A cloud-based system for dynamically capturing appliance usage relations

Nowadays, owing to the great advent of sensor technology, data can be collected easily. Mining Internet of Things IoT data has attracted researchers' attention owing to its practicability. Mining smart home data is one significant application in the IoT domain. Generally, the usage data of appliances in a smart environment are generated progressively; visualising how appliances are used from huge amount of data is a challenging issue. Hence, an algorithm is needed to dynamically discover appliance usage patterns. Prior studies on usage pattern discovery are mainly focused on discovering patterns while ignoring the dynamic maintenance of mined results. In this paper, a cloud-based system, Dynamic Correlation Mining System DCMS, is developed to incrementally capture the usage correlations among appliances in a smart home environment. Furthermore, several pruning strategies are proposed to effectively reduce the search space. Experimental results indicate that the developed system is efficient in execution time and possesses great scalability. Subsequent application of DCMS on a real data set also demonstrates the practicability of mining smart home data.

[1]  Mario Berges,et al.  Unsupervised disaggregation of appliances using aggregated consumption data , 2011 .

[2]  Shinkichi Inagaki,et al.  Validation of Nonintrusive Appliance Load Monitoring Based on Integer Programming , 2008 .

[3]  Umeshwar Dayal,et al.  PrefixSpan: Mining Sequential Patterns by Prefix-Projected Growth , 2001, ICDE 2001.

[4]  Wang-Chien Lee,et al.  A Novel System for Extracting Useful Correlation in Smart Home Environment , 2013, 2013 IEEE 13th International Conference on Data Mining Workshops.

[5]  Suh-Yin Lee,et al.  An efficient algorithm for mining time interval-based patterns in large database , 2010, CIKM.

[6]  Diane J. Cook,et al.  Using Temporal Relations in Smart Environment Data for Activity Prediction , 2007 .

[7]  Radu Zmeureanu,et al.  Using a pattern recognition approach to disaggregate the total electricity consumption in a house into the major end-uses , 1999 .

[8]  A. Prudenzi,et al.  A neuron nets based procedure for identifying domestic appliances pattern-of-use from energy recordings at meter panel , 2002, 2002 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.02CH37309).

[9]  Jane Yung-jen Hsu,et al.  Applying power meters for appliance recognition on the electric panel , 2010, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[10]  Tatsuya Yamazaki,et al.  Appliance Recognition from Electric Current Signals for Information-Energy Integrated Network in Home Environments , 2009, ICOST.

[11]  Diane J. Cook,et al.  Temporal pattern discovery for anomaly detection in a smart home , 2007 .

[12]  Wang-Chien Lee,et al.  Mining Appliance Usage Patterns in Smart Home Environment , 2013, PAKDD.

[13]  Tohru Hoshi,et al.  A method of appliance detection based on features of power waveform , 2004, 2004 International Symposium on Applications and the Internet. Proceedings..

[14]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[15]  Wang-Chien Lee,et al.  Mining Correlation Patterns among Appliances in Smart Home Environment , 2014, PAKDD.

[16]  Manish Marwah,et al.  Unsupervised Disaggregation of Low Frequency Power Measurements , 2011, SDM.