基于深度信念网络资源需求预测的虚拟网络功能动态迁移算法

Virtual Network Function Migration Algorithm Based on Deep Belief Network Prediction of Resource Requirements

针对5G网络场景下缺乏对资源需求的有效预测而导致的虚拟网络功能(VNF)实时性迁移问题,该文提出一种基于深度信念网络资源需求预测的VNF动态迁移算法。该算法首先建立综合带宽开销和迁移代价的系统总开销模型,然后设计基于在线学习的深度信念网络预测算法预测未来时刻的资源需求情况,在此基础上采用自适应学习率并引入多任务学习模式优化预测模型,最后根据预测结果以及对网络拓扑和资源的感知,以尽可能地减少系统开销为目标,通过基于择优选择的贪婪算法将VNF迁移到满足资源阈值约束的底层节点上,并提出基于禁忌搜索的迁移机制进一步优化迁移策略。仿真表明,该预测模型能够获得很好的预测效果,自适应学习率加快了训练网络的收敛速度,与迁移算法结合在一起的方式有效地降低了迁移过程中的系统开销和服务级别协议(SLA)违例次数,提高了网络服务的性能。

To solve the problem of real-time migration of Virtual Network Function (VNF) caused by lacking effective prediction in 5G network, a VNF migration algorithm based on deep belief network prediction of resource requirements is proposed. The algorithm builds firstly a system cost evaluation model integrating bandwidth cost and migration cost,and then designs a deep belief network prediction algorithm based on online learning which adopts adaptive learning rate and introduces multi-task learning mode to predict future resource requirements. Finally, based on the prediction result as well as the perception of network topology and resources, the VNFs are migrated to the physical nodes that meet the resource threshold constraints through greedy selection algorithm with the goal to optimize system cost,and then a migration mechanism based on tabu search is proposed to further optimize the migration strategy.The simulation results show that the prediction model can obtain good prediction results and adaptive learning rate accelerates the convergence speed of the training network.Moreover, the combination with the migration algorithm reduces effectively system cost and the number of Service Level Agreements (SLA) violations during the migration process, and improves the performance of network services.