Dynamic scheduling for multi-site companies: a decisional approach based on reinforcement multi-agent learning

  title={Dynamic scheduling for multi-site companies: a decisional approach based on reinforcement multi-agent learning},
  author={Nassima Aissani and Abdelghani Bekrar and D. Trentesaux and Bouziane Beldjilali},
  journal={Journal of Intelligent Manufacturing},
In recent years, most companies have resorted to multi-site or supply-chain organization in order to improve their competitiveness and adapt to existing real conditions. In this article, a model for adaptive scheduling in multi-site companies is proposed. To do this, a multi-agent approach is adopted in which intelligent agents have reactive learning capabilities based on reinforcement learning. This reactive learning technique allows the agents to make accurate short-term decisions and to… 
A centralized reinforcement learning approach for proactive scheduling in manufacturing
A centralized reinforcement learning approach is proposed for optimally scheduling of a manufacturing system of multi-stage processes and multiple machines for multiple types of products, which employs learning and control algorithms to enable real time cooperation of each processing unit inside the system.
Multi-agent reinforcement learning based maintenance policy for a resource constrained flow line system
A distributed multi-agent reinforcement learning algorithm is proposed to solve the maintenance problem for a flow line system consisting of two series machines with an intermediate finite buffer in between and to obtain the control-limit maintenance policy for each machine associated with the observed state represented by yield level and buffer level.
An interoperable adaptive scheduling strategy for knowledgeable manufacturing based on SMGWQ-learning
Results from the convergence analysis and simulation experiments show the effectiveness of the proposed adaptive scheduling mechanism, known as SMGWQ-learning, that endows the scheduling system with higher intelligence, interoperability and adaptability to environmental changes by self-learning.
An agent-based approach to intelligent manufacturing network configuration
The participation of small and medium enterprises in inter-firm collaboration can enhance their market reach while maintaining production lean. The conventional centralised collaboration approach is
A Model for Manufacturing Scheduling Optimization Through Learning Intelligent Products
An original approach combining active/intelligent product architecture with learning mechanism to assure flexibility and agility to the overall manufacturing system is proposed.
A heuristically accelerated reinforcement learning method for maintenance policy of an assembly line
This paper aims to investigate the maintenance policy for a two-machine one-buffer (2M1B) assembly line system. We assume that the observed quality states of the deteriorating machines in the system
Heurestics and reinforcement learning in manufacturing control: Optimization by phases
Manufacturing control still continues to attract the attention of researchers for 3 decades already. But what concerns them most is to find a compromise between optimizing either for cost, time, ect.
ALATO: An efficient intelligent algorithm for time optimization in an economic grid based on adaptive stochastic Petri net
This paper proposes ALATO, an intelligent algorithm based on learning automata and adaptive stochastic Petri nets (ASPNs) that optimizes the execution time for tasks in economic grids.


Real-time supply chain control via multi-agent adjustable autonomy
Towards agent-based multi-site scheduling
This contribution analyses the organizational structures found in distributed production networks and proposes an approach for their mapping to multiagent systems for integrated production planning and scheduling.
Dynamic scheduling of maintenance tasks in the petroleum industry: A reinforcement approach
Use of machine learning for continuous improvement of the real time heterarchical manufacturing control system performances
This paper presents the steps to work out a manufacturing control system where the decisions taken by the system are the result of an agents group work, and introduces a new type of agents called 'observant agent', which has the responsibility to supervise the evolution of the system's total performance.
Multi agent architecture for dynamic incremental process planning in the flexible manufacturing system
This paper initiatively combine the heuristic search algorithms of the process plan networks with the negotiation protocols, in order to generate suitable process plans for the target products real-timely and dynamically, based on the alternative manufacturing processes.
Approach by localization and multiobjective evolutionary optimization for flexible job-shop scheduling problems
Two new approaches to solve jointly the assignment and job-shop scheduling problems (with total or partial flexibility) are presented and an evolutionary approach controlled by the assignment model is generated.
A stigmergic approach for dynamic routing of active products in FMS
Fuzzy Policy Reinforcement Learning in Cooperative Multi-robot Systems
A multi-agent reinforcement learning algorithm with fuzzy policy used to deal with some control problems in cooperative multi-robot systems and results demonstrate that the control performance can be improved after the learning.
Multistage-Based Genetic Algorithm for Flexible Job-Shop Scheduling Problem
A multistage-based genetic algorithm with bottleneck shifting is developed for the fJSP problem and Phenotype-based crossover and mutation operators are proposed to adapt to the special chromosome structures and the characteristics of the problem.