Improving Warehouse Efficiency with Dynamic Slotting Optimization Using Genetic Algorithm

Traditional methods of slotting within a warehouse can't support patterns of demand fluctuation, which are associated with space constraints, poor utilization of storage, and increased times of retrieval. The approach this paper focuses on is Dynamic Slotting Optimization, where in the placements of Stock Keeping Units (SKUs) keep changing continuously via real-time changes in demand variation and SKU correlations. Unlike static slotting methods, our model dynamically reassigns storage locations to minimize picking distance, enhance accessibility, and optimize warehouse efficiency. This paper proposes the Genetic algorithm (GA) as an enhanced method to improve space utilization of order fulfillment with integrated heuristic-based slot selection and frequent itemset grouping. The performance of the proposed GA was determined by comparing its results to four other metaheuristic algorithms. The results demonstrate that the GA outperforms the other four metaheuristic algorithms.