Research On Optimization Of Temporal Data Distribution Strategy In Vehicle Network

In recent years,with the improvement of living standards,the number of vehicles is increasing,causing great pressure on road traffic systems.And the emerging intelligent traffic systems can effectively improve these problems.As the basis and core of the emerging intelligent transportation system,the information service technology of Internet of Vehicles(Io V)has attracted great attention in recent years.Especially the research on temporal data scheduling in the Internet of Vehicles.Many temporal data scheduling strategies of Internet of Vehicles have been proposed.However,due to the network instability of Internet of Vehicles,high mobility of vehicles and unpredictability of traffic conditions,the scheduling of temporal data often suffered from the decrease of temporal data quality and the timeout data scheduling.In addition,under uncertainty,how to ensure the data service request within the required time and not disturbed by external factors,is also a problem to be solved.According to the above problem,this paper presents the corresponding solutions,which are mainly as follows:For the problem that how to simultaneously guarantee high data quality and high service ratio during data scheduling under uncertainty factors,this paper proposed an improved decomposition-based multi-objective evolutionary algorithm for temporal data scheduling problem.By integrating an adaptive weight vector adjustment method on the traditional MOEA/D algorithm framework improves the performance of temporal data scheduling,ensuring high quality and high service ratio simultaneously.For the problem that how to control the inevitable uncertainty to improve the robustness,this paper proposed a robust MOEA/D-based optimization algorithm while optimizing two conflicting goals.First,specific coding and the defined transformation approach are used to form the feasible routes.Then Order Crossover and Exchange mutation operators are utilized to increase population diversity.The Monte-Carlo tests and the defined robust method are utilized to check the feasibility and calculate the solution robustness values.Finally,optimality and robustness are considered to form a set of highly robust and relatively optimal solutions.