Ordering food through mobile apps and crowdsourcing resources has become increasingly popular in the digital age. Restaurants can improve customer satisfaction to satisfy on-demand food orders by shortening waiting time and achieving sustainability through fuel reduction. In the present study, we construct a double-layer scheduling model, which is developed using the characteristics of on-demand food preparation, including the use of multiple stoves, a variety of dishes in one order, and the integration of the same dishes from different customers. The bottom layer is a multi-stove dish package scheduling model based on parallel machine scheduling. The upper layer is an order selection model based on the knapsack problem. To identify the optimal solution, four strategies for calculating the weight coefficient of the dish package are proposed to shorten the waiting time and realize sustainability. Numerical experiments are designed to analyze the differences of the final scheduling results under the four strategies. The bottom layer is extended to another model based on the vehicle routing optimization model, given the switch time between different dishes. The extension of the model is also compared in the numerical experiments. Our paper confirms the necessity of using a double-layer model for multi-strategy comparison in order to achieve sustainable on-demand scheduling.
Model-Based Advisory Systems for Treatment of Type 1 Diabetes: On-Demand Treatment Recommendations as a Precursor to Fully Closed-Loop Drug Delivery
