Paper
5 July 2024 Dynamic optimization approach for service composition in cloud manufacturing amidst stochastic disturbances
Chao Yin, Yuebin Zhang, Chen Chen
Author Affiliations +
Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 131844R (2024) https://doi.org/10.1117/12.3033209
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia
Abstract
Aiming at the problem of stochastic disturbance in the optimization of cloud manufacturing service portfolio, a dynamic optimization method based on deep reinforcement learning was proposed. The approach starts by creating a service portfolio optimization model that incorporates resource utilization that takes into account third-party benefits. Then, the Markov process was used to construct the reinforcement learning model, and the Double Deep Q-Network with Dueling Architecture (D3QN) algorithm was used to solve the problem. Experimental verification and comparative analysis verify the effectiveness of the algorithm in managing stochastic perturbations.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Chao Yin, Yuebin Zhang, and Chen Chen "Dynamic optimization approach for service composition in cloud manufacturing amidst stochastic disturbances", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 131844R (5 July 2024); https://doi.org/10.1117/12.3033209
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Manufacturing

Clouds

Stochastic processes

Mathematical optimization

Network architectures

Decision making

Algorithm testing

Back to Top