發(fā)布時間：2018-03-10 00:11

  本文選題：城市基站　切入點：流量預(yù)測　出處：《工業(yè)工程與管理》2017年04期 　論文類型：期刊論文

【摘要】：城市移動通信基站流量的準確預(yù)測對于關(guān)鍵基站的擁堵控制、基站新址的選擇有著重要作用。基站流量數(shù)據(jù)不僅是區(qū)域的靜態(tài)表現(xiàn),同時也反映區(qū)域人員的流動特性。基站流量具有非線性混沌特性,而傳統(tǒng)的線性時間序列方法比如自回歸移動平均模型難以有效地捕獲實際基站流量序列中復(fù)雜的非線性因素。同時,僅考慮單個基站時間序列而忽略鄰近基站的影響并不能反映基站流量的動態(tài)特征�；谙蛄孔曰貧w模型(VAR)對大規(guī)模基站流量數(shù)據(jù)進行整體分析,將多響應(yīng)變量預(yù)測問題轉(zhuǎn)化為單響應(yīng)變量預(yù)測模型,運用Lasso變量選擇方法篩選目標基站的重要關(guān)聯(lián)基站。實例表明,相對于傳統(tǒng)預(yù)測方法,VAR-Lasso類方法不僅提高了基站流量的預(yù)測精度,同時也實現(xiàn)了大規(guī)模基站的實時預(yù)測。
[Abstract]:The accurate prediction of base station traffic in urban mobile communication plays an important role in the congestion control of key base stations and the selection of new site of base station. The traffic data of base station is not only the static performance of the region. At the same time, it also reflects the flow characteristics of people in the region. However, the traditional linear time series methods such as the autoregressive moving average model can not effectively capture the complex nonlinear factors in the actual base station traffic sequence. Considering the time series of a single base station and neglecting the influence of adjacent base station, it can not reflect the dynamic characteristics of base station traffic. Based on the VAR-based vector autoregressive model, the traffic data of large scale base station are analyzed as a whole. The multiple response variable prediction problem is transformed into a single response variable prediction model, and the Lasso variable selection method is used to screen the important associated base stations of the target base stations. Compared with the traditional prediction method, the VAR-Lasso method not only improves the accuracy of base station traffic prediction, but also realizes the real-time prediction of large scale base station.
【作者單位】： 上海交通大學機械與動力工程學院;
【基金】：國家自然科學基金面上項目(71672109)
【分類號】：TN929.5

【相似文獻】

相關(guān)期刊論文 前1條

1 尚秀芹;宋紅軍;徐海勝;鄭經(jīng)波;;非均勻環(huán)境中的參量多通道目標檢測[J];電子與信息學報;2011年05期

，

本文編號：1590894