Tensor Flow Model with Hybrid Optimization Algorithm for Solving Vehicle Routing Problem
Document Type
Conference Proceeding
Publication Date
Summer 6-15-2023
Abstract
Vehicle routing and path management system improves the best key point of selecting the path of the vehicle to move. The applications that are used for delivering the products utilize Google data to organize the vehicle movement and its coordinate positions. The traffic level indicator and the speed of vehicle movement validate the Vehicle Routing Problem (VRP)- route. Since there is another important parameter that needs to consider for the delivery process. In that, the application needs to validate the amount of traveling time and the length through which the vehicle can travel to deliver the products. This requires a better prediction model to estimate the multiple parameters of vehicle routing problems. In the proposed study, a Tensor Flow-based routing path prediction approach was chosen to train and predict the best route using the attribute weight matrix. From the parameters of the distance between the coordinates with the amount of traffic range and other related attributes, the Tensor Flow model forms the rule to train the machine for predicting the route for vehicle movement. This model updates the learning model based on the change in parameter value and its range. The experimental result compares the suggested work to the current model of optimum VRP prediction approaches.
Program or Discipline Name
Information Systems Engineering and Management
Recommended Citation
Chowlur Revanna, J.K. and Al-Nakash, N.Y.B., 2023. Tensor Flow Model with Hybrid Optimization Algorithm for Solving Vehicle Routing Problem. In Inventive Systems and Control: Proceedings of ICISC 2023 (pp. 113-127). Singapore: Springer Nature Singapore.
Publication Title
Springer Conference 2023: Inventive systems and control
ISSN
978-981-99-1624-5
DOI
https://doi.org/10.1007/978-981-99-1624-5_8