PROJECT TITLE :

An Efficient Cloud Market Mechanism for Computing Jobs With Soft Deadlines - 2017

ABSTRACT:

This paper studies the cloud market for computing jobs with completion deadlines, and styles economical on-line auctions for cloud resource provisioning. A cloud user bids for future cloud resources to execute its job. Each bid includes: 1) a utility, reflecting the amount that the user is willing to obtain executing its job and a pair of) a soft deadline, specifying the preferred end time of the task, and a penalty function that characterizes the cost of violating the deadline. We tend to target cloud job auctions that executes in an online fashion, runs in polynomial time, provides truthfulness guarantee, and achieves optimal social welfare for the cloud ecosystem. Towards these goals, we leverage the following classic and new auction design techniques. Initial, we have a tendency to adapt the posted pricing auction framework for eliciting truthful online bids. Second, we address the challenge posed by soft deadline constraints through a new technique of compact exponential-size LPs let alone twin separation oracles. Third, we have a tendency to develop efficient social welfare approximation algorithms using the classic primal-dual framework based mostly on both LP duals and Fenchel duals. Empirical studies driven by real-world traces verify the efficacy of our online auction design.