Big data processing and analysis platform for condition monitoring of electric power system
Authors:
- 10 November 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 23, 1-6
Abstract
This paper presents a preliminary study of developing a novel platform for big data management, processing and analysis of modern power systems. The framework comprises a big data acquisition subsystem, a big data analysis subsystem, a decision-making assistance subsystem and an information integration subsystem. For the big data management system, a novel structure is designed according to three different data resources, including database, data files and data stream. Further, powerful open-source computation algorithms and self-developed novel intelligent methods are integrated in the big data analysis system. To be specific, our early work on statistical processing monitoring (Principal Component Analysis (PCA)), advanced modelling methods (Fast Recursive Algorithm (FRA)) and newly developed optimization method (Teaching-Learning Based Optimization (TLBO)) are integrated into a self-developed analysis module. Thus, with the novel big data acquisition structure and data processing engine, the proposed platform can provide a powerful tool for big data analytic based Smart Grid monitoring.Keywords
This publication has 34 references indexed in Scilit:
- Big Data Analytics for Dynamic Energy Management in Smart GridsBig Data Research, 2015
- Power system data management and analysis using synchrophasor data2014
- Integration of clustering power systems approach and data management infrastructure for smart grids2014
- GraphX2013
- Smart grid data analytics for digital protective relay event recordingsInformation Systems Frontiers, 2013
- Measures of Value: Data Analytics for Automated Fault AnalysisIEEE Power and Energy Magazine, 2012
- An Adaptive Power Management System for multimedia applications using data stream partitioning2011
- IPython: A System for Interactive Scientific ComputingComputing in Science & Engineering, 2007
- Monitoring Streams — A New Class of Data Management Applications2002
- Control Procedures for Residuals Associated With Principal Component AnalysisTechnometrics, 1979