Method for saving energy based on user group aggregation behavior model

Abstract

A method for saving energy based on a user group aggregation behavior model comprises the following steps: firstly, dividing grids, predicting flow of a single base station in the grids by utilizing aspace-time joint distribution model, and calculating a load sum of each base station in different grids according to a prediction result; and activating the base station according to the load sum ofthe base stations in the different grids under the condition that the switching frequency is minimized and the coverage area of the base station and the capacity threshold of the base station are met.Due to the fact that the space-time joint distribution model quantitatively describes the non-uniformity in all dimensions, quantitative description is carried out on the aggregation behavior business of the users, the rules of the aggregation behaviors of the users can be obtained easily, and therefore flow prediction and base station dormancy are facilitated. In a cellular network, the flow prediction based on the single base station provided by the invention utilizes a lattice base station mechanism to establish a mechanism matched with flow parents and children, so that the energy efficiency of the network is improved.

Description

technical field [0001] The invention relates to a method for energy saving based on a user group aggregation behavior model. Background technique [0002] The cellular network is also called the mobile network. The cellular network is mainly composed of the following three parts: mobile station, base station subsystem, and network subsystem. Complex business characteristics and user mobility behaviors have the characteristics of clustering in groups in time domain, air domain and spatio-temporal distribution. In the past, the resource allocation method was mainly to configure network resources in a static and isolated manner, which would cause a great waste of energy and resources. On the premise of studying the aggregation behavior of user groups, it is firstly based on the data collection and measurement of the actual operating cellular mobile communication system, and then conducts in-depth research on the data from multiple dimensions and aspects, and obtains the base s...

AI Technical Summary

Problems solved by technology

[0008] (1) The traditional prediction model shows a good prediction effect on linear data, but the prediction result is not good for nonlinear network traffic data. Although the prediction method based on neural network has relatively high prediction accuracy, but The convergence speed is slow and it is easy to fall into the local minimum

[0009] (2) In the research, there is no unified modeling method for business inhomogeneity, and there is no measurement standard to quantitatively describe the inhomogeneity in each dimension of the business, and the aggregation behavior of users cannot be quantified describe

Images