基于数据挖掘的公共建筑能耗监管平台异常数据修复研究
摘要：公共建筑用能设备多、建筑面积大、使用人数多，具有较大的节能潜力。但由于建设费用有限导致的数据分项计量异常及传感器或采集器故障导致的数据缺失和突变等问题，其配套的建筑能耗监管平台获取的电耗数据经常出现数据异常问题。本文研究以聚类算法为基础，提出了一种由KNN-Matrix算法与KNN-Slope算法共同构成的异常数据修复体系。KNN-Slope算法根据异常数据当日用电趋势线，寻找用电趋势一致的最近历史电耗数据，以加权计算后的电耗值作为插补值进行异常数据修复。KNN-Matrix算法引入以矩阵形式表征的用电强度量化等级，寻找量化等级与用电趋势均一致的最近历史数据或平均历史数据作为插补值进行异常数据修复。结果显示，在面向不同数据异常比例和不同公共建筑类型时，上述修复体系可使99%的异常数据在修复后与真实数据的相对误差在30%以下，且相对误差最大值、平均值均大幅下降。
关键词：公共建筑能耗监管数据挖掘临近算法量化等级数据修复
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] 中国建筑节能协会能耗统计专委会.2018中国建筑能耗研究报告[J].建筑，2019(2):26- 31.
[2] DENG S M,BURNETT J.A study of energy performance of hotel buildings in Hong Kong[J].Energy and buildings,2000,31(1):7- 12.
[3] LEE W L,YIK F W H,JONES P.A strategy for prioritising interactive measures for enhancing energy efficiency of air-conditioned buildings[J].Energy,2003,28(8):877- 893.
[4] ZHANG Y,BAI X M,MILLS F P,et al.Rethinking the role of occupant behavior in building energy performance:a review[J].Energy and buildings,2018,172:279- 294.
[5] MA Z J,SONG J L,ZHANG J L.A real-time detection method of abnormal building energy consumption data coupled POD-LSE and FCD[J].Procedia engineering,2017,205:1657- 1664.
[6] SEEM J E.Using intelligent data analysis to detect abnormal energy consumption in buildings[J].Energy and buildings,2007,39(1):52- 58.
[7] SEEM J E.Pattern recognition algorithm for determining days of the week with similar energy consumption profiles[J].Energy and buildings,2005,37(2):127- 139.
[8] LIN G J,CLARIDGE D E.A temperature-based approach to detect abnormal building energy consumption[J].Energy and buildings,2015,93:110- 118.
[9] SEHGAL M S B,GONDAL I,DOOLEY L S.Collateral missing value imputation:a new robust missing value estimation algorithm for microarray data[J].Bioinformatics,2005,21(10):2417- 2423.
[10] KLINGENBERGER M,HIRSCH O,VOTSMEIER M.Efficient interpolation of precomputed kinetic data employing reduced multivariate Hermite Splines[J].Computers & chemical engineering,2017,98:21- 30.
[11] FUMO N,MAGO P,LUCK R.Methodology to estimate building energy consumption using EnergyPlus Benchmark Models[J].Energy and buildings,2010,42(12):2331- 2337.
[12] DING Y,WANG Q C,WANG Z X,et al.An occupancy-based model for building electricity consumption prediction:a case study of three campus buildings in Tianjin[J].Energy and buildings,2019,202:109412.
[13] NETO A H,FIORELLI F A S.Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption[J].Energy and buildings,2008,40(12):2169- 2176.
[14] IQBAL I,AL-HOMOUD M S.Parametric analysis of alternative energy conservation measures in an office building in hot and humid climate[J].Building and environment,2007,42(5):2166- 2177.
[15] SONG K,KWON N,ANDERSON K,et al.Predicting hourly energy consumption in buildings using occupancy-related characteristics of end-user groups[J].Energy and buildings,2017,156:121- 133.
[16] TROYANSKAYA O,CANTOR M,SHERLOCK G,et al.Missing value estimation methods for DNA microarrays[J].Bioinformatics,2001,17(6):520- 525.
[17] MA L D,XU Y Y,QIN Y G.Identifying abnormal energy consumption data of lighting and socket based on energy consumption characteristics[C]//The 2018 International Conference on Smart City and Intelligent Building,2019:59- 72.
[18] UJEED T,ZHAO T Y,MA L D,et al.Research on electricity consumption characteristics of centralized air conditioning units for data restoration of building energy consumption monitoring platform[C]//11th International Symposium on Heating,Ventilation and Air Conditioning (ISHVAC 2019),2020:1295- 1303.
[19] 许艺颖.建筑能耗监测平台异常数据的辨识与修复[D].大连：大连理工大学，2019:33- 34.
[2] DENG S M,BURNETT J.A study of energy performance of hotel buildings in Hong Kong[J].Energy and buildings,2000,31(1):7- 12.
[3] LEE W L,YIK F W H,JONES P.A strategy for prioritising interactive measures for enhancing energy efficiency of air-conditioned buildings[J].Energy,2003,28(8):877- 893.
[4] ZHANG Y,BAI X M,MILLS F P,et al.Rethinking the role of occupant behavior in building energy performance:a review[J].Energy and buildings,2018,172:279- 294.
[5] MA Z J,SONG J L,ZHANG J L.A real-time detection method of abnormal building energy consumption data coupled POD-LSE and FCD[J].Procedia engineering,2017,205:1657- 1664.
[6] SEEM J E.Using intelligent data analysis to detect abnormal energy consumption in buildings[J].Energy and buildings,2007,39(1):52- 58.
[7] SEEM J E.Pattern recognition algorithm for determining days of the week with similar energy consumption profiles[J].Energy and buildings,2005,37(2):127- 139.
[8] LIN G J,CLARIDGE D E.A temperature-based approach to detect abnormal building energy consumption[J].Energy and buildings,2015,93:110- 118.
[9] SEHGAL M S B,GONDAL I,DOOLEY L S.Collateral missing value imputation:a new robust missing value estimation algorithm for microarray data[J].Bioinformatics,2005,21(10):2417- 2423.
[10] KLINGENBERGER M,HIRSCH O,VOTSMEIER M.Efficient interpolation of precomputed kinetic data employing reduced multivariate Hermite Splines[J].Computers & chemical engineering,2017,98:21- 30.
[11] FUMO N,MAGO P,LUCK R.Methodology to estimate building energy consumption using EnergyPlus Benchmark Models[J].Energy and buildings,2010,42(12):2331- 2337.
[12] DING Y,WANG Q C,WANG Z X,et al.An occupancy-based model for building electricity consumption prediction:a case study of three campus buildings in Tianjin[J].Energy and buildings,2019,202:109412.
[13] NETO A H,FIORELLI F A S.Comparison between detailed model simulation and artificial neural network for forecasting building energy consumption[J].Energy and buildings,2008,40(12):2169- 2176.
[14] IQBAL I,AL-HOMOUD M S.Parametric analysis of alternative energy conservation measures in an office building in hot and humid climate[J].Building and environment,2007,42(5):2166- 2177.
[15] SONG K,KWON N,ANDERSON K,et al.Predicting hourly energy consumption in buildings using occupancy-related characteristics of end-user groups[J].Energy and buildings,2017,156:121- 133.
[16] TROYANSKAYA O,CANTOR M,SHERLOCK G,et al.Missing value estimation methods for DNA microarrays[J].Bioinformatics,2001,17(6):520- 525.
[17] MA L D,XU Y Y,QIN Y G.Identifying abnormal energy consumption data of lighting and socket based on energy consumption characteristics[C]//The 2018 International Conference on Smart City and Intelligent Building,2019:59- 72.
[18] UJEED T,ZHAO T Y,MA L D,et al.Research on electricity consumption characteristics of centralized air conditioning units for data restoration of building energy consumption monitoring platform[C]//11th International Symposium on Heating,Ventilation and Air Conditioning (ISHVAC 2019),2020:1295- 1303.
[19] 许艺颖.建筑能耗监测平台异常数据的辨识与修复[D].大连：大连理工大学，2019:33- 34.
Research on abnormal data repair of public building energy consumption monitoring platform based on data mining
Abstract: Public buildings have many energy-using equipment, large construction areas, and a large number of users, which have great energy-saving potential. However, due to the problems of the abnormal data itemization caused by limited construction costs and the data loss and mutation caused by sensor or collector failures, the power consumption data obtained by its supporting building energy consumption monitoring platform often have anomalies. Based on the clustering algorithm, this paper proposes an abnormal data repair system composed of KNN-Matrix algorithm and KNN-Slope algorithm. Based on the current power consumption trend line of the abnormal data, the KNN-Slope algorithm looks for the recent historical power consumption data that are consistent with power consumption trend, and uses the weighted calculated power consumption value as the interpolated value to repair the abnormal data. The KNN-Matrix algorithm introduces a quantitative grade of electricity intensity characterized in matrix form, and looks for the recent historical data or average historical data that are consistent with the power consumption trend as an interpolated value for abnormal data repair. The results show that when facing different data anomalies and different public building types, the above repair system can make 99% of the abnormal data have a relative error of less than 30% with the real data after repair, and the maximum and average values of the relative errors are greatly reduced.
Keywords: public building; energy consumption monitoring; data mining; proximity algorithm; quantitative grade; data repair;
474
0
0