Abstract: Planning the order picking lists for warehouses to achieve some operational performances is a significant challenge when the costs associated with logistics are relatively high, and it is especially important in e-commerce era. Nowadays, many order planning techniques employ supervised machine learning algorithms. However, to define features for supervised machine learning algorithms is not a simple task. Against this background, we consider whether unsupervised algorithms can enhance the planning of order-picking lists. A double zone picking approach, which is based on using clustering algorithms twice, is developed. A simplified example is given to demonstrate the merit of our approach.
Abstract: This research tested the performance of alternative
warehouse designs concerning the picking process. The chosen
performance measures were Travel Distance and Total Fulfilment
Time. An explanatory case study was built up around a model
implemented with SIMUL8. Hypotheses were set by selecting
outcomes from the literature survey matching popular empirical
findings. 17.4% reductions were found for Total Fulfilment Time and
Resource Utilisation. The latter was then used as a proxy for
operational efficiency. Literal replication of theoretical data-patterns
was considered as an internal validity sign. Assessing the estimated
changes benefits ahead of implementation was found to be a
contribution to practice.