Font Size: a A A

Research On Edge Computing Task Scheduling Based On Internet Of Vehicles

Posted on:2022-08-28Degree:MasterType:Thesis
Country:ChinaCandidate:R D WuFull Text:PDF
GTID:2518306569451934Subject:Traffic and Transportation Engineering
Abstract/Summary:PDF Full Text Request
At present,the domestic car ownership is increasing,with the continuous improvement of living standards,people pay more and more attention to the driving experience and vehicle intelligent service level,resulting in the rapid increase of all kinds of mobile devices and sensing devices,thus putting forward higher requirements for the Internet of vehicles application computing task scheduling and cost reduction.However,the existing task allocation model and strategy are relatively simple,the strategy does not consider the reasonable task allocation,the model is limited to a single optimization of time delay or energy consumption.Therefore,it is very important to study the reasonable allocation of vehicle computing tasks to optimize the scheduling strategy and cost of computing tasks,and to enhance the level of traffic service and user driving experience.Firstly,this paper introduces the current situation and future development direction of edge computing at home and abroad,analyzes the classification and characteristics of computing tasks generated by Internet of Vehicles(Io V)applications,and summarizes the optimization objectives and distribution principles of edge computing control.Secondly,the AHP model was used to sort the task cases by taking the deadline time,the amount of task data and the CPU required for the task as the evaluation indexes.Based on the task decision variables,the optimization models of time and energy consumption were built,and the cost was taken as the final optimization objective.The task scheduling optimization model based on the edge computing of the Internet of Vehicles was established,and the model was decomposed into two sub-problems: computing resources and uplink allocation.Thirdly,in order to solve the problem that genetic algorithm is easy to fall into local optimum,Halton sequence is introduced to generate the initial population with small difference,and genetic operator adaptive improved genetic algorithm is designed to solve the model.Finally,taking the randomly generated small-scale computing tasks as an example,the task assignment model established in this paper and the improved algorithm designed in this paper are used for simulation analysis with the help of MATLAB tools.The simulation results show that the improved algorithm designed in this paper has more advantages in computational cost.According to the setting of task allocation decision variables and considering the adjustment of weight coefficient,different optimization strategies can be obtained,that is,reasonable task energy consumption and task delay,so as to optimize the overall cost of calculating the task.In this paper,the task scheduling optimization model based on edge computing of Internet of Vehicles(Io V)is established by using AHP to sort the task cases and considering factors such as time and energy consumption.This model has a certain theoretical value for the assignment and unloading of edge computing task scheduling of Io V,and has a supplementary effect on the theoretical system of scheduling of vehicle computing task.In practical life,it has certain reference significance for guiding enterprises to formulate reasonable calculation task allocation,task model optimization strategy and reasonable resource allocation.
Keywords/Search Tags:Internet of Vehicles, Edge Computing, Task Scheduling, Analytic hierarchy process, Adaptive Genetic Algorithm
PDF Full Text Request
Related items