GREEN project: PhD and Masters openings

Balancing energy saving with speed

Many devices, such as CPUs, disk drives and wireless transmitters, can adapt the speed at which they process data, with higher speeds requiring more power per bit.

This project will examine fundamental trade-offs incurred in such systems, including finding bounds on how much energy can be saved by real-time scheduling algorithms, and the effect that such algorithms have on the fairness between different classes of jobs.

Supervisor: Lachlan Andrew.

Power management of a supercomputing cluster

A large data centre consumes as much electricity as an entire city. These data centres consist of hundreds or thousands of individual computers serving a time-varying workload, and it is important to turn off as many servers as possible, with minimal degradation in performance. This project will both develop and study provably-good algorithms for such power management, and also develop state-of-the-art heuristics to minimise the power consumption of Swinburne's super computing cluster, the "Green Machine".

Supervisor: Lachlan Andrew.

Interaction between transport layer (TCP) and energy saving

TCP was designed to operate over constant-speed links which are always connected. However, energy saving technology allows lightly-utilised links to slow down, or power down completely. This project will consider both the impact that these link fluctuations have on TCP performance, and also how small changes in TCP's traffic patterns can improve the ability of links to enter low-power states.

Supervisor: Lachlan Andrew.