Title:Improving responsiveness of autoscaling systems
The aim of this project would be to implement more efficient and responsive autoscaling for the existing production parsers for a company I have connections with. Through this project I hope to: (i) improve the deployment model for autoscaling in terms of reactivity, granularity and termination speed; (ii) implement a system to predict and anticipate increased workload and scale up accordingly. There would also be potential to extend this project further by extending the deployment model to the whole system in order to prevent bottlenecks other system areas.
Deliverables: Initial plan
Final report
Student: Gregory Nichols
Supervisor: Omer F Rana
Moderator: Hantao Liu
Report: Archive