Intelligent Algorithms for Warehouse Management

Warehouses are important links in the supply chain; here, products are temporarily stored and retrieved subsequently from storage locations to fulfill customer’ orders. The order picking activity is one of the most time-consuming processes of a warehouse and is estimated to contribute for more than 55 % of the total cost of warehouse operations. Accordingly, scientists, as well as logistics managers, consider order picking as one of the most promising area for productivity improvements. This chapter is intended to provide the reader with an overview of different intelligent tools applicable to the issue of picking optimization. Specifically, by this chapter, we show how different types of intelligent algorithms can be used to optimize order picking operations in a warehouse, by decreasing the travel distance (and thus time) of pickers. The set of intelligent algorithms analyzed include: genetic algorithms, artificial neural networks, simulated annealing, ant colony optimization and particles swarm optimization models. For each intelligent algorithm, we start with a brief theoretical overview. Then, based on the available literature, we show how the algorithm can be implemented for the optimization of order picking operations. The expected pros and cons of each algorithm are also discussed.