AI RAN Slice Management for Mobile Handover QoS

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing communication technologies fail to maintain Quality of Service (QoS) for mobile device users during handovers and are affected by spectrum availability and network performance changes due to congestion, software issues, and carrier hardware failure.

Innovation Solution

Implementing AI/ML models in a RAN Intelligent Controller (RIC) to determine and configure network slices for mobile devices based on traffic information, ensuring seamless QoS by adjusting cell sites, bands, and Carrier Aggregation (CA) to balance load and predict application usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional handover mechanisms are used, then network coverage is maintained, but Quality of Service (QoS) is not maintained

Engineering Contradiction:

ImproveQoS maintenanceVSAvoidQoS adaptation to changing conditions

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary actions by predicting future network conditions and pre-configuring network slices before actual handover events occur. The AI/ML models analyze historical data and traffic patterns to anticipate quality degradation and proactively adjust network parameters, ensuring QoS is maintained without waiting for degradation to manifest.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where AI/ML models continuously monitor network performance metrics, traffic patterns, and user experience data. This feedback loop enables the system to learn from actual QoS outcomes and refine future predictions and configurations, creating a self-improving system that adapts to changing network conditions.

Inventive Principle:

Principle #23Feedback

2Productivity

If network resources are allocated statically, then configuration simplicity is maintained, but network performance deteriorates under congestion and changing conditions

Engineering Contradiction:

Improvenetwork performanceVSAvoiddynamic configuration complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system transitions from static resource allocation to dynamic configuration where network slices are continuously adjusted based on real-time conditions. The AI/ML models enable dynamic decision-making for resource allocation, handover timing, and parameter optimization, allowing the network to adapt its configuration to current traffic patterns, congestion levels, and user requirements.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes network parameters dynamically including bandwidth allocation, latency thresholds, priority levels, and resource reservation settings. The AI/ML models analyze multiple parameters simultaneously and adjust them in coordinated ways to optimize overall network performance while managing the complexity through automated decision-making frameworks.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If reactive network management is used, then operational simplicity is maintained, but user experience deteriorates during handovers and network changes

Engineering Contradiction:

Improvenetwork management simplicityVSAvoiduser experience consistency

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary analysis and configuration actions before handover events occur. AI/ML models predict potential quality degradation and pre-configure network slices, so when handover is needed, the network is already optimized for the transition, eliminating user experience disruptions without requiring complex manual intervention.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service network management where AI/ML models automatically monitor, analyze, and adjust network conditions without human intervention. The system self-optimizes resource allocation, detects anomalies, and executes corrective actions autonomously, maintaining ease of operation while significantly improving user experience consistency during dynamic network conditions.

Inventive Principle:

Principle #25Self-service

4Reliability

If AI/ML models are implemented for predictive slice management, then QoS consistency is improved, but system complexity increases

Engineering Contradiction:

ImproveQoS consistencyVSAvoidRIC and AI/ML integration complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the AI/ML functionality into separate, modular components within the RIC architecture. The predictive analytics, slice configuration, and network optimization functions are divided into distinct modules that can be independently developed, deployed, and maintained. This segmentation reduces overall system complexity by allowing specialized teams to work on specific AI/ML components without affecting the entire network management system.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250294406A1Traffic balancing for moving users, proactive slice management, and predictive slice management using artificial intelligence

Publication Date: 2025.09.18 BOOST SUBSCRIBERCO LLC

AI summary

Traffic balancing for moving users, proactive slice management, and predictive slice management using Artificial Intelligence (AI) are disclosed. Radio Access Networks (RANs) are adjusted based on predicted data usage for moving users based on the applications they are running using AI/machine learning (ML) models. Load balancing is performed when new users move into a coverage area. Predictive slice management is performed to allocate bandwidth to users for a period of time based on predicted application usage.