Air-space-ground integrated network intelligent switching method based on DQN
A network-intelligent, open-space technology, applied in neural learning methods, biological neural network models, electrical components, etc., can solve problems such as small state sets, difficult solutions, and high overhead, and achieve the goal of avoiding storage space and improving accuracy Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0221] Example:
[0222] The present invention is based on the deep reinforcement learning DQN switching method, which reduces the switching rate and switching signaling overhead, and improves the average return utility. like image 3 The simulation scenario shown is a satellite-ground fusion network composed of one GEO satellite and three ground stations. The simulation parameters are set as follows: the GEO satellite beam range is 1500km, the ground station cell coverage radius is 2km, and the GEO beam completely covers the three ground stations. , the three ground stations have overlapping coverage, the satellite-ground link is a Markov two-state model, the satellite elevation angle is 20 degrees, the decision interval is 1s, the step size is 1s, the user speed varies between 1 and 50m / s, and the setting is 16.67 m / s (about 60km / h) is the speed threshold.
[0223] like Figure 4 and Figure 5 Shown are the random test results of ten paths when the speed is v=15m / s, the ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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