Online Machine Learning System of Power Quality Information Technology Based on Big Data

Abstract

Power quality monitoring has the characteristics of large amount of collected data and high collection frequency. Long-term monitoring will form power quality big data, while conventional data storage and processing methods are difficult to effectively use big data and explore the value of big data. This paper proposes an online machine learning recognition and classification method for power quality disturbances based on inherent modal function singular value decomposition and least square support vector machines. Aiming at the characteristics of power quality data in distribution networks, this thesis proposes a power quality big data storage scheme based on Mongo DB + Redis, designs a power quality big data processing process, and builds an online machine learning system based on the Apache Spark power quality big data calculation framework.