Loading Events

IEEE WIE UKI Ambassadors’ Scheme | The Power of Data – Data Science Meeting Power & Energy

About this Event

The IEEE Women in Engineering and IEEE PES Women in Power will celebrate International Women in Engineering Day 2021 co-hosting the webinar “The Power of Data: Data Science Meeting Power & Energy”, in which researchers across UK and Ireland will explore together the possibilities of Data Science in Power & Energy domain.  Talks and speakers that will participate are following:

  • Meeting Societal Challenges: Big Data Driven AI-enabled Approaches by Prof Liangxiu Han, Manchester Metropolitan University
  • Big Data Solutions for Real-World Problems: Data Science for Social Good by Dr Arjumand Younus, University College Dublin
  • A decision support framework for the assessment of decentralised energy systems by Dr Ting Wu, The University of Manchester
  • Advanced computational techniques for robust power system analytics by Dr Tabia Ahmad, The University of Strathclyde
  • Unsupervised data mining methods for the analysis of the impact of HRES plant on system stability by Ms Ana Radovanovic, The University of Manchester
  • Data-driven protection scheme for superconducting-based electricity grids Ms Eleni Tsotsopoulou, The University of Strathclyde.

Talk Title: Meeting Societal Challenges: Big Data Driven AI-enabled Approaches

Speaker: Prof Liangxiu Han

Abstract: By 2025, the total size of digital data generated by social networks, sensors, biomedical imaging and simulation devices, will reach an estimated 163 Zettabytes (e.g. 163 trillion gigabytes) according to IDC report. This type of ‘big data’, together with the advances in information and communication technologies such as data analytics/machine learning/AI, Internet of things (IoT), connected smart objects, wearable technology, ubiquitous computing, is transforming every aspect of modern life and bringing great challenges and spectacular opportunities to fulfil our dream of a sustainable smart society.

This talk will focus on new developments and methods on scalable learning from large scale data and present real case studies to demonstrate how we applied big data driven, AI-enabled approaches in various application domains such as Health, Precision Agriculture to address society challenges.

Biography: Prof Liangxiu Han has a PhD in Computer Science from Fudan University, Shanghai, P.R.China (2002). She is currently a full Professor of Computer Science at the Department Computing and Mathematics, Manchester Metropolitan University. She is a co-Director of Centre for Advanced Computational Science and Deputy Director of ManMet Crime and Well-Being Big Data Centre. Her research areas mainly lie in the development of novel big data analytics/Machine Learning/AI, and development of novel intelligent architectures that facilitates big data analytics (e.g., parallel and distributed computing, Cloud/Service-oriented computing/data intensive computing) as  well as applications in different domains (e.g. Health, Precision Agriculture, Smart Cities, Cyber Security, Energy, etc.) using various large scale datasets such as images, sensor data, network traffic, web/texts and geo-spatial data. As a Principal Investigator (PI) or Co-PI, Prof. Han has been conducting research in relation to big data processing and data mining, cloud computing/parallel and distributed computing (funded by EPSRC, BBSRC, Innovate UK, Horizon 2020, British Council, Royal Society, Industry, Charity, respectively, etc.).

Prof Han is a member of EPSRC Peer Review College, an independent expert for Horizon 2020 proposal evaluation/mid-term project review, and British Council Peer Review Panel. She is served as an associate editor/a guest editor for a number of reputable international journals and a chair (or Co-Chair) for organisation of a number of international conferences/workshops in the field. She has been invited to give a number of keynotes and talks on different occasions (including international conferences, national and international institutions/organisations).

Talk Title: Big Data Solutions for Real-World Problems: Data Science for Social Good

Speaker: Dr Arjumand Younus

Abstract: With data being the new oil there has been an unprecedented race to make most of this data for various knowledge discovery processes. Knowledge creation enabled via the scientific process however has an underlying goal to improve the human condition and the well-being of society. This has ultimately led to a theme within data science known as data science for social good whereby machine learning is applied to problems in healthcare, journalism, finance, agriculture, manufacturing etc.

This talk will explore some potential application areas where data science for social good projects are explored and what role Big Data technologies play in such exploration. Fundamentally, we will have a look at network representation learning techniques for soil properties data in an attempt to yield more accurate predictions for crop yields.  Finally, an overview of other areas such as natural language processing will be provided.

Biography: Arjumand Younus is currently working as a Research Scientist  at a large multi-national business analytics company called “Afinit”; prior to that she was a post-doctoral researcher at CONSUS in University College Dublin for a massive government-funded project on data-driven agriculture for Ireland. She was also a part of the Recommender Systems group at Insight Centre for Data Analytics in University College Dublin. She is the co-founder of the Dublin chapter of Women in Machine Learning and Data Science and is also actively involved with the Python Ireland community.

She has a passion for projects belonging to the theme of data science for social good. She is the recipient of Google Women Techmakers scholarship for Europe, Middle East and Africa region. She completed her PhD in Computer Science in 2015 jointly from National University of Ireland, Galway and University of Milano-Bicocca, Italy; and her Masters in Computer Science from KAIST, South Korea.

Talk Title: A ddecision Support framework for the Assessment of Decentralised Energy systems

Speaker: Dr Ting Wu

Abstract: With the energy revolution and the development of renewable energy, policy making in the energy sector should take into account the performance of different decentralizsed energy systems and make an informed choice for a more efficient, more reliable, cleaner and economically efficient future of electricity. The performance assessment of decentralized energy systems can be viewed as a multiple criteria decision-making problem with correlating criteria and alternatives. In this research, a decision support framework using the Evidential reasoning approach and Data Envelopment Analysis (DEA) is developed for the assessment of decentralized energy systems.

Biography: Dr Ting Wu is currently a Postdoc Research Associate at Alliance Manchester Business School (AMBS), The University of Manchester. She completed her PhD in Business and Management at AMBS in 2021. Previously she worked as an Assistant/Associate Professor in Shanghai Dianji University, after she obtained her first PhD degree in Engineering: Precise Instruments and Mechanics from Shanghai Jiao Tong University.

Talk Title: Advanced Computational Techniques for Robust Power System Analytics

Speaker: Dr Tabia Ahmad

Abstract: The electric power system is witnessing significant transformations towards an integrated, active, and ubiquitously-sensed cyber-physical system. An abundance of multi-scaled data from phasor measurement units (PMU), point on wave (POW) measurement devices and digital disturbance recorders offers tremendous opportunities as well as scientific challenges to infer the state of the grid. Also, present day power systems in an attempt to mitigate climate change problems are increasingly moving towards more and more generation from sustainable energy resources which lead to intermittent and uncertain operations. Building on mathematical foundations and statistical analysis, this talk aims to provide an overview of data analytic tools in the modelling and operations of modern power systems.

The key highlights of this talk include revisiting the statistical nature of noise encountered in power system measurement data and discussing its effect on the accuracy of power system analytics. Moreover, the talk also reports the effect of stochastic perturbations like loads/renewable energy (RE) injections on power system frequency fluctuations under ambient conditions using physics informed data-driven methods. On a parallel note, this increased uncertainty due to RE can aggravate the detection of cascading failures in power systems and may lead to catastrophic blackouts, thus hampering the reliability and security of electric supply. The potential of machine learning to predict such events early on at their onset, using field data and data from simulation test cases is also outlined.

Biography: Tabia Ahmad received the B.Tech degree in Electrical Engineering and the M.Tech. degree in Instrumentation and Control Engineering from Aligarh Muslim University, Aligarh, India, in 2014 and 2016, respectively. She has recently submitted her Ph.D. thesis at the Indian Institute of Technology Delhi, New Delhi, India. Presently she is working as a post-doctoral researcher at the EEE department of University of Strathclyde, Glasgow (UK) working on, “Addressing the complexity of future power systems dynamic behavior” as a part of UKRI Future Leaders Fellowship. Her research interests include power system dynamics, WAMS based analytics and signal processing techniques in power systems.

Talk Title: Unsupervised Data Mining Methods for the Analysis of the Impact of HRES Plant on System Stability

Speaker: Ms Ana Radovanovic

Abstract: Stochastic production due to weather dependence is one of the main drawbacks of renewable energy sources (RESs). Hybrid renewable energy source (HRES) plants, comprising several renewable generation and storage technologies, have been recognized as a potential option for obtaining controllable power output from RESs. So far, the focus of the research has been on the economic benefits of HRES plants, with little attention being paid to the influence of HRES plant on system stability.

The assessment of the contribution of HRES plant to the overall system behaviour is more complex than in the case of single technology-based power plants due to a number of HRES plant’s individual components having different static and dynamic characteristics. This presentation focusses on the suitability of clustering methods for identifying patterns in the performance of HRES plants in system stability studies, which represents a foundation for developing equivalent model of the whole HRES plant.

Biography: Ana Radovanovic received the BSc and MSc degrees in electrical engineering and computer science from the University of Belgrade, Serbia. She is currently working toward the PhD degree at the Department of Electrical and Electronic Engineering, The University of Manchester, UK, in the areas of renewable energy sources and power system dynamics.

Talk Title: Data-Driven Protection Scheme for Superconducting-Based Electricity Grids

Speaker: Ms Eleni Tsotsopoulou

Abstract: The protection of Superconducting Cables (SCs) is considered a challenging task due to the quenching of the High Temperature Superconducting (HTS) windings. Specifically, under transient conditions, such as faults, when the current flowing through the superconducting tapes exceeds the critical current , the HTS tapes will automatically quench, presenting high values of resistance and reducing the fault current magnitude. Furthermore, it has been found that the presence of the fault resistance affects the quenching process, making the detection of highly resistive faults a difficult task. To address these challenges, the potentials of data-driven algorithms can be exploited for fault diagnosis of SCs. Specifically, a protection algorithm which combines signal processing techniques such as Stationary Wavelet Transform (SWT) and artificial intelligence techniques such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs) is proposed for fault detection and classification on SCs. For this purpose, a simplified model of SC has been developed in Matlab/Simulink software and integrated in a power system which contains Synchronous generators (SGs) and Inverter-connected generators (ICGs). The two classifiers have been tested under different scenarios, encircling different transient conditions.

The feasibility of the proposed algorithm was evaluated for real time implementation in order to assess the performance of the two classifiers in terms of their prediction speed. The obtained results confirm the effectiveness of the developed algorithm to detect faults occurred on the SC within short time and to remain stable for other transient events such as external fault and load switching events. Moreover, the ANN classifier has proven to be better for real time implementation.

Biography: Eleni Tsotsopoulou received the M.Eng (Hons) degree in Electrical and Computer Engineering from the Dimokrition University of Thrace, Greece, in 2018 and the MSc in Wind Energy Systems from the University of Strathclyde (with Distinction), Glasgow, UK, in 2019. She is currently a Ph.D. student at the Department of Electronic and Electrical Engineering, at the University of Strathclyde. She is a member of IEEE. Her main research interests lie within the area of power system protection, automation and control of future power grids, incorporating increased penetration of renewable energy sources, integration of distributed generation and applied superconductivity. Eleni’s main research methods include implementation of intelligent algorithms for protection, machine learning and signal processing techniques.

Go to Top