FREE PhD Study Fairs in Sheffield & Edinburgh | REGISTER NOW FREE PhD Study Fairs in Sheffield & Edinburgh | REGISTER NOW

Smart Energy and Performance Optimisation Framework for Modern Computing Platforms Using Deep Learning and Data Analytics


   School of Computing


About the Project

Applications are invited for a self-funded, 3-year full-time or 6-year part time PhD project.

The PhD will be based in the School of Computing and will be supervised by Dr Hamidreza Khaleghzadeh, Dr Mohamed Bader-El-Den and Dr Alexey Lastovetsky. The successful candidate collaborates with research staff members from the Heterogeneous Computing Lab (HCL) in University College Dublin and will remotely use their facilities and clusters to carry out some part of the experiments.  

The work on this project could involve:

  • Developing theoretical foundations and algorithms that enable designing scalable and energy-efficient parallel applications with low energy footprint 
  • Workload performance and energy consumption analysis on CPUs and ideally GPUs or accelerator architectures
  • Developing predictor models using different machine learning methods to estimate component-level performance and energy consumption in HPC computing platforms

Project description

The share of ICT in total energy consumption is quickly increasing and is set to reach 20% by 2030. Current trends indicate that by 2040, global carbon emissions from centres will be 40% of transportation’s current level.

The School of Computing at University of Portsmouth is seeking a suitable PhD candidate to conduct research on energy-efficient parallel computing in heterogeneous multicore era. The project aims to develop models, methods, algorithms, and software for optimization of the energy and performance of applications in modern highly heterogeneous and hybrid systems, used in High-Performance Computing (HPC), Internet of Things and many other current and emerging digital platforms. While the mainstream approach to energy optimization of computing is to optimize the execution environment rather than applications running in the environment, this project will focus on optimization of applications, not executing platforms, which has a huge potential for energy savings but have not been studied due to the complexity of the related engineering and scientific problems.

This project will use data analytics and machine learning tools, such as Neural Networks, to produce a scalable and accurate component-level energy and performance measurement approach. The output of the proposed energy/performance measurement technique is intended for developing, training, and tuning the optimisation framework and finding all energy/performance Pareto-optimal configurations of parallel applications. The developed methods and algorithms will be applied to a wide range of applications, such as machine learning methods, and heterogeneous HPC platforms.

The supervisory team consists of Dr Hamidreza Khaleghzadeh, who has a great deal of expertise and a proven track record of achievements in energy and performance optimisation of HPC platforms, Dr Mohamed Bader-El-Den with over 15 years of research experience in the areas of machine learning and its applications in Health Care, Cybersecurity, Digital Marketing, and Dr Alexey Lastovetsky, the director of Heterogeneous Computing Lab (HCL) in University College Dublin with over 20 successful PhD completions.

The successful candidate will also visit/work with research staff in HCL group, which will be excellent opportunities for skills and career development. 

General admissions criteria

You'll need a good first degree from an internationally recognised university or a Master’s degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

Specific candidate requirements

  • Experience programming in C/C++/Python
  • Good knowledge of machine learning basis and experience with Data Analysis, Data Visualisation tools (Keras, TensorFlow, Pandas) and implementing various machine learning models
  • Working experience of parallel computing concepts and familiarity with multithreaded and distributed tools and libraries such as CUDA, OpenCL, MPI etc
  • Excellent communication and academic writing skills
  • Fluency in working on Linux systems will be an advantage

How to Apply

We encourage you to contact Dr Hamidreza Khaleghzadeh () to discuss your interest before you apply, quoting the project code below.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process. 

When applying please quote project code:COMP5861023


Funding Notes

Self-funded PhD students only.
PhD full-time and part-time courses are eligible for the UK Government Doctoral Loan (UK students only).

Email Now


Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs