School of
Information Technology and Electrical Engineering

Speaker: David Ofosu Amoateng
Seminar Date: Mon, 09/12/2019 - 13:00
Venue: 78-622
Host: Prof Tapan Saha; Dr Richard Yan

Seminar Type:  PhD Confirmation Seminar


Significant changes are happening in the distribution grid, with the addition of more distributed energy resources and the introduction of more unpredictable disturbances. Though traditional SCADA measurements may provide an outlook into a grid’s operation, they may fail to capture transient phenomena which occur on low time scales, which if not handled properly may degrade the power quality. This has necessitated the need for a better monitoring system to provide insight into the grid’s condition and performance.

For these reasons, Energy Queensland is seeking to deploy newly developed phasor measurement units (PMUs) on its medium voltage distribution network. The deployment of these devices however will not necessarily lead to improved situational awareness of the distribution grid. To create actionable insights using data obtained from the PMUs, this project first reviewed PMU applications for distribution grids in order to determine the most beneficial ones that provide the best value for renewables and the distribution grid. These applications are mainly grouped into two categories: diagnostic and control-based applications and include but are not limited to:  event detection and classification, DG characterisation, state estimation, topology detection and verification, islanding detection and phase identification.

Since the beginning of the year, this project has focused on diagnostic applications and mainly on event detection and classification. Considering the high reporting rates of PMUs, it is imperative to develop schemes capable of analysing PMU data in near real-time, which will enable system operators take timely actions. However, current methods used for event detection on distribution grids are heavily dependent on data sample size or on detectors that require great effort in tuning. By training deep autoencoders with PMU data from a real active distribution network, a framework which automatically learns a representation of the network is developed. With this approach, the framework can monitor the state of the network and also detect events in a fraction of a second, making it suitable for online analysis of PMU data from multiple streams or analysis of large amounts of historical PMU data. The performance of the proposed model is validated by comparison with a sample based statistical anomaly detector.

The next stage of this project will concentrate on developing other PMU data applications and will involve determining the effectiveness of existing schemes, modifications to already existing algorithms with the aim of overcoming identified shortcomings and the investigation of the challenges posed by renewables to the distribution grid. The process of developing these applications will involve sifting through massive amounts of PMU data collated over long periods of time and as such big data mining tools will be employed. The outcome of this project will be a framework that provides more insight into active distribution system conditions and performance.


David Amoateng received his B.Sc degree in Electrical/Electronic Engineering from Kwame Nkrumah University of Science and Technology, Ghana and M.Sc degree in  Electronic Science and Technology from the  University of Electronic Science and Technology, China.  He is currently working towards his PhD degree at the University of Queensland, Australia. His research interests include data mining and power systems.