With the advancement of new technologies, the number of connected devices, the amount of data generated, and the need to build an intelligently connected network of things to improve and enrich the human ecosystem open new doors to modifications and adaptations of current cellular network infrastructures. While more focus is given to low power wide area (LPWA) applications and devices, a significant challenge is the definition of Internet of Things (IoT) use cases and the value generation of applications on already existing IoT devices. Smartphones and related devices are currently manufactured with a wide range of smart sensors such as accelerometers, video sensors, compasses, gyros, proximity sensors, fingerprint sensors, temperature sensors, and biometric sensors used for various purposes. Many of these sensors can be automatically expanded to monitor a user’s daily activities (e.g., fitness workouts), locations, movements, and real-time body temperatures. Mobile network operators (MNOs) play a substantial role in providing IoT communications platforms, as they manage traffic flow in the network. In this paper, we discuss the global concept of IoT and machine-type communication (MTC), and we conduct device performance analytics based on data traffic collected from a cellular network. The experiment equips service providers with a model and framework to monitor device performance in a network.

Network Operators are shifting their business interest towards Data services in a geometric progression manner, as Data services is becoming the major source of Telco revenue. The wide use of Data platforms; such as WhatsApp, Skype, Hangout and other Over the Top (OTT) voice applications over the traditional voice services is a clear indication that Network Operators need to adjust their business model and needs. And couple with the adoption of Smartphones usage which grows continuously year by year, this means more subscribers to manage, large amount of transactions generated, more network resources to be added and evidently more human technical expertise required to ensure good service quality. That has led to high investment on Robust Service Quality Management (SQM) and Customer Experience Management (CEM) to stay competitive in the market. The high investment is justified by the integration of Big Data Solutions, Machine Learning capabilities and good visualization of insight data. However, the Return on Investment (ROI) of the expensive systems are not as conspicuous as the provided functionalities and business rules. Therefore, in this paper an efficient model for low cost SQM system is presented, exploring the advantages of In-Memory Big Data processing and low cost business Intelligence tools to showcase how a good Service Quality Management can be implemented with no big investment.

Machine learning (ML) in wireless mobile communication is becoming more and more customary, with application trends leaning toward performance improvement and network automation. The radio access network (RAN), critical for service access, frequently generates performance data that mobile network operators (MNOs) and researchers leverage for planning, self-optimization, and intelligent network operations. However, missing values in the RAN performance data, as in any valuable data, impact analysis. Poor handling of such missing data in the RAN can distort the relationships between different metrics, leading to inaccurate and unreliable conclusions and predictions. Therefore, there is a need for imputation methods that preserve the overall structure of the RAN data to an optimal level. In this study, we present an imputation approach for handling RAN performance missing data based on machine learning algorithms. The method customizes the feature-extraction mechanism by using dynamic correlation analysis. We apply the method to actual RAN performance indicator data to evaluate its performance. We finally compare and evaluate the proposed approach with statistical imputation techniques such as the mean, median, and mode. The results show that machine learning-based imputation, as approached in this experimental study, preserves some relationships between KPIs compared to non-ML techniques. Random Forest regressor gave the best performance in imputing the data.