An application of data mining in district heating substations for improving energy performance

Automatic meter reading system is capable of collecting and storing a huge number of district heating (DH) data. However, the data obtained are rarely fully utilized. Data mining is a promising technology to discover potential interesting knowledge from vast data. This paper applies data mining methods to analyse the massive data for improving energy performance of DH substation. The technical approach contains three steps: data selection, cluster analysis and association rule mining (ARM). Two-heating-season data of a substation are used for case study. Cluster analysis identifies six distinct heating patterns based on the primary heat of the substation. ARM reveals that secondary pressure difference and secondary flow rate have a strong correlation. Using the discovered rules, a fault occurring in remote flow meter installed at secondary network is detected accurately. The application demonstrates that data mining techniques can effectively extrapolate potential useful knowledge to better understand substation operation strategies and improve substation energy performance.

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

[2]  Jian Pei,et al.  2012- Data Mining. Concepts and Techniques, 3rd Edition.pdf , 2012 .

[3]  Heikki Mannila,et al.  Principles of Data Mining , 2001, Undergraduate Topics in Computer Science.

[4]  Tianzhen Hong,et al.  A data-mining approach to discover patterns of window opening and closing behavior in offices , 2014 .

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

[6]  Bo Fan,et al.  Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis , 2014 .

[7]  Benjamin C. M. Fung,et al.  A systematic procedure to study the influence of occupant behavior on building energy consumption , 2011 .

[8]  Jian Pei,et al.  Data Mining: Concepts and Techniques, 3rd edition , 2006 .

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

[10]  Sven Werner,et al.  Daily Heat Load Variation in Swedish District Heating Systems , 2013 .

[11]  Benjamin C. M. Fung,et al.  A decision tree method for building energy demand modeling , 2010 .

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