Job Shop Scheduling: A Novel DRL approach for continuous schedule-generation facing real-time job arrivals - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Job Shop Scheduling: A Novel DRL approach for continuous schedule-generation facing real-time job arrivals

Nour El Houda Hammami
  • Fonction : Auteur
Benoit Lardeux
Atidel B Hadj-Alouane
  • Fonction : Auteur
Maher Jridi

Résumé

We present a DRL-based novel approach to solve the Job Shop Scheduling Problem (JSSP) in real-time while facing unpredictable job arrival disruptions. Our proposed approach consists of continuously generating improved schedules based on a rescheduling technique: It leads to continuous generation of schedules in triggered rescheduling points, and thus gives immediate response to random job arrivals. To implement the proposed technique, we use Proximal Policy Optimization Actor and Critic (PPO-AC), a combination of two RL algorithms. PPO-AC is used to assign job operations to available machines based on the job shop state that is represented by dynamic disjunctive graphs, modeling precedence constraints between job operations, and resource sharing constraints. Graph Embedding modeling is also applied for dynamic graph representation in PPO-AC algorithm. Preliminary numerical experiments of our innovative solution are discussed in this paper.
Fichier non déposé

Dates et versions

hal-03706994 , version 1 (28-06-2022)

Identifiants

  • HAL Id : hal-03706994 , version 1

Citer

Nour El Houda Hammami, Benoit Lardeux, Atidel B Hadj-Alouane, Maher Jridi. Job Shop Scheduling: A Novel DRL approach for continuous schedule-generation facing real-time job arrivals. 10th MIM Conference of the International Federation of Automatic Control, Jun 2022, Nantes, France. pp.2493-2498. ⟨hal-03706994⟩
69 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More