作者：金碧瑶, 李占培, 刘廷章, 张颖婍, 闫斌, 张修红

作者单位：上海大学机电工程与自动化学院 上海市电站自动化技术重点实验室, 上海 200072

关键词：冷负荷预测;建筑节能;ARX模型;辨识

摘要：

准确的冷负荷预测能减低空调能耗,对建筑节能意义重大。针对回归方法不能实时反映外部因素突变问题,提出一种实时气象因子和历史负荷为输入变量的自回归模型(ARX模型)的冷负荷预测方法。对辐射的情况进行分类,用最小二乘法辨识模型的参数,并与DeST仿真结果进行比较。实验结果表明:该方法可实现对冷负荷的逐时预测,具有良好的准确性,且简单有效。

Prediction method for room real-time cooling load based on ARX model

JIN Biyao, LI Zhanpei, LIU Tingzhang, ZHANG Yingqi, YAN Bin, ZHANG Xiuhong

Shanghai Key Laboratory of Power Station Automation Technology, School of Mechanical Engineering and Automation, Shanghai University, Shanghai 200072, China

Abstract: Accurate cooling load prediction helps to reduce air-conditioning energy consumption, which is essential to building energy saving. To solve the problem that regression method is unavailable in the application to the sudden change of real-time external factors, autoregressive with exogenous (ARX) model is proposed within the input of real time meteorological factor and historical load. Depending on the radiation, the parameter identified by least square method can be compared with that simulated by DeST. The methodology is proved to predict real-time cooling load precisely, it is more simple and effective.

Keywords: cooling load prediction;building energy saving;ARX model;identification

2016, 42(2): 132-135  收稿日期: 2015-4-11;收到修改稿日期: 2015-6-3

基金项目: 国家自然科学基金(61273190)

作者简介: 金碧瑶(1989-),女,浙江安吉县人,硕士研究生,专业方向为空调节能控制。

参考文献

[1] 李明财,郭军,史臖,等. 气候变化对天津市商场和居住建筑极端能耗的影响[J]. 高原气象,2014,33(2):574-583.
[2] GUO Y, NAZARIAN E, KO J, et al. Hourly cooling load forecasting using time-indexed ARX models with two-stage weighted least squares regression[J]. Energy Conversion and Management,2014(80):46-53.
[3] YUN K, CHO H, LUCK R, et al. Real-time combined heat and power operational strategy using a hierarchical optimization[C]∥Proceedings of the Institution of Mechanical Engineers,Part A:Journal of Power and Energy,2011,225(4):403-412.
[4] LI Q, MENG Q, CAI J, et al. Predicting hourly cooling load in the building: a comparison of support vector machine and different artificial neural networks[J]. Energy Convers Manage,2009,50(1):90-96.
[5] 徐今强,肖睿,黄冲,等. 基于温度区间的蓄冰空调负荷ARMAX模型[J]. 武汉理工大学学报,2009,10(31):109-112.
[6] PAI P, HONG W. Support vector machines with simulated annealing algorithms in electricity load forecasting[J]. Energy Convers Manage,2005,46(17):2669-2688.
[7] YAO Y, CHEN J. Global optimization of a central air-conditioning system using decomposition coordination method[J]. Energy and Buildings,2010,42(5):570-583.
[8] KUSIAK A, LI M, ZHANG Z. A data-driven approach for steam load prediction in building[J]. Applied Energy,2010,87(3):925-933.
[9] YUN K, LUCK R, MAGO P J, et al. Building hourly thermal load prediction using an indexed ARX model[J]. Energy and Buildings,2012(54):225-233.
[10] YOOL P, JONG-Il P. Analysis of energy perfor-mance by window directions in apartment[C]∥Summer Conference of Air-Conditioning Refrigeration Engineering,2012:1041-1044.
[11] 江亿. 建筑环境系统模拟分析方法——DeST[M]. 北京:中国建筑工业出版社,2006:117-141.