Prediction of Base Station Energy Saving Strategy Rationality Based on XGBoost

The power consumption of 5G base stations is a major pain point for operators, 5G energy-saving strategies are currently simplistic, it usually sets a unified energy-saving time periods, which can not achieve differentiation strategy in different scenarios. In this paper, we propose a new energy saving strategy prediction model based on XGBoost. First, the energy saving methods for 5G base stations are briefly described. Then, the energy-saving network elements are introduced to dynamically and uniformly manage the energy consumption of the whole 5G access network. In addition, the principle of XGBoost algorithms is further analyzed. Finally, the model training process and application effects are roughly proposed, which reduces the false shutdown rate to 2% and increases the recall rate to 87%. It realizes the intelligent identification of energy saving scenarios in the realistic wireless network. The intelligent recommendation of energy saving strategies achieve intelligent energy saving effects and ensure that the user experience is not affected.