Data Analysis and Energy Consumption Prediction in a Cloud-Fog RAN Environment

The extraction of information from data collected in a myriad of environments provides unprecedented opportunities for a big range of actions such as decision making and better resource management. Benefits from its processes are relatively large for many network domains such as protocol design, hybrid architectures redesign, and resource management and optimization. Time series or historical data series provide can be used in several ways like pattern analysis and prediction support, making it an important support tool for managers to develop goals and objectives focused on their business. The goal of this paper is to discuss the potential of data analysis in hybrid Cloud-Fog Radio Access Networks (CF-RAN) scenarios and present results of applications of the data in the process of prediction energy consumption. In particular, we analysed the knowledge data extraction of some metrics with a strong relationship with energy consumption and we perform a prediction by applying a deep learning algorithm using the previous four hour period to predict the next hour.