基于二次分解的混合神經(jīng)網(wǎng)絡(luò)蜂窩流量預(yù)測

打開文本圖片集

中圖分類號：TN929.5 文獻標志碼：A

Abstract：In the context of the rapid development of mobile communication networks，cellular trafic prediction plays an important role in network planning，optimization resource management.Taking the complexity nonlinear characteristics of cellular traffc data into acount，a hybrid neural network celllar trafic prediction method based on quadratic decomposition is proposed.The complete ensemble empirical mode decomposition with adaptive noise（CEEMDAN）method is first used to decompose the original traffic into multiple subsequences， reconstruct them into frequency trend sequences by using the K-Shape clustering algorithm.To reveal theunderlying structure of data in more detail，thevariational mode decomposition（VMD）method isused to perform secondary decomposition on the frequency sequence generate multi-dimensional frequency sequences.Subsequently，the one-dimensional trend sequence multidimensional frequency sequence are separately input into the local featureextraction module.The single-channel feature extraction layer uses the one-dimensional convolution neural network （1DCNN） method to extract local features of the one-dimensional trend sequence，while the multi-channel featureextraction layer combines the convolutional block attention module（CBAM）method to capture key information in the multi-dimensional frequency sequence.Then we input the extracted feature vectors into the temporal information learning module， use the bidirectional long short term memory（BiLSTM）model attention mechanism to complete the output prediction.Finally，we achieve accurate prediction of cellular traffic by summing the predicted results of frequency trend sequences.To verify the efectiveness of the proposed method，this paper conducts experimental verification by using publicly available datasets compares the predicted results with various methods.The experimental results show that the proposed method exhibits better predictive performance， which can provide strong support for the management optimization of cellular networks.

Keywords：cellular trafic prediction；modal decomposition；convolutional neural network（CNN） bidirectional long short term memory（BiLSTM） network；convolutional block attention module（CBAM）

0 引言

隨著智能移動終端的普及和通信網(wǎng)絡(luò)技術(shù)的創(chuàng)新，第5代移動通信技術(shù)推動了自動駕駛、遠程醫(yī)療、海量物聯(lián)網(wǎng)等通信業(yè)務(wù)種類的快速發(fā)展，導(dǎo)致蜂窩流量呈現(xiàn)爆發(fā)式增長[1-2]。（剩余18054字）