CPLP: An algorithm for tracking the changes of power consumption patterns in load profile data over time

Abstract In this paper, we propose a novel algorithm for tracking the Changes of Patterns in Load Profile (CPLP) data of factories. CPLP consists of two stages. The first stage is to cluster the load profiles in each time window and use the clusters to model the power consumption patterns. We propose a new ensemble clustering method to cluster the load profiles in consecutive time windows. It uses a hierarchical binary k-means algorithm to generate component clusterings and a new objective function to ensemble them to produce the final clustering. The second stage is to track the changes of patterns along the time windows. We propose a new method to detect the change of clusters from one window to the next one by using the distribution models of two related clusters in two neighboring windows. By using this method, we can link the clusters in the sequence of time windows to track the patterns. Experiments on synthetic and real-world load profile data have shown that the proposed algorithm was able to track the changes of power consumption patterns of different factory groups and identify the period of significant change, which are very useful for the smart grid applications.

[1]  Hamido Fujita,et al.  Hierarchical cluster ensemble model based on knowledge granulation , 2016, Knowl. Based Syst..

[2]  Gerhard Widmer,et al.  Learning in the Presence of Concept Drift and Hidden Contexts , 1996, Machine Learning.

[3]  Ana L. N. Fred,et al.  Combining multiple clusterings using evidence accumulation , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Joydeep Ghosh,et al.  Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions , 2002, J. Mach. Learn. Res..

[5]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[6]  Joshua Zhexue Huang,et al.  Incremental density-based ensemble clustering over evolving data streams , 2016, Neurocomputing.

[7]  Gianfranco Chicco,et al.  Overview and performance assessment of the clustering methods for electrical load pattern grouping , 2012 .

[8]  Shun-ichi Amari,et al.  The AIC Criterion and Symmetrizing the Kullback–Leibler Divergence , 2007, IEEE Transactions on Neural Networks.

[9]  Young-Il Kim,et al.  Methods for generating TLPs (typical load profiles) for smart grid-based energy programs , 2011, 2011 IEEE Symposium on Computational Intelligence Applications In Smart Grid (CIASG).

[10]  Carla E. Brodley,et al.  Random Projection for High Dimensional Data Clustering: A Cluster Ensemble Approach , 2003, ICML.

[11]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[12]  J. Lawless.  Statistical Models and Methods for Lifetime Data , 2002 .

[13]  Nguyen Thanh Tung,et al.  Ensemble Clustering of High Dimensional Data with FastMap Projection , 2014, PAKDD Workshops.

[14]  Wei Zhong,et al.  Clinical charge profiles prediction for patients diagnosed with chronic diseases using Multi-level Support Vector Machine , 2012, Expert Syst. Appl..

[15]  Jiye Liang,et al.  Trend analysis of categorical data streams with a concept change method , 2014, Inf. Sci..

[16]  Witold Pedrycz,et al.  Fuzzy C-Means clustering of incomplete data based on probabilistic information granules of missing values , 2016, Knowl. Based Syst..

[17]  Claudio Carpineto,et al.  Consensus Clustering Based on a New Probabilistic Rand Index with Application to Subtopic Retrieval , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[19]  Joshua Zhexue Huang,et al.  Stratified feature sampling method for ensemble clustering of high dimensional data , 2015, Pattern Recognit..

[20]  Ludmila I. Kuncheva,et al.  Using diversity in cluster ensembles , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[21]  Olivier Cappé,et al.  Robust changepoint detection based on multivariate rank statistics , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[22]  Ram Rajagopal,et al.  Household Energy Consumption Segmentation Using Hourly Data , 2014, IEEE Transactions on Smart Grid.

[23]  Ying Wah Teh,et al.  MuDi-Stream: A multi density clustering algorithm for evolving data stream , 2016, J. Netw. Comput. Appl..

[24]  D. Posada,et al.  Model selection and model averaging in phylogenetics: advantages of akaike information criterion and bayesian approaches over likelihood ratio tests. , 2004, Systematic biology.

[25]  Boleslaw K. Szymanski,et al.  NETWORK-BASED INTRUSION DETECTION USING NEURAL NETWORKS , 2002 .

[26]  C. Senabre,et al.  Classification, Filtering, and Identification of Electrical Customer Load Patterns Through the Use of Self-Organizing Maps , 2006, IEEE Transactions on Power Systems.

[27]  S. Venkatasubramanian,et al.  An Information-Theoretic Approach to Detecting Changes in Multi-Dimensional Data Streams , 2006 .

[28]  G. W. Milligan,et al.  The validation of four ultrametric clustering algorithms , 1980, Pattern Recognit..