基于机器学习的SPN网络流量预测与资源分配策略  

Machine Learning Based Traffic Prediction and Resource Allocation Strategies for SPN Network

作　　者：鲍雨 肖明坤 王兰兰 BAO Yu;XIAO Mingkun;WANG Lanlan(China Information Consulting&Design Institute Co.,Ltd.,Nanjing 210019,China)

机构地区：[1]中通服咨询设计研究院有限公司,江苏南京210019

出　　处：《通信电源技术》2025年第3期1-3,共3页Telecom Power Technology

摘　　要：基于机器学习的切片分组网(Slicing Packet Network,SPN)流量预测与资源分配策略旨在提升服务提供网络的性能和资源利用效率。通过对网络流量数据进行清洗、归一化和特征提取,构建深度信念网络模型,并利用粒子群优化算法进行训练和优化。实验结果表明,该方法在处理非线性和高噪声数据时具有较高的预测精度。基于预测结果,提出一种动态资源分配算法,通过实时调整资源配置,优化网络性能,降低运营成本。该策略为网络管理者提供了有效的决策支持,具有较高的实用价值。The Slicing Packet Network(SPN)traffic prediction and resource allocation strategy based on machine learning aims to improve the performance and resource utilization efficiency of service delivery networks.A deep belief network model was constructed by cleaning,normalizing,and extracting features from network traffic data,and trained and optimized using particle swarm optimization algorithm.The experimental results show that this method has high prediction accuracy when dealing with nonlinear and high noise data.Based on the predicted results,a dynamic resource allocation algorithm is proposed to optimize network performance and reduce operating costs by adjusting resource allocation in real-time.This strategy provides effective decision support for network managers and has high practical value.

关 键 词：机器学习 切片分组网(SPN) 网络流量预测 资源分配 优化策略 

分 类 号：TN929.5[电子电信—通信与信息系统] TP181[电子电信—信息与通信工程]