Self-Regulation in Self-Organising Multi-agent Systems for Adaptive and Intelligent Manufacturing Control

Abstract

In this paper, we explore the potential of distributed satisfaction techniques as to provide self-regulated manufacturing control. This work relies on a DisCSP-based modeling distributed among agents (e.g. machines) having enough and reasoning capabilities to cooperate and negotiate for a committed schedule. This approach is used to dynamically regulate the system (the network of machines) when perturbations occur (machine break-out, operator or container unavailability, or even priority command). Thus, for these machines, embodied intelligence and autonomy are a mean to provide a more flexible and adaptive manufacturing network. In this paper, we present two different multi-agent models and two extensions of well-known DisCSP solvers. Experiments using a dedicated simulation platform, MASC, are presented and discussed.

Multi-satellite Mission Planning Using a Self-Adaptive Multi-agent System

“…For example, [9] propose an adaptive multi-agent approach to provide self-regulated manufacturing control. A dynamic resource allocation problem is also treated thanks to a trust and cooperation-based algorithm by [1].…”

Characterizing and Evaluating Problem Solving Self-* Systems

“…In [8], it is expressed by the number of checked constraints, or more generally the number of performed atomic operation. Another frequent way is the measurement of computing time (CPU) [9] [11]. For this, the characteristics of machines should be considered.…”

“…[12] introduces some transformation ratios in order to make run-times of different machines comparable. Others authors study the time as the number of steps needed by agents to reach the solution, for example in [9], it is calculated as the fabrication cycle number. While in [13], it is the number of rounds for synchronous algorithm.…”

“…It is just the measure of the activity. For example, in [9], the progress is measured as the total number of finished containers at each step. During time, this can be observed by looking at the curves representing this progress as they will have specific forms (linear, exponential, and logarithmic) (see Section V).…”

Multi-variable distributed backtracking with sessions

“…Many definitions have been proposed in the literature, from the concept of metaactions that define the interactions [41] to the complex notions of anticipation [36], including self-organization and emergence [12,15,57], and junction tree models [61,62]. In this paper, we consider that coordination can also be defined as a search process in the "distributed problemsolving" context [26,53,66].…”