Value-Based Manufacturing Optimisation in Serverless Clouds for Industry 4.0

TY - GEN

T1 - Value-Based Manufacturing Optimisation in Serverless Clouds for Industry 4.0

AU - Dziurzanski, Piotr

AU - Swan, Jerry

AU - Soares Indrusiak, Leandro

PY - 2018/3/24

Y1 - 2018/3/24

N2 - There is increasing impetus towards Industry 4.0, a recently proposed roadmap for process automation across a broad spectrum of manufacturing industries. The proposed approach uses Evolutionary Computation to optimise real-world metrics. Features of the proposed approach are that it is generic (i.e. applicable across multiple problem domains) and decentralised, i.e. hosted remotely from the physical system upon which it operates. In particular, by virtue of being serverless, the project goal is that computation can be performed `just in time' in a scalable fashion. We describe a case study for value-based optimisation, applicable to a wide range of manufacturing processes. In particular, value is expressed in terms of Overall Equipment Effectiveness (OEE), grounded in monetary units. We propose a novel online stopping condition that takes into account the predicted utility of further computational effort. We apply this method to scheduling problems in the (max,+) algebra, and compare against a baseline stopping criterion with no prediction mechanism. Near optimal profit is obtained by the proposed approach, across multiple problem instances.

AB - There is increasing impetus towards Industry 4.0, a recently proposed roadmap for process automation across a broad spectrum of manufacturing industries. The proposed approach uses Evolutionary Computation to optimise real-world metrics. Features of the proposed approach are that it is generic (i.e. applicable across multiple problem domains) and decentralised, i.e. hosted remotely from the physical system upon which it operates. In particular, by virtue of being serverless, the project goal is that computation can be performed `just in time' in a scalable fashion. We describe a case study for value-based optimisation, applicable to a wide range of manufacturing processes. In particular, value is expressed in terms of Overall Equipment Effectiveness (OEE), grounded in monetary units. We propose a novel online stopping condition that takes into account the predicted utility of further computational effort. We apply this method to scheduling problems in the (max,+) algebra, and compare against a baseline stopping criterion with no prediction mechanism. Near optimal profit is obtained by the proposed approach, across multiple problem instances.

KW - Plant optimisation

KW - Genetic Algorithm

KW - Value Curve

KW - Stopping Condition

KW - Function as a Service

KW - FaaS

KW - Serverless Clouds

M3 - Conference contribution

BT - Proceedings of the Genetic and Evolutionary Computation Conference

T2 - The Genetic and Evolutionary Computation Conference

Y2 - 15 July 2018 through 19 July 2018

ER -