Analyzing Harmonic Monitoring Data Using Supervised and Unsupervised Learning

Abstract

Abstract-Harmonic monitoring has become an important tool for harmonic management in distribution system. A comprehensive harmonic monitoring program has been designed and implemented on a typical electrical medium-voltage distribution system in Australia. The monitoring program involved measurements of the three-phase harmonic currents and voltages from the residential, commercial, and industrial load sectors. Data over a three year period have been downloaded and available for analysis. The large amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. More sophisticated analysis methods are required to automatically determine which part of the measurement data are of importance. Based on this information, a closer inspection of smaller data sets can then be carried out to determine the reasons for its detection. In this paper, we classify the measurement data using unsupervised learning based on clustering techniques using the minimum message length technique, which can provide the engineers with a rapid, visually oriented method of evaluating the underlying operational information contained within the clusters. Supervised learning is then used to describe the generated clusters and to predict the occurrences of unusual clusters in future measurement data.

Data Analytics to Support Operational Distribution Network Monitoring

“…Distribution network data has been analysed for different purposes, including the assessment of the impact of different technologies on the network, the detection and classification of events, the characterisation of normal network behaviour 978-1-5386-4505-5/18/$31.00 ©2018 IEEE as well as the prediction of faults. The impacts of harmonic distortion caused by the increased use of power electronics in the distribution network were investigated in [1] and [2]. Data mining tools and techniques were utilised in order to identify clusters in the data that represent different operating conditions that could be used to detect anomalies.…”

Symbolic Modelling of Dynamic Human Motions

“…However, whilst such models were often pruned significantly, which may also reduce the domain dimensionality the models address, this process always provides a transparent view of any resultant rules, patterns-often leading to new discovered knowledge. Thus the developer is able to readily critique and further explore various properties and consequences, often through a visualization process, that an individual element of existing or discovered knowledge poses in relation to any reduction in a models resolution (Asheibi, 2009). Apart from this, motioning the induced symbolic patterns also provides a diagnostic ability guiding the often cyclic and interactive nature of applying machine learning in general.…”

Development, implementation and characterization of a DSP based data acquisition system with on-board processing

“…In fact, the rapid development of fast ADCs capable of achieving resolutions above 10-12 bit has revolutionized the instrumentation and measurement field and can be considered as one of the crucial building blocks to our worldwide digital content driven society. The possibility to measure just about anything, sometimes with extremely reduced costs, has increased many times the deployment of sensor based measurement systems as well as the total amount of acquired data, the rapid development of signal processing algorithms to extract real-time information of the raw data, the use of data mining to analyze the results [1], sensor fusion to combine the measurements from multiple sources [2].…”