O-RAN Non-RT RIC AI Resource Allocation for Slice Subnets

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current 5G networks face challenges in dynamically and efficiently allocating resources among multiple network nodes to support diverse services with varying requirements, such as eMBB, URLLC, and mMTC, due to sporadic network traffic patterns and differing usage patterns in time, location, and types of applications.

Innovation Solution

The implementation of an AI/ML model-based resource allocation optimization system within the O-RAN Non-Real Time RIC, which monitors performance metrics, trains on historical data, predicts traffic demand, and automatically reallocates network resources across network slice subnet instances to optimize resource usage based on service requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If network resources are statically allocated to network slice subnet instances, then device complexity is reduced and ease of operation is improved, but adaptability to varying traffic demands deteriorates and resource utilization efficiency decreases

Engineering Contradiction:

Improveresource allocation managementVSAvoidtraffic demand adaptation

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic resource allocation by enabling network slice subnet instances to be activated and deactivated based on real-time traffic conditions. The system transitions from static configuration to dynamic adjustment, where resource allocation changes automatically in response to varying traffic demands, service requirements, and network conditions, thereby resolving the contradiction between operational simplicity and adaptability.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the operational state parameter of network slice subnet instances between activated and deactivated states. By dynamically adjusting this parameter based on traffic patterns and service requirements, the system achieves both ease of operation through automated management and adaptability to changing conditions, eliminating the need for manual reconfiguration while maintaining flexibility.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If multiple network slice subnet instances are maintained in active state, then service availability and reliability are improved, but resource consumption and operational costs increase

Engineering Contradiction:

Improveservice availabilityVSAvoidnetwork resource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary configuration of network slice subnet instances, keeping them in a deactivated state until needed. By preparing instances in advance but activating them only when traffic conditions and service requirements dictate, the system ensures service availability when needed while minimizing resource consumption during periods of low or no demand, thus resolving the contradiction between reliability and energy usage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service mechanisms where network slice subnet instances are automatically activated or deactivated based on monitored traffic conditions and service requirements, without requiring continuous manual intervention. This automated resource management maintains service availability through on-demand activation while reducing overall resource consumption by keeping unused instances deactivated.

Inventive Principle:

Principle #25Self-service

3Manufacturing precision

If manual configuration and management of network slice subnet instances is performed, then resource allocation precision is improved, but productivity and response time to traffic changes deteriorate

Engineering Contradiction:

Improveresource allocation accuracyVSAvoidresource allocation speed

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The system implements feedback mechanisms that continuously monitor traffic conditions, service requirements, and resource utilization metrics. Based on this real-time feedback, the system automatically adjusts the activation state of network slice subnet instances, achieving both precise resource allocation accuracy and high productivity through automated decision-making that responds rapidly to changing conditions without manual intervention.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system introduces an automated resource management intermediary that mediates between traffic conditions and resource allocation decisions. This intermediary layer processes traffic data, evaluates service requirements, and makes activation/deactivation decisions, thereby maintaining allocation precision while dramatically improving response speed and productivity compared to manual configuration processes.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11917527B2Resource allocation and activation/deactivation configuration of open radio access network (O-RAN) network slice subnets

Publication Date: 2024.02.27 INTEL CORP

AI summary

An apparatus for a Non-Real-Time RAN Intelligent Controller (Non-RT RIC) of a Service Management and Orchestration (SMO) entity of an Open Radio Access Network (O-RAN) includes processing circuitry coupled to memory. To configure the Non-RT RIC for allocation of network slice subnet instance (NSSI) resources in the O-RAN, the processing circuitry is to collect performance measurements related to usage of the NSSI resources. An artificial intelligence (AI)/machine learning (ML) model is trained based on the performance measurements. The allocation of the NSSI resources is optimized at a time determined by an inference of the AI/ML model.