Low-orbit satellite routing strategy method based on deep reinforcement learning architecture

A reinforcement learning, low-orbit satellite technology, applied in the field of wireless communication

Active Publication Date: 2019-07-12
BEIJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the on-off switching of inter-satellite links, real-time changes in satellite load status, and satellite routing failures during the operation of low-orbit constellations, the present invention proposes a

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
  • Low-orbit satellite routing strategy method based on deep reinforcement learning architecture
  • Low-orbit satellite routing strategy method based on deep reinforcement learning architecture
  • Low-orbit satellite routing strategy method based on deep reinforcement learning architecture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] specific implementation plan

[0052] The present invention will be further described in detail with reference to the accompanying drawings and embodiments.

[0053] A Routing Strategy for LEO Constellation Based on Deep Reinforcement Learning based on the deep reinforcement learning architecture of the present invention, the research object is polar orbit constellation networking, such as figure 1 As shown, according to the periodicity and predictability of satellite constellation operation, the topology strategy of "combination of dynamic and static" is adopted. The virtual node (VN) strategy is adopted in the low-orbit satellite network topology to transform the dynamic satellite network topology into a static topology based on virtual nodes. Any virtual satellite node is actually served by a physical satellite closest to it. When the physical satellite moves away from the virtual node due to relative motion with the ground, its stored routing table information and...

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 a low-orbit satellite routing strategy method based on a deep reinforcement learning architecture, and belongs to the field of wireless communication. Firstly, an iridium constellation network is established, and a deep reinforcement learning framework is established in combination with a Markov decision process; and for a certain satellite node A, a HELLO packet is periodically sent to a neighbor node, and an adjacent node communicated with the link state of the current node A is searched, a next hop node of a current node is obtained by inputting a destination node coordinate, a link state of the current node and a link state of a neighbor node into a deep reinforcement learning architecture, and a next hop node is continuously obtained in the same way; and when aspecial routing condition (such as open circuit, loop and congestion) occurs, a link state is repeatedly input into the deep reinforcement learning architecture by adopting a corresponding solution strategy until a destination node is reached, and a path planning process is finished. According to the method, the system complexity and the storage overhead are reduced, the effect of detecting the satellite link state in real time is achieved, and satellite routing is more stable and reliable.

Description

technical field [0001] The invention belongs to the field of wireless communication, relates to the technical problem of inter-satellite routing in a low-orbit constellation system, and specifically relates to a low-orbit satellite routing strategy method based on a deep reinforcement learning framework. Background technique [0002] As the infrastructure for future space system information exchange, satellite network has become an important part of the global information network. Low Earth Orbit (LEO) satellites have the advantages of low loss, low delay, wide coverage, short development cycle and low cost, and are more suitable for carrying real-time services. [0003] The low-orbit satellite communication systems that have been launched and networked and are in operation so far include: "Iridium" (Iridium) satellites, "Globalstar" (Globalstar) and "Orbit Communication" (Orbcomm) systems. After years of operation and development, the above low-orbit satellite communicatio...

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
IPC IPC(8): H04W40/18H04L12/705H04L12/751H04B7/185G06N3/04H04L45/02H04L45/18
CPCH04W40/18H04L45/18H04L45/08H04B7/18521G06N3/045
Inventor 王程王慧文徐玭王卫东崔高峰胡欣
Owner BEIJING UNIV OF POSTS & TELECOMM
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