20230106706. GENERATIVE ADVERSARIAL NETWORKS (GANs) BASED IDENTIFICATION OF AN EDGE SERVER simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

GENERATIVE ADVERSARIAL NETWORKS (GANs) BASED IDENTIFICATION OF AN EDGE SERVER

Organization Name

International Business Machines Corporation

Inventor(s)

Mari Abe Fukuda of Tokyo (JP)

Yasutaka Nishimura of Yamato-shi (JP)

Shoichiro Watanabe of Tokyo (JP)

Kenichi Takasaki of Tokyo (JP)

Sanehiro Furuichi of Tokyo (JP)

GENERATIVE ADVERSARIAL NETWORKS (GANs) BASED IDENTIFICATION OF AN EDGE SERVER - A simplified explanation of the abstract

This abstract first appeared for US patent application 20230106706 titled 'GENERATIVE ADVERSARIAL NETWORKS (GANs) BASED IDENTIFICATION OF AN EDGE SERVER

Simplified Explanation

The abstract describes a technique for using generative adversarial networks (GANs) to identify and group edge servers. The method involves training a global discriminator with common data at the first edge server. The global discriminator is used to determine imbalanced area data. Then, a local discriminator is trained with the area data to generate a result. The local discriminator from a second edge server is also trained with the same area data to generate another result. By comparing the results, it is determined that the first and second edge servers are proximate, and they are added to an edge server group list. Additionally, the application model and configuration can be updated from either server, and the application can be executed.

  • Technique for identifying and grouping edge servers using generative adversarial networks (GANs)
  • Global discriminator trained with common data at the first edge server
  • Imbalanced area data detected using the global discriminator
  • Local discriminator trained with area data to generate a result at the first edge server
  • Local discriminator from a second edge server trained with the same area data to generate another result
  • Comparison of results indicates proximity between the first and second edge servers
  • First and second edge servers added to an edge server group list
  • Application model and configuration can be updated from either server
  • Application can be executed using the updated model and configuration

Potential Applications

This technology can be applied in various scenarios where edge servers need to be identified and grouped. Some potential applications include:

  • Edge computing networks: The technique can be used to efficiently organize and manage edge servers in a distributed computing network.
  • Internet of Things (IoT): Identifying and grouping edge servers can enhance the performance and scalability of IoT systems by optimizing data processing and storage.
  • Content delivery networks: The technology can be utilized to improve the delivery of content by grouping edge servers based on their proximity to users.

Problems Solved

The technique addresses the following problems:

  • Identifying edge servers: It provides a method for accurately identifying and categorizing edge servers in a network.
  • Imbalanced area data: The technique detects imbalanced data in specific areas, allowing for targeted training and optimization of local discriminators.
  • Proximity determination: By comparing the results of local discriminators, the technique can determine the proximity between different edge servers.

Benefits

The use of this technique offers several benefits:

  • Efficient edge server management: By grouping edge servers based on proximity, resources can be allocated more effectively, leading to improved performance and reduced latency.
  • Enhanced scalability: The ability to identify and categorize edge servers enables better scalability in distributed computing environments.
  • Optimized application execution: Updating application models and configurations from edge servers allows for real-time optimization and adaptation to changing conditions.


Original Abstract Submitted

provided are techniques for a generative adversarial networks (gans) based identification of an edge server. at a first edge server, a global discriminator that has been trained with common data is received. it is determined that area data is imbalanced using the global discriminator. a local discriminator is trained with the area data to generate a first result. an exchanged local discriminator from a second edge server is trained with the area data to generate a second result. the first result and the second result indicate that the first edge server and the second edge server are proximate. the first edge server and the second edge server are added to an edge server group list. at least one of an application model and a configuration of an application is updated from one of the first edge server and the second edge server, and the application is executed.

Retrieved from "http://wikipatents.org/index.php?title=20230106706._GENERATIVE_ADVERSARIAL_NETWORKS_(GANs)_BASED_IDENTIFICATION_OF_AN_EDGE_SERVER_simplified_abstract_(International_Business_Machines_Corporation)&oldid=21248"