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 designs economical online 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 number that the user is willing to buy executing its job and a pair of) a soft deadline, specifying the preferred finish time of the task, furthermore a penalty function that characterizes the price of violating the deadline. We tend to target cloud job auctions that executes in an on-line fashion, runs in polynomial time, provides truthfulness guarantee, and achieves optimal social welfare for the cloud ecosystem. Towards these goals, we tend to leverage the subsequent classic and new auction style techniques. First, we tend to adapt the posted pricing auction framework for eliciting truthful online bids. Second, we tend to address the challenge posed by soft deadline constraints through a replacement technique of compact exponential-size LPs as well as twin separation oracles. Third, we tend to develop economical 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 style.