Estimation of the building energy use intensity in the urban scale by integrating GIS and big data technology
Estimation of the building energy use intensity in the urban scale by integrating GIS and big data technology
复制标题
DOI：
10.1016/j.apenergy.2016.08.079
复制
发表时间：
2016-12
期刊：
影响因子：
11.2
通讯作者：
Jun Ma;Jack C. P. Cheng
中科院分区：
文献类型：
--
作者：
Jun Ma;Jack C. P. Cheng
建筑物是城市地区能源消耗的主要来源。城市尺度建筑能耗强度的准确建模与预测在能源标杆管理、城市能源基础设施规划等方面具有重要的应用价值。大数据技术的使用有望整合大量预测因子，准确预测城市范围内建筑物的能源使用强度。然而，由于数据收集和特征工程等方面的挑战，过去的研究经常使用大数据技术来估计单个建筑物的能耗，而不是城市规模的能耗。因此，本文提出了一个地理信息系统集成的数据挖掘方法框架，估计在城市规模的建筑物EUI，包括预处理，功能选择，算法优化。基于216准备的功能，估计在纽约市的3640多户住宅建筑的网站EUI的案例研究，进行了测试和验证，使用建议的方法框架。在案例研究中还对特征选择策略和常用的回归算法进行了比较研究。结果表明，该框架能够帮助产生比以往研究更低的估计误差，并且支持向量回归算法在弹性网络选择的特征上建立的模型具有最小的交叉验证均方误差。
Buildings are the major source of energy consumption in urban areas. Accurate modeling and forecasting of the building energy use intensity (EUI) in the urban scale have many important applications, such as energy benchmarking and urban energy infrastructure planning. The use of Big Data technology is expected to have the capability of integrating a large number of predictors and giving an accurate prediction of the energy use intensity of buildings in the urban scale. However, past research has often used Big Data technology in estimating energy consumption of a single building rather than the urban scale, due to several challenges such as data collection and feature engineering. This paper therefore proposes a geographic information system integrated data mining methodology framework for estimating the building EUI in the urban scale, including preprocessing, feature selection, and algorithm optimization. Based on 216 prepared features, a case study on estimating the site EUI of 3640 multi-family residential buildings in New York City, was tested and validated using the proposed methodology framework. A comparative study on the feature selection strategies and the commonly used regression algorithms was also included in the case study. The results show that the framework was able to help produce lower estimation errors than previous research, and the model built by the Support Vector Regression algorithm on the features selected by Elastic Net has the least cross-validation mean squared error.