Feed-forward active operation optimization for CCHP system considering thermal load forecasting

被引：15
|
作者：
Kang, Ligai [1 ]
Yuan, Xiaoxue [1 ]
Sun, Kangjie [1 ]
Zhang, Xu [1 ]
Zhao, Jun [2 ]
Deng, Shuai [2 ]
Liu, Wei [3 ]
Wang, Yongzhen [4 ]
机构：
[1] Hebei Univ Sci & Technol, Sch Civil Engn, Shijiazhuang 050018, Hebei, Peoples R China
[2] Tianjin Univ, MOE, Key Lab Efficient Utilizat Low & Medium Grade Ene, Tianjin 300072, Peoples R China
[3] Hebei Acad Sci, Inst Energy Resources, Shijiazhuang 050081, Hebei, Peoples R China
[4] Tsinghua Univ, Inst Energy Internet Innovat, Dept Elect Engn, Beijing 100084, Peoples R China
来源：
ENERGY | 2022年 / 254卷
基金：
中国国家自然科学基金;
关键词：
CCHP system; Load forecasting; Operation optimization; Integrated performance; SOURCE HEAT-PUMP; OPTIMAL-DESIGN; GAS-TURBINE; ENERGY; PERFORMANCE; SOLAR; STRATEGY; POWER; USERS; CYCLE;
D O I：
10.1016/j.energy.2022.124234
中图分类号：
O414.1 [热力学];
学科分类号：
摘要：
Using simulated load obtained by energy consumption simulation software is a feasible way to optimize operation of combined cooling heating and power (CCHP) system. However, due to attenuation and delay of thermal energy on transmission, there may be a mismatch between real demand and supplied energy. To obtain more accurate assessment of supplied energy, this paper analyzes characteristics of thermal load through correlation analysis and principal component analysis. Then, the model of thermal load forecasting considering attenuation and delay on transmission is constructed and a case study with actual monitored data in an energy system is employed. Finally, a method of feed-forward active operation optimization for CCHP system is put forward. Based on forecasted thermal load on weekday and weekend in heating, transition and cooling season, dynamic matching optimization and evaluation were carried out. Results show that mean absolute percentage error are 5.43% for heating load forecasting and 6.84% for cooling load forecasting, respectively. The performances of CCHP system are better than that of separate system based on the forecasted thermal load and the maximum integrated performance index is 68.81%, obtained at weekend in cooling season. (C) 2022 Elsevier Ltd. All rights reserved.
引用
收藏
页数：12
相关论文
共 50 条
  • [1] Electrical Load Demand Forecasting Using Feed-Forward Neural Networks
    Machado, Eduardo
    Pinto, Tiago
    Guedes, Vanessa
    Morais, Hugo
    ENERGIES, 2021, 14 (22)
  • [2] Load forecasting based on grasshopper optimization and a multilayer feed-forward neural network using regressive approach
    Talaat, M.
    Farahat, M. A.
    Mansour, Noura
    Hatata, A. Y.
    ENERGY, 2020, 196
  • [3] Operation and Configuration Optimization of A CCHP System for General Building Load
    Chang, Liuchen
    Weng, Gongyu
    Hu, Jie
    Mao, Meiqin
    2016 IEEE 8TH INTERNATIONAL POWER ELECTRONICS AND MOTION CONTROL CONFERENCE (IPEMC-ECCE ASIA), 2016,
  • [4] Dynamic short-term forecasting of electricity load using feed-forward ANNs
    Milojkovic, J. B.
    Litovski, V. B.
    ENGINEERING INTELLIGENT SYSTEMS FOR ELECTRICAL ENGINEERING AND COMMUNICATIONS, 2009, 17 (01): : 39 - 48
  • [5] Dynamic short-term forecasting of electricity load using feed-forward ANNs
    Milojković, J.B.
    Litovski, V.B.
    Engineering Intelligent Systems, 2009, 17 (01): : 39 - 48
  • [6] Feed-Forward Active Noise Control System Using Microphone Array
    Liu, Lichuan
    Li, Yang
    Kuo, Sen M.
    IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2018, 5 (05) : 946 - 952
  • [7] Feed-Forward Active Noise Control System Using Microphone Array
    Lichuan Liu
    Yang Li
    Sen M.Kuo
    IEEE/CAA Journal of Automatica Sinica, 2018, 5 (05) : 946 - 952
  • [8] Enhancing the Performance of Feed-Forward Neural Networks in the Bus Short-Term Load Forecasting
    Panapakidis, Ioannis P.
    Papagiannis, Grigoris K.
    2014 49TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC), 2014,
  • [9] Full-field feed-forward equalizer with adaptive system optimization
    Zhao, Jian
    Bessler, Vivian
    Ellis, Andrew
    OPTICAL FIBER TECHNOLOGY, 2010, 16 (05) : 323 - 328
  • [10] Unit load control system based on multivariable feed-forward and feedback GPC
    Guo, Peng
    Proceedings of 2006 International Conference on Machine Learning and Cybernetics, Vols 1-7, 2006, : 860 - 864
12345