A Markov Chain Load Modeling Approach through a Stream Clustering Algorithm

Advanced Metering Infrastructure (AMI) is improving the quality and quantity of information within power systems. Thus, these data should be wisely used for efficient management and control. For these reasons, advanced functionalities have to be implemented in order to deal with the massive data stream. In this work, a stream clustering algorithm is used to model any load with a Markov Chain (MC). This algorithm is able to describe the typical load profile in real-time, thanks to a design and an implementation that minimizes the computational burden. The proposed procedure has been tested on an IEEE industrial machines dataset. In addition, a discussion on the parameter selection is provided.

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

[2]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[3]  Witold Pedrycz,et al.  Agreement-based fuzzy C-means for clustering data with blocks of features , 2014, Neurocomputing.

[4]  José Luis Díez,et al.  Dynamic clustering of residential electricity consumption time series data based on Hausdorff distance , 2016 .

[5]  S. E. Ahmed,et al.  Markov Chain Monte Carlo: Stochastic Simulation for Bayesian Inference , 2008, Technometrics.

[6]  Pierre Pinson,et al.  Online adaptive clustering algorithm for load profiling , 2019, Sustainable Energy, Grids and Networks.

[7]  Athanasios V. Vasilakos,et al.  Energy Big Data Analytics and Security: Challenges and Opportunities , 2016, IEEE Transactions on Smart Grid.

[8]  Yi Wang,et al.  Review of Smart Meter Data Analytics: Applications, Methodologies, and Challenges , 2018, IEEE Transactions on Smart Grid.

[9]  Piotr A. Kowalski,et al.  Clustering using flower pollination algorithm and Calinski-Harabasz index , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[10]  F. Silvestro,et al.  Pseudo-measurements modeling using neural network and Fourier decomposition for distribution state estimation , 2014, IEEE PES Innovative Smart Grid Technologies, Europe.

[11]  Federico Silvestro,et al.  Implementation of advanced functionalities for Distribution Management Systems: Load forecasting and modeling through Artificial Neural Networks ensembles , 2019, Electric Power Systems Research.

[12]  Federico Silvestro,et al.  An Instantaneous Growing Stream Clustering Algorithm for Probabilistic Load Modeling/Profiling , 2020, 2020 International Conference on Probabilistic Methods Applied to Power Systems (PMAPS).

[13]  Witold Pedrycz,et al.  Clustering Spatiotemporal Data: An Augmented Fuzzy C-Means , 2013, IEEE Transactions on Fuzzy Systems.

[14]  James C. Bezdek,et al.  Some new indexes of cluster validity , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[15]  Chongqing Kang,et al.  Load profiling and its application to demand response: A review , 2015 .

[16]  Purnima Bholowalia,et al.  EBK-Means: A Clustering Technique based on Elbow Method and K-Means in WSN , 2014 .