基于PSO-LS-SVMR的公共建筑能耗短期预测模型
|
摘要
提出一种粒子群算法优化的最小二乘支持向量机回归模型(PSO-LS-SVMR),以实现对公共建筑能耗的短期预测。采用某大型公共建筑物连续31期的用电量及所在地区相关天气指标的实测数据,分别运用PSO-LS-SVMR模型和LMBP神经网络模型对其建筑能耗进行短期预测,并对预测结果展开深入研究。研究结果表明,提出的PSO-LS-SVMR模型在对样本内数据和样本外数据的预测上均取得了较好效果,可以满足公共建筑能耗短期预测的实际需要,为建筑节能管理提供理论支持与决策参考。
To forecast the short-term energy consumption of public building,a novel particle swarm optimization based least squares support vector machine regression model has been proposed. By selecting the monitoring data of a large public building as the original data,i. e. meteorological factors and daily energy consumption,the short-term energy consumption of the large public building was estimated with PSO-LS-SVMR and LMBP neural network separately based on the original data. In order to discover the differences in prediction effect of these models,the predictions were analyzed deeply in accuracy and rationality. The results indicated that the forecasting based on PSO-LS-SVMR is better than others when the samples are known or unknown. Meanwhile,the predictions of short-term public building energy consumption provide the theoretical basis and decision support for the energy-saving management.
To forecast the short-term energy consumption of public building,a novel particle swarm optimization based least squares support vector machine regression model has been proposed. By selecting the monitoring data of a large public building as the original data,i. e. meteorological factors and daily energy consumption,the short-term energy consumption of the large public building was estimated with PSO-LS-SVMR and LMBP neural network separately based on the original data. In order to discover the differences in prediction effect of these models,the predictions were analyzed deeply in accuracy and rationality. The results indicated that the forecasting based on PSO-LS-SVMR is better than others when the samples are known or unknown. Meanwhile,the predictions of short-term public building energy consumption provide the theoretical basis and decision support for the energy-saving management.
引文
[1]孙海玲,王红平.基于岭回归的城市建筑能耗增长驱动因素研究[J].城市发展研究,2013,20(5):21-24.
[2]刘魁星,王阳,刘刚,等.办公建筑空调系统能耗拆分方法研究[J].天津大学学报:自然科学与工程技术版,2018,51(5):522-526.
[3]杨柳,侯立强,李红莲,等.空调办公建筑能耗预测回归模型[J].西安建筑科技大学学报:自然科学版,2015,47(5):707-711.
[4]周峰,张立茂,秦文威,等.基于SVM的大型公共建筑能耗预测模型与异常诊断[J].土木工程与管理学报,2017,34(6):80-86.
[5]何春华,刘秀云,杨从斌,等.不同方法建立的建筑能耗模型比较[J/OL].沈阳工业大学学报:1-6[2018-06-21].http://kns.cnki.net/kcms/detail/21.1189.T.20180507.1544.008.html.
[6]姚丽丽,张红利,万玉建,等.一种面向大规模建筑群能耗预测的BP神经网络模型配置方法[J].建筑节能,2016,44(5):64-69.
[7]黄文,王正林.数据挖掘:R语言实战[M].北京:电子工业出版社,2014.
[8]Vladimir Vapnik.Estimation of dependences based on empirical data[M].New York,NY:Springer New York,2006.
[9]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[10]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5):481-484.
[11]Suykens J A K.Nonlinear Modelling and Support Vector Machines[C]//IMTC 2001.Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference,Budapest,May21-23,2001:287-294.
[12]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[13]Vladimir Vapnik,Esther Levin,Yann Le Cun.Measuring the vc-dimension of a learning machine[J].Neural Comput,1994,6(5):851-876.
[14]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005(2):302-304.
[15]董春曦,饶鲜,杨绍全,等.支持向量机参数选择方法研究[J].系统工程与电子技术,2004,26(8):1117-1120.
[16]熊忠阳,江帆,张玉芳,等.一种改进的多项式核支持向量机文本分类器[J].计算机应用研究,2009,26(8):2905-2907.
[17]赵超,戴坤成,王贵评.基于KPCA-WLSSVM的建筑能耗预测模型[J].土木建筑与环境工程,2015,37(5):109-115.
[18]王尉同,潘毅群,黄治钟.梯度渐进回归树在建筑能耗短期预测中的应用[J].建筑节能,2018,46(3):112-116.
[19]路阔,钟伯成.基于LMBP神经网络的建筑能耗短期预测[J].建筑节能,2014,42(11):79-81.
[20]李明财,郭军,史珺,等.利用采暖/制冷度日分析建筑能耗变化的适用性评估[J].气候变化研究进展,2013,9(1):43-48.
[21]Kennedy J,Eberhart R.Particle Swarm Optimization[C]//Proceedings of ICNN'95-International Conference on Neural Netw orks,Perth,WA,Australia,Nov.27-Dec.1,1995:1942-1948.
[22]Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[C]//M HS'95.Proceedings of the Sixth International Symposium on M icro M achine and Human Science,Nagoya,Japan,Oct.4-6,1995:39-43.
[23]王东风,孟丽.粒子群优化算法的性能分析和参数选择[J].自动化学报,2016,42(10):1552-1561.
[24]杜军岗,魏汝祥,刘宝平.基于PSO优化LS-SVM的小样本非线性协整检验与建模研究[J].系统工程理论与实践,2014,34(9):2322-2331.
[2]刘魁星,王阳,刘刚,等.办公建筑空调系统能耗拆分方法研究[J].天津大学学报:自然科学与工程技术版,2018,51(5):522-526.
[3]杨柳,侯立强,李红莲,等.空调办公建筑能耗预测回归模型[J].西安建筑科技大学学报:自然科学版,2015,47(5):707-711.
[4]周峰,张立茂,秦文威,等.基于SVM的大型公共建筑能耗预测模型与异常诊断[J].土木工程与管理学报,2017,34(6):80-86.
[5]何春华,刘秀云,杨从斌,等.不同方法建立的建筑能耗模型比较[J/OL].沈阳工业大学学报:1-6[2018-06-21].http://kns.cnki.net/kcms/detail/21.1189.T.20180507.1544.008.html.
[6]姚丽丽,张红利,万玉建,等.一种面向大规模建筑群能耗预测的BP神经网络模型配置方法[J].建筑节能,2016,44(5):64-69.
[7]黄文,王正林.数据挖掘:R语言实战[M].北京:电子工业出版社,2014.
[8]Vladimir Vapnik.Estimation of dependences based on empirical data[M].New York,NY:Springer New York,2006.
[9]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[10]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5):481-484.
[11]Suykens J A K.Nonlinear Modelling and Support Vector Machines[C]//IMTC 2001.Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference,Budapest,May21-23,2001:287-294.
[12]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-300.
[13]Vladimir Vapnik,Esther Levin,Yann Le Cun.Measuring the vc-dimension of a learning machine[J].Neural Comput,1994,6(5):851-876.
[14]李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005(2):302-304.
[15]董春曦,饶鲜,杨绍全,等.支持向量机参数选择方法研究[J].系统工程与电子技术,2004,26(8):1117-1120.
[16]熊忠阳,江帆,张玉芳,等.一种改进的多项式核支持向量机文本分类器[J].计算机应用研究,2009,26(8):2905-2907.
[17]赵超,戴坤成,王贵评.基于KPCA-WLSSVM的建筑能耗预测模型[J].土木建筑与环境工程,2015,37(5):109-115.
[18]王尉同,潘毅群,黄治钟.梯度渐进回归树在建筑能耗短期预测中的应用[J].建筑节能,2018,46(3):112-116.
[19]路阔,钟伯成.基于LMBP神经网络的建筑能耗短期预测[J].建筑节能,2014,42(11):79-81.
[20]李明财,郭军,史珺,等.利用采暖/制冷度日分析建筑能耗变化的适用性评估[J].气候变化研究进展,2013,9(1):43-48.
[21]Kennedy J,Eberhart R.Particle Swarm Optimization[C]//Proceedings of ICNN'95-International Conference on Neural Netw orks,Perth,WA,Australia,Nov.27-Dec.1,1995:1942-1948.
[22]Eberhart R,Kennedy J.A New Optimizer Using Particle Swarm Theory[C]//M HS'95.Proceedings of the Sixth International Symposium on M icro M achine and Human Science,Nagoya,Japan,Oct.4-6,1995:39-43.
[23]王东风,孟丽.粒子群优化算法的性能分析和参数选择[J].自动化学报,2016,42(10):1552-1561.
[24]杜军岗,魏汝祥,刘宝平.基于PSO优化LS-SVM的小样本非线性协整检验与建模研究[J].系统工程理论与实践,2014,34(9):2322-2331.