Reducing Delivery Time in E-Commerce Orders With Advanced Ant Colony Hybridization by GRU Algorithm

The efficiency of the supply chain is highly corelated with the acceleration of preparing orders from the warehouse to meet customer requests on time. A unified framework optimising the movement of item pickers throughout the warehouse aisles and shelves via reducing their motion route length during orders collected. The framework consists of three stages. The preamble stage aims to sort the items according to XYZ/ABC pattern ‘‘assignment policy’’. The 2nd stage classifies the customers’ orders according to route similarity via hybridising the (Extreme Gradient Boosting) XGboost and (gate recurrent unit) GRU algorithms that generate all possible orders’ lists/route in 1.2586 sec with RMSE 0.01395 and called ‘‘initial layout structure’’, which is filtered in the 3rd stage via creating their shortest route via hybridising (Ant Colony Optimisation) ACO and GRU algorithms with innovative tuning parameters to give workers to pick up more items in minimum time to accelerate preparing orders ‘‘priority pace motion’’. The 3rd creates the minimum route via two steps, the 1st the original route sketched in Map(A), which is tracked until out of the determined zone of orders picked, then updates the remaining route via a nine-step approach hybridised to get the shortest route served more customers as sketched in Map (B_i) to accelerate the total order collection in the 2nd step. The proposed model called ‘‘Acceleration Customer Orders’ Preparation’’ (ACOP). The challenge lies in assigning a new order to Map (A) lists and creating Map (B_i). The paper presents innovative tuning parameters for ACO that help in accelerating orders preparation by 152.49%/worker/day. According to OEE, the proposed strategy is approximately 88% effective. The ACO_GRU superior to Regular Ant Colony (RgACO), Elitist Ant Colony (EACO), Ranked Ant Colony (RnACO), Best-Worst Ant Colony (BWACO), Min-Max Ant Colony (MMACO), Mat-ACO, A∗ algorithm, Dijkstra’s algorithm, and MRL-SA with 19%, 16%, 9%, 12%, 6%, 6%, 5%, 5%, 3%, respectively. Choosing a suitable hybridization model according to order contents increased the customer serviced mainly by 52.5% daily.