18399314. DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE simplified abstract (Intel Corporation)
Contents
- 1 DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE
Organization Name
Inventor(s)
Dawei Ying of Hillsboro OR (US)
DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE - A simplified explanation of the abstract
This abstract first appeared for US patent application 18399314 titled 'DATA-CENTRIC SERVICE-BASED NETWORK ARCHITECTURE
Simplified Explanation
The data-centric network architecture and non-Real-Time RAN Intelligence Controller (RIC) described in the patent application provide a shared database for control functions, user functions, and management functions in a network. The non-RT RIC manages functions via rApps, performs conflict mitigation and security functions, monitors machine learning performance, and provides a ML model catalog.
- Data-centric network architecture with data plane functions serving as a shared database for control, user, and management functions.
- Non-RT RIC managing functions via rApps, performing conflict mitigation, security functions, and monitoring machine learning performance.
- ML training host training and evaluating ML models, obtaining data from the database, and retraining ML models.
Potential Applications
This technology could be applied in telecommunications networks, specifically in the management and optimization of data plane resources.
Problems Solved
This technology helps in efficiently managing and optimizing data plane resources in a network, improving overall network performance and reliability.
Benefits
The benefits of this technology include enhanced network performance, improved resource management, and increased reliability in telecommunications networks.
Potential Commercial Applications
Potential commercial applications of this technology include telecommunications companies looking to optimize their network resources and improve overall network performance.
Possible Prior Art
One possible prior art could be the use of data-centric network architectures in other industries such as cloud computing or data centers.
Unanswered Questions
How does the non-RT RIC handle security functions in the network?
The abstract mentions that the non-RT RIC performs security functions, but it does not provide specific details on how these functions are implemented.
What types of machine learning models are included in the ML model catalog?
The abstract mentions a ML model catalog, but it does not specify the types of machine learning models that are included in this catalog.
Original Abstract Submitted
A data-centric network and non-Real-Time (RT) RAN Intelligence Controller (RIC) architecture are described. The data-centric network architecture provides data plane functions (DPFs) that serve as a shared database for control functions, user functions and management functions for data plane resources in a network. The DPFs interact with control plane functions, user plane functions, management plane functions, compute plane functions, network exposure functions, and application functions of the NR network via a service interface. The non-RT RIC provides functions via rApps, manages the rApps, performs conflict mitigation and security functions, monitors machine learning (ML) performance, provides a ML model catalog that contains ML model information, provides interface terminations and stores ML data and Near-RT RIC related information in a database. An ML training host trains and evaluates ML models in the catalog, obtains training and testing data from the database, and retrains and updates the ML models.