Design And Implementation Of Migration Decision Subsystem For Internet Of Vehicles Container Applications

The Internet of Vehicles(IoV)application services integrating with edge computing will significantly drive the growth of IoV.However,the contradiction between the high-speed mobility of vehicles,the delay sensitivity of corresponding IoV applications and the limited coverage and resource capacity of distributed edge computing nodes will pose challenges to the service continuity and stability of IoV application services.IoV application service migration is a promising solution that can be supported by application containerization,a technology for seamless cross-edgecomputing-nodes application migration without user perception.The existing IoV container application migration strategies are deficient in designing migration trigger determination conditions and quantifying migration target evaluation criteria,which reduces the accuracy and efficiency of the migration strategy.To address the above problems,this paper proposes a migration mechanism for IoV container applications.First,a migration trigger determination algorithm is designed,including the active-initiated migration trigger determination algorithm caused by vehicle movement and the passive-competitive migration trigger determination algorithm caused by the carrying capacity degradation of the edge computing node,to determine the set of services to be migrated.Then,a migration target evaluation model is established,which comprehensively considers the target edge computing node availability,current average migration cost and future average service sustainability to evaluate the superiority of candidate migration targets.Finally,a migration decision algorithm based on the improved artificial bee colony algorithm is designed to obtain the optimal migration decision.Simulation results show that the migration mechanism proposed in this paper can reduce the average migration cost and increase the average service reward,improve the overall migration efficiency,and enhance the stability and adaptability of IoV application services.In addition,to meet the user’s visual operation demand for functions such as edge computing node resource monitoring,IoV application service migration decision execution,and IoV application service migration evaluation metrics comparison,this paper designs and implements a migration decision simulation subsystem for IoV container application,including functional modules such as object data collection,object monitoring,migration decision and object management.This paper carries out functional tests on each module.The test results show that the migration decision simulation subsystem of IoV container application designed in this paper can meet the functional and performance requirements of each module.