针对太阳能供暖系统中因热量供需不匹配而引起的能源浪费现象,提出一种基于卷积神经网络-双向长短期记忆神经网络的短期热负荷预测模型。首先对数据进行清洗,使数据准确完整;其次依据皮尔逊相关系数对输入特征进行筛选;最后依据其空间-时间特征建立卷积神经网络-双向长短期记忆神经网络模型。在与单一神经网络模型长短期记忆神经网络及双向长短期记忆神经网络进行详细比较和分析后,结果表明,该模型相较于传统神经网络模型在精确度上存在明显提升,验证了本模型在太阳能供暖负荷预测中的有效性。
Abstract
Aiming at the phenomenon of energy waste caused by the mismatch between heat supply and demand in solar heating system, a short-term heat load forecasting model based on convolutional neural network-bidirectional long short-term memory neural network is proposed. Firstly, the data is cleaned to make the data accurate and complete. Secondly, the input features are screened according to the Pearson correlation coefficient. Finally, a convolutional neural network-bidirectional long-term and short-term memory neural network model is established based on its spatial-temporal characteristics. After detailed comparison and analysis with the single neural network model, the length of the memory neural network and the two-way long short-term memory neural network, the results show that the model has a significant improvement in accuracy compared with the traditional neural network model, which verifies the effectiveness of the model in the prediction of solar heating load.
关键词
太阳能供暖 /
卷积神经网络 /
长短期记忆网络 /
热负荷 /
神经网络模型
Key words
solar heating /
convolutional neural network（CNN） /
long short-term memory（LSTM） /
thermal load /
neural network model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 孙峰, 毕文剑, 周楷, 等. 太阳能热利用技术分析与前景展望[J]. 太阳能, 2021(7): 23-36.
SUN F, BI W J, ZHOU K, et al.Analysis and prospect of solar thermal utilization technology[J]. Solar energy, 2021(7): 23-36.
[2] 闫云飞, 张智恩, 张力, 等. 太阳能利用技术及其应用[J]. 太阳能学报, 2012, 33(增刊1): 47-56.
YAN Y F, ZHANG Z E, ZHANG L, et al.Application and utilization technology of solar energy[J]. Acta energiae solaris sinica, 2012, 33(S1): 47-56.
[3] 周浩杰. 集中供热系统换热站负荷预测与控制算法研究[D]. 天津: 天津理工大学, 2019.
ZHOU H J.Research on load forecasting and control algorithm of heat exchange station in central heating system[D]. Tianjin: Tianjin University of Technology, 2019.
[4] FANG T T, LAHDELMA R.Evaluation of a multiple linear regression model and SARIMA model in forecasting heat demand for district heating system[J]. Applied energy, 2016, 179: 544-552.
[5] CATALINA T, IORDACHE V, CARACALEANU B.Multiple regression model for fast prediction of the heating energy demand[J]. Energy and buildings, 2013, 57: 302-312.
[6] 朱学莉, 齐维贵, 陆亚俊. 建筑供热负荷预报与预测控制策略研究[J]. 控制与决策, 2002, 17(增刊1): 703-706.
ZHU X L, QI W G, LU Y J.Heating load prediction and predictive control tactics of heat supply for building[J]. Control and decision, 2002, 17(S1): 703-706.
[7] KAWASHIMA M, DORGAN C E, MITCHELL J W.Hourly thermal load prediction for the next 24 hours by Arima, Ewma, LR, and an artificial neural network[J]. ASHRAE transactions, 1995(1): 186-200.
[8] 孙瑞. 基于负荷预测和瞬态模拟的集中供热系统控制策略优化[D]. 吉林: 东北电力大学, 2020.
SUN R.Control strategy optimization of central heating system based on load forcasting and transient simulation[D]. Jilin: Northeast Dianli University, 2020.
[9] WOJDYGA K.Predicting heat demand for a district heating systems[J]. International journal of energy and power engineering, 2014, 3(5): 237.
[10] 欧阳静, 杨吕, 尹康, 等. 基于ALIF-LSTM多任务学习的综合能源系统短期负荷预测[J]. 太阳能学报, 2022, 43(9): 499-507.
OUYANG J, YANG L, YIN K, et al.Short-term load forecasting method for integrated energy system based on ALIF-LSTM and multi-task learning[J]. Acta energiae solaris sinica, 2022, 43(9): 499-507.
[11] 闫露, 雷东强, 李晓, 等. 基于混合神经网络的槽式太阳能集热场出口温度预测研究[J]. 太阳能学报, 2023, 44(5): 265-273.
YAN L, LEI D Q, LI X, et al.Outlet temperature prediction of parabolic trough solar field based on hybrid neural network[J]. Acta energiae solaris sinica, 2023, 44(5): 265-273.
[12] SONG J C, ZHANG L Y, XUE G X, et al.Predicting hourly heating load in a district heating system based on a hybrid CNN-LSTM model[J]. Energy and buildings, 2021, 243: 110998.
[13] KIM T Y, CHO S B.Predicting residential energy consumption using CNN-LSTM neural networks[J]. Energy, 2019, 182: 72-81.
[14] RAFI S H, NAHID-AL-MASOOD, DEEBA S R, et al.A short-term load forecasting method using integrated CNN and LSTM network[J]. IEEE access, 2021, 9: 32436-32448.
[15] ZENG J W, QIAO W.Support vector machine-based short-term wind power forecasting[C]//2011 IEEE/PES Power Systems Conference and Exposition. Phoenix, AZ, USA, 2011: 1-8.
[16] XAVIER G, YOSHUA B.Proceedings of the thirteenth international conference on artificial intelligence and statistics[J]. Proceedings of machine learning research, 2010, 9: 249-256.
[17] JONES D R.A taxonomy of global optimization methods based on response surfaces[J]. Journal of global optimization, 2001, 21(4): 345-383.
[18] SNOEK J, LAROCHELLE H, ADAMS R P.Practical Bayesian optimization of machine learning algorithms[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 2. Lake Tahoe, Nevada, 2012: 2951-2959.
基金
国家重点研发计划（2021YFE0194500）; 北京市自然科学基金（3222042）; 国家自然科学基金重大项目（52090064）
PDF(5673 KB)
