Modeling for indoor temperature prediction based on time-delay and Elman neural network in air conditioning system

Abstract An effective indoor temperature model would assist in improving energy efficiency and indoor thermal comfort of air conditioning system. However, it is difficult to build an accurate model due to lag response characteristic in the regulation process of indoor temperature. To solve this problem, the modeling and prediction methods for indoor temperature lag response characteristic based on time-delay neural network (TDNN) and Elman network neural (ENN) are presented. Then, taking variable air volume (VAV) air conditioning system as the study object, the effectiveness and practicability of proposed methods are validated using simulation sampling data and real-time operating data. Results indicate that ENN could be considered as a better modeling method for indoor temperature prediction for its simpler network structure, smaller storing space and better prediction accuracy. The contribution of this study is to provide an applicable online ANN modeling method for indoor temperature lag characteristic, and detailed training and validation for online implementation are presented, which will benefit for engineers and technicians to use in practical engineering. Meanwhile, this study provides the reference for online application of advanced intelligent algorithms in the building engineering.

[1]  Richard Marquez,et al.  An extension of predictive control, PID regulators and Smith predictors to some linear delay systems , 2002 .

[2]  Duc Truong Pham,et al.  Training of Elman networks and dynamic system modelling , 1996, Int. J. Syst. Sci..

[3]  Gabriele Comodi,et al.  The role of data sample size and dimensionality in neural network based forecasting of building heating related variables , 2016 .

[4]  Yue Yuan,et al.  Improving prediction performance for indoor temperature in public buildings based on a novel deep learning method , 2019, Building and Environment.

[5]  Farrokh Janabi-Sharifi,et al.  Review of modeling methods for HVAC systems , 2014 .

[6]  Ji-Hoon Jang,et al.  Prediction of optimum heating timing based on artificial neural network by utilizing BEMS data , 2019, Journal of Building Engineering.

[7]  Ye Yao,et al.  A state-space model for dynamic response of indoor air temperature and humidity , 2013 .

[8]  Jili Zhang,et al.  Predication control for indoor temperature time-delay using Elman neural network in variable air volume system , 2017 .

[9]  Shengwei Wang,et al.  Development of an adaptive Smith predictor-based self-tuning PI controller for an HVAC system in a test room , 2008 .

[10]  Huanxin Chen,et al.  Machine learning-based thermal response time ahead energy demand prediction for building heating systems , 2018, Applied Energy.

[11]  Gm. Shafiullah,et al.  Modeling techniques used in building HVAC control systems: A review , 2017 .

[12]  Ye Yao,et al.  A review of recent developments and technological advancements of variable-air-volume (VAV) air-conditioning systems , 2016 .

[13]  John Cosmas,et al.  Time-Delay Neural Network for Continuous Emotional Dimension Prediction From Facial Expression Sequences , 2016, IEEE Transactions on Cybernetics.

[14]  Pan Dongmei,et al.  Forecasting performance comparison of two hybrid machine learning models for cooling load of a large-scale commercial building , 2019, Journal of Building Engineering.

[15]  Xuemei Ren,et al.  Identification of Nonlinear Systems With Unknown Time Delay Based on Time-Delay Neural Networks , 2007, IEEE Transactions on Neural Networks.

[16]  Robert S. McLeod,et al.  Forecasting indoor temperatures during heatwaves using time series models , 2018, Building and Environment.

[17]  X. J. Luo,et al.  A novel clustering-enhanced adaptive artificial neural network model for predicting day-ahead building cooling demand , 2020 .

[18]  Jean-Pierre Richard,et al.  Time-delay systems: an overview of some recent advances and open problems , 2003, Autom..

[19]  Vugar E. Ismailov,et al.  On the approximation by neural networks with bounded number of neurons in hidden layers , 2014 .

[20]  Jerome A. Feldman,et al.  Dynamic connections in neural networks , 1990, Biological Cybernetics.

[21]  Min Xu,et al.  Practical generalized predictive control with decentralized identification approach to HVAC systems , 2007 .

[22]  Alfonso Capozzoli,et al.  Deep reinforcement learning to optimise indoor temperature control and heating energy consumption in buildings , 2020 .

[23]  Kotaro Hirasawa,et al.  Universal learning network and its application for nonlinear system with long time delay , 2006, Comput. Chem. Eng..