An adaptive genetic algorithm with neighborhood search for integrated O2O takeaway order assignment and delivery optimization by e-bikes with varied compartments

Abstract

To improve the dining experiences, online-to-offline (O2O) takeaway services with warm-keeping or refrigerated requirements are quickly expanding and becoming popular. However, single-compartment e-bikes are commonly used in takeaway platforms, which can only meet one kind of requirements and may result in an inflexible delivery. Within this context, a new type of e-bikes, namely e-bikes with mixed compartments, is introduced. Thus, warm-keeping and refrigerated orders can be delivered by one bike, namely on one route. This paper considers an integrated order assignment and delivery problem by e-bikes with warm, refrigerated, and mixed compartments (AD-EBM). To solve the problem, we develop a novel integer programming formulation to minimize the total cost by determining order assignments and finding optimal routes, and then some properties of the solutions are provided from the view of mathematics. An algorithm is designed by combining the self-adaptive genetic algorithm with the neighborhood search method (SGA-NS). Numerical experiments are conducted based on simulated different-scale takeaway instances. The experimental results highlight the excellent performance of the SGA-NS and the results are quite encouraging compared with Gurobi solver, SGA, and NS. The results of the model comparison demonstrate that the AD-EBM offers 12.38% total cost savings on average, compared to using only single-compartment e-bikes. A sensitivity analysis is performed to explore the effects of the mixed compartment costs, the customer acceptable delay time, the penalty costs for delays, and the e-bike capacity for the platform’s daily operations. Some management insights are provided to facilitate the O2O takeaway delivery.