SMARTPED: Smart Urban Energy Systems: Integrating Deep Learning and Digital Twins for Positive Energy Distribution

Doctoral Training Grant Funding Information 

This funding model includes a 36 month fully funded PhD Studentship, set in-line with UK Research & Innovation values. For 2025/6, this will be £20,780 per year. The tax-free stipend will be paid monthly. This PhD Studentship also includes a Full-Time Fee Scholarship for up to 3 years. The funding is subject to your continued registration on the research degree, making satisfactory progression within your PhD, as well as attendance on and successful completion of the Postgraduate Certificate in Research Practice.    

All applicants will receive the same stipend irrespective of fee status. 

Application Closing Date: 


Midday (UK Time) on Wednesday 17th September 2025 for a start date of 2nd February 2026.  

How to Apply 

To apply, please follow the below steps:  

  1. Complete the BCU Online Application Form. 
  2. Complete the Doctoral Studentship Proposal Form in full, ensuring that you quote the project ID. You will be required to upload your proposal in place of a personal statement on the BCU online application form.  
  3. Upload two references to your online application form (at least one of which must be an academic reference). 
  4. Upload your qualification(s) for entry onto the research degree programme. This will be Bachelor/Master’s certificate(s) and transcript(s). 
  5. International applicants must also provide a valid English language qualification. Please see the list of English language qualifications accepted here. Please check the individual research degree course page for the required scores. 

Frequently Asked Questions 

To help support you to complete your application, please consult the frequently asked questions below: 

Project title: Smart Urban Energy Systems: Integrating Deep Learning and Digital Twins for Positive Energy Districts

Project Lead: ​​Dr. Syed Attique Shah​

Project ID: ​​24 - 45462304​ 

Project description:

​The UK faces a growing challenge in building a reliable and efficient energy system that supports its 2035 net-zero emissions target. Each year, the economy loses over £12 billion due to inaccurate energy demand forecasts, underutilised renewables, and emergency reliance on fossil fuels. At the same time, the UK government is committing £40 billion annually to modernise the national grid and clean energy infrastructure. However, without transparent, accurate data governance and predictive tools, these investments remain vulnerable to inefficiencies and unnecessary grid reinforcements. ​ 

​This project proposes an AI-enabled Digital Twin Framework for Positive Energy Districts (PEDs) to address these critical issues. Existing PED models are reactive and fragmented, lacking real-time adaptability and systems-level integration. To close this gap, we will develop a hybrid AI framework combining Deep Reinforcement Learning (DRL), Convolutional Neural Networks (CNNs), and Graph Neural Networks (GNNs). These models will collectively analyse multimodal urban energy data—capturing real-time usage, generation volatility, and spatial interdependencies between prosumers, energy storage, and grid components. 

​Our core research objectives include: 

  • ​Developing hybrid deep learning models to predict short-term energy demand, renewable generation patterns, and stress points across grid infrastructure. 
  • ​Creating and validating a prototype AI-powered digital twin through live data and pilot studies. 
  • ​Evaluating outcomes such as carbon reduction, grid stability, cost-efficiency, and social equity. 

​This digital twin will act as a virtual lab, allowing researchers, municipalities, and energy providers to simulate various energy strategies and responses to both predictable fluctuations and unexpected disruptions. Powered by AI, the system will recommend optimised actions for energy balancing, fault detection, and storage deployment transforming urban neighbourhoods from passive consumers into active energy hubs. 

​Key features of the platform include: 

  • ​Real-time sensing and control of local energy systems. 
  • ​Visual, interactive simulation interfaces for stakeholders. 
  • ​Integration with explainable AI (XAI) methods to ensure transparency, interpretability, and public trust. ​ 

​The research addresses a critical national question: How can urban districts generate more renewable energy than they consume while ensuring affordable, reliable power for all? In 2023, UK households faced average energy bills of £2,500, with 30% of power wasted due to outdated grid infrastructure. This project aims to deliver intelligent, community-centred solutions by fusing digital twinning, AI, and advanced energy systems design. The outcomes will help future-proof urban energy infrastructures and guide climate-resilient planning, directly supporting the UK’s legally binding climate targets for 2035. 

Anticipated findings and contributions to knowledge:

​​This project is expected to yield several novel insights and technological advancements in the field of AI-enabled energy systems and Positive Energy Districts (PEDs). First, we anticipate that the hybrid deep learning framework, integrating Deep Reinforcement Learning (DRL), Convolutional Neural Networks (CNNs), and Graph Neural Networks (GNNs), will significantly enhance the accuracy of short-term energy demand forecasting and renewable generation prediction at the district scale. This improvement will allow more dynamic and efficient balancing of energy supply and demand in real time, minimising curtailment of renewables and reducing reliance on fossil-fuel backup systems. 

​The digital twin prototype will demonstrate how AI can be embedded into live urban infrastructure to model, simulate, and optimise energy flows, identifying stress points and proposing actionable mitigation strategies. By validating this system in collaboration with Tyseley Energy Park, we will provide empirical evidence for the feasibility, adaptability, and scalability of AI-enhanced PEDs in real-world urban contexts. ​ 

​A key contribution to knowledge will be the development of an explainable AI (XAI) layer for digital twins, addressing transparency and public trust concerns that currently limit adoption of autonomous energy systems. The project will also generate new methodologies for modelling energy interdependencies using graph-based learning and multi-agent simulation within complex urban environments, filling a gap in current systems engineering approaches. ​ 

​Overall, this research advances the scientific understanding of how AI and digital twinning can support decarbonisation and resilience in energy infrastructure. It contributes to both academic literature and practical innovation by offering a replicable, open-access tool that informs energy planning, real-time management, and climate-aligned policy interventions. 

Person Specification:

We are seeking a highly motivated and capable individual to undertake a PhD as part of a cutting-edge research project focused on the development of AI-enabled digital twins for optimising energy flow in Positive Energy Districts (PEDs). The successful candidate will join an interdisciplinary team working at the intersection of artificial intelligence, energy systems, and urban digital infrastructure. 

Entry Requirements: 

  • To apply for our Computing PhD Research Degree you should have, or expect to be awarded, a Master’s degree in a relevant subject area from a British or overseas university.  
  • Exceptional candidates without a Master’s degree, but holding a first class or upper second class Bachelor’s degree in a relevant subject area, may be considered.  
  • We also welcome enquiries from potential PhD researchers with appropriate levels of professional experience. 

Essential Criteria: 

  • Programming and Technical Skills: Demonstrable proficiency in Python or similar programming languages, with experience in using libraries such as TensorFlow, PyTorch, or Keras for deep learning. Familiarity with data analysis and data visualisation tools is essential. 
  • AI and Machine Learning Knowledge: A sound understanding of machine learning principles and techniques, including supervised, unsupervised, and reinforcement learning. Basic knowledge of neural network architectures such as CNNs, GNNs, or RNNs is required. 
  • Energy Systems Awareness: A general understanding of smart grids, energy storage, renewable energy integration, or demand-side energy management. 
  • Analytical and Problem-Solving Skills: Ability to design experiments, analyse data, and draw meaningful conclusions. Capacity for independent critical thinking and creative problem-solving is crucial. 
  • Communication and Collaboration: Strong written and verbal communication skills with the ability to work effectively in a multidisciplinary environment and engage with academic, industry, and public stakeholders.  

Desirable Criteria: 

  • Research Experience: Prior experience in conducting academic or industry-based research projects, especially those involving simulation, optimisation, or real-time systems. 
  • Digital Twin Technologies: Familiarity with digital twinning platforms, system modelling tools (e.g., Simulink, Modelica), or urban simulation environments. 
  • Energy Modelling Expertise: Understanding of energy flow modelling in urban environments, energy consumption forecasting, or grid-interactive building systems. 
  • Publications and Dissemination: Authorship or co-authorship of research papers, conference presentations, or technical reports in relevant domains. 
  • GIS or IoT Knowledge: Exposure to Internet of Things (IoT) frameworks or Geographic Information Systems (GIS) is an advantage, especially where they relate to urban analytics and sensor-driven data. 

The ideal candidate will have a genuine interest in sustainability, climate change mitigation, and the digital transformation of energy systems. This PhD offers an opportunity to contribute meaningfully to the UK’s Net Zero goals while developing expertise in one of the most promising research areas in urban infrastructure and artificial intelligence. 

Overseas applicants:

International applicants must also provide a valid English language qualification, such as International English Language Test System (IELTS) or equivalent with an overall score of 6.5 with no band below 6.0.

Contact:

If you have any questions or need further information, please use the contact details below: 

- For enquiries about the funding or project proposal, please contact: syedattique.shah@bcu.ac.uk

- For enquiries about the application process, please contact:research.admissions@bcu.ac.uk