Real-Time Radio Access Network Intelligence Controller for Sub-Millisecond Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The Open Radio Access Network (O-RAN) lacks a real-time RIC (Radio Access Network Intelligence Controller) capable of operating at cell sites with latency less than 1 millisecond, which is essential for efficient and timely decision-making in radio access networks.

Innovation Solution

An artificial intelligence planning method and a real-time radio access network intelligence controller are introduced, utilizing a causal reasoning model to predict input data, generate a current state, and navigate a planning tree to find specific action instructions for controlling the target system, thereby enabling low-latency decision-making and control within the O-RAN architecture.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If non-RT RIC or near-RT RIC is used for control, then the system can operate with existing architecture, but the latency is greater than 1 millisecond which is insufficient for real-time decision-making

Engineering Contradiction:
Improvereal-time control capabilityVSAvoidcontrol latency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the RAN intelligent controller into two parts: non-RT RIC for non-critical control functions and RT RIC for real-time critical functions. This segmentation allows the RT RIC to handle time-sensitive operations with latency less than 1 millisecond while the non-RT RIC handles less time-critical tasks, thus resolving the contradiction between existing architecture compatibility and real-time control requirements

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an RT RIC as an intermediary component between the non-RT RIC and the radio access network elements. This intermediary RT RIC specifically handles real-time control decisions with sub-millisecond latency, bridging the gap between the existing non-RT RIC architecture and the need for ultra-low latency control

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of time

If RT RIC with less than 1 millisecond latency is implemented, then real-time decision-making is enabled, but the device complexity increases

Engineering Contradiction:
Improvecontrol latencyVSAvoidcontroller architecture complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

By segmenting the controller architecture into non-RT RIC and RT RIC components with distinct functional responsibilities, the patent manages complexity through modular design. The RT RIC focuses solely on real-time control with sub-millisecond latency, while the non-RT RIC handles other control functions, making the overall system complexity manageable despite the addition of real-time capabilities

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic resource allocation and adaptive control mechanisms in the RT RIC that allow the system to adjust its operational complexity based on real-time network conditions. This dynamic approach enables sub-millisecond latency performance when needed while avoiding unnecessary complexity during less critical periods

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20230112534A1Artificial intelligence planning method and real-time radio access network intelligence controller
Publication Date: 2023.04.13 WISTRON CORP
  • US20230112534A1 patent drawing
  • US20230112534A1 patent drawing
  • US20230112534A1 patent drawing

AI summary

An artificial intelligence planning method and a real-time radio access network intelligence controller are provided. The method includes: obtaining current input data; predicting a prediction result based on the current input data by using a causal reasoning model; generating a current state at least based on the prediction result; treating the current state as an initial state of an artificial intelligence planner and finding a specific planning path in a planning tree based on the initial state by using the artificial intelligence planner; and controlling a target system based on a plurality of action instructions.