A graph mining-based methodology for discovering and visualizing high-level knowledge for building energy management

Abstract Building operations have evolved to be not only energy-intensive, but also information-intensive. Advanced data-driven methodologies are urgently needed to facilitate the tasks in building energy management. Currently, there are two main bottlenecks in analyzing building operational data. Firstly, few methodologies are available to represent and analyze data with complicated structures. Conventional data analytics are capable of analyzing information stored in a single two-dimensional data table, while lacking the ability to handle multi-relational databases. Secondly, it is still challenging to visualize the analysis results in a generic and flexible fashion, making it ineffective for knowledge interpretations and applications. As a promising solution, graphs can integrate and represent various types of information, providing promising approaches for the knowledge discovery from massive building operational data. This study proposes a novel graph-based methodology to analyze building operational data. The methodology consists of various stages and provides solutions for data exploration, graph generations, knowledge discovery and post-mining. It has been applied to analyze the actual building operational data of a public building in Hong Kong. The research results validate the potential of the graph-based methodology in characterizing high-level building operation patterns and atypical operations.

[1]  Jiawei Han,et al.  gSpan: graph-based substructure pattern mining , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[2]  Lawrence B. Holder,et al.  Graph-Based Data Mining , 2000, IEEE Intell. Syst..

[3]  Benjamin C. M. Fung,et al.  A novel methodology for knowledge discovery through mining associations between building operational data , 2012 .

[4]  Wenjie Gang,et al.  Assessment of deep recurrent neural network-based strategies for short-term building energy predictions , 2019, Applied Energy.

[5]  Yisheng Lv,et al.  Data driven parallel prediction of building energy consumption using generative adversarial nets , 2019, Energy and Buildings.

[6]  Fu Xiao,et al.  Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review , 2018 .

[7]  George Karypis,et al.  GREW - a scalable frequent subgraph discovery algorithm , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).

[8]  Ashwin M. Khambadkone,et al.  Energy optimization methodology of multi-chiller plant in commercial buildings , 2017 .

[9]  Frans Coenen,et al.  A survey of frequent subgraph mining algorithms , 2012, The Knowledge Engineering Review.

[10]  Gianfranco Chicco,et al.  Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings , 2018, Energy.

[11]  Wei Wang,et al.  Efficient mining of frequent subgraphs in the presence of isomorphism , 2003, Third IEEE International Conference on Data Mining.

[12]  Gary Higgins,et al.  Real-time prediction model for indoor temperature in a commercial building , 2018, Applied Energy.

[13]  Lawrence B. Holder,et al.  Substructure Discovery Using Minimum Description Length and Background Knowledge , 1993, J. Artif. Intell. Res..

[14]  Fu Xiao,et al.  A short-term building cooling load prediction method using deep learning algorithms , 2017 .

[15]  Fu Xiao,et al.  A framework for knowledge discovery in massive building automation data and its application in building diagnostics , 2015 .

[16]  Chirag Deb,et al.  Determining key variables influencing energy consumption in office buildings through cluster analysis of pre- and post-retrofit building data , 2018 .

[17]  Gail Brager,et al.  Making sense of building data: New analysis methods for understanding indoor climate , 2018 .

[18]  Jui-Sheng Chou,et al.  Smart meter monitoring and data mining techniques for predicting refrigeration system performance , 2014, Expert Syst. Appl..

[19]  Yibo Chen,et al.  Short-term prediction of electric demand in building sector via hybrid support vector regression , 2017 .

[20]  Fu Xiao,et al.  A novel methodology to explain and evaluate data-driven building energy performance models based on interpretable machine learning , 2019, Applied Energy.

[21]  Melvin Robinson,et al.  Prediction of residential building energy consumption: A neural network approach , 2016 .

[22]  Yonglin Ju,et al.  The analysis of the operating performance of a chiller system based on hierarchal cluster method , 2017 .

[23]  Christian Borgelt,et al.  Mining molecular fragments: finding relevant substructures of molecules , 2002, 2002 IEEE International Conference on Data Mining, 2002. Proceedings..

[24]  Vivek Srikumar,et al.  Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks , 2018 .

[25]  Yang Zhao,et al.  Deep learning-based feature engineering methods for improved building energy prediction , 2019, Applied Energy.

[26]  Yueren Wang,et al.  A novel ensemble learning approach to support building energy use prediction , 2018 .

[27]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[28]  Shengwei Wang,et al.  A system-level fault detection and diagnosis method for low delta-T syndrome in the complex HVAC systems , 2016 .

[29]  Lawrence B. Holder,et al.  Mining Graph Data , 2006 .

[30]  K. Hornik,et al.  Unbiased Recursive Partitioning: A Conditional Inference Framework , 2006 .

[31]  Henrik Madsen,et al.  Temporal knowledge discovery in big BAS data for building energy management , 2015 .

[32]  David Liben-Nowell,et al.  The link-prediction problem for social networks , 2007 .

[33]  Zeyu Wang,et al.  A review of artificial intelligence based building energy use prediction: Contrasting the capabilities of single and ensemble prediction models , 2017 .

[34]  Fu Xiao,et al.  Data mining in building automation system for improving building operational performance , 2014 .

[35]  David F. Nettleton,et al.  Data mining of social networks represented as graphs , 2013, Comput. Sci. Rev..

[36]  Pei Huang,et al.  A clustering based grouping method of nearly zero energy buildings for performance improvements , 2019, Applied Energy.

[37]  Joost N. Kok,et al.  A quickstart in frequent structure mining can make a difference , 2004, KDD.

[38]  Frank Dalene.  Technology and information management for low-carbon building , 2012 .

[39]  Arno Schlueter,et al.  A review of unsupervised statistical learning and visual analytics techniques applied to performance analysis of non-residential buildings , 2018 .

[40]  Shengwei Wang,et al.  Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques , 2014 .

[41]  Fu Xiao,et al.  Discovering gradual patterns in building operations for improving building energy efficiency , 2018, Applied Energy.

[42]  Nora El-Gohary,et al.  A review of data-driven building energy consumption prediction studies , 2018 .