首页--工业技术论文--无线电电子学、电信技术论文--无线通信论文--移动通信论文

5G移动通信网络中的呼叫记录分析

致谢第4-5页
摘要第5-6页
Abstract第6-7页
Abbreviations第14-15页
Chapter 1 Introduction第15-22页
    1.1 Background第15-16页
    1.2 Overview of CDR data第16-18页
    1.3 Contribution of the thesis第18-20页
        1.3.1 Investigating the Anomalous activities第18页
        1.3.2 CDRs driven Traffic Predictions第18-19页
        1.3.3 Spatiotemporal Explorations of CDRs第19页
        1.3.4 Traffic Classification and Optimization第19-20页
        1.3.5 Understanding of Mobile traffic with Internet Activity Records(IARs)第20页
    1.4 Organization of the Thesis第20-22页
Chapter 2 Literature Review第22-39页
    2.1 Call details Record (CDR)第22页
    2.2 Impacts of CDR data Analysis第22-26页
        2.2.1. Social Impact第23-24页
        2.2.2. Private Sector Impact第24-26页
    2.3 4G/LTE: Networks第26-28页
        2.3.1. LTE Network Architecture第26-28页
            2.3.1.1. Core Network第27-28页
            2.3.1.2. Radio Access Network第28页
    2.4 5G Networks第28-32页
        2.4.1 Major Milestone of 5G Networks第29-31页
        2.4.2 Current Standard and Technology Enablers for 5G Networks第31-32页
    2.5 Data Analytics and Machine learning Perspective on 5G Networks第32-38页
        2.5.1 Data analytics and 5G Networks第32-34页
        2.5.2 Machine Learning Impacts on 5G networks第34-37页
        2.5.3 Role of Neural Networks in 5G Networks第37-38页
    2.6 Summary第38-39页
Chapter 3 Big data driven framework for 5G Networks第39-47页
    3.1 Introduction第39页
    3.2 Big data第39-41页
        3.2.1 Volume第39-40页
        3.2.2 Velocity第40页
        3.2.3 Variety第40-41页
        3.2.4 Veracity第41页
        3.2.5 Value第41页
    3.3 Big data driven solutions for 5GNetworks第41-44页
    3.4 Big data driven framework for 5G Networks第44-45页
    3.5 Summary第45-47页
Chapter 4 CDR data analytics for cellular network第47-68页
    4.1 Introduction第47页
    4.2 Related work第47-48页
    4.3 The Importance of CDR Data and Use Case第48-50页
    4.4 CDRs Driven Anomaly Detection and Traffic Prediction In Mobile Cellular Networks第50-67页
        4.4.1 System Model and Dataset Description第51-54页
        4.4.2 Anomaly Detection and Verification第54-58页
        4.4.3 Preparation of Anomaly-Free Data And Mean Square Error Evaluation第58-61页
        4.4.4 ARIMA Time-Series Forecasting Model第61-67页
    4.5 Summary第67-68页
Chapter 5 Mobile traffic classification and optimization using call details record-A spatiotemporal approach第68-85页
    5.1 Intoduction第68-69页
    5.2 Background第69-70页
    5.3 System Model and Dataset Description第70-73页
        5.3.1 Description of Dataset第72-73页
        5.3.2 Data Preparation第73页
    5.4 Spatio-Temporal Approach第73-78页
        5.4.1 Spatial Approach第74-75页
        5.4.2 Spatial Correlation第75-76页
        5.4.3 Temporal Approach第76-77页
        5.4.4 Temporal Correlation第77-78页
    5.5 Hybrid DNN Model第78-84页
        5.5.1 Clustering Analysis第79-81页
        5.5.2 DNN-Traffic Classification第81-84页
    5.6 Summary第84-85页
Chapter 6 Understanding and partitionng mobile traffic using internet activity records data第85-98页
    6.1 Introduction第85页
    6.2 Description of Dataset第85-86页
        6.2.1 Data Preprocessing第86页
    6.3 Spatial and Temporal Explorations of IARs第86-90页
        6.3.1 Spatial Mining of IARs第86-88页
        6.3.2 Temporal Mining of IARs第88-90页
    6.4 Clustering Based RNN-LSTM Model for Traffic Partitioning第90-94页
        6.4.1 k-means Clustering第90-91页
        6.4.2 TrafficPartitioing第91-92页
        6.4.3 Simulation Results第92-94页
        6.4.4 Comparative Analysis第94页
    6.5 Insights into CDRs Driven Traffic Optimization Approach第94-97页
    6.6 Summary第97-98页
Chapter 7 Conclusions第98-101页
    7.1 Conclusions第98-99页
    7.2 Future Work第99-101页
Authors' Publication (first author/co-author)第101-104页
References第104-113页
作者简历及在学研究成果第113-115页
学位论文数据集第115页

论文共115页,点击 下载论文
上一篇:物联网环境下连续目标检测和边缘节点重配置策略
下一篇:边缘计算环境下安全防御模型及算法研究