Modeling and Optimization of Complex Building Energy Systems with Deep Neural Networks

被引:0
|
作者
Chen, Yize [1 ]
Shi, Yuanyuan [1 ]
Zhang, Baosen [1 ]
机构
[1] Univ Washington, Dept Elect Engn, Seattle, WA 98195 USA
关键词
Building energy management; deep learning; gradient algorithms; HVAC systems; SIMULATION;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Modern buildings encompass complex dynamics of multiple electrical, mechanical, and control systems. One of the biggest hurdles in applying conventional model-based optimization and control methods to building energy management is the huge cost and effort of capturing diverse and temporally correlated dynamics. Here we propose an alternative approach which is model-free and data-driven. By utilizing high volume of data coming from advanced sensors, we train a deep Recurrent Neural Networks (RNN) which could accurately represent the operation's temporal dynamics of building complexes. The trained network is then directly fitted into a constrained optimization problem with finite horizons. By reformulating the constrained optimization as an unconstrained optimization problem, we use iterative gradient descents method with momentum to find optimal control inputs. Simulation results demonstrate proposed method's improved performances over model-based approach on both building system modeling and control.
引用
收藏
页码:1368 / 1373
页数:6
相关论文
共 50 条
  • [1] Modeling and Optimizing Building HVAC Energy Systems Using Deep Neural Networks
    Deng, Jiahao
    Wang, Haoran
    [J]. 2018 INTERNATIONAL CONFERENCE ON SMART GRID AND CLEAN ENERGY TECHNOLOGIES (ICSGCE), 2018, : 181 - 185
  • [2] Building Energy Load Forecasting using Deep Neural Networks
    Marino, Daniel L.
    Amarasinghe, Kasun
    Manic, Milos
    [J]. PROCEEDINGS OF THE IECON 2016 - 42ND ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2016, : 7046 - 7051
  • [3] BACKPROPAGATION NEURAL NETWORKS FOR MODELING COMPLEX-SYSTEMS
    GOH, ATC
    [J]. ARTIFICIAL INTELLIGENCE IN ENGINEERING, 1995, 9 (03): : 143 - 151
  • [4] Complex Valued Deep Neural Networks for Nonlinear System Modeling
    Mario Lopez-Pacheco
    Wen Yu
    [J]. Neural Processing Letters, 2022, 54 : 559 - 580
  • [5] Complex Valued Deep Neural Networks for Nonlinear System Modeling
    Lopez-Pacheco, Mario
    Yu, Wen
    [J]. NEURAL PROCESSING LETTERS, 2022, 54 (01) : 559 - 580
  • [6] GA optimization for distributed energy systems in complex building blocks
    Kayo, Genku
    Ooka, Ryozo
    [J]. Journal of Environmental Engineering, 2010, 75 (649) : 297 - 303
  • [7] Modeling, case studies, and optimization methods for building energy systems
    Cremaschi, Lorenzo
    [J]. SCIENCE AND TECHNOLOGY FOR THE BUILT ENVIRONMENT, 2018, 24 (04) : 325 - 326
  • [8] Scour modeling using deep neural networks based on hyperparameter optimization
    Asim, Mohammed
    Rashid, Adnan
    Ahmad, Tanvir
    [J]. ICT EXPRESS, 2022, 8 (03): : 357 - 362
  • [9] Cascade Complex Systems - Global Modeling Using Neural Networks
    Dralus, Grzegorz
    Mazur, Damian
    [J]. 2016 13TH SELECTED ISSUES OF ELECTRICAL ENGINEERING AND ELECTRONICS (WZEE), 2016,
  • [10] Complex systems modeling using dynamic fuzzy neural networks
    Kwok, DP
    Deng, ZD
    Sun, DQ
    [J]. 1998 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AT THE IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE - PROCEEDINGS, VOL 1-2, 1998, : 1130 - 1135