International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 05 | May 2024
p-ISSN: 2395-0072
www.irjet.net
Investigating the application of Quantum-Enhanced Generative Adversarial Networks in optimizing supply chain processes Saurabh A Pahune1, Noopur Rewatkar2 1
Cardinal Health, Dublin OH 43017, USA saurabh.pahune@cardinalhealth.com
2Christian Brothers University, Memphis TN 38104, USA nrewatka@cbu.edu ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Considering the advancement of industries into
facilities, and the overall strategic goals of the business. This stage includes the examination of market demand, the establishment of supply sources, and the formulation and arrangement of manufacturing processes.
the era of quantum computing, new possibilities emerge for enhancing complex structures like supply chains. This study investigates the possibilities of utilizing quantum-enhanced Generative Adversarial Networks (GANs) to transform supply chain and operations management (SCOM). Our objective is to improve transportation efficiency, warehouse management, distribution processes, inbound logistics, and retail and channel logistics by combining quantum computing breakthroughs with GANs. The paper explores the fundamental principles of quantum computing and GANs, emphasizing their collective capacity to tackle the complexities of supply chain difficulties. We aim to investigate the ability of GANs to construct more precise models and identify optimal solutions for supply chain optimization. This will involve enhancing training efficiency, optimizing skills, and incorporating quantum computing modeling. Quantum Generative Adversarial Networks (QGANs), which rely on quantum computing, are predominantly employed for the purpose of generating images and synthesizing data. However, they can also be modified to do language modeling tasks. This research is expected to result in substantial cost savings, improved productivity, and decreased delays across the supply chain. These outcomes will facilitate breakthrough advancements in SCOM.
In the planning phase, a strategic supply chain plan is created to efficiently manage the balance between supply and demand. It encompasses the strategic management of inventories, the coordination of assets, and the optimization of product delivery, services, and information flow between suppliers and customers. The main goal of this phase is to guarantee the efficient operation of the supply chain and fulfill the requirements of the company and its consumers. The execution phase involves the implementation and supervision of supply chain activities, which include warehouse and inventory management, transportation and logistics, and worldwide trade management. It also entails utilizing execution-oriented applications and systems, such as real-time decision support, supply chain visibility, and order management systems. This phase guarantees the efficient operation of the supply chain and ensures that it is in line with the strategic objectives established during the design and planning phases [1].
Key Words: Quantum computing, Generative Adversarial Networks (GANs), Supply chain, Operations management, Transportation efficiency, Warehouse management, Distribution processes, Inbound logistics, Retail, Channel logistics, Optimization, Quantum-enhanced, Complexity, Training efficiency, Cost savings, Productivity, Delays.
B. Introduction to Quantum Computing and
Generative Adversarial Networks (GANs)
This subsection offers a fundamental introduction to quantum computing and Generative Adversarial Networks (GANs), explaining their importance in transforming supply chain optimization. This text delves into the core principles of quantum computing, emphasizing its ability to effectively manage intricate computations and efficiently solve optimization problems. Furthermore, it explores the notion of Generative Adversarial Networks (GANs), explaining its ability to produce artificial data and enhance models through adversarial learning. The purpose of this subsection is to create a theoretical structure for comprehending the following conversation on the application of quantum-enhanced GANs for optimizing supply chains. The search results indicate the following important information about the utilization of QuantumEnhanced Generative Adversarial Networks (Quantum
I. INTRODUCTION A. Supply Chain Optimization Efficiency Supply chain optimization can be categorized into three essential stages, each of which has a vital function in the overall effectiveness of the process. The design phase is centered around developing an efficient supply chain network that takes into account several elements, including the placement of facilities (such as manufacturing plants, warehouses, and distribution centers), the movement of products between these
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 446