🎓 Discover PhD and Master's programmes at leading universities worldwide — Sign up free to save searches and get email alerts
SHU

Agentic Reconfigurable Battery Scheduling for Multi-Energy Markets

Sheffield Hallam University Engineering and Built Environment
✓ Funded (Competition) 🎓 Artificial Intelligence 🎓 Electrical Engineering 🎓 Energy Technologies digital twins energy storage agentic ai battery scheduling multi-energy markets reconfigurable batteries smart grid multi-agent reinforcement learning

Investigate autonomous AI-driven battery systems that optimize multi-energy market participation. Develop novel algorithms integrating AI with advanced battery models to enhance grid flexibility and decarbonization. Create simulation tools to test real-world operational performance.

AI-generated overview

🌍
Why This Research Matters

This research enables the development of flexible, intelligent battery systems critical for integrating increasing renewables into energy grids. By optimizing multi-vector energy markets and supporting grid stability, it advances the transition to low-carbon, resilient energy infrastructures with real benefits for microgrids and remote communities.

Agentic AI Reconfigurable Batteries Multi-Energy Markets Smart Energy Systems Autonomous Optimization Energy Storage

Project Description

Project Overview

This project explores reconfigurable battery systems (RBS) integrated with agentic artificial intelligence capable of autonomous reasoning, planning, and multi-step actions. The aim is to develop AI-enabled batteries that respond in real time to dynamic multi-energy market signals by reconfiguring internal topology for revenue, battery health, emission reduction, and grid resilience. RBS will participate intelligently across electricity, heat, transport, and hydrogen markets, enhancing flexibility and resilience in evolving renewable-based energy systems.

What You Will Do

You will develop advanced AI frameworks including multi-agent reinforcement learning, autonomous optimization agents, and large model-based reasoning integrated with accurate reconfigurable battery models. You will design and test strategies for market participation such as frequency response, peak shaving, EV charging optimization, heat pump support, and hydrogen production. Building simulation environments or digital twins will enable realistic performance evaluation under operational and market conditions.

Expected Outcomes

Deliver innovative algorithms that enable RBS to autonomously optimize across multiple energy vectors and market environments. Demonstrate improved grid stability, revenue maximization, battery longevity, and decarbonization impacts. Provide a foundation for next-generation smart grid architectures featuring intelligent, self-adaptive energy storage solutions.

Why This Matters

As renewable energy expands, intelligent storage systems are critical to grid flexibility and low-carbon transitions. This research addresses limitations of traditional battery scheduling by creating AI-driven adaptable batteries that integrate diverse energy vectors. Results will directly impact microgrids, remote communities, and grid-constrained regions, offering practical solutions aligned with future multi-energy market developments and carbon reduction goals.

Entry Requirements

Applicants should hold at least a 1st or 2:1 Honours degree in BEng/BSc/MSc/MEng Electrical and Electronic Engineering, Power Systems, or a related discipline. Strong analytical, programming, AI or optimization, and power systems experience is essential.

How to Apply

To apply for this GTA scholarship, please use Sheffield Hallam University's online application form. Upload a personal statement (up to 2 pages) detailing interest and relevant experience. For questions, contact Dr. Augustine Ikpehai at a.ikpehai@shu.ac.uk.

Eligibility

UK/Home
EU
International

Supervisor Profile

DA
Dr Augustine Ikpehai
Sheffield Hallam University, Engineering and Built Environment

Dr. Augustine Ikpehai is a researcher specializing in intelligent energy systems, focusing on integrating advanced AI frameworks with battery technologies to enhance energy storage and smart grid resilience. His work bridges electrical engineering, optimization, and AI to deliver practical low-carbon energy solutions. He is actively involved in multidisciplinary projects addressing future energy market challenges.

More PhDs with Dr Augustine Ikpehai

Agentic Reconfigurable Battery Scheduling for Multi-Energy Markets
Sheffield Hallam University Dr Augustine Ikpehai Deadline: 07 May 2026

Develop cutting-edge agentic AI algorithms to autonomously control reconfigurable battery systems across complex multi-energy markets. Lead innovation in smart grid intelligence that dynamically adapts to evolving energ…

This research is vital for integrating renewable energy by enabling flexible, intelligent battery storage that maximises revenue, optimises…

1200+ citations · h18
Agentic AI Reconfigurable Batteries Multi-Energy Markets Smart Grid

Related Opportunities

PhD Scholarship in Hydrogen Storage for Clean Energy
University of Sydney Prof. Francois Aguey-Zinsou 🎓 Applied Chemistry 🎓 Chemical Engineering

Explore the development of novel hydrogen storage materials for clean energy applications. Join a world-class team at the University of Sydney to advance technologies critical for sustainable energy and decarbonization.

The research addresses the urgent global need for efficient hydrogen storage to enable widespread renewable energy deployment and combat cl…

9382+ citations · h52
Hydrogen technologies Storage Fuel cells Electrolyzers
Grid-Forming Wind Turbines for Power System Stability and Resilience
University of Exeter Dr Shuyue Lin 🎓 Electrical Engineering 🎓 Energy Technologies

Explore how grid-forming control can enhance the stability and resilience of power grids through wind turbine systems. Investigate critical control strategies and system interactions to support future renewable-heavy el…

This research supports the global transition to low-carbon electricity by enabling wind turbines to actively maintain grid stability and re…

Grid-Forming Control Wind Energy Power System Stability Renewable Integration
Signal Processing for X-ray Computed Tomography Data Compression
University of Warwick Dr Jay Warnett 🎓 Applied Mathematics 🎓 Artificial Intelligence

Explore advanced compression methods for massive XCT data to reduce storage needs by up to 80% without losing vital scientific detail. Develop predictive models exploiting XCT data redundancy within an open-source frame…

This project addresses the critical challenge of managing enormous volumes of XCT data, which currently pose storage, transmission, and arc…

1495+ citations · h21
X-Ray CT Metrology NDE/NDT Granular flows
Assessing Identification and Quantification Errors in Mass Spectrometry-Based Proteomics
Centre for Genomic Regulation (CRG) Prof. Lukas Käll 🎓 Artificial Intelligence 🎓 Biochemistry

Develop and apply hierarchical Bayesian networks to assess and quantify errors in proteomic data analysis. Build scalable tools improving protein identification accuracy and fostering more reliable biological insights.

This research improves the accuracy and reliability of proteomics data, essential for biological and biomedical studies that rely on mass s…

17413+ citations · h45
Computational Biology Proteomics Machine learning