基于时序算法的可再生能源建筑数据分析系统研究与实现
|
摘要
可再生能源建筑是我国建筑节能的发展方向。“十一五”国家科技支撑计划专门制定了“可再生能源与建筑集成技术研究与示范”重点项目。该项目对示范工程能源系统进行监测和技术经济评价,将完善可再生能源与建筑集成技术,并通过对示范成果的推广,提高可再生能源在降低民用建筑能耗中的贡献率。
为了评价不同种类可再生能源在建筑中的使用情况,本文在对大量数据分析的基础上搭建“可再生能源示范建筑数据分析系统”,重点研究可再生能源在建筑中替代常规能源的效果。通过对现有节能建筑评价体系的研究,基于时序算法提出适用于我国建筑行业范围内不同可再生能源使用效果的评价模型,从而对可再生能源在建筑中的使用效率提供标准。主要研究以下内容:
1.针对“十一五”可再生能源与建筑集成技术研究与示范重点项目,设计并实现基于web方式的可再生能源示范建筑数据分析平台。提出一种在Microsoft .NET开发平台上设计统一能源模型的方法,介绍平台的多层次系统框架和功能模块,对后台数据库设计、算法设计以及平台实现过程中相关的关键技术进行了阐述。
2.根据可再生能源与建筑集成项目的要求,设计由总体概念层、公共层、基础模型层组成的能源分析模型,并结合不同实例对模型进行了分析。3.在比较各种时间序列预测算法之后,根据可再生能源示范建筑的数据特点,采用Microsoft时序算法对经济指标进行预测,并通过实例证明Microsoft时序算法能很好对可再生能源监测系统的可再生能源利用率进行预测。
经过初步测试,本系统实现了各项设计目标,能够完成对5个建筑气候区、3种建筑集成可再生能源中23幢示范建筑的异构数据源信息集成,并完成数据统计、模型建立、数据预测、图形显示等功能。
It is the developing orientation for our country’s efforts in architecture economization to upgrade the technological innovation in the utilization of reproducible energy sources. Therefore, a key project entitled“the Academic and Demonstrative Project in Reproducible Energy Sources and Architecture Integration Technology”has been established in“the National Scientific and Technological Supporting Plan”in“the 11th Five-year Project”.
Our project aims to provide monitoring and evaluation in technological economics for the Energy Sources System of the Demonstrative Project, consummate the reproducible energy sources and architecture integration technology, and enhance the contribution rate of reproducible energy sources in reducing the energy consumption in civil architecture programs through efforts in promoting the achievements of the demonstrative project.
In order to estimate objectively the operation of different kinds of reproducible energy sources in architecture engineering, the writer of this thesis makes great efforts in establishing“the Data Analysis System for Reproducible Energy Sources in Demonstrative Architecture Programs,”on the basis of analyzing a great deal of data, with the emphasis on the effect of the substitution of reproducible energy sources for conventional ones.
On the basis of investigations on certain existing energy-economization evaluation systems, the writer proposes a evaluation model for different energy sources within the scopes of our country’s architecture industries, based on time-order algorithm,so as to provide a set of standards to estimate the utility efficiency of reproducible energy sources in architecture programs.
The main contents of this thesis are as follows:
(1) The writer makes efforts in designing and consummating a web-based data analysis platform for demonstrative architecture programs utilizing reproducible energy sources, so as to meet the demands of the key Academic and Demonstrative Project for Reproducible Energy Sources and Architecture Integration Technology, according to the 11th Five-year Project. Furthermore, the writer proposes a conception and method to design a universal energy-source model on the developing platform of Microsoft.Net System, introduces the multi-layer-structured systematic framework and all the functional blocks on the platform, and accounts for the relevant key techniques of the data-base designing, algorithm designing, and consummation of the platform as well.
(2) According to the requirements of the Reproducible Energy Sources and Architecture Integration Project, the writer constitutes a energy-source analysis model for the system, with a general conception layer, a public layer, and a basic model layer as well, and undertakes some analytic work on this model, combined with different examples selected from practice.
(3) After a comparison between a few time-ordered predictive algorithms, the writer adopts Microsoft time-ordered algorithm to predict the economic indicators, according to the data features of the reproducible energy-source demonstrative architecture programs, and justifies that this algorithm performs outstandingly in predicting the utilization rate of the reproducible energy sources in practical programs.
After several initial testing performances, this system is proved to meet all the targets for the design purposes, while it can fulfill the designations for data collection for multiple isomeric data sources from five different architecture climate zones as well as those from twenty-three demonstrative buildings with three kinds of reproducible energy sources for architecture integration, and consummate the functions such as data statistics, model establishments, data prediction, and image demonstrations.
为了评价不同种类可再生能源在建筑中的使用情况,本文在对大量数据分析的基础上搭建“可再生能源示范建筑数据分析系统”,重点研究可再生能源在建筑中替代常规能源的效果。通过对现有节能建筑评价体系的研究,基于时序算法提出适用于我国建筑行业范围内不同可再生能源使用效果的评价模型,从而对可再生能源在建筑中的使用效率提供标准。主要研究以下内容:
1.针对“十一五”可再生能源与建筑集成技术研究与示范重点项目,设计并实现基于web方式的可再生能源示范建筑数据分析平台。提出一种在Microsoft .NET开发平台上设计统一能源模型的方法,介绍平台的多层次系统框架和功能模块,对后台数据库设计、算法设计以及平台实现过程中相关的关键技术进行了阐述。
2.根据可再生能源与建筑集成项目的要求,设计由总体概念层、公共层、基础模型层组成的能源分析模型,并结合不同实例对模型进行了分析。3.在比较各种时间序列预测算法之后,根据可再生能源示范建筑的数据特点,采用Microsoft时序算法对经济指标进行预测,并通过实例证明Microsoft时序算法能很好对可再生能源监测系统的可再生能源利用率进行预测。
经过初步测试,本系统实现了各项设计目标,能够完成对5个建筑气候区、3种建筑集成可再生能源中23幢示范建筑的异构数据源信息集成,并完成数据统计、模型建立、数据预测、图形显示等功能。
It is the developing orientation for our country’s efforts in architecture economization to upgrade the technological innovation in the utilization of reproducible energy sources. Therefore, a key project entitled“the Academic and Demonstrative Project in Reproducible Energy Sources and Architecture Integration Technology”has been established in“the National Scientific and Technological Supporting Plan”in“the 11th Five-year Project”.
Our project aims to provide monitoring and evaluation in technological economics for the Energy Sources System of the Demonstrative Project, consummate the reproducible energy sources and architecture integration technology, and enhance the contribution rate of reproducible energy sources in reducing the energy consumption in civil architecture programs through efforts in promoting the achievements of the demonstrative project.
In order to estimate objectively the operation of different kinds of reproducible energy sources in architecture engineering, the writer of this thesis makes great efforts in establishing“the Data Analysis System for Reproducible Energy Sources in Demonstrative Architecture Programs,”on the basis of analyzing a great deal of data, with the emphasis on the effect of the substitution of reproducible energy sources for conventional ones.
On the basis of investigations on certain existing energy-economization evaluation systems, the writer proposes a evaluation model for different energy sources within the scopes of our country’s architecture industries, based on time-order algorithm,so as to provide a set of standards to estimate the utility efficiency of reproducible energy sources in architecture programs.
The main contents of this thesis are as follows:
(1) The writer makes efforts in designing and consummating a web-based data analysis platform for demonstrative architecture programs utilizing reproducible energy sources, so as to meet the demands of the key Academic and Demonstrative Project for Reproducible Energy Sources and Architecture Integration Technology, according to the 11th Five-year Project. Furthermore, the writer proposes a conception and method to design a universal energy-source model on the developing platform of Microsoft.Net System, introduces the multi-layer-structured systematic framework and all the functional blocks on the platform, and accounts for the relevant key techniques of the data-base designing, algorithm designing, and consummation of the platform as well.
(2) According to the requirements of the Reproducible Energy Sources and Architecture Integration Project, the writer constitutes a energy-source analysis model for the system, with a general conception layer, a public layer, and a basic model layer as well, and undertakes some analytic work on this model, combined with different examples selected from practice.
(3) After a comparison between a few time-ordered predictive algorithms, the writer adopts Microsoft time-ordered algorithm to predict the economic indicators, according to the data features of the reproducible energy-source demonstrative architecture programs, and justifies that this algorithm performs outstandingly in predicting the utilization rate of the reproducible energy sources in practical programs.
After several initial testing performances, this system is proved to meet all the targets for the design purposes, while it can fulfill the designations for data collection for multiple isomeric data sources from five different architecture climate zones as well as those from twenty-three demonstrative buildings with three kinds of reproducible energy sources for architecture integration, and consummate the functions such as data statistics, model establishments, data prediction, and image demonstrations.
引文
[1]王斌.西安地区办公建筑节能设计研究[D]:西安建筑科技大学, 2009.
[2]李金云.节能建筑评价体系研究[D]:西安建筑科技大学, 2009.
[3]黄璘.国家中长期科学和技术发展规划纲要[J].甘肃科技. 2006, 22(002): 1-1.
[4]徐莉燕.绿色建筑评价方法及模型研究[D]:同济大学, 2006.
[5] Tromly K, Burgert S, United States GBC 2000 Team: Supporting green buildings and communities for a healthy and prosperous planet, 2000, NREL/BR-810-29045, National Renewable Energy Laboratory, Golden, CO (US).
[6] Leed E. No Man's Land: Combat and Identity in World War 1[M]. Cambridge Univ Pr, 1981.
[7]建设部,民用建筑节能设计标准(采暖居住建筑部分)(JGJ26-95), 1995,北京:中国标准出版社.
[8]胡璘,杨善勤.新编《民用建筑节能设计标准》内容介绍[J].暖通空调. 1987, 17(2).
[9]王宁.节约能源法[J].中国轮胎资源综合利用. 2008, (007): 18-18.
[10]《夏热,冬冷地区居住建筑节能设计标准》JGJ 134-2001, 2001,北京:中国建筑工业出版社.
[11]住宅性能评定技术标准, 2005, GB Patent T50,362.
[12]建设部.民用建筑节能管理规定[J]. 1999.
[13]邓凤琴.新修订的《中华人民共和国节约能源法》专增设了“建筑节能”一节[J].工程建设标准化. 2008, (002): 38-38.
[14]绿色建筑评价标准, 2006, GB Patent T50,378.
[15]吴延鹏.公共建筑节能设计标准[J].暖通空调. 2005, 35(006): 101-101.
[16]建设部,建筑节能工程施工质量验收规范, 2007,北京:中国建筑工业出版社. p.
[17]江亿,林波荣.绿色奥运建筑评估体系[J].研究. 2004.
[18]邓毛颖.民用建筑能效测评标识技术导则[J].建设科技(建设部). 2008, (013): 7-7.
[19]龙惟定.建筑节能的行政手段与市场机制[J].建设科技(建设部). 2008, (001): 84-88.
[20] Priestley M. Spectral analysis and time series (Probability and mathematical statistics)[M]. Academic Press Limited, London, 1994.
[21]王勇.时序数据挖掘技术及其在水质预测中的应用研究[D]:广东工业大学, 2005.
[22]成刚,袁佩琦,陈瑾.北京市人均GDP的时间序列分析及预测[J].生产力研究. 2007, 3.
[23]严彬,李冠英.广东省区域经济增长的收敛性:时间序列的经验研究[J].现代经济:现代物业下半月. 2008, (006): 49-50.
[24]邵瑶,孙育河,梁岚珍.基于ARMA模型的风电场风速短期预测[J].电网与清洁能源. 2008, 24(7).
[25]施建刚,王万力.基于时间序列的房地产价格走势辨识[J].统计与决策. 2007, (016): 130-131.
[26]张正中,王华,王迎新.基于时间序列分析的餐饮市场需求预测模型[J].商业研究. 2008, (002): 44-46.
[27]叶美盈,汪晓东,张浩然.基于在线最小二乘支持向量机回归的混沌时间序列预测[J].物理学报. 2005, 54(006): 2568-2573.
[28]崔万照,朱长纯,保文星, et al.混沌时间序列的支持向量机预测[J].物理学报. 2004, 53(010): 3303-3310.
[29]汪成亮,宋军.智能神经网络在时序信号预测上的应用[J].重庆大学学报:自然科学版. 2003,26(001): 34-37.
[30]潘毅群,吴刚.建筑全能耗分析软件EnergyPlus及其应用[J].暖通空调. 2004, 34(009): 2-7.
[31] Winkelmann F, Birdsall B, Buhl W, et al. DOE-2 supplement, version 2.1 E[J]. LBL-34947. Berkeley, Calif.: Lawrence Berkeley Laboratory. 1993.
[32]燕达,张野,江亿.建筑环境设计模拟分析软件DeST—第7讲空气处理设备方案模拟分析[J].暖通空调. 2005, 35(001): 49-58.
[33] CHEN T, CHAN C, CHEN H, et al. Clinical characteristics and endoscopic findings associated with Blastocystis hominis in healthy adults[J]. The American journal of tropical medicine and hygiene. 2003, 69(2): 213.
[34] Tang Z, Maclennan J. Data mining with SQL Server 2005[M]. Wiley India Pvt. Ltd., 2005.
[35] Harter A, Hopper A, Steggles P, et al. The anatomy of a context-aware application[J]. Wireless Networks. 2002, 8(2): 187-197.
[36] Richter J, Balena F. Applied Microsoft. NET framework programming[M]. Microsoft Press Redmond, VA, 2002.
[37]吴延鹏.中华人民共和国可再生能源法[J].暖通空调. 2005, 35(005): 122-122.
[38] Meek C, Chickering D, Heckerman D. Autoregressive tree models for time-series analysis[A]. 2002. 229–244.
[39] de Oliveira P. Séries Temporais: Analisar o Passado, Predizer o Futuro[J].
[40]陈玉祥.指数平滑法[J].汽车与配件. 1984, 4.
[41] Urushibara A, Moritomo Y, Arima T, et al. Insulator-metal transition and giant magnetoresistance in La_ {1-x} Sr_ {x} MnO_ {3}[J]. Physical Review B. 1995, 51(20): 14103-14109.
[42]王国林.塔西南地区地层剥蚀厚度恢复研究[J].石油学报. 2002, (01).
[43]陈磊.数据挖掘技术在处理交通流数据中的研究及应用[D]:长安大学, 2009.
[44]郑瑞澄.民用建筑太阳能热水系统工程技术手册[M].化学工业出版社, 2006.
[45]赵争鸣.太阳能光伏发电及其应用[M].科学出版社, 2005.
[46]陈焕新,杨培志.地源热泵[J].太阳能. 2001, 4.
[47]李戬洪,马伟斌,江晴, et al. 100kW太阳能制冷空调系统[J].太阳能学报. 1999, 20(003): 239-243.
[48]王飞,余世杰,苏建徽, et al.太阳能光伏并网发电系统的研究[J].电工技术学报. 2005, 20(005): 72-74.
[49]赵军.竖直埋管型地源热泵地下传热及热力性能的研究[D]:天津大学, 2003.
[50] Phillips P, Perron P. Testing for a unit root in time series regression[J]. Biometrika. 1988, 75(2): 335.
[51] Dickey D, Fuller W. Distribution of the estimators for autoregressive time series with a unit root[J]. Journal of the American statistical association. 1979, 74(366): 427-431.
[52] Harvey A. Time series models[M]. Harvester Wheatsheaf New York, 1993.
[53] Brockwell P, Davis R. Time series: theory and methods[M]. Springer, 1991.
[54] Chongchong Y, Qidi Y. The Application of PMML in Healthy Housing Evaluation and Rules Discovery Decision Support System[A]. IEEE Computer Society, 2008. 459-465.
[55] Clark J. XSL transformations (XSLT) version 1.0[J]. W3C Recommendation. 1999, 16(11).
[56]吴志勇,孙乐昌,王岩, et al.一个关于漏洞扫描插件的调度算法[J].安徽大学学报:自然科学版. 2008, 32(004): 36-40.
[57] Janis I, Mann L. Decision making: A psychological analysis of conflict, choice, and commitment[M]. The Free Press New York, 1977.
[58] Selinger P, Astrahan M, Chamberlin D, et al. Access path selection in a relational database management system[A]. ACM New York, NY, USA, 1979. 23-34.
[59] Paolucci M, Kawamura T, Payne T, et al. Semantic matching of web services capabilities[J]. Lecture Notes in Computer Science. 2002: 333-347.
[60] Dewey B. The embedded librarian: Strategic campus collaborations[J]. Libraries within their institutions: creative collaborations. 2005: 5.
[2]李金云.节能建筑评价体系研究[D]:西安建筑科技大学, 2009.
[3]黄璘.国家中长期科学和技术发展规划纲要[J].甘肃科技. 2006, 22(002): 1-1.
[4]徐莉燕.绿色建筑评价方法及模型研究[D]:同济大学, 2006.
[5] Tromly K, Burgert S, United States GBC 2000 Team: Supporting green buildings and communities for a healthy and prosperous planet, 2000, NREL/BR-810-29045, National Renewable Energy Laboratory, Golden, CO (US).
[6] Leed E. No Man's Land: Combat and Identity in World War 1[M]. Cambridge Univ Pr, 1981.
[7]建设部,民用建筑节能设计标准(采暖居住建筑部分)(JGJ26-95), 1995,北京:中国标准出版社.
[8]胡璘,杨善勤.新编《民用建筑节能设计标准》内容介绍[J].暖通空调. 1987, 17(2).
[9]王宁.节约能源法[J].中国轮胎资源综合利用. 2008, (007): 18-18.
[10]《夏热,冬冷地区居住建筑节能设计标准》JGJ 134-2001, 2001,北京:中国建筑工业出版社.
[11]住宅性能评定技术标准, 2005, GB Patent T50,362.
[12]建设部.民用建筑节能管理规定[J]. 1999.
[13]邓凤琴.新修订的《中华人民共和国节约能源法》专增设了“建筑节能”一节[J].工程建设标准化. 2008, (002): 38-38.
[14]绿色建筑评价标准, 2006, GB Patent T50,378.
[15]吴延鹏.公共建筑节能设计标准[J].暖通空调. 2005, 35(006): 101-101.
[16]建设部,建筑节能工程施工质量验收规范, 2007,北京:中国建筑工业出版社. p.
[17]江亿,林波荣.绿色奥运建筑评估体系[J].研究. 2004.
[18]邓毛颖.民用建筑能效测评标识技术导则[J].建设科技(建设部). 2008, (013): 7-7.
[19]龙惟定.建筑节能的行政手段与市场机制[J].建设科技(建设部). 2008, (001): 84-88.
[20] Priestley M. Spectral analysis and time series (Probability and mathematical statistics)[M]. Academic Press Limited, London, 1994.
[21]王勇.时序数据挖掘技术及其在水质预测中的应用研究[D]:广东工业大学, 2005.
[22]成刚,袁佩琦,陈瑾.北京市人均GDP的时间序列分析及预测[J].生产力研究. 2007, 3.
[23]严彬,李冠英.广东省区域经济增长的收敛性:时间序列的经验研究[J].现代经济:现代物业下半月. 2008, (006): 49-50.
[24]邵瑶,孙育河,梁岚珍.基于ARMA模型的风电场风速短期预测[J].电网与清洁能源. 2008, 24(7).
[25]施建刚,王万力.基于时间序列的房地产价格走势辨识[J].统计与决策. 2007, (016): 130-131.
[26]张正中,王华,王迎新.基于时间序列分析的餐饮市场需求预测模型[J].商业研究. 2008, (002): 44-46.
[27]叶美盈,汪晓东,张浩然.基于在线最小二乘支持向量机回归的混沌时间序列预测[J].物理学报. 2005, 54(006): 2568-2573.
[28]崔万照,朱长纯,保文星, et al.混沌时间序列的支持向量机预测[J].物理学报. 2004, 53(010): 3303-3310.
[29]汪成亮,宋军.智能神经网络在时序信号预测上的应用[J].重庆大学学报:自然科学版. 2003,26(001): 34-37.
[30]潘毅群,吴刚.建筑全能耗分析软件EnergyPlus及其应用[J].暖通空调. 2004, 34(009): 2-7.
[31] Winkelmann F, Birdsall B, Buhl W, et al. DOE-2 supplement, version 2.1 E[J]. LBL-34947. Berkeley, Calif.: Lawrence Berkeley Laboratory. 1993.
[32]燕达,张野,江亿.建筑环境设计模拟分析软件DeST—第7讲空气处理设备方案模拟分析[J].暖通空调. 2005, 35(001): 49-58.
[33] CHEN T, CHAN C, CHEN H, et al. Clinical characteristics and endoscopic findings associated with Blastocystis hominis in healthy adults[J]. The American journal of tropical medicine and hygiene. 2003, 69(2): 213.
[34] Tang Z, Maclennan J. Data mining with SQL Server 2005[M]. Wiley India Pvt. Ltd., 2005.
[35] Harter A, Hopper A, Steggles P, et al. The anatomy of a context-aware application[J]. Wireless Networks. 2002, 8(2): 187-197.
[36] Richter J, Balena F. Applied Microsoft. NET framework programming[M]. Microsoft Press Redmond, VA, 2002.
[37]吴延鹏.中华人民共和国可再生能源法[J].暖通空调. 2005, 35(005): 122-122.
[38] Meek C, Chickering D, Heckerman D. Autoregressive tree models for time-series analysis[A]. 2002. 229–244.
[39] de Oliveira P. Séries Temporais: Analisar o Passado, Predizer o Futuro[J].
[40]陈玉祥.指数平滑法[J].汽车与配件. 1984, 4.
[41] Urushibara A, Moritomo Y, Arima T, et al. Insulator-metal transition and giant magnetoresistance in La_ {1-x} Sr_ {x} MnO_ {3}[J]. Physical Review B. 1995, 51(20): 14103-14109.
[42]王国林.塔西南地区地层剥蚀厚度恢复研究[J].石油学报. 2002, (01).
[43]陈磊.数据挖掘技术在处理交通流数据中的研究及应用[D]:长安大学, 2009.
[44]郑瑞澄.民用建筑太阳能热水系统工程技术手册[M].化学工业出版社, 2006.
[45]赵争鸣.太阳能光伏发电及其应用[M].科学出版社, 2005.
[46]陈焕新,杨培志.地源热泵[J].太阳能. 2001, 4.
[47]李戬洪,马伟斌,江晴, et al. 100kW太阳能制冷空调系统[J].太阳能学报. 1999, 20(003): 239-243.
[48]王飞,余世杰,苏建徽, et al.太阳能光伏并网发电系统的研究[J].电工技术学报. 2005, 20(005): 72-74.
[49]赵军.竖直埋管型地源热泵地下传热及热力性能的研究[D]:天津大学, 2003.
[50] Phillips P, Perron P. Testing for a unit root in time series regression[J]. Biometrika. 1988, 75(2): 335.
[51] Dickey D, Fuller W. Distribution of the estimators for autoregressive time series with a unit root[J]. Journal of the American statistical association. 1979, 74(366): 427-431.
[52] Harvey A. Time series models[M]. Harvester Wheatsheaf New York, 1993.
[53] Brockwell P, Davis R. Time series: theory and methods[M]. Springer, 1991.
[54] Chongchong Y, Qidi Y. The Application of PMML in Healthy Housing Evaluation and Rules Discovery Decision Support System[A]. IEEE Computer Society, 2008. 459-465.
[55] Clark J. XSL transformations (XSLT) version 1.0[J]. W3C Recommendation. 1999, 16(11).
[56]吴志勇,孙乐昌,王岩, et al.一个关于漏洞扫描插件的调度算法[J].安徽大学学报:自然科学版. 2008, 32(004): 36-40.
[57] Janis I, Mann L. Decision making: A psychological analysis of conflict, choice, and commitment[M]. The Free Press New York, 1977.
[58] Selinger P, Astrahan M, Chamberlin D, et al. Access path selection in a relational database management system[A]. ACM New York, NY, USA, 1979. 23-34.
[59] Paolucci M, Kawamura T, Payne T, et al. Semantic matching of web services capabilities[J]. Lecture Notes in Computer Science. 2002: 333-347.
[60] Dewey B. The embedded librarian: Strategic campus collaborations[J]. Libraries within their institutions: creative collaborations. 2005: 5.