Call Details Record Analysis Towards 5G Wireless Communication Networks

With the mammoth development in mobile and the internet of things(IoT)technologies,it can be anticipated that in next generation-networks(5G)everything will be connected.With every incremental step towards 5G development.the number of mobile devices such as smart phones,tablets,and wearable devices are on the rise exponentially.Such a huge connectivity of wireless devices and advancement in mobile networks technology will increase the data traffic volume largely.This large data is typically rich in useful information.However,the extract of useful information from such a big data is challenging.This thesis is focused on the analysis of cellular network data for improving the performance of next-generation networks.In particular,we focus on call details record(CDR)data.Whenever a subscriber uses a service such as voice call.SMS.or internet connection,a CDR is generated which is recorded by network operators.The information contained within the CDR of mobile networks can be used to study the operational efficacy of cellular networks and behavioral pattern of mobile subscribers.In this thesis,firstly we highlight the significance of big data analysis for 5G networks.We describe that to overcome the challenges and to fulfill the ke\requirements of 5G networks,big data driven analytics framework is of vital role.Second,we utilize the call details record data to detect anomalies in the network.For authenticatio n and verification of anomalies.we use k-means clustering,an unsupervised machine learning algorithm.Through effective detection of anomalies.we can proceed to suitable design for resource distribution as well as fault detection and avoidance.Iurther,ww prepare anomaly free data by removing anomalous activities and train a neural network model.By passing the anomaly and anomaly free data through this model.we observe the effect of anomalous aetivities in training of the model and also observe mean square error of the anomaly and anomaly free data.At last,we use an autoregressive integrated moving average model to predict future traffic for a user.Through simple visualization.we show that the anomaly free data better generalizes the learning models and performs better on prediction task.Third,we extract actionable insights from the CDR data and show that there exists a strong spatiotemporal predictability in real network traffic patterns.This knowledge can be leveraged by the mobile operators for effective network planning such as resource management and optimization.Motivated by thiswe perform the spatiotemporal analysis of CDR data publicly available from Telecom Italia.Thus,on the basis of spatiotemporal insights,we propose a framework for mobile traffic classification.Experimental results show that the proposed model based on machine learning technique is able to accurately model and classify the network traffic patterns.Furthermore,we demonstrate the application of such insights for resource optimization.Finally,we analyze the internet activity record data separately for understanding and partitioning of network traffic,The internet activity records(IARs)of a mobile cellular network possess significant information which can be exploited to identify the network's efficacy and the mobile users' behavior.We extract useful information from the IAR data and identify a healthy predictability of spatiotemporal pattern within the network traffic.The inormation extracted is helpful for network operators to plan effective network configuration and perform management and optimization of network's resources.We report experimentation on spatiotemporal analysis of IAR data of the Telecom Italia.Based on this,we present mobile traffic partitioning scheme.Ex perimental results of the proposed model are helpful in modeling and partitioning of network traffic patterns.