A Base Station Dormancy Method Based on Mobile Network Traffic Prediction

Abstract

The invention discloses a dormancy method for a base station based on mobile network traffic prediction. In a mobile network, the traffic of a base station is predicted through a prediction model based on spatio-temporal characteristics, and then a suitable base station is scheduled to enter a dormant state according to the predicted traffic. Save energy consumption of the base station. Fang Ming uses the temporal convolutional network to extract the temporal characteristics of mobile network traffic, uses the three-dimensional convolutional network traffic to extract the spatial characteristics of mobile network traffic, and then uses the extracted features to accurately predict the traffic of the base station, and then uses the predicted traffic to pass the planning The method of selecting a suitable base station for dormancy can effectively reduce the energy consumption of the base station and at the same time ensure the quality of service for users.

Description

technical field [0001] The invention relates to a dormancy method for a base station based on mobile network traffic prediction, belonging to the field of mobile networks. Background technique [0002] With the rapid growth of the number of mobile devices, mobile network traffic is also growing extremely rapidly, which accelerates the expansion of mobile network infrastructure. The expansion of mobile networks has also led to an increase in mobile network energy consumption. Operators need to build green mobile networks considering economic and ecological issues. Previous studies have shown that the energy consumption of base stations accounts for about 80% of mobile network traffic consumption. Therefore, saving the energy consumption of the base station is the key to constructing a green mobile network. [0003] In related research on energy saving of base stations, dormancy of base stations is a common method. Since the base station is designed according to the traffi...

AI Technical Summary

Problems solved by technology

Sheng Zhang et al considered the dynamics of traffic (References: Zhang S, Zhao S, YuanM, et al. Traffic prediction based power saving in cellular networks: A machine learning method[C] / / Proceedings of the 25th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 2017:29.), but when designing the dormancy algorithm, only the number of base stations that should be dormant at the next moment is considered, and the base stations that should be dormant cannot be obtained exactly

The above methods have the disadvantages of inaccurate forecast flow and insufficient scheduling strategy

Images