Agent-based distributed manufacturing scheduling: an ontological approach

Abstract

The purpose of this paper is the need for self-sequencing operation plans in autonomous agents. These allow resolution of combinatorial optimisation of a global schedule, which consists of the fixed process plan jobs and which requires operations offered by manufacturers. The proposed agent-based approach was adapted from the bio-inspired metaheuristic-particle swarm optimisation (PSO), where agents move towards the schedule with the best global makespan. The research has achieved a novel ontology-based optimisation algorithm to allow agents to schedule operations whilst cutting down on the duration of the computational analysis, as well as improving the performance extensibility amongst others. The novelty of the research is evidenced in the development of a synchronised data sharing system allowing better decision-making resources with intrinsic manufacturing intelligence. The multi-agent platform is built upon the Java Agent Development Environment (JADE) framework. The operation research case studies were used as benchmarks for the evaluation of the proposed model. The presented approach not only showed a practical use case of a decentralised manufacturing system, but also demonstrated near optimal makespans compared to the operational research benchmarks.

Global Resources Management: A Systematic Review and Framework Proposal for Collaborative Management of CPPS

“…The distributed management paradigm is well-suited for permitting the decomposition of management problems, which may arise in the scope of extended, agile, and virtual production systems, usually characterized by higher levels of complexity associated with its underlying networked organization [7,40,43,44,46,96,102].…”

“…Saeidlou et al in 2019 [43] propose a cooperative system to perform distributed manufacturing scheduling, based on a set of rules considered to be most relevant, which are integrated through their proposed cooperative system, through an agent-based decision support system that, according to the authors, enables them to find near-optimal solutions within a reasonable computational time.…”

Analysis of a Collaborative Scheduling Model Applied in a Job Shop Manufacturing Environment

“…There are different kinds of approaches that can be used for establishing production schedules, varying from enumerative algorithms to the application of simple priority rules. Moreover, these approaches can be based on pure mathematical programming models or use simulation technique among other approaches [5], for instance, based on multi-agents, among others [18,24,[37][38][39].…”

Towards decentralised job shop scheduling as a web service

“…As discussed in the literature, systems of this nature requiring problem-solving capability need improvement using optimisation alorithms; these can also be multi-agent systems, or exchange models. The latter acknowledges the flow and development of information as opposed to the optimisation model which addresses the agents' objective functions (Nedic & Ozdaglar, 2009;Saeidlou et al, 2019b). Previous work by the authors has demonstrated encouraging findings regarding decentralised GA optimisation acquired through the use of REPAST (Jules & Saadat, 2017).…”