Base Station Energy Saving based on Imitation Learning in 5G
This article first proposes a dynamic base station switching framework based on deep reinforcement learning (DRL), which optimizes the power consumption of switching BSs.
• The 5G base station energy consumption prediction model based on LSTM proposed in this paper takes into account the energy consumption characteristics of 5G base stations. The prediction results have high accuracy and provide data support for the subsequent research on BSES aggregation and optimal scheduling.
According to the energy consumption characteristics of the base station, a 5G base station energy consumption prediction model based on the LSTM network is constructed to provide data support for the subsequent BSES aggregation and collaborative scheduling.
In this region, the communication base stations are equipped with energy storage systems with a rated capacity of 48 kWh and a maximum charge/discharge power of 15.84 kW. The self-discharge efficiency is set at 0.99, and the state of charge (SOC) is allowed to range between a maximum of 0.9 and a minimum of 0.1. Figure 3.
In recent years, many models for base station power con-sumption have been proposed in the literature. The work in proposed a widely used power consumption model, which explicitly shows the linear relationship between the power transmitted by the BS and its consumed power.
PDF version includes complete article with source references.
Get technical specifications, European subsidy information, and ROI analysis tools for peak shaving and container energy storage solutions.
ul. Technologii 15, Park Przemysłowy
geochojnice.pl, Poland
Office: +48 22 525 6683
Technical: +48 189 486 173
Monday - Friday: 8:00 AM - 6:00 PM CET