SC17 Denver, CO

P61: Cloud Resource Selection Based on PLS Method for Deploying Optimal Infrastructures for Genomic Analytics Application


Authors: Katsunori Miura (Kitami Institute of Technology), Courtney Powell (Hokkaido University), Masaharu Munetomo (Hokkaido University)

Abstract: This poster proposes a method for determining infrastructures composed of cloud resources that concurrently meet satisfiability and optimality system requirements, such as computational performance, maximum price payable, and deployment location of a genomic analytics application. The input to the proposed method is a mathematical formula that captures the system requirements given by the user, which is defined in accordance with first-order predicate logic, whereas the output is a set of unit clauses representing infrastructures for deploying the genomic analytics application. In the proposed method, an equivalent transformation algorithm is used to generate valid solutions with respect to system requirements, and a genetic algorithm is used to evaluate the optimality of the solutions.
Award: Best Poster Finalist (BP): no

Poster: pdf
Two-page extended abstract: pdf


Poster Index