Agile satellite task parallel scheduling method based on data driving

A data-driven, scheduling method technology, applied in electrical digital data processing, computing models, execution paradigms, etc., can solve the problems of slow scheduling of large-scale agile satellites, unable to quickly provide scheduling plans, etc., to improve scheduling efficiency and complexity. The effect of problem simplification

Active Publication Date: 2019-07-02
NAT UNIV OF DEFENSE TECH
View PDF5 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a data-driven agile satellite task parallel scheduling method for the slow scheduling rate of large-scale agile satellites and the problem that the scheduling scheme cannot be quickly given within a limited time

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
  • Agile satellite task parallel scheduling method based on data driving
  • Agile satellite task parallel scheduling method based on data driving
  • Agile satellite task parallel scheduling method based on data driving

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] Figure 1 to Figure 13 It shows an embodiment of the present invention based on the data type agile satellite thinking dispatching planning method, such as figure 2 As shown, the present invention includes step 1: obtaining the historical task scheduling data of the agile imaging satellite and the task set to be assigned; step 2: using the historical task scheduling data based on the deep learning algorithm to train the task prediction model, and based on the trained prediction model Predict the task scheduling probability of each agile imaging satellite; Step 3: According to the prediction result of the satellite task scheduling probability, assign each task in the task set to be allocated to the agile satellite with the highest scheduling probability, so as to allocate large-scale multi-agile imaging satellite tasks The scheduling problem is transformed into multiple parallel single-satellite scheduling problems; Step 4: Solve multiple parallel single-satellite sched...

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 discloses an agile satellite task parallel scheduling method based on data driving. The method comprises the steps of 1, obtaining agile imaging satellite historical task scheduling dataand a to-be-allocated task set; 2, training a task prediction model based on a deep learning algorithm, and predicting the scheduling probability of each to-be-allocated task; 3, according to a probability prediction result, allocating each task to the satellite with the maximum scheduling probability, and converting a large-scale satellite task scheduling problem into a plurality of parallel single-satellite scheduling problems; 4, solving; and 5, outputting the agile imaging satellite task scheduling sequence of each task to be distributed. The task scheduling probability prediction model is obtained through the machine learning algorithm, each task is allocated to the satellite with the maximum scheduling probability for execution, the complex problem is simplified, the task schedulingtime is shortened from the hour level to the minute level, and the scheduling efficiency of large-scale agile imaging satellite tasks is effectively improved.

Description

technical field [0001] The invention belongs to the field of task planning and dispatching, in particular to a data-driven agile satellite task parallel dispatching method. Background technique [0002] With the continuous development of satellite technology and the continuous development and utilization of earth and space resources by human beings, the application of satellites has become a very important space-based resource. According to different satellite application types, application satellites can generally be divided into imaging satellites, communication satellites and navigation satellites. Among them, earth imaging satellites mainly take or collect images and intelligence information on the earth's surface, and have been widely used in various military or civilian fields such as resource surveying, geographic information system management, weather forecasting, and missile early warning. With the continuous development of the breadth and depth of imaging satellit...

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): G06F9/448G06F9/48G06N3/00
CPCG06F9/4494G06F9/4881G06N3/006
Inventor 鲁籍赵啸宇陈盈果杜永浩邢立宁陈成王涛刘晓路姚锋贺仁杰张忠山陈英武陈宇宁吕济民
Owner NAT UNIV OF DEFENSE TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap