Climate Control Optimization in Radio Base Stations using Machine Learning : Energy Savings in Radio Base Stations

Sammanfattning

In the domain of telecommunication infrastructure, the operation of Climate Control Units (CCUs) within the Radio Base Stations (RBSs) is crucial for supporting the operation of RBSs and preventing the wear of hardware parts. However, the improvement of energy efficiency in CCUs still attracts research attention. This master thesis analyzes the methods for optimizing the operation and power savings of CCU implementation in RBS. The primary objective focused on power efficiency and hardware lifespan, sets the foundation for this research that leads to the development of Machine Learning (ML) based algorithms. These algorithms are used to create dynamic predictive models that are responsible for setting the best temperature and fan speed control over time for a particular RBS hosting the CCU. This ML approach is reinforced by a data-driven approach involving data preprocessing, exploratory analysis, and model training. The work is also strengthened by assessing the operational approach using Reinforcement Learning (RL) methodology and evaluating how it contributes towards a predictive model. The results prove that there were up to 70% energy savings for the fans’ operation while using RL based methods for climate control, when compared to traditional methods. The developed algorithm not only allows for reducing energy costs and environmental impact but also enhances the operational reliability of telecommunication infrastructure. With many RBSs deployed all over the world, the results of this study aim to contribute towards sustainable and greener technologies and also open the world of opportunities for the real- life application of Artificial Intelligence (AI).