18250120. QoS AWARE REINFORCEMENT LEARNING PREVENTION INTRUSION SYSTEM simplified abstract (Telefonaktiebolaget LM Ericsson (publ))
QoS AWARE REINFORCEMENT LEARNING PREVENTION INTRUSION SYSTEM
Organization Name
Telefonaktiebolaget LM Ericsson (publ)
Inventor(s)
Amine Boukhtouta of Laval (CA)
Hyame Alameddine of Montreal (CA)
Christian Miranda Moreira of Montreal (CA)
QoS AWARE REINFORCEMENT LEARNING PREVENTION INTRUSION SYSTEM - A simplified explanation of the abstract
This abstract first appeared for US patent application 18250120 titled 'QoS AWARE REINFORCEMENT LEARNING PREVENTION INTRUSION SYSTEM
Simplified Explanation
The patent application describes a network node that is designed to perform network routing for multiple wireless devices in a communication system. The network node collects information about the network topology and uses self-learning techniques to determine actions for updating network routes. These actions are then transmitted to a controller, which instructs the wireless devices to update their network routes accordingly.
- The network node collects graph states associated with multiple graphs, where each graph represents the network topology and has nodes associated with wireless devices.
- Using self-learning techniques, the network node determines actions to update network routes in the graphs based on the collected graph states.
- The determined actions are transmitted to a controller, which then instructs the wireless devices to update their network routes based on the actions.
Potential Applications
- This technology can be applied in various communication systems that involve multiple wireless devices, such as cellular networks, IoT networks, and wireless sensor networks.
- It can be used to optimize network routing and improve the overall performance and efficiency of the communication system.
Problems Solved
- Traditional network routing algorithms may not be able to adapt to dynamic changes in the network topology and may result in suboptimal routing decisions.
- This technology solves the problem of inefficient network routing by using self-learning techniques to update network routes based on real-time information about the network topology.
Benefits
- The use of self-learning techniques allows for adaptive and efficient network routing, improving the overall performance and reliability of the communication system.
- By updating network routes based on real-time information, this technology can optimize the utilization of network resources and reduce network congestion.
- The ability to collect and analyze graph states associated with multiple graphs enables a more comprehensive understanding of the network topology, leading to better routing decisions.
Original Abstract Submitted
Methods, systems, and apparatuses are disclosed. A network node configured for performing network routing associated with a plurality of wireless devices, WDs, in a communication system is described. The network node includes processing circuit configured to collect, from a control plane, a plurality of graph states associated with a plurality of graphs. Each graph of the plurality of graphs has at least one graph node associated with one WD of the plurality of WDs. At least one action is determined, using self-learning, to update at least one route in at least one graph of the plurality of graphs based on the collected plurality of graphs states. The at least one action is transmitted to a controller for instructing at least one WD to update at least one network route based on the at least one action.
