Fujitsu and Toyota Systems Optimize Large-Scale Supply Chain Logistics Using Quantum-Inspired Technology
– Fujitsu and Toyota Systems Conducted a Joint Trial to Optimize Complex Distribution and Supply Chains for Automotive Parts in Japan
– Fujitsu’s Quantum-Inspired Digital Annealer Computing Technology Was Applied to a Problem With 3 Million Potential Routes for Parts Delivery From Hundreds of Suppliers
– Leveraging Fujitsu’s Digital Annealer, Toyota Systems Identified an Approach That Takes Just 30 Minutes and Can Reduce Logistics Costs by 2-5 Percent
Fujitsu Limited and Toyota Systems Corporation successfully demonstrated optimization of supply chain and logistics network operations essential to support automobile production in a joint trial leveraging Fujitsu’s Quantum-Inspired Digital Annealer computing solution.
The Digital Annealer solves complex combinatorial optimization problems at speeds not possible with current conventional computing technologies, and was used to rapidly calculate variables including the number of transport trucks, total mileage, and package sorting tasks, determining the most cost-effective approach for an automotive parts supply chain optimization problem with more than 3 million possible delivery routes to dozens of factories.
Ultimately, the trial revealed it was possible that within 30 minutes an optimal route was calculated that can potentially reduce logistics costs by approximately 2 to 5% by discovering effective, previously unidentified distribution routes, thereby improving loading efficiency and streamlining transportation-related expenses.
Recommended AI News: IBM Announces Red Hat Marketplace to Accelerate Open Hybrid Cloud Innovation
In the future, Fujitsu and Toyota Systems will further verify and refine the solution with the aim of commercializing it for real-world supply chain and logistics operations.
While logistics has become an increasingly vital part of the infrastructure supporting society, factors including driver shortages, traffic congestion, and increased CO2 emissions present an urgent and persistent challenge to businesses in the logistics and supply chain industry. The management of manufacturing supply chains represents one area for possible improvements in efficiency and cost reductions, which may also contribute to solving more fundamental logistics and environmental issues. Nevertheless, conventional technologies remain ill-suited to solving these problems due to their scale and complexity, requiring enormous amounts of time for parameter-adjustments and calculations.
Outline of the Field Trial
With these challenges in mind, Fujitsu and Toyota Systems endeavoured to find a solution through joint trials and the development of innovative technologies.
Toyota Systems was first established in January 2019 as an IT solutions company to support Toyota Motor Corporation and its group companies in the development of technology offerings. Since prior to the establishment of the company, Toyota Systems has been conducting research with Fujitsu on the use of quantum computing.
During the trial Toyota Systems and Fujitsu applied Fujitsu’s Digital Annealer quantum-inspired technology to formulate and solve an optimization problem involving a large-scale logistics network with more than 3 million route candidates. The objective of the trial was to quickly determine the route with the lowest distribution cost from millions of potential candidates for procuring parts from hundreds of suppliers and delivering them through several transit warehouses to dozens of factories. Distribution costs were calculated based on variables including the number of trucks, total travel distance, and the amount of work done in sorting packaged parts.
In order to apply this technology to real-world operations, a new system was developed that incorporates a large-scale problem-solving technology (Figure 2, Left)(1) previously developed by Fujitsu Limited and Fujitsu Laboratories, Ltd., and the following two technologies:
– Global Search Technology: searches a wide range of possible solutions while efficiently escaping from a local solution groups (Figure 2, Center)
– Dynamic Multipoint Search Technology: dynamically determines search starting points based on the current search status and interim results (Figure 2 Right)
Recommended AI News: Kubernetes-driven PlanetScale DBaaS Enters Red Hat Marketplace
The application of the Digital Annealer and new solving techniques made it possible to calculate a new route within 30 minutes, leading to the potential for significant overall cost reduction.
During the trials, simulations using the newly discovered routes proved that this method can reduce costs by approximately 2-5% compared to conventional methods.
Based on these results, the two companies aim to use the Digital Annealer to calculate logistics routes related to automobile manufacturing distribution chains, and they are working to further verify and identify opportunities for additional practical applications.
As the automotive industry progresses toward a new paradigm, CASE (Connectivity, Autonomous, Sharing, Electrification) promises to redefine the concept of mobility itself, and a demand for unprecedented technological innovation and the creation of new mobility services has emerged. Based on the technology accumulated during this trial, Toyota Systems will promote the use of quantum inspired computing capabilities in the automobile industry, with the aim of creating new mobility services and contributing to the resolution of societal problems.
Fujitsu will support Toyota Systems in this domain with new solutions based on its Digital Annealer technology and contribute further to digital innovation in the automotive industry.
Fujitsu additionally plans in 2020 to offer the developed solutions from this trial as part of the existing Fujitsu Digital Annealer Cloud Service, with the aim of expanding application of the solutions to a variety of other industries and business domains.