU H M, XIE Y F, et al. Short-term forecasting of electricity and gas demand in multi-energy system based on RBF-NN model[C]// 2019 IEEE International Conference on Energy Internet (ICEI). IEEE, 2019.
[22]	温港成, 石鑫, 张怡, 等. 考虑设备变工况特性的园区综合能源系统两阶段规划优化方法研究[J]. 综合智慧能源, 2022, 44(10): 1-11. doi: 10.3969/j.issn.2097-0706.2022.10.001
	WEN Gangcheng, SHI Xin, ZHANG Yi, et al. Research on two-stage planning optimization approach for community integrated energy systems considering off-design conditions[J]. Integrated Intelligent Energy, 2022, 44(10): 1-11. doi: 10.3969/j.issn.2097-0706.2022.10.001
[23]	王义, 杨志伟, 吴坡, 等. 计及高比例分布式光伏能源接入的配电网状态估计[J]. 综合智慧能源, 2022, 44(10): 12-18. doi: 10.3969/j.issn.2097-0706.2022.10.002
	WANG Yi, YANG Zhiwei, WU Po, et al. State estimation for the distribution network with high-proportion distributed photovoltaic energy[J]. Integrated Intelligent Energy, 2022, 44(10): 12-18. doi: 10.3969/j.issn.2097-0706.2022.10.002
[24]	李朋真, 刘艳红, 吴振龙. 高比例可再生能源的多区域电力系统负荷频率自抗扰控制[J]. 综合智慧能源, 2022, 44(10): 33-41. doi: 10.3969/j.issn.2097-0706.2022.10.005
	LI Pengzhen, LIU Yanhong, WU Zhenlong. Active disturbance rejection control on load frequency of multi-area power systems with high-proportion renewable energy[J]. Integrated Intelligent Energy, 2022, 44(10): 33-41. doi: 10.3969/j.issn.2097-0706.2022.10.005

项目	对应编号	影响因素
电负荷	h₂	温度平均值
	h₅	湿度平均值
	h₈	风速平均值
冷负荷	h₁	温度最大值
	h₅	湿度平均值
	h₉	风速最小值
热负荷	h₃	温度最小值
	h₄	湿度最大值
	h₉	风速最小值

基于Transformer算法的园区综合能源需求预测

Integrated energy demand forecasting for the park based on the Transformer algorithm

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 24

相关文章 2

编辑推荐

Metrics

本文评价

[1]	钟鹏元, 杨晓宏, 寇建玉. 含储氢结构的园区综合能源系统优化配置研究[J]. 综合智慧能源, 2022, 44(9): 11-19.
[2]	温港成, 石鑫, 张怡, 房方. 考虑设备变工况特性的园区综合能源系统两阶段规划优化方法研究[J]. 综合智慧能源, 2022, 44(10): 1-11.