|
Ph.D. position: Real-Time Cloud Computing
Applications are invited for a Research Assistant/Ph.D. position in Real-Time Cloud Computing at the University of Pennsylvania. The candidate will be associated with the PRECISE Center and the NetDB@Penn research group. The candidate must hold a M.S. or equivalent with top performance in computer science or electrical engineering. The candidate must have a combination of strong theoretical and practical interests. Experience in embedded systems, real-time systems, or cloud computing, as well as good implementation skills are desirable. The candidate should have interest in conducting original highly competitive scientific research, publishing the results in top conferences and scientific journals, and participating in teaching duties. Self-motivation and the ability to work both independently and as a team member are expected. Applications from women and members of other under-represented groups are particularly welcome. To apply, please send a description of research interests and past experience, a CV, degrees and grades, a copy of Master thesis (or a draft thereof), relevant publications, and other relevant documents to Linh T.X. Phan (linhphan AT cis.upenn.edu). Inquiries can be directed to the PIs: Project Description: Cloud computing enables flexible, dynamic outsourcing while improving cost efficiencies. These operational and economic benefits, however, are today not available to the prominent class of safety-critical and mission-critical real-time applications due to the lack of timeliness supports by current cloud infrastructures. Unlike traditional real-time scheduling environments, providing real-time guarantees in cloud environments faces several novel challenges due to the unpredictable system performance as a result of virtualization, failures, heterogeneity, and multi-tenancy. This research extends current cloud infrastructures with real-time resource management techniques to enable real-time guarantees on the cloud. The project (i) introduces a formal framework for modeling and performance evaluation of real-time applications in cloud environments; (ii) develops algorithms for scheduling continuous streams of real-time cloud applications in an online setting; (iii) designs techniques to address issues introduced by virtualization and machine failures; and (v) evaluates these techniques in the context of practical real-time applications. This project will provide data-parallel middleware infrastructures that will enable a new generation of applications with real-time requirements to be deployed on the cloud, bringing the benefits of virtualization and utility computing to novel mission-critical application domains. The outcomes of this project will be released as open source to spur the advancement of research and development of cloud computing targeting real-time applications and systems. Back to the homepage |