典型文献
Spatio-Temporal Cellular Network Traffic Prediction Using Multi-Task Deep Learning for AI-Enabled 6G
文献摘要：
Spatio-temporal cellular network traffic prediction at wide-area level plays an important role in resource reconfiguration, traffic scheduling and intrusion detection, thus potentially support-ing connected intelligence of the sixth generation of mobile communications technology (6G). How-ever, the existing studies just focus on the spatio-temporal modeling of traffic data of single net-work service, such as short message, call, or Internet. It is not conducive to accurate prediction of traffic data, characterised by diverse network service, spatio-temporality and supersize volume. To address this issue, a novel multi-task deep learning framework is developed for citywide cellular net-work traffic prediction. Functionally, this framework mainly consists of a dual modular feature sharing layer and a multi-task learning layer (DMFS-MT). The former aims at mining long-term spatio-temporal dependencies and local spatio-temporal fluctuation trends in data, respectively, via a new combination of convolutional gated recurrent unit (ConvGRU) and 3-dimensional convolu-tional neural network (3D-CNN). For the latter, each task is performed for predicting service-spe-cific traffic data based on a fully connected network. On the real-world Telecom Italia dataset, sim-ulation results demonstrate the effectiveness of our proposal through prediction performance mea-sure, spatial pattern comparison and statistical distribution verification.
文献关键词：
中图分类号：
作者姓名：
Xiaochuan Sun;Biao Wei;Jiahui Gao;Difei Cao;Zhigang Li;Yingqi Li
作者机构：
The College of Artificial Intelligence, North China University of Science and Tech-nology, Tangshan 063210, Hebei, China
文献出处：
引用格式：
[1]Xiaochuan Sun;Biao Wei;Jiahui Gao;Difei Cao;Zhigang Li;Yingqi Li-.Spatio-Temporal Cellular Network Traffic Prediction Using Multi-Task Deep Learning for AI-Enabled 6G)[J].北京理工大学学报（英文版）,2022(05):441-453
A类：
supersize,citywide
B类：
Spatio,Temporal,Cellular,Network,Traffic,Prediction,Using,Multi,Task,Deep,Learning,Enabled,6G,cellular,network,traffic,prediction,area,level,plays,important,role,resource,reconfiguration,scheduling,intrusion,detection,thus,potentially,support,connected,intelligence,sixth,generation,mobile,communications,technology,How,ever,existing,studies,just,focus,spatio,modeling,single,service,such,short,message,call,Internet,not,conducive,accurate,characterised,by,diverse,temporality,volume,To,address,this,issue,novel,multi,task,deep,learning,framework,developed,Functionally,mainly,consists,dual,modular,feature,sharing,layer,DMFS,MT,former,aims,mining,long,term,dependencies,local,fluctuation,trends,respectively,via,new,combination,convolutional,gated,recurrent,unit,ConvGRU,dimensional,neural,For,latter,each,performed,predicting,cific,fully,On,real,world,Telecom,Italia,dataset,sim,ulation,results,demonstrate,effectiveness,proposal,through,performance,mea,sure,spatial,pattern,comparison,statistical,distribution,verification
AB值：
0.658217
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
