8 / 2018-08-28 21:53:24

Prediction of users charging time in cloud environment using machine learning

Charging management, Random forest, SVM, Predictive modelling, Cloud resources, Service optimization, mobile operators, resource consumption management

Due to the rapid growing of mobile devices, the new generation of mobile technologies and services, the term of mobile charging and billing processes arise and became a hot area for researchers and mobile telecommunications operator. Supporting the new revenue schemas and different pricing points will require a progressive improvement not only on the platform/applications level or the physical infrastructure but also on the cloud resources across different layers both IaaS and PaaS. Operators avail such cloud resources to vendors to manage the users charging transaction that will put the need for a certain performance management and enhancement. Using analytical models and machine leaning techniques to manage and analyze the users’ data/logs and getting more useful info that can be used in the management of the cloud resources in order to reach the best resources utilization with the highest revenue stream from the services users. Using machine learning to predict the users charging behavior based on their previous charging history and clustering them into a set of clusters based on the similarity of the charging logs in a self-adaptive model that learn from old and current charging transactions as well. A detailed experiment on how to reduce the number of charging transactions to the minimum that does not affect the revenue stream and at the same time leads to the best resources utilization. Finer tuning on this by applying forecasting and prediction techniques on the data to enhance the result and more than one prediction technique applied to reach the highest accuracy level of prediction. Numerical results serve to confirm the accuracy of the proposed analytical model while providing insight on how the different parameters and designs affect cloud resources performance.