Skip to content

PhD Scholarship: Digital Twins, AI and Future Energy Systems

PhD Scholarship - Digital Twins, AI and Future Energy Systems

Queensland-Bavaria Collaborative Research Project, University of Southern Queensland (UniSQ), Australia with Julius-Maximilians-Universität Würzburg, Chemnitz University of Technology and Queensland energy-industry partners

Project description

This PhD offers a rare opportunity to join a funded Queensland-Bavaria research program and adapt an established European Digital Twin platform for real Queensland energy-system applications, supported by an experienced international team and industry engagement.

About this unique opportunity

The Artificial Intelligence Applications Laboratory (AIAL) at the University of Southern Queensland (UniSQ) invites applications from an outstanding domestic or international candidate for a PhD scholarship in Digital Twins, Artificial Intelligence and Future Energy Systems.

The PhD will form a central research position within a recently funded Queensland-Bavaria collaborative research project focused on developing, transferring and applying advanced Digital Twin and AI technologies for the renewable-energy transition.

The successful candidate will join an international research and industry team spanning UniSQ, Queensland energy-sector partners, Julius-Maximilians-Universität Würzburg and Chemnitz University of Technology (TU Chemnitz).

A major advantage: an established Digital Twin platform

The candidate will not be starting from a blank page. The Würzburg research team already has an established Digital Twin architecture and modelling framework. The successful candidate will work directly with the Würzburg developers and the UniSQ supervisory team to learn and transfer this capability to Queensland, then adapt, extend and validate it for Queensland electricity-network conditions.

The research

The PhD will investigate how Digital Twins, AI/ML, distributed-energy-resource modelling, short-horizon forecasting and flexibility services can support increasingly renewable-rich electricity distribution networks. Key activities may include:

· developing a spatially resolved flexible-demand and distributed-energy-resource (DER) inventory, including rooftop PV, EV charging, batteries, heat pumps/air-conditioning loads and flexible demand;

· adapting the existing Bavarian Digital Twin architecture to Queensland feeder, transformer and zone-substation conditions;

· integrating distribution-system simulation tools such as OpenDSS and developing aggregated virtual-device models for PV, EV fleets, batteries and flexible loads;

· developing AI/ML-based short-horizon solar-generation, residual-load and demand nowcasting and integrating forecasts into feeder-level Digital Twin workflows;

· assessing demand-response, flexibility and market-service scenarios and developing decision-support approaches for spatially targeted flexible-demand activation;

· validating the adapted Digital Twin against Queensland transformer, feeder and zone-substation observations, including inverter and power-quality considerations;

· undertaking Queensland-Bavaria comparative analysis and progressing an industry-ready Digital Twin research platform and future scale-up pathway.

The research pathway is designed to move from an established Digital Twin architecture through Queensland adaptation, AI/ML forecasting and DER flexibility to real industry data, operational validation and decision support.

International supervision, industry engagement and research environment

The successful candidate will receive extensive supervision and mentoring from a multidisciplinary UniSQ team and will work closely with international and industry collaborators.

Candidate Profile

We are seeking an excellent candidate with demonstrated capacity for independent computational research and a strong interest in future energy systems. The ideal candidate will bring solid computational and/or energy-system foundations and then use the established international Digital Twin framework as a platform for original doctoral research.

Preferred academic background

Preference will be given to applicants who have completed, or are close to completing, a substantial research-based Master's degree or equivalent research qualification demonstrating independent research capability in one or more of the following areas:

· electrical or power engineering;

· renewable-energy engineering or energy systems;

· computer science, data science or digital-system design;

· artificial intelligence or machine learning;

· computational engineering;

· control and optimisation;

· applied mathematics; or

· a closely related field.

Applicants with an Honours qualification meeting UniSQ PhD admission requirements may also be eligible; however, for this project, demonstrated research maturity and independent computational capability will be particularly important.

Essential or strongly preferred capabilities

· advanced programming capability, preferably in Python, MATLAB or equivalent scientific-computing environments;

· skills in machine learning, deep learning, optimisation, simulation, data-driven forecasting or advanced data analysis;

· experience working with computational models, simulation tools or research software;

· a sound understanding of electricity networks, renewable energy, DERs or power-system operation;

· experience with time-series modelling and large-scale datasets;

· competence in quantitative modelling, model validation and technically challenging problem solving;

· strong academic writing and scientific communication skills; and

· evidence of research maturity through a substantial thesis and, preferably, peer-reviewed publications.

Particularly valuable experience

Experience in one or more of the following would be an advantage:

Digital Twins; distribution-network modelling; OpenDSS or similar simulation environments; DER modelling; solar/PV or load forecasting; EV or battery modelling; demand response and flexibility markets; inverter or power-quality modelling; geospatial energy data; probabilistic or uncertainty-aware forecasting; optimisation for energy systems; cloud/HPC computing; research software engineering; or integration of existing modelling platforms.

What will make a candidate stand out

· a strong research Master's project in energy, power systems, AI/ML, optimisation or a closely related area;

· excellent programming and quantitative problem-solving ability;

· ability to connect AI/ML methods with physical or engineering processes;

· experience learning, modifying or extending an existing modelling or computational framework;

· confidence engaging with industry engineers and international academics;

· independence, initiative, curiosity and the ability to learn new technical systems efficiently;

· strong publication potential and genuine interest in translating research into practical energy-sector outcomes.

Applicants are not expected to have prior experience with the specific Würzburg Digital Twin system. The project provides direct knowledge transfer and technical support from the German and Australian teams.

Why this PhD is different

The candidate begins with a substantial advantage: an established Digital Twin architecture, direct access to its developers in Würzburg, a funded international research program, experienced UniSQ supervisors, defined work packages and real energy-sector problems. This allows the student to focus doctoral effort on scientifically valuable questions - adapting the platform to a new electricity-network environment, integrating Queensland datasets, developing AI/ML forecasting capability, modelling DER flexibility, improving decision support and validating performance against real network observations.

The project is expected to contribute to validated DER and flexible-demand datasets, Queensland Digital Twin adaptation, operational short-horizon forecasting, feeder/transformer-level integration, AI-informed flexibility and decision-support tools, Queensland-Bavaria comparative evaluation, an industry-ready Digital Twin platform, high-quality publications and future grant and industry-development pathways.

For an ambitious candidate with the right foundations, the opportunity combines established technology, international knowledge transfer, original research, real industry data, advanced AI, Digital Twin application, industry engagement and professional research mentoring.

Value

Successful applicants will be entitled to:

  • Living stipend A$40,000 per annum (tax-free, subject to scholarship conditions)
  • International tuition fees valued at approximately A$39,000 per annum for eligible international candidates
  • Project expenses / development support valued at approximately A$5,000-A$7,000, subject to funding approvals
  • Indicative package Indicative core scholarship package for an eligible international candidate: approximately A$240,000+ over three years

Outstanding international applicants are strongly encouraged to apply. Tuition-fee support is subject to UniSQ policies, eligibility and availability.

Additional paid research experience and professional development

A high-performing candidate may have opportunities for additional employment as a Research Assistant, separate from the PhD scholarship and subject to university rules, performance and available funding. Such work may include competitive grant development, industry proposals, technical reviews, modelling/data analysis, research reports, research concepts and project planning under direct mentoring from the project leadership team.

Subject to project funding, satisfactory progress and institutional approval, opportunities may also include Australian and international conference participation, energy-industry workshops, Queensland-Bavaria project meetings and a potential research visit to the partner university in Germany for hands-on Digital Twin knowledge transfer and joint technical development.

Applicants must:

· meet UniSQ's PhD admission and English-language requirements;

· have completed an eligible Bachelor Honours degree with First Class or Second Class Honours Division A, or equivalent, with a significant research component, or a Master’s degree with a significant research component, or equivalent. Preference will be given to applicants with a Master’s by Research or Honours qualification demonstrating strong research outcomes, including quality publications where applicable,

· be eligible for admission to, and apply for, the Doctor of Philosophy (PhD) at UniSQ;

· enrol as a full-time PhD student and spend at least 38 hours per week,

· not have previously completed, or be currently completing, a PhD;

· not be receiving equivalent primary scholarship support contrary to UniSQ scholarship conditions;

· be able to commence the PhD in January 2027, and

· be primarily based at UniSQ Springfield Campus, Queensland.

Competitive applicants should:

· have a strong interest in Digital Twins, artificial intelligence, renewable energy, power systems and real-world industry impact;

· demonstrate strong computational capability and evidence of independent research;

· have a sound understanding of, or demonstrated capacity to work with, energy-system or electricity-network problems;

· be capable of working with complex datasets, computational models and existing research software;

· be willing to learn and work with the established Würzburg Digital Twin architecture and adapt, extend, validate and apply it to Queensland electricity-network conditions;

· be eager to work across AI/ML, Digital Twins and energy-system modelling, including forecasting, DER data, flexibility assessment and operational decision support;

· be able to work independently while collaborating effectively with UniSQ, Queensland energy-industry partners, Julius-Maximilians-Universität Würzburg and TU Chemnitz;

· have strong written and verbal communication skills and be able to engage professionally with academic researchers, industry engineers and international collaborators; and

· be motivated to contribute to high-quality publications, industry-relevant outcomes and practical Digital Twin applications for the renewable-energy transition.

To apply, please ensure you have digital copies of the below information:

· Curriculum vitae including research experience, technical skills, conference presentations, publications, awards, scholarships and relevant industry or project experience.

· Research master’s thesis or equivalent substantial research dissertation. Applicants should provide either the full thesis, a permanent repository link, or a detailed thesis summary if the thesis is not yet publicly available.

· Research outcomes arising from the master’s degree, including copies or links to:

o peer-reviewed journal articles; conference papers or presentations; technical reports;

o datasets, software, modelling tools or computational outputs or any other evidence demonstrating independent research capability.

· A one-page summary of the applicant’s master’s research, clearly describing:

o the research problem and objectives; the applicant’s individual contribution; computational, modelling, AI/ML or engineering methods used;

o software/programming tools used; the major research findings; and the research outputs or publications produced.

· Evidence of advanced computational capability, where relevant. This may include a brief description or examples of Python, MATLAB, machine learning, optimisation, simulation, Digital Twin, power-system modelling, data analytics or research-software experience.

· details of programming, computational research and energy/power-system experience;

· details of relevant experience with Digital Twins, AI/ML, optimisation, simulation or advanced modelling;

· copies of or links to relevant publications; and

· a brief research statement explaining why the project fits the applicant's background, their strongest computational and energy skills, an example of an independently solved research problem, experience with existing modelling/software frameworks, industry or multidisciplinary teamwork, and interest in adapting an established Bavarian Digital Twin framework for Queensland.

o Shortlisted applicants may be invited to discuss their previous research and how their existing skills could be applied to the Queensland-Bavaria Digital Twin project. Prior knowledge of the specific Würzburg Digital Twin architecture is not required.

· Preliminary Research Thesis Topic Proposal, to be completed in consultation with Professor Ravinesh Deo, e-mail: ravinesh.deo@unisq.edu.au

Application must be made via the UniSQ Scholarship Application Management System by the closing date.

If you require assistance in completing your application, please download the Scholarships Online Application Manual.

4 December 2026

Prospective applicants are encouraged to contact:

Professor Ravinesh Deo

Project Leader, Queensland-Bavarian Digital Twin Research Alliance

University of Southern Queensland (UniSQ)

Email: ravinesh.deo@unisq.edu.au

Office: B413, UniSQ Springfield

Campus Phone: +61 7 3470 4430

Highly qualified prospective applicants are welcome to make contact before submitting a formal scholarship application, particularly if they wish to discuss the alignment of their research background with the Digital Twin, AI/ML and future-energy focus of the project.