Ant Colony Optimization with Simulated Annealing Algorithm for Google Maps

Abstract

In the article that is being suggested, a brandnew, sophisticated route optimization is created using cuttingedge software that makes use of Google APIs and unsupervised machine learning. Since Google Maps and its API have improved recently, outmoded solutions have been decommissioned. Therefore, route optimization is carried out in this study using a heuristic method by merging three approaches, including ant colony optimization (ACO), simulated annealing algorithm (SA), and updated Google APIs. Along with executing route optimization, these three techniques-based ACO-SA-Google Maps (ASG) API will be contrasted with other approaches including genetic algorithms, K-means clustering, particle swarm optimization (PSO), etc. to assess performance, cost, and carbon emissions. The demand for home delivery, travel, and other necessities is increasing as a result of population increase and a developing technology lifestyle, necessitating the use of contemporary equipment by the average person. To increase performance, the ASG technique will develop route optimization using a modernized methodology. Route optimization eventually aims to be used in a variety of contexts, from uber applications to Amazon deliveries. Variation coefficient and relative percentage difference are two types of statistical indicators that are employed in the process of studying and verifying this model. To display and contrast the findings, the execution times in seconds are also considered.