Improvement of Genetic Algorithm and the Application in Computer Simulation Model of O2O Delivery Strategies

2020 13th International Symposium on Computational Intelligence and Design (ISCID) Pub Date : 2020-12-01 DOI:10.1109/ISCID51228.2020.00072

Guangyu Zou, Yonglin Li

{"title":"Improvement of Genetic Algorithm and the Application in Computer Simulation Model of O2O Delivery Strategies","authors":"Guangyu Zou, Yonglin Li","doi":"10.1109/ISCID51228.2020.00072","DOIUrl":null,"url":null,"abstract":"The popularity of the Internet has provided the foundation for the rapid development of Online to Offline (O2O) business. With the increase of the number of users, online food ordering platforms are facing more and more challenges and pressures. The efficiency of order processing directly determines the customer satisfaction with the platform and the comprehensive competitiveness of the platform. In this paper, The Genetic Algorithm (GA) is applied to solve the TSP problem to optimize the delivery path of riders, so as to improve the delivery speed of orders. By comparing the efficiency of GA and Dynamic Programming (DP) algorithm in a simulation model of O2O system developed by SUMO, we found that the dynamic programming will not be applicable when the number of TSP nodes is beyond a threshold, i.e., 10 in this case. To improve the efficiency further, multiple genetic algorithms were run in a manner of parallel computing for the distribution strategy of takeout orders, which means that an independent genetic algorithm serves for processing the TSP route of an individual rider.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCID51228.2020.00072","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

Abstract

The popularity of the Internet has provided the foundation for the rapid development of Online to Offline (O2O) business. With the increase of the number of users, online food ordering platforms are facing more and more challenges and pressures. The efficiency of order processing directly determines the customer satisfaction with the platform and the comprehensive competitiveness of the platform. In this paper, The Genetic Algorithm (GA) is applied to solve the TSP problem to optimize the delivery path of riders, so as to improve the delivery speed of orders. By comparing the efficiency of GA and Dynamic Programming (DP) algorithm in a simulation model of O2O system developed by SUMO, we found that the dynamic programming will not be applicable when the number of TSP nodes is beyond a threshold, i.e., 10 in this case. To improve the efficiency further, multiple genetic algorithms were run in a manner of parallel computing for the distribution strategy of takeout orders, which means that an independent genetic algorithm serves for processing the TSP route of an individual rider.

查看原文本刊更多论文

遗传算法的改进及其在O2O配送策略计算机仿真模型中的应用

互联网的普及为O2O (Online to Offline)业务的快速发展提供了基础。随着用户数量的增加，在线订餐平台面临越来越多的挑战和压力。订单处理的效率直接决定了客户对平台的满意度和平台的综合竞争力。本文采用遗传算法求解TSP问题，优化骑手的配送路径，从而提高订单的配送速度。通过对SUMO开发的O2O系统仿真模型中遗传算法和动态规划(DP)算法的效率进行比较，我们发现当TSP节点数量超过某个阈值(即10个)时，动态规划算法将不再适用。为了进一步提高效率，以并行计算的方式运行多个遗传算法来求解外卖订单分配策略，即使用独立的遗传算法来处理单个骑手的TSP路线。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2020 13th International Symposium on Computational Intelligence and Design (ISCID)

自引率

0.00%

发文量