A Comparison of NARX and BP Neural Network in Short-Term Building Cooling Load Prediction

Abstract:

A comparison of nonlinear autoregression with exogenous inputs (NARX) neural network and back-propagation (BP) neural network in short-term prediction of building cooling load is presented in this dissertation. Both predictive models have been applied in a group of commercial buildings and analysis of prediction errors has been highlighted. Training and testing data for both prediction models have been generated from DeST (Designers Simulation Toolkits) with climate data of Shanghai. The simulation results indicate that NARX method can achieve better accuracy and generalization ability than traditional method of BP neural network. This work provides a key support in smooth and optimizing control in air-conditioning system.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 1545-1548
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.1545
• Online since: February 2014
• Authors: Yan Li Xu*, Hong Xun Chen, Wang Guo, Qiu Yu Zhu
• Keywords: BP Neural Network (BPNN), Cooling Load Prediction, HVAC, NARX

References

[1] Bronislav Chramcov, Forecast of Heat Demand according the Box-Jenkins Methodology for Specific Locality [J], Latest Trends on Systems.

[2] Abdullatif E. Ben-Nakhi, Mohamed A. Mahmoud, Cooling Load Prediction for Buildings using General Regression Neural Networks [J]. Energy Conversion and Management45: 2127–2141. (2004).

DOI: 10.1016/j.enconman.2003.10.009

[3] Masatoshi Sakawa, Kosuke Kato, Cooling Load Prediction in a District Heating and Cooling System through Simplified Robust Filter and Multilayered Neural Network [J], Applied Artificial Intelligence, 15: 633-643, (2001).

DOI: 10.1080/088395101750363975

[4] Qiong Li, Qinglin Meng, JiejinCai, Hiroshi Yoshino, Akashi Mochida, Applying Support Vector Machine to Predict Hourly Cooling Load in the Building [J], Applied Energy 2249–2256, (2009).

DOI: 10.1016/j.apenergy.2008.11.035

[5] Qiong Li, Qinglin Meng, Jiejin Cai, Hiroshi Yoshino, Akashi Mochida, Predicting Hourly Cooling Load in the Building: A Comparison of Support Vector Machine and Different Artificial Neural Networks, Energy Conversion and Management 50, 90–96, (2009).

DOI: 10.1016/j.enconman.2008.08.033

[6] Li Xuemei, Lu Jin-hu, Ding Lixing, Xu Gang, Li Jibin, Building Cooling Load Forecasting Model Based on LS-SVM [J]. Asia-Pacific Conference on Information Processing , (2009).

DOI: 10.1109/apcip.2009.22

[7] S.F. Fux; M.J. Benz; A. Ashouri; L. Guzzella, Short-term Thermal and Electric Load forecast in Buildings, CISBAT 2013 - September 4-6, (2013).

[8] Jos´e Maria P. J´unior and Guilherme A. Barreto, Long-Term Time Series Prediction with the NARX Network: An Empirical Evaluation, Preprint submitted to Elsevier Science. (2007).

[9] M. Ramasmy, H. Zabiri, N.T. Thanhha, N.M. Pamli, Heat Exchanger Performance Prediction Modeling using NARX-type Neural Networks, Proceedings of the WSEAS Int. Conf. on Waste Management, Water Pollution, Air Pollution, Indoor Climate, France, October 14-16, (2007).

[10] C. A. Mitrea, C. K. M. Lee, Z. Wu, A Comparison between Neural Networks and Traditional Forecasting Methods: A Case Study [J], International Journal of Engineering Business Management, Vol. 1, No. 2, pp.19-24, (2009).

DOI: 10.5772/6777

[11] Wei-Chiang Hong, Chaotic Particle Swarm Optimization Algorithm in a Support Vector Regression Electric Load Forecasting Model [J], Energy Conversion and Management. (2009).

DOI: 10.1016/j.enconman.2008.08.031