基于模型校准的建筑冷负荷短期预测模型人工内扰特征变量获取方法
摘要：准确的短期建筑冷负荷预测对于建筑供能系统的运行优化具有重要意义。数据驱动模型因在挖掘建筑实际负荷特性、提高预测精度方面具有较大的优势而得到广泛应用。然而，内扰特征变量的缺失严重影响着数据驱动负荷预测模型的预测效果。为此，本文提出了一种利用模型校准技术从冷负荷时间序列中反向挖掘内扰相关数据信息的方法。案例研究结果表明，利用该方法获得的人工内扰特征变量数据对使用人工神经网络模型的短期建筑冷负荷预测效果的提升具有显著作用。相比于完全缺失内扰特征变量的预测模型，预测误差可降低11.46%,相比于使用日历信息作为内扰特征变量的预测模型，预测误差可降低6.51%。
关键词：负荷预测模型校准内扰时刻表数据驱动模型内扰特征变量
尊敬的用户，本篇文章需要2元，点击支付交费后阅读
限时优惠福利：领取VIP会员
全年期刊、VIP视频免费!
全年期刊、VIP视频免费!
参考文献[1] 姜玲玲，刘晓龙，葛琴，等.我国能源结构转型趋势与对策研究[J].中国能源，2020,42(9):15- 19,27.
[2] 龙惟定.碳中和城市建筑能源系统(1):能源篇[J].暖通空调，2022,52(3):2- 17.
[3] 龙惟定，潘毅群，王皙.碳中和城市建筑能源系统(3):负荷篇[J].暖通空调，2022,52(9):1- 14.
[4] 孙靖，程大章.基于季节性时间序列模型的空调负荷预测[J].电工技术学报，2004,19(3):88- 93.
[5] 于军琪，井文强，赵安军，等.基于改进PSO-BP算法的冷负荷预测模型[J].系统仿真学报，2021,33(1):54- 61.
[6] OLIVEIRA-LIMA J A,MORAIS R,MARTINS J F,et al.Load forecast on intelligent buildings based on temporary occupancy monitoring[J].Energy and buildings,2016,116:512- 521.
[7] 陈锐彬，李泽奇，黄永益.基于BP神经网络模型的大型公共建筑冷负荷预测[J].建设科技，2019(1):38- 42.
[8] KWOK S,LEE E.A study of the importance of occupancy to building cooling load in prediction by intelligent approach[J].Energy conversion and management,2011,52(7):2555- 2564.
[9] LÜ X S,LU T,KIBERT C J,et al.Modeling and forecasting energy consumption for heterogeneous buildings using a physical-statistical approach[J].Applied energy,2015,144:261- 275.
[10] MASSANA J,POUS C,BURGAS L,et al.Short-term load forecasting in a non-residential building contrasting models and attributes[J].Energy and buildings,2015,92:322- 330.
[11] DÍAZ J A,JIMÉNEZ M J.Experimental assessment of room occupancy patterns in an office building:comparison of different approaches based on CO2 concentrations and computer power consumption[J].Applied energy,2017,199:121- 141.
[12] SANDELS C,WIDEN J,NORDSTROM L,et al.Day-ahead predictions of electricity consumption in a Swedish office building from weather,occupancy,and temporal data[J].Energy and buildings,2015,108:279- 290.
[13] NETO A H,FIORELLI F.Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption[J].Energy and buildings,2008,40(12):2169- 2176.
[14] LEUNG P,LEE E.Estimation of electrical power consumption in subway station design by intelligent approach[J].Applied energy,2013,101:634- 643.
[15] HEO Y.Bayesian calibration of building energy models for energy retrofit decision-making under uncertainty[D].Georgia:Georgia Institute of Technology,2011:1- 129.
[16] CAMPOLONGO F,CARIBONI J,SALTELLI A.An effective screening design for sensitivity analysis of large models[J].Environmental modelling and software,2007,22(10):1509- 1518.
[17] LU S L,TANG X L,JI L R,et al.Research on energy-saving optimization for the performance parameters of rural-building shape and envelope by TRNSYS-GenOpt in hot summer and cold winter zone of China[J].Sustainability,2017,9(2):1- 18.
[18] ZHANG Q,TIAN Z,MAZ J,et al.Development of the heating load prediction model for the residential building of district heating based on model calibration[J].Energy,2020,205:117949.
[19] CACABELOS A,EGUÍA P,MÍGUEZ J L,et al.Calibrated simulation of a public library HVAC system with a ground-source heat pump and a radiant floor using TRNSYS and GenOpt[J].Energy and buildings,2015,108:114- 126.
[2] 龙惟定.碳中和城市建筑能源系统(1):能源篇[J].暖通空调，2022,52(3):2- 17.
[3] 龙惟定，潘毅群，王皙.碳中和城市建筑能源系统(3):负荷篇[J].暖通空调，2022,52(9):1- 14.
[4] 孙靖，程大章.基于季节性时间序列模型的空调负荷预测[J].电工技术学报，2004,19(3):88- 93.
[5] 于军琪，井文强，赵安军，等.基于改进PSO-BP算法的冷负荷预测模型[J].系统仿真学报，2021,33(1):54- 61.
[6] OLIVEIRA-LIMA J A,MORAIS R,MARTINS J F,et al.Load forecast on intelligent buildings based on temporary occupancy monitoring[J].Energy and buildings,2016,116:512- 521.
[7] 陈锐彬，李泽奇，黄永益.基于BP神经网络模型的大型公共建筑冷负荷预测[J].建设科技，2019(1):38- 42.
[8] KWOK S,LEE E.A study of the importance of occupancy to building cooling load in prediction by intelligent approach[J].Energy conversion and management,2011,52(7):2555- 2564.
[9] LÜ X S,LU T,KIBERT C J,et al.Modeling and forecasting energy consumption for heterogeneous buildings using a physical-statistical approach[J].Applied energy,2015,144:261- 275.
[10] MASSANA J,POUS C,BURGAS L,et al.Short-term load forecasting in a non-residential building contrasting models and attributes[J].Energy and buildings,2015,92:322- 330.
[11] DÍAZ J A,JIMÉNEZ M J.Experimental assessment of room occupancy patterns in an office building:comparison of different approaches based on CO2 concentrations and computer power consumption[J].Applied energy,2017,199:121- 141.
[12] SANDELS C,WIDEN J,NORDSTROM L,et al.Day-ahead predictions of electricity consumption in a Swedish office building from weather,occupancy,and temporal data[J].Energy and buildings,2015,108:279- 290.
[13] NETO A H,FIORELLI F.Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption[J].Energy and buildings,2008,40(12):2169- 2176.
[14] LEUNG P,LEE E.Estimation of electrical power consumption in subway station design by intelligent approach[J].Applied energy,2013,101:634- 643.
[15] HEO Y.Bayesian calibration of building energy models for energy retrofit decision-making under uncertainty[D].Georgia:Georgia Institute of Technology,2011:1- 129.
[16] CAMPOLONGO F,CARIBONI J,SALTELLI A.An effective screening design for sensitivity analysis of large models[J].Environmental modelling and software,2007,22(10):1509- 1518.
[17] LU S L,TANG X L,JI L R,et al.Research on energy-saving optimization for the performance parameters of rural-building shape and envelope by TRNSYS-GenOpt in hot summer and cold winter zone of China[J].Sustainability,2017,9(2):1- 18.
[18] ZHANG Q,TIAN Z,MAZ J,et al.Development of the heating load prediction model for the residential building of district heating based on model calibration[J].Energy,2020,205:117949.
[19] CACABELOS A,EGUÍA P,MÍGUEZ J L,et al.Calibrated simulation of a public library HVAC system with a ground-source heat pump and a radiant floor using TRNSYS and GenOpt[J].Energy and buildings,2015,108:114- 126.
Acquisition method of artificial internal disturbance feature variables for short-term prediction model of building cooling load based on model calibration
Abstract: Accurate prediction of short-term building cooling load is of great significance to the operation optimization of building energy supply systems. Data-driven models have been widely used due to their advantages in mining the actual building load characteristics and improving the prediction accuracy. However, the absence of internal disturbance feature variables seriously affects the prediction effect of data-driven load prediction models. Therefore, this paper proposes a method to mine internal disturbance data from cooling load time series using model calibration techniques. The case study results show that the data of artificial internal disturbance feature variables obtained by this method can significantly improve the prediction effect of short-term building cooling load using the artificial neural network model. The prediction error can be reduced by 11.46% compared to the prediction model without internal disturbance feature variables, and by 6.51% compared to the prediction model using calendar information as internal disturbance feature variables.
Keywords: load prediction; model calibration; internal disturbance schedule; data-driven model; internal disturbance feature variable;
615
0
0