Building heating load forecasting based on the theory of transient heat transfer and deep learning

被引:2
|
作者
Shi, Zekun [1 ,2 ]
Zheng, Ruifan [1 ,2 ]
Shen, Rendong [1 ,2 ]
Yang, Dongfang [1 ,2 ]
Wang, Guangliang [1 ,2 ]
Liu, Yuanchao [1 ,2 ]
Li, Yang [1 ,2 ]
Zhao, Jun [1 ,2 ]
机构
[1] Tianjin Univ, Key Lab Efficient Utilizat Low & Medium Grade Ener, Minist Educ China, Tianjin 300350, Peoples R China
[2] Tianjin Univ, Sch Mech Engn, Tianjin 300350, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
Heating load forecasting; Feature selection; Transient heat transfer; Conduction transfer function; Deep learning; MODEL-PREDICTIVE CONTROL; ENERGY PERFORMANCE; OCCUPANT BEHAVIOR; OFFICE BUILDINGS; OPTIMIZATION;
D O I
10.1016/j.enbuild.2024.114290
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Reliable and accurate heating load forecasting can provide comprehensive information for the monitoring and control of Heating, Ventilation, and Air Conditioning (HVAC) in buildings, which reduce uncertainty on the load demand of energy effectively. Data-driven method has demonstrated a potential to forecast heating load, but current methods generally lack the consideration of features on model forecasting performance and applicability. Based on the theory of transient heat transfer and conduction transfer function for building hourly heating load calculation, this study proposes an idea that comprehensively selects physical variables affecting the hourly dynamic changes of the building heating load as features, which enhances the persuasiveness of selecting datasets features. Then we use the deep learning method to build short-term heating load forecasting models, and explore the influence of different feature combinations and time steps on the model forecasting performance. Combining the physical property of building heat gains, we divide the features into external heat gains, internal heat gains and historical heating load and then show their performance of models at different time steps. It is shown that the two-hour data of external heat gains and internal heat gains, the three-hour data of past heat load have the highest value. The best model can achieve a mean absolute error of 0.153 kW and a mean absolute percentage error of 6.2 %. These findings are helpful for researchers to select more relevant features to forecast heating load in buildings and improve their models through physical aspect.
引用
收藏
页数:18
相关论文
共 50 条
  • [11] Forecasting Heat Load for Smart District Heating Systems: A Machine Learning Approach
    Idowu, Samuel
    Saguna, Saguna
    Ahlund, Christer
    Schelen, Olov
    2014 IEEE INTERNATIONAL CONFERENCE ON SMART GRID COMMUNICATIONS (SMARTGRIDCOMM), 2014, : 554 - 559
  • [12] Effects of combined heat and mass transfer on heating load in building drying period
    Kong, Fanhong
    Zheng, Maoyu
    ENERGY AND BUILDINGS, 2008, 40 (08) : 1614 - 1622
  • [13] Heat Distribution of Heat Exchange Station in District Heating System based on Load Forecasting
    Zhao, Bingwen
    Zheng, Hanyu
    Yan, Ruxue
    THERMAL ENGINEERING, 2024, 71 (04) : 364 - 373
  • [14] Building cooling load forecasting of IES considering spatiotemporal coupling based on hybrid deep learning model
    Yu, Min
    Niu, Dongxiao
    Zhao, Jinqiu
    Li, Mingyu
    Sun, Lijie
    Yu, Xiaoyu
    APPLIED ENERGY, 2023, 349
  • [15] The predictive management in campus heating system based on deep reinforcement learning and probabilistic heat demands forecasting
    Chen, Minghao
    Xie, Zhiyuan
    Sun, Yi
    Zheng, Shunlin
    APPLIED ENERGY, 2023, 350
  • [16] Deep Learning Based Densely Connected Network for Load Forecasting
    Li, Zhuoling
    Li, Yuanzheng
    Liu, Yun
    Wang, Ping
    Lu, Renzhi
    Gooi, Hoay Beng
    IEEE TRANSACTIONS ON POWER SYSTEMS, 2021, 36 (04) : 2829 - 2840
  • [17] Power Load Forecasting Based on LSTM Deep Learning Algorithm
    Wu, Dalei
    Liang, Shuhua
    Chen, Changji
    Chen, Yupei
    Wang, Pishi
    Long, Zhiyuan
    Tehnicki Vjesnik, 2024, 31 (06): : 2156 - 2160
  • [18] A federated and transfer learning based approach for households load forecasting
    Singh, Gurjot
    Bedi, Jatin
    KNOWLEDGE-BASED SYSTEMS, 2024, 299
  • [19] Individualized Short-Term Electric Load Forecasting With Deep Neural Network Based Transfer Learning and Meta Learning
    Lee, Eunjung
    Rhee, Wonjong
    IEEE ACCESS, 2021, 9 : 15413 - 15425
  • [20] Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand
    Sekhar, Charan
    Dahiya, Ratna
    ENERGY, 2023, 268