...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Energy Conversion & Management >Association rule mining based quantitative analysis approach of household characteristics impacts on residential electricity consumption patterns
【24h】

Association rule mining based quantitative analysis approach of household characteristics impacts on residential electricity consumption patterns

机译：基于关联规则挖掘的家庭特征对居民用电模式影响的定量分析方法

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The comprehensive understanding of the residential electricity consumption patterns (ECPs) and how they relate to household characteristics can contribute to energy efficiency improvement and electricity consumption reduction in the residential sector. After recognizing the limitations of current studies (i.e. unreasonable typical ECP (TECP) extraction method and the problem of multicollinearity and interpretability for regression and machine learning models), this paper proposes an association rule mining based quantitative analysis approach of household characteristics impact on residential ECPs trying to address them together. First, an adaptive density-based spatial clustering of applications with noise (DBSCAN) algorithm is utilized to create seasonal TECP of each individual customer only for weekdays. K-means is then adopted to group all the TECPs into several clusters. An enhanced Apriori algorithm is proposed to reveal the relationships between TECPs and thirty five factors covering four categories of household characteristics including dwelling characteristics, socio-demographic, appliances and heating and attitudes towards energy. Results of the case study using 3326 records containing smart metering data and survey information in Ireland suggest that socio-demographic and cooking related factors such as employment status, occupants and whether cook by electricity have strong significant associations with TECPs, while attitudes related factors almost have no effect on TECPs. The results also indicate that those households with more than one person are more likely to change ECP across seasons. The proposed approach and the findings of this study can help to support decisions about how to reduce electricity consumption and CO2 emissions.
机译：对住宅用电模式（ECP）及其与家庭特征的关系的全面了解可以有助于提高住宅部门的能效和减少用电。在认识到当前研究的局限性（即不合理的典型ECP（TECP）提取方法以及回归模型和机器学习模型的多重共线性和可解释性问题）之后，本文提出了一种基于关联规则挖掘的家庭特征对住宅ECP影响的定量分析方法试图一起解决他们。首先，利用基于噪声的应用程序基于密度的自适应空间聚类（DBSCAN）算法，仅在工作日中为每个客户创建季节性的TECP。然后采用K均值将所有TECP分为几个集群。提出了一种改进的Apriori算法，以揭示TECP与35个因素之间的关系，这些因素涵盖了四类家庭特征，包括居住特征，社会人口统计学，家用电器和供暖以及对能源的态度。案例研究的结果使用了3326条包含智能计量数据和爱尔兰调查信息的记录，表明与社会人口统计学和烹饪相关的因素，例如就业状况，居住者以及用电做饭是否与TECP密切相关，而与态度相关的因素几乎与对TECP没有影响。结果还表明，拥有多于一个人的家庭在整个季节内更可能改变ECP。提议的方法和本研究的结果可以帮助支持有关如何减少电力消耗和CO2排放的决策。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号