Abstract
The previous research on temperature prediction presented different approaches which are physical-rule based adaptive neuro-fuzzy inferential sensor (ANFIS) model and GA-BP (genetic algorithm back propagation) based model to estimate the average indoor temperature in the building environment. Their good prediction performances improved energy efficiency of district heating system and indoor comfort ratio. However, either of these two models has its drawback in a certain condition. In this paper, the two prediction models are reviewed and evaluated by three performance measures (RMSE, RMS, and R2). Their limitations are discussed and potential solution is proposed.
Publisher
Trans Tech Publications, Ltd.
Reference15 articles.
1. Liang Huang, Zaiyi Liao. A neuro-fuzzy based adaptive set-point heating exchanger control scheme in district heating system. The 7th International Symposium on Heating, Vetilation and Air Conditioning, (2011).
2. Liao Z, Dexter AL, An inferential control scheme for optimizing the operation of boilers in multi-zone heating systems. Building and Environment (2004); 39(9): 1009-18.
3. S. Jassar, Z. Liao and L. Zhao, Adaptive neuro-fuzzy based inferential sensor model for estimating the average air temperature in space heating systems, Building and Environment, (2009); 44: 1609-1616.
4. Liang Huang, Zaiyi Liao, Hua Ge, & Lian Zhao, Physical rules based adaptive neuro-fuzzy inferential sensor model for predicting the indoor temperature in heating system. Advantage Material Research, ICEEP (2012).
5. Abdennour A. Long horizon neuro-fuzzy predictor for MPEG video traffic. J King Saud Univ (2005); 18: 161–80.