Unlock instant, AI-driven research and patent intelligence for your innovation.

Satellite internet user terminal short-term service volume demand prediction method and device

A technology of demand forecasting and user terminals, which is applied in the field of satellite Internet resource management to achieve the effects of improving prediction accuracy, reducing related signaling interactions, and improving operational efficiency

Active Publication Date: 2021-07-09
湖南国科轩宇信息科技有限公司
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the past ten years, with the wide application of various mobile communication devices, people's demand for broadband access, mobile Internet and other communication services has grown rapidly. At the same time, satellite Internet space segment communication satellites are usually deployed in medium and low orbits. Internet user terminal business volume requirements and system communication resources are highly dynamic, which brings major challenges to the optimal allocation of satellite resources and system engineering construction

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Satellite internet user terminal short-term service volume demand prediction method and device
  • Satellite internet user terminal short-term service volume demand prediction method and device
  • Satellite internet user terminal short-term service volume demand prediction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0045] The satellite Internet user terminal short-term traffic demand prediction model and method proposed by the present invention are all realized under the environment of matlab2015a, and all programs run on a computer with Intel(R) Core(TM) i5-3210M2.5GHz and 4GB memory. Select 30 days of data from the system database, of which the first 25 days are used as the training data set of the deep loop network, and the last 5 days are used as the test data set of the network.

[0046] A kind of concrete embodimen...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a short-term service volume demand prediction method and device for a satellite internet user terminal. The method comprises the following steps: training a deep recurrent neural network model with a flexible characteristic by using historical service volume data of a satellite internet user; during training, randomly generating a plurality of sets of network parameter value combination schemes, training the plurality of sets of network parameter value combination schemes by using a training sample set, evaluating a training result, and selecting an optimal network parameter value combination scheme; obtaining current service data, inputting the current service data into the network model, and outputting a user terminal short-term service volume demand prediction value. According to the method, the deep recurrent neural network model with the flexible characteristic is used, which model is selected to be optimal according to prediction result evaluation, which model is bound into a trained network structure for prediction, training and prediction are not limited to one model, the optimization space of the deep recurrent network for solving the prediction problem is effectively expanded, and the prediction precision is improved.

Description

technical field [0001] The invention belongs to the technical field of satellite Internet resource management, and in particular relates to a method and device for predicting short-term traffic demand of satellite Internet user terminals. Background technique [0002] Satellite Internet can provide global users with high-speed, wireless broadband access and multi-type communication services, and solve the communication and interconnection needs of users who lack ground network coverage. Compared with terrestrial optical fiber, satellite Internet is used for interactive communication between ultra-long-distance users with a smaller delay. The satellite Internet system is mainly composed of the space segment, the ground segment and the user segment. The space segment is a constellation of communication satellites with global coverage; the ground segment includes the operation management center and several gateway stations distributed around the world; the user segment include...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04W24/06H04B7/185H04W16/22H04L12/24G06Q10/04G06Q10/06G06Q50/30G06N3/04G06N3/08
CPCH04W24/06H04B7/1851H04W16/22H04L41/147G06Q10/04G06Q10/06315G06Q10/06312G06N3/08G06N3/048G06N3/044G06Q50/40Y02D30/70
Inventor 李湘常中祥
Owner 湖南国科轩宇信息科技有限公司