20240039788. DEEP REINFORCEMENT LEARNING FOR ADAPTIVE NETWORK SLICING IN 5G FOR INTELLIGENT VEHICULAR SYSTEMS AND SMART CITIES simplified abstract (University of South Florida)

From WikiPatents
Jump to navigation Jump to search

DEEP REINFORCEMENT LEARNING FOR ADAPTIVE NETWORK SLICING IN 5G FOR INTELLIGENT VEHICULAR SYSTEMS AND SMART CITIES

Organization Name

University of South Florida

Inventor(s)

Almuthanna Nassar of Tampa FL (US)

Yasin Yilmaz of Tampa FL (US)

DEEP REINFORCEMENT LEARNING FOR ADAPTIVE NETWORK SLICING IN 5G FOR INTELLIGENT VEHICULAR SYSTEMS AND SMART CITIES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240039788 titled 'DEEP REINFORCEMENT LEARNING FOR ADAPTIVE NETWORK SLICING IN 5G FOR INTELLIGENT VEHICULAR SYSTEMS AND SMART CITIES

Simplified Explanation

The patent application describes systems and methods for processing service requests within a network environment using fog nodes. Here is a simplified explanation of the abstract:

  • The system includes a cluster of fog nodes that execute service tasks.
  • The cluster consists of a primary fog node and nearest neighbor fog nodes.
  • The primary fog node receives a service request from the network.
  • It determines the resource data required to serve the request, including the quantity of resource blocks and hold time.
  • An edge controller, connected to the network and the cluster, receives the resource data from the primary fog node.
  • The edge controller identifies available resources at the nearest neighbor fog nodes and the primary fog node.
  • It uses deep reinforcement learning algorithms to determine if resource blocks are available to fulfill the service request.
  • If the request is rejected, the edge controller refers it to a cloud computing system for execution.

Potential applications of this technology:

  • Efficient processing of service requests within a network environment.
  • Improved resource allocation and utilization in fog computing systems.
  • Enhanced decision-making capabilities for edge controllers.

Problems solved by this technology:

  • Optimizing resource allocation in fog computing systems.
  • Reducing latency by processing service requests locally.
  • Improving overall system performance and efficiency.

Benefits of this technology:

  • Faster response times for service requests.
  • Reduced reliance on cloud computing systems.
  • Enhanced scalability and flexibility in network environments.


Original Abstract Submitted

systems and methods for processing a service request within a network environment can include a first cluster of fog nodes that execute service tasks. the cluster can include a primary fog node and nearest neighbor fog nodes. the primary fog node can receive, from the network, a service request, determine service request resource data that includes a first time, quantity of resource blocks required to serve the request, and a hold time required to serve the request locally. an edge controller, connected to the network and the first cluster, can receive, from the primary fog node, the service request resource data, identify available resources at the nearest neighbor fog nodes and the primary fog node, and determine whether resource blocks are available to fulfill the service request using deep reinforcement learning algorithms. the edge controller can also refer a rejected service request to a cloud computing system for execution.

Retrieved from "http://wikipatents.org/index.php?title=20240039788._DEEP_REINFORCEMENT_LEARNING_FOR_ADAPTIVE_NETWORK_SLICING_IN_5G_FOR_INTELLIGENT_VEHICULAR_SYSTEMS_AND_SMART_CITIES_simplified_abstract_(University_of_South_Florida)&oldid=31005"