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

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.

Automated summary

This study proposed a modeling and prediction method for indoor temperature lag response characteristic based on time-delay neural network and Elman network neural, validated using variable air volume air conditioning system. Results showed that Elman network neural can be considered as a better modeling method with improved prediction accuracy and smaller storage space.