基于自适应动态预测的网络切片资源冲突优化

doi:10.19678/j.issn.1000-3428.0067985

摘要/Abstract

摘要：

网络切片(NS)是5G网络中的一种关键性技术，在多业务动态场景下发挥着重要作用。针对5G网络切片中由切片需求动态变化引起的资源冲突问题，采用一种基于自适应动态预测(ADP)的优化方法，提出“自适应动态预测-模型优化”的优化方案。在自适应动态预测模块，对动态的切片流量进行波动等级划分，以确保切片流量预测的准确性以及自适应性。根据划分结果，分别采用2种不同的循环神经网络算法来预测切片未来时间的流量需求，包括基于注意力机制-双向门控循环单元(Att-BiGRU)的点预测以及基于自举法-BiGRU的区间预测。在模型优化模块，根据预测结果定义用户满意度函数和切片优化配置的开销，将资源冲突优化问题表示为最大化网络收益。由于预测模块的输出可能含有不确定参数，根据鲁棒优化和基于可变粒子数量的粒子群优化算法求解出切片优化配置方案。在仿真部分对所提优化方案进行验证，结果表明，该方法在满足切片动态需求的同时，降低了资源冲突带来的负面影响，其在网络收益以及请求接受率等方面优于对比算法，链路资源利用率达到90%以上。

关键词: 网络切片, 资源冲突, 动态预测, 模型优化, 循环神经网络

Abstract:

Network Slicing(NS) is a key technology in 5G networks, playing an important role in multi service dynamic scenarios. To address the resource conflict problem caused by dynamic changes in slicing requirements in 5G network slicing, an optimization method based on Adaptive Dynamic Prediction(ADP) is adopted, and an optimization scheme called "adaptive dynamic prediction-model optimization" is proposed. In the adaptive dynamic prediction module, the fluctuation level of dynamic slice traffic is divided to ensure the accuracy and adaptability of slice traffic prediction. Based on the partitioning results, two different Recurrent Neural Network(RNN) algorithms are used to predict the future traffic demand of slices, including point prediction based on Attention mechanism-Bidirectional Gated Recurrent Unit(Att-BiGRU) and interval prediction based on bootstrap method BiGRU. In the model optimization module, the user satisfaction function and the cost of slicing optimization configuration are defined based on the predicted results, and the resource conflict optimization problem is represented as maximizing network benefits. Due to the possibility of uncertain parameters in the output of the prediction module, a slice optimization configuration scheme is solved based on robust optimization and particle swarm optimization algorithms with variable particle numbers. In the simulation section, the proposed optimization scheme is validated. This method not only meets the dynamic requirements of slicing, but also reduces the negative impact of resource conflicts. It outperforms the comparison algorithm in terms of network revenue and request acceptance rate, with a link resource utilization rate of over 90%.

Key words: Network Slicing(NS), resource conflict, dynamic prediction, model optimization, Recurrent Neural Network(RNN)

赵季红, 张富, 崔曌铭. 基于自适应动态预测的网络切片资源冲突优化[J]. 计算机工程, 2024, 50(1): 183-190.

Jihong ZHAO, Fu ZHANG, Zhaoming CUI. Optimization of Resource Conflicts in Network Slicing Based on Adaptive Dynamic Prediction[J]. Computer Engineering, 2024, 50(1): 183-190.

https://www.ecice06.com/CN/Y2024/V50/I1/183

图/表 11

图1 底层物理网络及网络切片

Fig.1 Underlying physical network and network slicing

图2 “自适应动态预测-模型优化”方案框架

Fig.2 Framework of "adaptive dynamic prediction-model optimization" scheme

图3 Att-BiGRU结构

Fig.3 Strucute of Att-BiGRU

图4 自举法-BiGRU示意图

Fig.4 Schematic diagram of bootstrap-BiGRU

图5 点预测算法对比

Fig.5 Comparison of point prediction algorithms

图6 区间预测算法对比

Fig.6 Comparison of interval prediction algorithms

图7 不同算法下链路资源利用率

Fig.7 Link resource usage under different algorithms

图8 不同算法下网络收益

Fig.8 Network income under different algorithms

图9 不同算法下切片请求接受率

Fig.9 Request acceptance rate under different algorithms

参考文献 29

1	ABBAS K, KHAN T A, AFAQ M, et al. Network slice lifecycle management for 5G mobile networks: an intent-based networking approach. IEEE Access, 2021, 9, 80128- 80146. doi: 10.1109/ACCESS.2021.3084834
2	CHAHBAR M, DIAZ G, DANDOUSH A, et al. A comprehensive survey on the E2E 5G network slicing model. IEEE Transactions on Network and Service Management, 2021, 18(1): 49- 62. doi: 10.1109/TNSM.2020.3044626
3	WEN R H, FENG G, TANG J H, et al. On robustness of network slicing for next-generation mobile networks. IEEE Transactions on Communications, 2019, 67(1): 430- 444. doi: 10.1109/TCOMM.2018.2868652
4	YU H, TALEB T, ZHANG J W, et al. Deterministic latency bounded network slice deployment in IP-over-WDM based metro-aggregation networks. IEEE Transactions on Network Science and Engineering, 2022, 9(2): 596- 607. doi: 10.1109/TNSE.2021.3127718
5	TRAN T D, LE L B. Resource allocation for multi-tenant network slicing: a multi-leader multi-follower stackelberg game approach. IEEE Transactions on Vehicular Technology, 2020, 69(8): 8886- 8899. doi: 10.1109/TVT.2020.2996966
6	ZHOU J H, ZHAO W J, CHEN S. Dynamic network slice scaling assisted by prediction in 5G network. IEEE Access, 2020, 8, 133700- 133712. doi: 10.1109/ACCESS.2020.3010623
7	SCIANCALEPORE V, COSTA-PÉREZ X, BANCHS A. RL-NSB: reinforcement learning-based 5G network slice broker. IEEE/ACM Transactions on Networking, 2019, 27(4): 1543- 1557. doi: 10.1109/TNET.2019.2924471
8	SUBRAMANYA T, RIGGIO R. Machine learning-driven scaling and placement of virtual network functions at the network edges[C]//Proceedings of 2019 IEEE Conference on Network Softwarization. Washington D. C., USA: IEEE Press, 2019: 414-422.
9	WEI F S, QIN S, FENG G, et al. Hybrid model-data driven network slice reconfiguration by exploiting prediction interval and robust optimization. IEEE Transactions on Network and Service Management, 2022, 19(2): 1426- 1441. doi: 10.1109/TNSM.2021.3138560
10	WANG G, FENG G, TAN W, et al. Resource allocation for network slices in 5G with network resource pricing[C]//Proceedings of IEEE Global Communications Conference. Washington D. C., USA: IEEE Press, 2017: 1-6.
11	SONG C, ZHANG M, ZHAN Y Y, et al. Hierarchical edge cloud enabling network slicing for 5G optical fronthaul. Journal of Optical Communications and Networking, 2019, 11(4): 60- 70. doi: 10.1364/JOCN.11.000B60
12	MEI J, WANG X B, ZHENG K. An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks. Intelligent and Converged Networks, 2020, 1(3): 281- 294. doi: 10.23919/ICN.2020.0019
13	YUE W, YU G, TAO X F. Edge network slicing with statistical QoS provisioning. IEEE Wireless Communi- cations Letters, 2019, 8(5): 1464- 1467. doi: 10.1109/LWC.2019.2922605
14	WEI F S, FENG G, SUN Y, et al. Network slice reconfiguration by exploiting deep reinforcement learning with large action space. IEEE Transactions on Network and Service Management, 2020, 17(4): 2197- 2211. doi: 10.1109/TNSM.2020.3019248
15	GABILONDO Á, FERNÁNDEZ Z, VIOLA R, et al. Traffic classification for network slicing in mobile networks. Electronics, 2022, 11(7): 1097. doi: 10.3390/electronics11071097
16	SATTAR D, MATRAWY A. Optimal slice allocation in 5G core networks. IEEE Networking Letters, 2019, 1(2): 48- 51. doi: 10.1109/LNET.2019.2908351
17	GIORGETTI A, SCANO D, VALCARENGHI L. Guaranteeing slice performance isolation with SDN. IEEE Communications Letters, 2021, 25(11): 3537- 3541. doi: 10.1109/LCOMM.2021.3113175
18	ALKHAFAJI A R, AL-TURAIHI F S. Multi-layer network slicing and resource allocation scheme for traffic-aware QoS ensured SDN/NFV-5G network[C]//Proceedings of the 1st Babylon International Conference on Information Technology and Science. Washington D. C., USA: IEEE Press, 2021: 327-331.
19	KHODAPANAH B, AWADA A, VIERING I, et al. Framework for slice-aware radio resource management utilizing artificial neural networks. IEEE Access, 2020, 8, 174972- 174987. doi: 10.1109/ACCESS.2020.3026164
20	DOGANI J, KHUNJUSH F, SEYDALI M. Host load prediction in cloud computing with Discrete Wavelet Transformation(DWT) and Bidirectional Gated Recurrent Unit(BiGRU) network. Computer Communications, 2023, 198, 157- 174. doi: 10.1016/j.comcom.2022.11.018
21	邹国建, 赖子良, 李晔. 基于时空注意力网络的动态高速路网交通速度预测. 计算机工程, 2023, 49(2): 303- 313. URL
	ZOU G J, LAI Z L, LI Y. Traffic speed prediction of dynamic expressway network based on spatio-temporal attention network. Computer Engineering, 2023, 49(2): 303- 313. URL
22	PAN L, POLITIS D N. Bootstrap prediction intervals for linear, nonlinear and nonparametric autoregressions. Journal of Statistical Planning and Inference, 2016, 177, 1- 27. doi: 10.1016/j.jspi.2014.10.003
23	ZOLA E, MARTIN-ESCALONA I. A robust user association, backhaul routing, and switching off model for a 5G network with variable traffic demands. IEEE Access, 2020, 8, 96714- 96726. doi: 10.1109/ACCESS.2020.2992330
24	郑振康, 周金和. 面向多租户网络资源分配的博弈优化策略. 计算机工程, 2022, 48(5): 170- 177. URL
	ZHENG Z K, ZHOU J H. Game optimization strategy for multi-tenant network resource allocation. Computer Engineering, 2022, 48(5): 170- 177. URL
25	BACANIN N, ANTONIJEVIC M, BEZDAN T, et al. Energy efficient offloading mechanism using particle swarm optimization in 5G enabled edge nodes. Cluster Computing, 2023, 26(1): 587- 598. doi: 10.1007/s10586-022-03609-z
26	杨靖, 张宏军, 赵水宁, 等. 基于粒子群优化算法的虚拟机部署策略. 计算机应用, 2016, 36(1): 117- 121.
	YANG J, ZHANG H J, ZHAO S N, et al. Virtual machine deployment strategy based on particle swarm optimization algorithm. Journal of Computer Applications, 2016, 36(1): 117- 121.
27	CORTEZ P, RIO M, ROCHA M, et al. Multi-scale Internet traffic forecasting using neural networks and time series methods. Expert Systems, 2012, 29(2): 143- 155. doi: 10.1111/j.1468-0394.2010.00568.x
28	MARKOVICS D, MAYER M J. Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction. Renewable and Sustainable Energy Reviews, 2022, 161, 112364. doi: 10.1016/j.rser.2022.112364
29	BAUMGARTNER A, BAUSCHERT T, BLZAROUR A A, et al. Network slice embedding under traffic uncertainties—a light robust approach[C]//Proceedings of the 13th International Conference on Network and Service Management. Washington D. C., USA: IEEE Press, 2018: 1-5.

[1]	更藏措毛, 黄鹤鸣, 杨毅杰. 融合多尺度特征与上下文信息的语音增强方法[J]. 计算机工程, 2024, 50(6): 138-147.
[2]	宫阿娟, 潘天荣. 多病种眼底疾病诊断的深度学习策略讨论[J]. 计算机工程, 2024, 50(5): 363-372.
[3]	杨静, 陆铭华, 马洁琼, 吴金平, 刘星璇. 基于交替循环神经网络的水下防御态势预测方法[J]. 计算机工程, 2023, 49(9): 69-78.
[4]	牛淑芬, 闫森, 吕锐曦, 周思玮, 张美玲. V2V车联网中隐私保护性异构聚合签密方案[J]. 计算机工程, 2022, 48(9): 20-27,36.
[5]	郑振康, 周金和. 面向多租户网络资源分配的博弈优化策略[J]. 计算机工程, 2022, 48(5): 170-177.
[6]	张会云, 黄鹤鸣. 基于异构并行神经网络的语音情感识别[J]. 计算机工程, 2022, 48(4): 113-118.
[7]	李小剑, 谢晓尧, 徐洋, 张思聪. 基于CNN-SIndRNN的恶意TLS流量快速识别方法[J]. 计算机工程, 2022, 48(4): 148-157,164.
[8]	施荣华, 金鑫, 胡超. 基于图注意力网络的方面级别文本情感分析[J]. 计算机工程, 2022, 48(2): 34-39.
[9]	吴铁洲, 邹智, 姜奔, 张晓星. 基于TLBGA-GRU神经网络的短期负荷预测[J]. 计算机工程, 2022, 48(11): 69-76.
[10]	李江和, 王玫. 一种用于因果式语音增强的门控循环神经网络[J]. 计算机工程, 2022, 48(11): 77-82.
[11]	朱思猛, 杜瑞颖, 陈晶, 何琨. 基于循环神经网络的Web应用防火墙加固方案[J]. 计算机工程, 2022, 48(11): 120-126.
[12]	张稣荣, 卜佑军, 陈博, 孙重鑫, 王涵, 胡先君. 基于多层双向SRU与注意力模型的加密流量分类方法[J]. 计算机工程, 2022, 48(11): 127-136.
[13]	徐兴荣, 张帅鹏, 李婷, 郭娜, 董乐乐, 刘聪, 任崇广. 基于轨迹聚类的业务流程剩余时间预测方法[J]. 计算机工程, 2022, 48(11): 247-256,265.
[14]	杨志军, 寇倩兰, 丁洪伟. 5G切片架构下具有重传机制的轮询系统研究[J]. 计算机工程, 2022, 48(10): 202-211.
[15]	何彦琦, 彭大芹, 赵雪志. 一种基于循环神经网络的极化码BP译码算法[J]. 计算机工程, 2022, 48(1): 197-203.

选择文件类型/文献管理软件名称

选择包含的内容