Glasgow Carbon-Conscious Computing (GC3) lab
The GC3 lab is a computer systems laboratory in the Glasgow Systems Section and the School of Computing Science at the University of Glasgow. Its research falls into the School's Low-Carbon and Sustainable Computing theme.
Interested in joining as a PhD student? We are looking for motivated students to work with us on sustainable computer systems.
starting point:
An increasing number of data-driven and AI-enabled applications process large amounts of data and make use of machine learning. These range from scientific data analysis in research organizations and large-scale data analytics in industry to applications built around the distributed sensors and devices of the Internet of Things.
We believe there is immense potential in using data-driven methods and machine learning across domains and disciplines. However, without careful consideration and new management techniques, this development will further increase computing's substantial and growing environmental footprint.
research agenda:
The central aim of our research is to reduce the carbon footprint of resource-intensive distributed systems running on today's diverse computing infrastructures. To this end, we work on methods and tools that enable a more resource-efficient and sustainable use of modern distributed computing infrastructures (e.g. edge and cloud resources) for scalable data-intensive applications (e.g. machine learning, big data analytics, stream processing), while also taking performance and dependability requirements into account.
Our guiding principles are:
- compute when and where green energy is available (which can, for instance, translate to carbon-aware scheduling, scaling, and resource allocation) as the carbon intensity of grids and renewable energy availability often varies
- allocate resources for high resource utilization and highly utilize allocated resources (which can, for example, translate to "right-sizing", server consolidation, co-location of jobs with complementary resource demands, and bottleneck mitigation) as any energy is wasted with mostly idling resources
- save computation and communication through distributed and dynamic architectures (which can, for instance, translate to edge computing, adaptively offloading tasks and scaling out to more nodes only when necessary, effective caching, or distributed learning) as it is sometimes possible to do the same with less in complex software systems
Much of the lab's work builds on our broader research on adaptive resource management for data-intensive systems, developed over several years and through close collaboration with TU Berlin, HU Berlin, and other partners. On this basis, we currently focus on investigating and making use of:
- profiling and predicting application and infrastructure performance as well as power consumption
- forecasting computational loads, carbon emissions, and the availability of renewable energy
- carbon-optimized resource allocation, dynamic scheduling and scaling, and automatic system tuning
Another focus is on techniques and tools that support monitoring, testing, and benchmarking of the performance and footprint of data-intensive distributed systems.
current lab members:
- lead researcher: Lauritz Thamsen
- doctoral researchers / research assistants: Gelara Jafari Pouyani (incoming), Jacob Roberts, James Nurdin, Kathleen West, Max MacDonald, Tobias Froehlich, Youssef Moawad
- L4/L5 project students: Adam Yuan, Finlay Raynor, Magnus Reid, Matthew Waters, Mohammed Akanbi
- visitors: Vasilis Bountris (April-June 2026; PhD student from HU Berlin)
Group photo (April 2026):
Left to right: James, Mohammed, Matthew, Kathleen, Lauritz, Max, Tobey, Vasilis, Magnus, and Youssef.
Previous photos: Isle of Bute away day (August 2025)
past lab members:
- L4/L5 project students: Andres La Riva Perez, Danial Tariq, Isabella Gard, James Sharma, John Wilson, Karl Hartmann, Richard Arthurs, Rishabh Mathur
- summer interns: Domonkos Revesz, Frederik Glitzner, Hubert Dymarkowski, Niovi Lampiri
- visitors: Giulio Attenni (April-September 2025; PhD student from Sapienza Rome), Philipp Wiesner (April-August 2022; PhD student from TU Berlin)
selected results:
- A Systematic Evaluation of the Potential of Carbon-Aware Execution for Scientific Workflows. Future Generation Computer Systems 182. 2026.
- Extended article of work first presented at CCGrid'25, with an expanded evaluation (additional workflows, tasks, and regions; processor governors; embodied emissions) and a thorough discussion of all results.
- Flora: Efficient Cloud Resource Selection for Big Data Processing via Job Classification. 25th IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid'25).
- Our paper is accompanied by an extensible toolkit for Spark performance benchmarking and a trace dataset of Spark executions on GCP.
- FedZero: Leveraging Renewable Excess Energy in Federated Learning. 14th ACM International Conference on Future Energy Systems (e-Energy'24).
- Lotaru: Locally Predicting Workflow Task Runtimes for Resource Management on Heterogeneous Infrastructures. Future Generation Computer Systems 150. 2024.
- Extended article of work first presented at SSDBM'22, showing heterogeneous cluster scheduling, cloud cost estimation, and carbon-aware scheduling based on predicted runtimes
- Karasu: A Collaborative Approach to Efficient Cluster Configuration for Big Data Analytics. 42nd IEEE International Performance Computing and Communications Conference (IPCCC'23).
- Our prototype implementation in Python with PyTorch and BoTorch is available on GitHub
- Cucumber: Renewable-Aware Admission Control for Delay-Tolerant Cloud and Edge Workloads. 28th International European Conference on Parallel and Distributed Computing (Euro-Par'22).
- Phoebe: QoS-Aware Distributed Stream Processing through Anticipating Dynamic Workloads. 20th IEEE International Conference on Web Services (ICWS'22).
- Let's Wait Awhile: How Temporal Workload Shifting Can Reduce Carbon Emissions in the Cloud. 22nd ACM/IFIP International Middleware Conference (Middleware'21).
- Towards a Staging Environment for the Internet of Things. 19th IEEE International Conference on Pervasive Computing and Communications (PerCom'21).
- LEAF: Simulating Large Energy-Aware Fog Computing Environments. 5th IEEE International Conference on Fog and Edge Computing (ICFEC'21).
Several of these works are featured in my talk in our Low-Carbon and Sustainable Computing seminar series and the recording of the talk is available online.
academic collaborations:
- the Distributed and Operating Systems group at TU Berlin (Prof. Dr. Odej Kao)
- the Knowledge Management in Bioinformatics group at Humboldt University of Berlin (Prof. Dr. Ulf Leser)
- the Operating Systems and Middleware group at Hasso Plattner Institute (Prof. Dr. Andreas Polze)
- the Artificial Intelligence Lab at the University of Nicosia (Dr. Demetris Trihinas)
- the Edge Computing Hub at the University of St Andrews (Dr. Blesson Varghese)
industry collaborations:
- AWS (partner in the EPSRC-funded Casper research project)
- BBC R&D (partner in the EPSRC-funded Casper research project)
- Barclays (funding a sustainable computing PhD research project)
research infrastructure:
For our research, we have access to CPU and GPU clusters as well as a variety of individual devices (e.g. different server architectures, IoT systems, energy meters) in Glasgow. In addition, we are regularly able to access other compute infrastructure (e.g. public/private cloud services) through grants and collaborations.