Internet of vehicles node forwarding utility learning method based on double-update strategy
A node forwarding and learning method technology, which is applied in the direction of specific environment-based services, machine learning, and vehicle components, can solve the problems of sparse node distribution, rapid network topology changes, and difficulty in promoting the Internet of Vehicles, and achieve the goal of improving transmission performance Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment 1
[0067] according to Figure 3 to Figure 10 As shown, the present invention provides a kind of vehicle networking node forwarding utility learning method based on double updating strategy, a kind of vehicle networking node forwarding utility learning method based on double updating strategy, comprises the following steps:
[0068] Step 1: Based on the information update during the information interaction process between vehicle nodes, determine the basic elements in the learning process;
[0069] The step 1 is specifically:
[0070] Determine the basic elements needed in the learning process, the elements include: environment, agent, state space, action space and immediate return; define node update information table, the node update information table includes node contact information table and node state- action value table;
[0071] The environment provides the required information for the entire vehicular opportunistic network in the city as the data packets are forwarded ...
specific Embodiment 2
[0115] attached image 3 Shown is the overall framework of the forwarding utility learning model design process in the present invention. Node opportunistic contact is the premise of on-board opportunistic network packet forwarding, and also a necessary condition for node forwarding utility update. Node contact can update the contact freshness coefficient and contact probability between node pairs, and the contact freshness coefficient can be used to dynamically adjust the freshness of node contact probability; the key components of the update formula of the forwarding utility learning model include node contact probability, immediate Reward function and dynamic discount factor; the learning process of forwarding utility mainly includes the use of Q learning strategy to realize the learning of data packets in the process of transmitting data packets between nodes in the vehicle-mounted opportunistic network and the learning in the process of node contact, using the forwarding ...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com