A novel heat load prediction model of district heating system based on hybrid whale optimization algorithm (WOA) and CNN-LSTM with attention mechanism

被引:6
|
作者
Cui, Xuyang [1 ]
Zhu, Junda [2 ]
Jia, Lifu [3 ]
Wang, Jiahui [1 ]
Wu, Yusen [1 ]
机构
[1] Tianjin Chengjian Univ, Sch Energy & Safety Engn, Tianjin 300384, Peoples R China
[2] Tianjin Univ, Sch Mech Engn, Tianjin 300350, Peoples R China
[3] Shaanxi Jinghe Thermal Power Co Ltd, Yulin 713700, Shaanxi, Peoples R China
关键词
District heating systems (DHS); Heat load prediction model; Whale optimization algorithm (WOA); Long short-term memory (LSTM); Convolution neural network (CNN); Attention mechanism (ATT);
D O I
10.1016/j.energy.2024.133536
中图分类号
O414.1 [热力学];
学科分类号
摘要
Machine learning models, particularly long short-term memory (LSTM) networks, have been extensively employed for heat load prediction in district heating systems (DHS). Nevertheless, the over-reliance on default hyperparameter settings in most methods hinders further enhancement of prediction accuracy. A novel load prediction model is presented, which integrates the whale optimization algorithm (WOA) to refine the hyperparameters of an LSTM model bolstered by an attention mechanism (ATT) and convolutional neural network (CNN). Three hybrid models (WOA-CNN-ATT-LSTM, PSO-CNN-ATT-LSTM and GA-CNN-ATT-LSTM) are constructed by comparing WOA with particle swarm optimization (PSO) and genetic algorithm (GA). The proposed hybrid models are evaluated against traditional LSTM models using an 1100-h dataset from a real DHS. The outcomes reveal that the WOA-CNN-ATT-LSTM model surpasses both the PSO-CNN-ATT-LSTM and GA-CNNATT-LSTM models in heat load prediction accuracy, achieving improvements of 1.9 % and 3.2 % respectively, and attaining the highest prediction accuracy (R2 = 0.9962, MSE = 0.0001, MAE = 0.0082). Moreover, the WOACNN-ATT-LSTM model demonstrates superior performance across various time scales (half-day, one-day, threedays, and one-week), highlighting its robustness in heat load prediction. This novel model adaptively adjusts its hyperparameters to identify the optimal configuration, thereby significantly augmenting the overall predictive capabilities of the model.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] A Prediction Method for Fuel Cell Degradation Based on CNN-LSTM Hybrid Model
    Zhang, Yufan
    Li, Yuren
    Liang, Bo
    Ma, Rui
    2022 25TH INTERNATIONAL CONFERENCE ON ELECTRICAL MACHINES AND SYSTEMS (ICEMS 2022), 2022,
  • [22] An enhanced CNN-LSTM remaining useful life prediction model for aircraft engine with attention mechanism
    Li, Hao
    Wang, Zhuojian
    Li, Zhe
    PEERJ COMPUTER SCIENCE, 2022, 8
  • [23] An Improved Hybrid CNN-LSTM-Attention Model with Kepler Optimization Algorithm for Wind Speed Prediction
    Huang, Yuesheng
    Li, Jiawen
    Li, Yushan
    Lin, Routing
    Wu, Jingru
    Wang, Leijun
    Chen, Rongjun
    ENGINEERING LETTERS, 2024, 32 (10) : 1957 - 1965
  • [24] Machine Fault Detection Using a Hybrid CNN-LSTM Attention-Based Model
    Borre, Andressa
    Seman, Laio Oriel
    Camponogara, Eduardo
    Stefenon, Stefano Frizzo
    Mariani, Viviana Cocco
    Coelho, Leandro dos Santos
    SENSORS, 2023, 23 (09)
  • [25] An Attention-Based CNN-LSTM Model with Limb Synergy for Joint Angles Prediction
    Zhu, Chang
    Liu, Quan
    Meng, Wei
    Ai, Qingsong
    Xie, Sheng Q.
    2021 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM), 2021, : 747 - 752
  • [26] A CNN-LSTM Hybrid Model Based Short-term Power Load Forecasting
    Ren, Chang
    Jia, Li
    Wang, Zhangliang
    2021 POWER SYSTEM AND GREEN ENERGY CONFERENCE (PSGEC), 2021, : 182 - 186
  • [27] A Novel Hybrid Spatial-Temporal Attention-LSTM Model for Heat Load Prediction
    Lin, Tao
    Pan, Yu
    Xue, Guixiang
    Song, Jiancai
    Qi, Chengying
    IEEE ACCESS, 2020, 8 : 159182 - 159195
  • [28] CNN-LSTM Base Station Traffic Prediction Based On Dual Attention Mechanism and Timing Application
    Jia, Hairong
    Wang, Suying
    Ren, Zelong
    COMPUTER JOURNAL, 2024, 67 (06): : 2246 - 2256
  • [29] Pressure prediction for air cyclone centrifugal classifier based on CNN-LSTM enhanced by attention mechanism
    Li, Wenhao
    Li, Xinhao
    Yuan, Jiale
    Liu, Runyu
    Liu, Yuhan
    Ye, Qing
    Jiang, Haishen
    Huang, Long
    CHEMICAL ENGINEERING RESEARCH & DESIGN, 2024, 205 : 775 - 791
  • [30] Remaining Useful Life Prediction for Pneumatic Control Valve System Based on Hybrid CNN-LSTM Model
    Chen, Jianliang
    You, Hong
    Yang, Peng
    Guo, Xiang
    2022 34TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2022, : 1849 - 1854