Skip to content Search
Search our website:

Performance Optimisation for Cloud and Big Data Systems

Performance Optimisation for Cloud and Big Data Systems

Supervisors: Dr Stelios Sotiriadis

The distributed computing system is currently used more than ever, from cloud computing to big data processing and storage. This PhD area is related to a selection of topics, including:

a) Performance modelling and optimisation for resource management of distributed systems: Methods and techniques for improving the performance of real - world systems including OpenStack, Hadoop MapReduce, Spark, YARN, NoSQL database systems and others as in [1] and [2]. Students will utilise modern workloads to demonstrate the effectiveness of optimisation algorithms for such systems.

b) Data science and analytics for distributed systems: These systems generate enormous size datasets, e.g., in the form of time - series data or log data or Internet of Things systems. Students will develop algorithms and machine learning methods for automated analysis and optimisation. This included improved reliability and fault tolerance, anoma ly detection, scalability etc. as in [3].

The projects are highly technical and are based on state-of-the-art systems and approaches used heavily in IT industry. Students will investigate methods and techniques for evaluating the performance of distribute d systems.

Candidate Requirements:

This PhD is aimed at graduates with a strong computer science background and programming. Research will be organised around real-world systems and workloads. The student should be familiar or looking to learn distribute d computing concepts, use of Linux environments and develop programming skills

Key Reference:

[1] Sotiriadis, S., Bessis, N., Amza, C., Buyya, R. (2016), “A new approach to elastic load balancing for dynamic virtual machine reconfiguration”, IEEE Transactions on Services Computing, vol. PP, no.99.

[2] Sotiriadis, S., Bessis, N., Anjum, A. , Buyya, R., (2015) "An Inter - Cloud Meta - Scheduling (ICMS) Simulation Framework: Architecture and Evaluation", IEEE Transactions on Services Computing, vol. PP, no.99, pp.1,1 DOI: 10.1109/TSC.2015.2399312

[3] Bhattacharyya, A., Jokar , A., Sotiriadis, S. and Amza, C., Semantic Aware Online Detection of Resource Anomalies on the Cloud, 8th IEEE International Conference on Cloud Computing Technology and Science (CLOUDCOM 2017), Luxembourg, Dec 12th - Dec 15th, 2016.

Further details about the project may be obtained from:

Principal supervisor: Dr Stelios Sotiriadis

Further information about PhDs at CSIS is available via this link.