Performance and reliability engineering
I work extensively on applications of modelling and simulation to manage performance and reliability in cloud and Big data systems. My work focuses on decision problems arising in resource provisioning, architectural design, and QoS/SLA management.
- Resource management
- Software architecture
- Scheduling and load-balancing
- System configuration auto-tuning
I investigate analytical modelling methods to describe phenomena such as queueing, synchronization, caching, and temporal dependence. Models of these phenomena help in describing, among others, service workflows, software architectures, computer networks, business processes, web service compositions, manufacturing systems, and bike/car sharing systems.
- Queueing theory
- Markov chains
- Petri nets
- Synchronization and workflows
- Time series
- Markov decision processes
- Process mining