Distributed Systems and Services
We explore emerging issues in the infrastructure and systems performance for the next generation of distributed/Internet computing. Our research is focused on large-scale systems spanning communities, organisations, industries, and nations, bringing together computational power, big data, and human knowledge. Through this diversity, we play a leading role in designing the next generation of systems and tools for:
- Evaluating the performance of cloud services
- Flexible software abstractions
- Heterogeneous hardware platforms
- Massive-scale simulation
- Virtual systems engineering
- Data centre scheduling and analysis.
Our research
Our current research can be grouped into six main areas. It has been applied in a wide range of domains, including engineering, e-science, social science, business, health, technology-enhanced learning, and transport, nationally and internationally.
Architecture, security and dependability
This involves architecting and developing dependable and secure large-scale distributed systems. Examples include fault tolerance, transactions, access control, and dependable storage, with a focus on real-world cloud computing systems.
Performance and quality of service
This focuses on the quality of cloud/Edge-based services to enable organisations to manage their high-end computing resources efficiently. Balancing QoS and performance is essential for cloud providers to meet service level agreements (SLAs) and maintain user trust.
Collaboration in distributed environments
This builds on the semantic web, which provides an additional layer of intelligence and interoperability for systems over the Internet. Examples include techniques for transiting from requirements to semantics, models of collaborative working, and the use of provenance to reinforce trust.
Self-management of decentralised networked systems
This focuses on designing decentralized and self-managed techno-socio-economic systems, self-regulated supply-demand data sharing systems, and decentralized optimization and collective learning over crowd-sourced computational resources of citizens, enabling a new generation of artificial intelligence for socio-technical systems equipped with socially responsible self-management capabilities applied on emerging application domains of Smart Grids, Smart Cities and their sharing economies.
Machine learning in software development
This focuses on program optimisation and analysis, software testing and software reliability, accelerating large-scale deep learning models, and applied machine learning, with the aim of making software development easier and more accessible so that every programmer can easily write, maintain and optimise software.
Scheduling and optimisation in distributed computing
This focuses on Deterministic scheduling theory, scheduling with controllable parameters, and the application of optimisation techniques in distributed computing.
Collaborations and partnerships
We collaborate extensively with other universities and companies across the world. Ongoing collaborations include:
- The Communications Hub for Empowering Distributed Cloud Computing Applications and Research (CHEDDAR), EPSRC
- Trust and legitimation in the digital democracy, 77 National Research Programme
- Digitally-assisted Collective Governance of Smart City Commons-ARTIO, UKRI
- H2OforAll: protecting and treating drinking water (H2OforAll), Horizon Europe
Further information
View all members of our research group and publications.
PhD projects
Find out more about our opportunities for prospective postgraduate researchers.
Contact us
If you are interested in collaborating with us or joining our research team, please get in touch with Professor Jie Xu or Professor Karim Djemame.