基于5G技术的化工智能园区虚拟网络功能仿真实验研究  

Research on virtual network function simulation in intelligentchemical industrial parks based on 5G technology

作　　者：王颖 张龙龙 WANG Ying;ZHANG Longlong(CNOOC Energy Logistics Co.,Ltd.,Tianjin 300452,China;CNOOC(Huizhou)Logistics Co.,Ltd.,Huizhou 516000,Guangdong China)

机构地区：[1]中海油能源物流有限公司物流研究所,天津300452 [2]中海石油(惠州)物流有限公司,广东惠州516000

出　　处：《粘接》2023年第7期132-136,共5页Adhesion

摘　　要：为降低化工智能园区虚拟网络功能部署成本问题,以最小化虚拟网络功能部署代价为目标函数,考虑容量、延迟等约束条件,提出化工智能园区虚拟网络功能部署方案。采用长短期记忆神经网络(LSTM)预测化工园中网络用户未来可能的位置,并利用基于模型预测控制(MPC)的算法求解最小部署总代价,以使得虚拟网络功能部署成本最小。仿真结果表明:相对于Heuristic和Heuristic With Predict的求解方法,迁移部署虚拟网络功能的总代价最小,为13628。所提方案具有一定的有效性,可节约化工智能工业园区的虚拟网络功能部署成本。To reduce the high cost of virtual network function deployment caused by the dynamic change of user location in the chemical logistics park,a virtual network function deployment scheme for the chemical logistics park was designed with the objective function of minimizing the cost of virtual network function deployment,considering the constraints such as capacity and delay.Long Short Term Memory(LSTM)neural network was used to predict the future location of users,and the algorithm based on Model Predictive Control(MPC)was used to solve the minimum total deployment cost,saving the cost of virtual network function deployment.The simulation results showed that.Compared with the Heuristic algorithm and Heuristic With Predict algorithm,the migration-based deployment of virtual network functions had the lowest total cost,which was 13628.This proposed approach proves to be effective in reducing the virtual network function deployment costs in intelligent chemical industrial parks..

关 键 词：虚拟网络功能部署 5G网络切片 LSTM网络 MPC算法 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]