Decision-making in low-carbon supply chain networks considering demand uncertainty

• Published in: Neural computing & applications 2024-06, Vol.36 (17), p.9891-9901
• Main Authors: Li, Yuxian, Wang, Jiuhe
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Carbon; Communication; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Decision making; Demand; Emissions trading; Environmental tax; Fiscal policy; Image Processing and Computer Vision; Impact analysis; Innovations; Inventory; Multiagent systems; Normal distribution; Optimization; Order quantity; Pricing; Probability and Statistics in Computer Science; Retail stores; S.I.: Neural Networks and Machine Learning Empowered Methods and Applications in Healthcare; Special Issue on Neural Networks and Machine Learning Empowered Methods and Applications in Healthcare; Subsidies; Supply chains
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-09595-0

This paper studies supply chain pricing and production/ordering decisions under carbon tax policy and retailer’s stochastic demand. Firstly, a supply chain model with random demand obeying normal distribution is established. Based on this, a stochastic optimization problem with the goal of maximizing expected social welfare is constructed. The multi-agent consensus is used to solve the optimization problem, and the pricing and production/ordering decisions with random demand obeying normal distribution are obtained. Finally, the theoretical results are verified by numerical simulation, and the influence and effectiveness of multi-agent consensus theory on supply chain decision-making are demonstrated in the presence of random demand and sudden failure of an enterprise in the supply chain and further analyze the impact of carbon tax policy on supply chain decision-making.