Optimising Grid Transmission Capacity and Voltage Quality in Low, Medium and High Voltage Grids using learning algorithms

By Ms Nancy Van Nieuwenhove | 12 December 2020

Abu Pengwah

2nd Year PhD candidate, Faculty of Engineering/ Department of ECSE

Research interests: Topology identification, graph theory, optimisation and power systems management

Abu Pengwah holds a Bachelor (Honours) in Electrical and Computer Systems Engineering from Monash University. “I was ranked 6th in Mauritius in Physics during my School Certificate, and 9th and 10th in Chemistry and Mathematics during my Higher School Certificate. I already had in mind that I would want to be working in Power Systems. In my final year project at Monash, I worked under Dr Reza Razzaghi on a project called “Topology Identification of Low Voltage networks using Smart Meter Data”. Aside from developing the algorithm and evaluating its performance on synthetic datasets, we discussed with a Distribution Network Service Provider in Victoria to access real smart meter measurements and validate our developed algorithms using real data sets. I was awarded the best poster presentation in 2019 at the Electric Energy Society of Australia (EESA) poster competition and tasting the success of a research project encouraged me to continue doing research in the area”.

We have moved from a unidirectional power flow (from the power utility to your houses) to a two directional power flow (more dynamic system) due to the presence of distributed energy resources (DERs). These additions complicate the management of the power system. “Normally during daylight, when everyone is at work, your solar panel is generating power, but if no one is consuming what has been generated, that generation excess gets exported back to the grid. That is causing major challenges such as voltage problems in distribution networks”. One of the main bottlenecks of managing the power grid is due to the lack of observability and access to network topology and parameters in low-voltage distribution networks. With regular maintenance and reconfigurations, the network changes from time to time such that manual recordings are prone to errors.

Abu Pengwah, supervised by Dr Reza Razzaghi (Monash University) and Dr Lachlan Andrew (Lecturer in Computer and Information Systems, University of Melbourne), focuses on advanced data analytics methods to enhance visibility of distribution networks. He is working on a cost-effective way to estimate the topology of a power grid using available data such as smart meter measurements. “During the first 6 months of my PhD, we finalised the algorithm created during my final project with novelties encompassing both power systems and graph theories.

Abu’s research encompasses techniques from three areas; Power Systems, Signal Processing and Computer Science Graph Theory. “Measurements from smart meters are used with power system and graph theory constraints, to estimate the resistance and reactance values of the power lines connecting the houses (loads) and the Low Voltage transformer powering the grid. A graph learning algorithm estimates the network with unmetered buses, from the impedance estimates of the loads”.

Abu has already started using these algorithm models with real-world applications. His novel approach has been implemented and tested on synthetic and smart meter measurements from a low voltage feeder in Australia. “The synthetic data consisted of both an IEEE test case and randomly generated topologies. The impact of noisy measurements was considered for randomly generated topologies, with the wide range of the signal-to-noise ratio. The performance has been validated using real smart meter measurements. The proposed method proved to be superior to the state-of-the-art approaches and the findings have been submitted for publication in a top-tier journal. “Now, I’m working on a similar objective of identifying the topology and electrical characteristics of power networks, but with a new approach using the electromagnetic transients as a result of switching events. This will be used in fault location algorithms.”

As right now Abu’s technique is only applicable to low voltage. “My new project is to have some kind of algorithm to work with all scales, low, medium, and high voltage, so I can propose a target to industry and work with them to develop robust techniques. Industries might have different interests with what I’m doing, but hopefully I can integrate theirs and my interests and work out something that can be helpful to both industry and society”.

This year, Abu Pengwa received a top-up scholarship from the Monash University Grid Innovation Hub (GIH) for his contribution in identifying Low voltage (LV) networks from measurements of smart meters, including power factor, voltage and current magnitudes. “I had to conduct an extensive literature review to grasp the fundamentals and I’m still doing it. Aside from the technical perspective, there is also personal growth as a PhD requires patience more than anything. Developing an idea is one thing but conveying the idea and its importance to the general public requires additional communication skills. The GIH funding allows me to fully focus on my research. At some point in my research, we might build a prototype and the funding would eliminate any inconveniences that might arise due to the budget, which in turn helps us to deliver an optimal product. It’s also a major source of motivation knowing that such a prestigious organisation is backing my research”.

In 2021, Abu would want to see a larger adoption of renewable energy resources. “The trends indicate that it will happen. In 2019, the growth in usage of renewable energy resources such as solar panels grew by around 25%. Fossil fuels still dominate the energy generated and I want to see the gap narrower in 2021”.