[1]张德杨,任佳玺.基于多时间粒度时空图网络的蜂窝网络流量预测[J].计算机技术与发展,2024,34(10):24-30.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0191]
　ZHANG De-yang,REN Jia-xi.Cellular Network Traffic Prediction Based on Spatio-temporal Graph Network with Multiple Temporal Granularity[J].,2024,34(10):24-30.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0191]
点击复制

基于多时间粒度时空图网络的蜂窝网络流量预测()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
34
期数:
2024年10期
页码:
24-30
栏目:
大数据与云计算
出版日期:
2024-10-10

文章信息/Info

Title:
Cellular Network Traffic Prediction Based on Spatio-temporal Graph Network with Multiple Temporal Granularity
文章编号:
1673-629X(2024)10-0024-07
作者:
张德杨1; 任佳玺2
1. 河南省科学技术情报中心,河南 郑州 450003;2. 郑州轻工业大学,河南 郑州 450000
Author(s):
ZHANG De-yang1; REN Jia-xi2
1. The Scientific & Technological Information Center of Henan,Zhengzhou 450003,China;2. Zhengzhou University of Light Industry,Zhengzhou 450000,China
关键词:
流量预测; 多时间粒度; 图注意力网络; 空间聚合; 一维卷积网络
Keywords:
traffic prediction; multi-temporal granularity; graph attention network; spatial aggregation; 1D convolutional network
分类号:
TP18;TN929.53
DOI:
10.20165/j.cnki.ISSN1673-629X.2024.0191
摘要:
蜂窝网络流量预测对于运营商提高网络服务质量、降低能耗、优化资源配置具有重要意义。 针对当前蜂窝网络流量预测方法无法同时提取多时间粒度序列特征和空间特征的问题,提出一种基于多时间粒度时空图神经网络的蜂窝网络流量预测方法。 该方法首先将基站历史数据建模为多个时间粒度的时序数据,并使用一维卷积网络提取每个序列的特征,然后使用图注意力网络对多时间粒度的特征进行聚合得到单一基站的数据特征,最后将多个基站的特征进行空间聚合,并使用全连接层将每个基站聚合后的特征映射为预测结果。 实验选择公开数据集 Telecom Italia 验证该方法的有效性,使用 RMSE 和 R2 作为预测结果的评价指标,与当前已有方法相比该方法可取得最好的预测结果。 论文最后分析了不同时间粒度序列对最终预测结果的影响,结果表明时间粒度位于 40 分钟至 1. 5 小时之间的序列对提高模型预测效果的贡献最大。
Abstract:
Cellular network traffic prediction is of great significance for operators to improve network service quality,reduce energy con-sumption,and optimize resource allocation. A cellular network traffic forecasting approach based on a multi-time granularity spatio-temporal graph neural network is proposed to address the problem that current cellular network traffic forecasting methods cannot extract multi-time granularity sequence features and spatial features effectively. The historical traffic data of the base station is modeled as time series of multiple time granularities,and the one-dimensional convolutional network is applied to extract the features of each sequence.Then the graph attention network is employed to aggregate the features of multi-time granularities to obtain the embedding of a single base station. Finally,the embeddings of multiple base stations are spatially aggregated,and the final prediction result for each base station is obtained via a fully connected network. The public dataset Telecom Italia is used to verify the effectiveness of the proposed method,and RMSE and R2 are used as evaluation indicators for the prediction results. The proposed method can achieve the best prediction results compared with the current existing methods. Finally we analyze the influence of different time granularity sequences on the final prediction results. The results show that sequences with time granularity between 40 minutes and 1. 5 hours make the greatest contribution to improving the model prediction effect.

相似文献/References:

[1]要趁红 王民.基于模糊控制的自适应流量抽样方法[J].计算机技术与发展,2012,(03):110.
　YAO Chen-hong,WANG Min.Adaptive Traffic-Sampling Measurement Method Based on Fuzzy Control[J].,2012,(10):110.
[2]邓宗强,曾碧卿.一种新参数优化算法及其在流量预测中的应用[J].计算机技术与发展,2013,(10):36.
　DENG Zong-qiang[],ZENG Bi-qing[].A New Parameter Optimization Algorithm and Its Application in Traffic Prediction[J].,2013,(10):36.
[3]李莉,吴润泽,包正睿,等.可重构分层感知网络流量预测算法[J].计算机技术与发展,2018,28(05):197.[doi:10.3969/ j. issn.1673-629X.2018.05.044]
　LI Li,WU Run-ze,BAO Zheng-rui,et al.Network Traffic Prediction Algorithm Based on Reconfigurable Hierarchical Perceptron Network[J].,2018,28(10):197.[doi:10.3969/ j. issn.1673-629X.2018.05.044]
[4]王健松,李学俊,王桂娟,等.基于数字孪生的城市交通流量可视预测研究[J].计算机技术与发展,2024,34(07):192.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0112]
　WANG Jian-song,LI Xue-jun,WANG Gui-juan,et al.City Traffic Flow Visual Prediction Based on Digital Twin[J].,2024,34(10):192.[doi:10.20165/j.cnki.ISSN1673-629X.2024.0112]

更新日期/Last Update: 2024-10-10