Bayesian Optimization Algorithm with Agent-based Supply Chain Simulator for Multi-echelon Inventory Management

Kiuchi, Atsuki; Wang, Haiyan; Wang, Qiyao; Ogura, Takahiro; Nomoto, Tazu; Gupta, Chetan; Matsui, Takeshi; Serita, Susumu; Zhang, Chi

doi:10.1109/case48305.2020.9216792

Cited by 10 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two proposed methods for handling such a constraint are as follows [13]. One involves introducing a high penalty cost whenever the parameter setting falls into an infeasible region (i.e., the constraint is violated).…”

Section: Proposed Methods For Supply Chain Inventory Controlmentioning

confidence: 99%

“…In terms of application of Bayesian optimization to SCM, Kiuchi et al [13] proposed a Bayesian optimization framework for inventory control problem and verified that the methodology can get optimal solution faster than GA with serial 3-echelon SC model.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Therefore, this study is intended to extend the Bayesian optimization framework [13] to apply it to more general real-world scale of multi-echelon SC and to verify its effectiveness. In order to achieve the purpose, we introduce multi-echelon distribution SC model in the next chapter and formulate an inventory control problem with the SC model.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Our second method is motivated by the effectiveness of using a GP to approximate the objective function in Bayesian optimization. We approximate the constraint function using another GP then adapt the acquisition function to handle the constraint, as proposed Gardner et al [13]. Suppose we use another GP model g(x) ∼ GP µ g (•), Σ g (•, •) to approximate g(x).…”

Section: Bayesian Optimization With Constraintsmentioning

confidence: 99%

See 3 more Smart Citations

Bayesian Optimization Methods for Inventory Control with Agent-Based Supply-Chain Simulator

Ogura

Wang

et al. 2022

IEICE Trans. Fundamentals

Self Cite

View full text Add to dashboard Cite

We propose a penalty-based and constraint Bayesian optimization methods with an agent-based supply-chain (SC) simulator as a new Monte Carlo optimization approach for multi-echelon inventory management to improve key performance indicators such as inventory cost and sales opportunity loss. First, we formulate the multi-echelon inventory problem and introduce an agent-based SC simulator architecture for the optimization. Second, we define the optimization framework for the formulation. Finally, we discuss the evaluation of the effectiveness of the proposed methods by benchmarking it against the most commonly used genetic algorithm (GA) in simulation-based inventory optimization. Our results indicate that the constraint Bayesian optimization can minimize SC inventory cost with lower sales opportunity loss rates and converge to the optimal solution 22 times faster than GA in the best case.

show abstract

Section: Proposed Methods For Supply Chain Inventory Controlmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

Section: Bayesian Optimization With Constraintsmentioning

confidence: 99%

See 2 more Smart Citations

Bayesian Optimization Methods for Inventory Control with Agent-Based Supply-Chain Simulator

Ogura

Wang

et al. 2022

IEICE Trans. Fundamentals

Self Cite

View full text Add to dashboard Cite

show abstract

“…The fundamental idea of SAO is to approximate the performance measures by a surrogate model whose computational cost is relatively lower than simulation. As surrogate models, linear regression (LR) [19], support vector machine (SVM) [20], gradient boosting trees (GBT) [21], artificial neural networks (NN) [22], and Gaussian process (GP) [23] are utilized. Bayesian optimization (BO), which uses GP as a surrogate model, is one of the most popular SAO methods.…”

Section: Surrogate-assisted Optimizationmentioning

confidence: 99%

Fast Simulation-Based Order Sequence Optimization Assisted by Pre-Trained Bayesian Recurrent Neural Network

Suemitsu

Bhamgara

Utsugi

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

This paper presents a fast optimization method for the picking order sequence of automated order picking systems in logistics warehouses. In this order sequencing problem (OSP), the fulfillment sequence of the given picking order set is determined to optimize the performance measures such as makespan and deadlock occurrence. Simulation is generally necessary to evaluate these measures for complex automated systems. However, their order sequence cannot be optimized quickly due to the long calculation time. It may make the system productivity and flexibility lower than expected because its picking schedules cannot be updated frequently. We, therefore, propose a fast optimization method to solve these simulation-based OSPs by taking a pretrained surrogate-assisted optimization approach. Firstly, we utilized a Bayesian recurrent neural network (BRNN) as a surrogate model to accurately learn the relationship between picking order sequence and performances. Secondly, we developed the surrogate-assisted optimization method based on simulated annealing (SA) and BRNN. Numerical experiments show that the surrogate model can evaluate about 10000 times faster than the simulation. The proposed method also obtains an optimized solution 8.9 times faster than simulation-based optimization by the original SA.

show abstract

A Simulation Optimization Approach to Inventory Optimization in Supply Chain Networks

Mahmoudi,

Eshghi,

Basirati

et al. 2023

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Bayesian Optimization Algorithm with Agent-based Supply Chain Simulator for Multi-echelon Inventory Management

Cited by 10 publications

References 7 publications

Bayesian Optimization Methods for Inventory Control with Agent-Based Supply-Chain Simulator

Bayesian Optimization Methods for Inventory Control with Agent-Based Supply-Chain Simulator

Fast Simulation-Based Order Sequence Optimization Assisted by Pre-Trained Bayesian Recurrent Neural Network

A Simulation Optimization Approach to Inventory Optimization in Supply Chain Networks

Contact Info

Product

Resources

About