基于NARX神经网络的热负荷预测中关键影响因素分析

doi:10.11772/j.issn.1001-9081.2018041222

计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3180-3187.DOI: 10.11772/j.issn.1001-9081.2018041222

• 第七届中国数据挖掘会议(CCDM 2018) • 上一篇下一篇

基于NARX神经网络的热负荷预测中关键影响因素分析

谢吉洋¹, 闫冬², 谢垚¹, 马占宇¹

1. 北京邮电大学模式识别与智能系统实验室, 北京 100876;
2. 北京邮电大学图书馆, 北京 100876

收稿日期:2018-03-29 修回日期:2018-06-06 出版日期:2018-11-10 发布日期:2018-11-10
通讯作者: 马占宇
作者简介:谢吉洋(1995-),男,北京人,硕士研究生,主要研究方向:模式识别、机器学习、贝叶斯学习、智能能源网络中的能源数据分析;闫冬(1980-),女,北京人,硕士,主要研究方向:数据分析、数据挖掘;谢垚(1995-),男,河南三门峡人,硕士研究生,主要研究方向:模式识别、机器学习;马占宇(1982-),男,河北邯郸人,副教授,博士,CCF会员,主要研究方向:模式识别与机器学习基础理论、多媒体信号处理、数据挖掘、生物医学信号处理、生物信息学。
基金资助:
国家自然科学基金资助项目（61773071）；北京市科技新星项目（Z171100001117049）；北京市自然科学基金资助项目（4162044）；北京市科技新星计划交叉学科合作课题（Z181100006218137）。

Analysis of key factors in heat demand prediction based on NARX neural network

XIE Jiyang¹, YAN Dong², XIE Yao¹, MA Zhanyu¹

1. Pattern Recognition and Intelligent Systems Laboratory, Beijing University of Posts and Telecommunications, Beijing 100876, China;
2. Library, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2018-03-29 Revised:2018-06-06 Online:2018-11-10 Published:2018-11-10
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61773071), the Beijing Nova Program (Z171100001117049), the Beijing Natural Science Foundation (4162044), the Beijing Nova Program Interdisciplinary Cooperation Project (Z181100006218137).

摘要/Abstract

摘要： 在区域供热（DH）网络中，精确预测热负荷已被认为是提高效率和节省成本的重要环节。为了提高预测精度，研究不同影响因素对热负荷预测的影响极为重要。使用引入不同影响因素的数据集训练得到带外部输入的非线性自回归（NARX）神经网络模型，并比较其预测性能，以讨论直接太阳辐射和风速对热负荷预测的影响程度。实验结果表明，直接太阳辐射和风速都是热负荷预测中的关键影响因素。只引入风速时，预测模型的平均绝对百分比误差（MAPE）和均方根误差（RMSE）均低于只引入直接太阳辐射，同时引入风速和直接太阳辐射能够得到最佳的模型预测性能，但是对于MAPE和RMSE降低的贡献不大。

关键词: 区域供热, 热负荷预测, 非线性自回归神经网络, 直接太阳辐射, 风速

Abstract: In District Heating (DH) network, accurate heat demand prediction has been considered as an important part for efficiency improvement and cost saving. In order to improve the prediction accuracy, it is extremely important to study the influence of different factors on heat load forecasting. In this paper, the Nonlinear AutoRegressive with eXogenous input (NARX) neural network models were trained using the datasets with different key factors and used to compare their prediction performance in order to investigate the impact of direct solar radiance and wind speed on heat demand prediction. The experimental results show that direct solar radiance and wind speed are key factors of heat demand prediction. Including wind speed only, the Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) of the proposed prediction model are lower than those of direct solar radiation only. Including both wind speed and direct solar radiance shows the best model performance, but it cannot result in a large decrease of MAPE and RMSE.

Key words: District Heating (DH), heat demand prediction, Nonlinear AutoRegressive with eXogenous input (NARX) neural network, direct solar radiance, wind speed

中图分类号:

TP183

谢吉洋, 闫冬, 谢垚, 马占宇. 基于NARX神经网络的热负荷预测中关键影响因素分析[J]. 计算机应用, 2018, 38(11): 3180-3187.

XIE Jiyang, YAN Dong, XIE Yao, MA Zhanyu. Analysis of key factors in heat demand prediction based on NARX neural network[J]. Journal of Computer Applications, 2018, 38(11): 3180-3187.

参考文献

[1] LUND H, WERNER S, WILTSHIRE R, et al. 4th generation district heating (4GDH) integrating smart thermal grids into future sustainable energy systems[J]. Energy, 2014, 68:1-11.
[2] MA Z, LI H, SUN Q, et al. Statistical analysis of energy consumption patterns on the heat demand of buildings in district heating systems[J]. Energy and Buildings, 2014, 85:464-472.
[3] SHAMSHIRBAND S, PETKOVIC D, ENAYATIFAR R, et al. Heat load prediction in district heating systems with adaptive neuro-fuzzy method[J]. Renewable & Sustainable Energy Reviews, 2015, 48:760-767.
[4] DOTZAUER E. Simple model for prediction of loads in district-heating systems[J]. Applied Energy, 2002, 73:277-284.
[5] YANG H, JIN S, FENG S, et al. Heat load forecasting of district heating system based on numerical weather prediction model[C]//IFEEA 2015:2015 International Forum on Electrical Engineering and Automation. Paris:Atlantis Press, 2015:1-5.
[6] 王文标, 蔡麒, 汪思源.基于气象因素的集中供热系统热负荷预测研究[J]. 计算机测量与控制, 2016, 24(02):22-26. (WANG W B, CAI Q, WANG S Y. Research of district heating system heat load prediction based on weather factors[J]. Computer Measurement and Control, 2016, 24(02):22-26.)
[7] 陈双. 建筑室内温度影响因素分析及热负荷预测研究[D]. 大连:大连海事大学, 2015. (CHEN S. Analysis on the influence factors of indoor temperature and study on thermal load forecasting[D]. Dalian:Dalian Maritime University, 2015.)
[8] MELIKYAN Z, EGNATOSYAN S. Encyclopedia of Energy Engineering and Technology[M]. Abingdon:Taylor and Francis, 2007:1272-1277.
[9] FOUDA A E, MELIKYAN Z. Assessment of a modified method for determining the cooling load of residential buildings[J]. Energy, 2010, 35(12):4726-4730.
[10] TORCHIO M F, GENON G, POGGIO A, et al. Merging of energy and environmental analyses for district heating systems[J]. Energy, 2009, 34(3):220-227.
[11] DOTZAUER E. Simple model for prediction of loads in district-heating systems[J]. Applied Energy, 2002, 73(3):277-284.
[12] SUN Q, LI H, MA Z, et al. A comprehensive review of smart energy meters in intelligent energy networks[J]. IEEE Internet of Things Journal, 2016, 3(4):464-479.
[13] MA Z, XIE J, LI H, et al. The role of data analysis in the development of intelligent energy networks[J]. IEEE Network, 2017, 31(5):88-95.
[14] YOSHIDA H, TERAI T. An ARMA type weather model for air-conditioning, heating and cooling load calculation[J]. Energy and Buildings, 1991, 16(1):625-634.
[15] GROSSWINDHAGERA S, VOIGTB A, KOZEKA M. Online short-term forecast of system heat load in district heating networks[EB/OL].[2018-03-20].https://pdfs.semanticscholar.org/82ad/6a51ec2848a8121c461ce8f6e6f1aa35ea3e.pdf.
[16] ZHOU X, LIU Q D, LIU G Q, et al. Multi-variable time series forecasting for thermal load of air-conditioning system on SVR[C]//CCC 2015:2015 Chinese Control Conference. Piscataway, NJ:IEEE, 2015:8276-8280.
[17] 王美萍. 城镇供热系统层级热量结算点中短期热负荷预测方法研究[D]. 太原:太原理工大学, 2017. (WNAG M P. Research on short and medium term heat demand load forecasting for scale heat settlement site in urban heating system[D]. Taiyuan:Taiyuan University of Technology, 2017.)
[18] KUMAR R, AGGARWAL R K, SHAMRMA J D. Estimation of total energy load of building using artificial neural network[J]. Energy and Environmental Engineering, 2013, 1(2):25-35.
[19] 李琦,韩颖.基于天气预报的集中供热系统短期热负荷预测[J].自动化与仪表, 2015, 30(5):5-8. (LI Q,HAN Y. Short-term heat load forecasting of district heating system based on weather[J]. Automation & Instrumentation, 2015, 30(5):5-8.)
[20] 张经博,郭凌,王朝霞,等.基于遗传算法优化BP神经网络的供暖系统热负荷预测模型[J].四川兵工学报,2014,35(4):152-156. (ZHANG J B, GUO L, WANG Z X, et al. Thermal load forecasting model of heating system based on genetic algorithm optimization BP neural network[J]. Journal of Sichuan Ordnance, 2014, 35(4):152-156.)
[21] HASHMI M U, ARORA V, PRIOLKAR J G. Hourly electric load forecasting using Nonlinear AutoregRessive with eXogenous (NARX) based neural network for the state of Goa India[C]//ICIC 2015:International Conference on Industrial Instrumentation and Control. Piscataway, NJ:IEEE, 2015:1418-1423.
[22] PRAKASH G, SAMBASIVARAO K, KIRSALI P, et al. Short term load forecasting for Uttarakhand using neural network and time series models[C]//ICCC 2014:2014 International Conference on Computer Communications. Piscataway, NJ:IEEE, 2014:1-6.
[23] AWAN S M, KHAN Z A, ASLAM M, et al. Application of NARX based FFNN, SVR and ANN fitting models for long term industrial load forecasting and their comparison[C]//ISIE 2012:2012 International Symposium on Industrial Electronics. Piscataway, NJ:IEEE, 2012:803-807.
[24] SANSA I, MISSAOUI S, BOUSSADA Z, et al. PV power forecasting using different artificial neural networks strategies[C]//ICGE 2014:2014 International Conference on Green Energy. Piscataway, NJ:IEEE, 2014:54-59.
[25] CUI H, PENG X. Short-term city electric load forecasting with considering temperature effects:an improved ARIMAX model[J]. Mathematical Problems in Engineering, 2015, 1:1-10.
[26] CHANG C, LIN C. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):Article No. 27.
[27] BOX G E, TIAO G C. Intervention analysis with applications to economic and environmental problems[J]. Journal of the American Statistical Association, 1975, 70(349):70-79.

基于NARX神经网络的热负荷预测中关键影响因素分析

Analysis of key factors in heat demand prediction based on NARX neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

[1]	郭秀婷, 朱昶胜, 张生财, 赵奎鹏. 分形插值在风速时间序列中的应用[J]. 计算机应用, 2020, 40(9): 2628-2633.
[2]	苏永新罗培屿段斌. 基于FIR神经网络的风电场虚拟风速传感器[J]. 计算机应用, 2012, 32(05): 1446-1449.