INSPIRE: Stochastic Processing Calculus: A New Methodology for Advanced Semiconductor Manufacturing and Data Center Networking

University Of California-San Diego, La Jolla CA

Investigators

Abstract

This INSPIRE award is partially funded by Research in Networking Technology and Systems Program in the Division of Computer and Network Systems in the Directorate for Computer and Information Science and Engineering, the Manufacturing Enterprise Systems Program in the Division of Civil, Mechanical and Manufacturing in the Directorate for Engineering, and the Communications and Information Foundations Program in the Division of Computing and Communications Foundations in the Directorate for Computer and Information Science and Engineering. This project addresses common problems across two traditionally separate disciplines of manufacturing and networking by focusing on the following applications in the two fields-advanced semiconductor manufacturing and virtualized data center networking. Research in each field has heretofore focused on different problems, with semiconductor manufacturing largely focused on throughput maximization, mean cycle time minimization and system stability and cloud networking on network performance guarantees. However, the two areas would benefit from sharing a common integrated focus and a unifying stochastic processing network model for modeling and analyzing problems. This project contributes this new mathematical foundation along with a set of practical service disciplines and scheduling algorithms to enable reasoning about and to provide performance guarantees in stochastic processing networks. In particular, this project will concurrently investigate the problems of delivery guarantees in semiconductor manufacturing and network performance guarantees in virtualized data centers so that the two application domains can inform each other and by doing so develop new solutions that might not otherwise be imagined. The central contribution of the proposed work will be a new mathematical foundation, which the principal investigators call Stochastic Processing Calculus that will allow researchers and practitioners to reason about and provide performance guarantees for diverse range of applications that can be modeled as stochastic processing networks. Scientific discoveries often happen at the intersection of two disciplines. This project involves very competent and accomplished researchers (in the areas of networking, network theory, and industrial systems engineering and operations research) and crosses diverse disciplines with the intension of looking at a set of intersections as it explores and advances Stochastic Processing Calculus. The contributions from this effort include exploring this new area of mathematics and in its potentially transformational application to each of the two research areas. Broader Impact: This INSPIRE project is transformational in that it promises to deliver a new rigorous modeling and analytical framework that can encompass a broad range of emerging networking problems. New analytical and algorithmic results that will be developed for the general abstraction of stochastic processing network are expected to have broad applications in a diverse range of fields. More broadly speaking, the proposed work is transformational in that it will contribute to a larger body of 'Network Science'. Network Science is being recognized as an emerging field in its own right in that many of the mathematical foundations and network algorithmics developed in the networking community are finding wide applications in many other fields.