山东大学学报 (工学版) ›› 2022, Vol. 52 ›› Issue (1): 9-18.doi: 10.6040/j.issn.1672-3961.0.2021.308
• • 上一篇
孙鸿昌1,周风余1*,单明珠2,翟文文2,牛兰强2
SUN Hongchang1, ZHOU Fengyu1*, SHAN Mingzhu2, ZHAI Wenwen2, NIU Lanqiang2
摘要： 针对公共建筑能耗监测平台采集的空调能耗数据存在缺失、异常等问题,提出一种将无监督学习与监督学习结合的基于模式划分的空调能耗混合填补方法。利用k-means聚类算法将空调能耗数据划分至制冷、制热和独立新风3种运行模式中。在制冷及制热模式下,提出了一种BP神经网络(back propagation neural network, BPNN)和改进粒子群优化算法(ameliorate particle swarm optimization, APSO)相结合的混合填补策略,进行能耗填补,采用随机森林(random forest, RF)作为特征提取策略,用改进的惯性权重和速度更新方程的APSO优化BPNN的初始参数;在独立新风模式下,采用k最邻近算法(k-nearest neighbor, kNN)填补能耗。青岛市某商场空调能耗试验数据分析结果表明,与RF-APSO-BPNN算法、BPNN算法、小脑神经网络算法(cerebellar model articulation controller, CMAC)相比,本研究方法填补空调能耗的平均百分比误差分别减少了53.44%、69.39%、62.15%。RF-APSO-BPNN-kNN混合方法填补空调能耗更优于其他算法。
中图分类号:
| [1] 丁勇,吕婕. 公共建筑能耗与能效披露制度试点问题与建议[J]. 暖通空调, 2021, 51(8): 70-77. DING Y, LÜ J. Problems and suggestions on pilot of building energy consumption and energy efficiency disclosure systems [J]. Journal of HV&AC, 2021, 51(8): 70-77. [2] 梁金涵,章文杰,林常青,等. 新型城镇化背景下中国建筑能耗总量分析与政策建议[J]. 制冷与空调, 2020, 34(2): 175-184. LIANG J H, ZHANG W J, LIN C Q, et al. Analysis of China's total building energy consumption and policy proposal under the background of new urbanization[J]. Refrigeration and Air Conditioning, 2020, 34(2): 175-184. [3] WANG T H. Research on influencing factors and prediction model of public building energy consumption in colleges and universities[D]. Xi'an: Xi'an University of Architecture and Technology, 2018. [4] FAN C, XIAO F, MADSEN H, et al. Temporal knowledge discovery in big BAS data for building energy management[J]. Energy and Buildings, 2015, 109: 75-89. [5] FAN C, XIAO F, YAN C C. A framework for knowledge discovery in massive building automation data and its application in building diagnostics[J]. Automation in Construction, 2015, 50: 81-90. [6] MOR G, CIPRIANO J, MARTIRANO G, et al. A data-driven method for unsupervised electricity consumption characterisation at the district level and beyond[J]. Energy Reports, 2021, 7: 5667-5684. [7] 李梅香,彭惠旺,陈毅兴,等. 商场建筑运行能耗实测数据修复方法研究[J]. 建筑节能, 2021, 49(5): 37-45. LI M X, PENG H W, CHEN Y X, et al. A novel method of shopping mall energy consumption data restoration[J]. Journal of Building Energy Efficiency, 2021, 49(5): 37-45. [8] 周璇,崔少伟,周裕东. 办公建筑逐时能耗异常数据在线插补方法[J]. 建筑科学, 2018, 34(6): 82-90. ZHOU X, CUI S W, ZHOU Y D. Online interpolation methods for abnormal data of hourly energy consumption of office buildings[J]. Building Science, 2018, 34(6): 82-90. [9] SHAO M L, WANG X, BU Z, et al. Prediction of energy consumption in hotel buildings via support vector machines[J]. Sustainable Cities and Society, 2020, 57: 102-128. [10] 周优,陈义波,谭洪卫,等. 公共建筑电耗监测数据缺失及异常的预处理方法探究[J]. 建筑技术, 2018, 49(5): 469-472. ZHOU Y, CHEN Y B, TAN H W, et al. Study on preprocessing methods of missing and abnormal monitored electricity consumed in public buildings[J]. Architecture Technology, 2018, 49(5): 469-472. [11] 章挺飞, 罗恒, 刘杭. 基于LSTM网络的建筑能耗预测方法[J]. 苏州科技大学学报(自然科学版), 2020, 37(4): 78-84. ZHANG T F, LUO H, LIU H. Prediction of building energy consumption based on LSTM[J]. Journal of Suzhou University of Science and Technology(Natural Science), 2020, 37(4): 78-84. [12] KAPETANAKIS D S, MANGINA E, FINN D P. Input variable selection for thermal load predictive models of commercial buildings[J]. Energy and Buildings, 2017, 137: 13-26. [13] DING Y, ZHANG Q, YUAN T H, et al. Effect of input variables on cooling load prediction accuracy of an office building[J]. Applied Thermal Engineering, 2018, 128: 225-234. [14] BIAN H, ZHONG Y, SUN J, et al. Study on power consumption load forecast based on K-means clustering and FCM-BP model[J]. Energy Reports, 2020, 6:693-700. [15] ROSTAM M G, SADATINEJAD S J, MALEKIAN A. Precipitation forecasting by large-scale climate indices and machine learning techniques[J]. Journal of Arid Land, 2020, 12(5): 854-864. [16] 张雪嫣,黎晓东,孙洁香. 基于随机森林的烟草烘丝设备参数数据相关性分析研究[J]. 制造业自动化, 2019, 41(8): 145-148. ZHANG X Y, LI X D, SUN J X. Correlation analysis of parameter data of tobacco drying equipment based on random forest[J]. Manufacturing Automation, 2019, 41(8): 145-148. [17] YU M, YANG J Q, LU Y, et al. BP-ANN model coupled with particle swarm optimization for the efficient prediction of 2-chlorophenol removal in an electro-oxidation system[J]. International Journal of Environmental Research and Public Health, 2019, 16(14): 24-54. [18] HEFNY H A, AZAB S S. Chaotic particle swarm optimization[C] //2010 the 7th International Conference on Informatics and Systems(INFOS). Cairo, Egypt: IEEE, 2010: 1-8. [19] 李洪奇, 杨中国, 朱丽萍, 等. 基于数据集特征的KNN最优K值预测方法[J]. 计算机应用与软件, 2016, 33(6): 54-58. LI H Q, YANG Z G, ZHU L P, et al. Prediction method of optimal K value in KNN based on dataset features[J]. Computer Applications and Software, 2016, 33(6): 54-58. [20] 谢霖铨,赵楠,徐浩,等. 基于属性相关性的KNN近邻填补算法改进[J]. 江西理工大学学报, 2019, 40(1): 95-101. XIE L Q, ZHAO N, XU H, et al. KNN nearest neighbor filling algorithm based on attribute correlation[J]. Journal of Jiangxi University of Science and Technology, 2019, 40(1): 95-101. [21] MARTINO A, GHIGLIETTI A, IEVA F, et al. A k-means procedure based on a Mahalanobis type distance for clustering multivariate functional data[J]. Statistical Methods and Applications, 2019, 28: 301-322. |
| [1] | 袁高腾,刘毅慧,黄伟,胡兵. 基于Gabor特征的乳腺肿瘤MR图像分类识别模型[J]. 山东大学学报 (工学版), 2020, 50(3): 15-23. |
| [2] | 高铭壑,张莹,张蓉蓉,黄子豪,黄琳焱,李繁菀,张昕,王彦浩. 基于预测数据特征的空气质量预测方法[J]. 山东大学学报 (工学版), 2020, 50(2): 91-99. |
| [3] | 张大鹏,刘雅军,张伟,沈芬,杨建盛. 基于异质集成学习的虚假评论检测[J]. 山东大学学报 (工学版), 2020, 50(2): 1-9. |
| [4] | 刘玉田, 孙润稼, 王洪涛, 顾雪平. 人工智能在电力系统恢复中的应用综述[J]. 山东大学学报 (工学版), 2019, 49(5): 1-8. |
| [5] | 李童,马然,郑鸿鹤,安平,胡翔宇. 基于视频统计特征的差错敏感度模型[J]. 山东大学学报 (工学版), 2019, 49(2): 116-121. |
| [6] | 邹启杰,李昊宇,张汝波,裴腾达,刘艳. 自主驾驶的人机交互控制[J]. 山东大学学报 (工学版), 2019, 49(2): 23-33. |
| [7] | 张冕,黄颖,梅海艺,郭毓. 基于Kinect的配电作业机器人智能人机交互方法[J]. 山东大学学报 (工学版), 2018, 48(5): 103-108. |
| [8] | 刘洋,刘博,王峰. 基于Parameter Server框架的大数据挖掘优化算法[J]. 山东大学学报(工学版), 2017, 47(4): 1-6. |
| [9] | 魏波,张文生,李元香,夏学文,吕敬钦. 一种选择特征的稀疏在线学习算法[J]. 山东大学学报(工学版), 2017, 47(1): 22-27. |
| [10] | 周旺,张晨麟,吴建鑫. 一种基于Hartigan-Wong和Lloyd的定性平衡聚类算法[J]. 山东大学学报(工学版), 2016, 46(5): 37-44. |
| [11] | 孟令恒,丁世飞. 基于单静态图像的深度感知模型[J]. 山东大学学报(工学版), 2016, 46(3): 37-43. |
| [12] | 刘杰, 杨鹏, 吕文生, 刘阿古达木, 刘俊秀. 基于气象因素的PM2.5质量浓度预测模型[J]. 山东大学学报(工学版), 2015, 45(6): 76-83. |
| [13] | 郑毅, 朱成璋. 基于深度信念网络的PM2.5预测[J]. 山东大学学报(工学版), 2014, 44(6): 19-25. |
| [14] | 谢琳1,殷熙尧2,李凡长3,吴佳3. 一种逆归结学习表示[J]. 山东大学学报(工学版), 2013, 43(4): 46-50. |
| [15] | 何雪英1,2, 秦伟1, 尹义龙1*, 赵联征1,乔昊3. 基于机器学习的视频指纹识别[J]. 山东大学学报(工学版), 2011, 41(4): 29-33. |
|
||
