Quantum Computing for Warehouse Inventory Optimization

In collaboration with a major warehouse management firm and CQTech, this project explored the application of quantum computing techniques to large-scale logistics optimization problems. Modern warehouse operations involve complex allocation and routing decisions that are often formulated as combinatorial optimization problems with significant computational overhead. The warehouse inventory allocation model formulates as an integer-binary optimization problem, a class of problems that is typically NP-hard problem and difficult to solve efficiently as system size grows. To address this challenge, the WISER team developed Five custom quantum optimization solvers to tackle large-scale warehouse configurations. These solvers were evaluated against state-of-the-art classical high-performance computing approaches as well as pure quantum annealing implementations, using comprehensive industry-scale benchmark scenarios.

Experimental evaluations demonstrated up to 66% faster order fulfillment performance compared with baseline classical optimization methods. The framework was tested on warehouse configurations with up to 528 shelving units, with results indicating favorable scaling behavior as warehouse size increases.

The project provides an important demonstration of how quantum optimization techniques can be applied to real-world logistics and supply chain challenges, highlighting the potential of quantum annealing based approaches for improving operational efficiency in large-scale warehouse environments.

WISER Research Fellows: Abdellah Tounsi, Mohamed M. Louamri, Nacer Belaloui, Taha Rouabah