IDENTIFICATION OF TYPE DAILY DIAGRAMS OF ELECTRIC CONSUMPTION BASED ON CLUSTER ANALYSIS OF MULTI-DIMENSIONAL DATA BY NEURAL NETWORK

• Published in: Neural Network World Vol. 23; no. 3; pp. 271 - 283
• Main Authors: GARLIK, Bohumír, KRIVAN, Miloš
• Format: Journal Article
• Language: English
• Published: Praha Institute of Information and Computer Technology 01.01.2013; Ústav informatiky Akademie věd České republiky; Institute of Computer Science
• Subjects: Applied sciences; Artificial intelligence; Cluster analysis; Computer science; control theory; systems; Connectionism. Neural networks; Data processing. List processing. Character string processing; Diagrams; Electrical engineering. Electrical power engineering; Electrical power engineering; Energy consumption; Exact sciences and technology; Memory organisation. Data processing; Neural networks; Power networks and lines; Software; intelligent building; Self-Organizing Map (SOM); Kohonen map; counter-propagation neural network; load prediction; cluster analysis; micro grid; Artificial Neural Network (ANN); Type Daily Diagrams (TDD); Cluster analysis; Energy consumption; Home automation; Process computer; Grid; History; Multidimensional analysis; Self organization; Efficiency; Network analysis; Classification; Sampling; Civil engineering; Data analysis; Neural network; Kohonen algorithm; Experimental study; Electrical network; Electric energy
• ISSN: 1210-0552; 2336-4335
• DOI: 10.14311/NNW.2013.23.017

This article establishes a mathematical description of a self-organizing neural network used for cluster analysis with a subsequent sampling of its effectiveness as an example of identification of the type daily diagrams of electric energy-consumption of complex intelligent buildings within an electric micro grid, namely for a typical work day and a day off on the basis of its annual history. The mentioned type daily diagram can be used to predict power consumption. This method is given in the context of the commonly used procedure for cluster analysis. The experiment was processed in the computer program Artint © 2010.