Clustering Method for Low Voltage Substation-Area Users Based on Edge Computing Architecture

Measurement and monitoring of data in power networks are of great value. A hierarchical clustering analysis method based on edge computing architecture for low-voltage power consumption data is proposed. Based on edge computing architecture, edge nodes are used to collect data and cluster locally, a cloud computing platform is used to aggregate and optimize clustering results. The algorithm flow and optimization strategy are described. The simulation results show that the method has certain advantages in improving computational efficiency and reducing time delay.

[1]  Andreas Seitz,et al.  Poster Abstract: Continuous Computing from Cloud to Edge , 2016, 2016 IEEE/ACM Symposium on Edge Computing (SEC).

[2]  Weizhong Zhao,et al.  PDMiner：a cloud computing based parallel and distributed data mining toolkit platform , 2014 .

[3]  Naoki Tanaka,et al.  Nonintrusive Load-Shed Verification , 2011, IEEE Pervasive Computing.

[4]  Richa Gupta,et al.  Cloud computing data mining to SCADA for energy management , 2015, 2015 Annual IEEE India Conference (INDICON).

[5]  Andrew John Berrisford.  A tale of two transformers: An algorithm for estimating distribution secondary electric parameters using smart meter data , 2013, 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[6]  T. R. Gopalakrishnan Nair,et al.  Data mining using hierarchical virtual k-means approach integrating data fragments in cloud computing environment , 2011, 2011 IEEE International Conference on Cloud Computing and Intelligence Systems.

[7]  Andreas Seitz,et al.  Seamless Computing for Industrial Systems Spanning Cloud and Edge , 2017, 2017 International Conference on High Performance Computing & Simulation (HPCS).

[8]  Lu Huang,et al.  A survey of mass data mining based on cloud-computing , 2012, Anti-counterfeiting, Security, and Identification.

[9]  Tom A. Short,et al.  Advanced Metering for Phase Identification, Transformer Identification, and Secondary Modeling , 2013, IEEE Transactions on Smart Grid.

[10]  D.J. King,et al.  Electricity load profile classification using Fuzzy C-Means method , 2008, 2008 43rd International Universities Power Engineering Conference.

[11]  Norhasnelly Anuar,et al.  Electricity Load Profile Determination by using Fuzzy CMeans and Probability Neural Network , 2012 .