AI-based Traffic Control for Energy Saving in 5G

Sammanfattning

The rapid roll-out of 5G networks has ushered in an era of unprecedented connectivity, but it also poses challenges related to energy consumption and sustainability. This thesis explores the application of Artificial Intelligence (AI) to optimize network operations and reduce energy consumption in 5G networks. In contrast to conventional energy saving strategies that often rely on static rules, the focus is on employing forecasting techniques to predict network load for a proactive energy saving approach. However, a key challenge is to strike a balance between energy saving and maintaining quality of service. This thesis compares an AI-based approach with a non-AI benchmark, derived from conventional solutions, to evaluate their effectiveness in achieving energy savings and optimizing network operations. Moreover, a comparative analysis is conducted between two different forecasting methods to determine the most effective one for predicting network load. Results show that the AI-based approach outperforms the benchmark, demonstrating greater energy savings and quality of service preservation. This thesis emphasizes how AI can be used to improve energy efficiency in 5G networks, providing valuable insights for network operators and service providers seeking to integrate AI-driven solutions to reduce energy consumption and operational costs.