中圖分類號： TN919.2；TP181 文獻(xiàn)標(biāo)識碼： A DOI：10.16157/j.issn.0258-7998.211517 中文引用格式： 徐海兵，郭久明. 基于雙向GRU模型的網(wǎng)絡(luò)流量預(yù)測的研究[J].電子技術(shù)應(yīng)用，2022，48(2)：19-22，27. 英文引用格式： Xu Haibing，Guo Jiuming. Research on network traffic prediction based on Bi-GRU model[J]. Application of Electronic Technique，2022，48(2)：19-22，27.
Research on network traffic prediction based on Bi-GRU model
Xu Haibing，Guo Jiuming
Technological Innovation Department，Maipu Communication Technology Co.，Ltd.，Chengdu 610094，China
Abstract： At present, there are some problems such as lag and low prediction accuracy when using gated recurrent units(GRU) neural network to predict traffic. This paper proposes an improved GRU model for traffic prediction. Firstly, based on GRU neural network, a network model integrating Bi-GRU neural network and artificial neural network is proposed, which satisfies the input of multi-dimensional vectors such as traffic features, time features and event features. At the same time, in order to improve the accuracy of some time periods, the training samples are classified into date classes, and a separate network model is generated for each type of date. It can greatly improve the accuracy of prediction and improve the lag of prediction. Finally, in order to improve the prediction accuracy of peak traffic, the experimental results show that the proposed goal can be achieved by the means of sample propensity balance and user-defined loss function.
Key words : traffic prediction；neural network；gated recurrent unit；loss function
0 引言
隨著網(wǎng)絡(luò)的普及，網(wǎng)絡(luò)流量的規(guī)模不斷被刷新，高效且合理地利用網(wǎng)絡(luò)資源變得尤為重要。一方面，網(wǎng)絡(luò)資源分配的不合理可能導(dǎo)致部分網(wǎng)絡(luò)資源由于耗盡而無法正常使用，甚至造成網(wǎng)絡(luò)癱瘓，而其他鏈路資源可能卻處于過剩的狀態(tài)，嚴(yán)重影響了用戶的上網(wǎng)體驗(yàn)；另一方面，雖然在前期合理分配了網(wǎng)絡(luò)資源，但網(wǎng)絡(luò)流量具有突發(fā)性，原本充足的網(wǎng)絡(luò)資源可能出現(xiàn)短缺的情況。為了解決此問題，現(xiàn)有軟件定義網(wǎng)絡(luò)(Software Defined Network，SDN)[1]控制器會(huì)實(shí)時(shí)檢查鏈路狀況，在一定程度上緩解了網(wǎng)絡(luò)擁塞，但由于調(diào)度時(shí)已經(jīng)發(fā)生了擁塞，無法滿足更高等級、更好服務(wù)質(zhì)量的要求。鑒于此，如果能夠精準(zhǔn)預(yù)測網(wǎng)絡(luò)流量，提前發(fā)現(xiàn)未來時(shí)刻的網(wǎng)絡(luò)流量變化情況，流量調(diào)度系統(tǒng)則可以提前進(jìn)行合理調(diào)度，有效避免擁塞的發(fā)生。
