Patterns and Temporal Resolution in Commercial and Industrial Typical Load Profiles

Abstract Load patterns often have a periodicity of a day, week and year, which can be taken advantage of when preprocessing load data before clustering. A typical load profile, which reflects the customer's load for a characteristic day, week or year, could be constructed to reduce the data to be processed during the clustering. Typical Daily Profiles (TDP) and Typical Weekly Profiles (TWP) are compared to see how the time resolution of data affects the clustering. Results show that the number of clusters affects the Davies-Bouldin Index and the Dunn Index more than the temporal resolution of data as well as if TDPs or TWPs are clustered. Further, clustering based on customers’ TWP instead of TDP makes it easier to find customers which have equipment turned on during Saturdays. This could be of importance when clustering is used to improve forecasting, distribution planning or tariff design.

[1]  Michael Conlon,et al.  A clustering approach to domestic electricity load profile characterisation using smart metering data , 2015 .

[2]  Shanlin Yang,et al.  Big data driven smart energy management: From big data to big insights , 2016 .

[3]  Christoph Flath,et al.  Clusteranalyse von Smart-Meter-Daten , 2012, Wirtschaftsinf..

[4]  David C. H. Wallom,et al.  Impacts of Raw Data Temporal Resolution Using Selected Clustering Methods on Residential Electricity Load Profiles , 2015, IEEE Transactions on Power Systems.

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

[6]  Saeid Nahavandi,et al.  Improving load forecast accuracy by clustering consumers using smart meter data , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[7]  Donald W. Bouldin,et al.  A Cluster Separation Measure , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Ali Azadeh,et al.  Short term load forecasting by ANN , 2009, 2009 IEEE Workshop on Hybrid Intelligent Models and Applications.

[9]  Mikko Kolehmainen,et al.  Feature-Based Clustering for Electricity Use Time Series Data , 2009, ICANNGA.

[10]  Peter A. Flach,et al.  Feature Construction and Calibration for Clustering Daily Load Curves from Smart-Meter Data , 2016, IEEE Trans. Ind. Informatics.

[11]  B. De Moor,et al.  Short-term load forecasting, profile identification, and customer segmentation: a methodology based on periodic time series , 2005, IEEE Transactions on Power Systems.

[12]  Mikko Kolehmainen,et al.  Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data , 2010 .

[13]  J. Dunn.  Well-Separated Clusters and Optimal Fuzzy Partitions , 1974 .

[14]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[15]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[16]  Diego Klabjan,et al.  Clustering time-series energy data from smart meters , 2015, 1603.07602.

[17]  G. K. Papagiannis,et al.  Load profiling in the deregulated electricity markets: A review of the applications , 2012, 2012 9th International Conference on the European Energy Market.

[18]  Ali Al-Wakeel,et al.  Low carbon cities and urban energy systems K-means based cluster analysis of residential smart meter measurements , 2016 .

[19]  Z. Vale,et al.  Typical load profiles in the smart grid context — A clustering methods comparison , 2012, 2012 IEEE Power and Energy Society General Meeting.

[20]  Zhu Han,et al.  Kernel-based non-parametric clustering for load profiling of big smart meter data , 2015, 2015 IEEE Wireless Communications and Networking Conference (WCNC).

[21]  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).