Handover Target Determination Using Neural Networks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Network densification in 5G cellular networks increases handover complexity, leading to potential delays that negate the benefits of improved network capacity, necessitating a method to efficiently determine handover targets.

Innovation Solution

A method and device utilizing machine learning and AI to process handover calculations by receiving measurement reports from user equipment, generating and updating handover priority lists based on signal references, handover parameters, and neighborhood information, with a Recursive Neural Network or Deep Recursive Neural Network model to optimize handover decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If network densification is implemented to increase network capacity, then network capacity is improved, but handover complexity increases leading to delays

Engineering Contradiction:

Improvenetwork capacityVSAvoidhandover delay

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the network to automatically optimize handover decisions through machine learning models that continuously learn from historical handover data and measurement reports, eliminating the need for manual configuration and adaptation while handling the increased handover complexity in dense networks

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent applies parameter changes by dynamically adjusting handover parameters such as threshold offsets, hysteresis values, and priority weights based on learned patterns from the neural network model, allowing the system to adapt to varying network conditions and optimize handover timing to reduce delays

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If traditional handover methods are used in dense networks, then implementation is simple, but handover delays neutralize network densification gains

Engineering Contradiction:

Improvehandover processing complexityVSAvoidhandover delay

Core Design Contradiction:

Device complexityVSLoss of time

Solution Approach 1:

The patent replaces traditional mechanical handover decision-making systems with an intelligent system based on neural networks and machine learning algorithms. The system processes measurement reports and neighborhood information through trained models to predict optimal handover targets, substituting rule-based mechanisms with data-driven intelligence to reduce processing delays

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Speed

If machine learning models are implemented to optimize handover decisions, then handover speed is improved, but system complexity increases

Engineering Contradiction:

Improvehandover processing speedVSAvoidsystem complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The system applies preliminary action by pre-training machine learning models offline using historical handover data and measurement reports before deployment. The trained models are then deployed in the network to make real-time handover decisions, separating the complex training process from the real-time operation to achieve fast processing without adding operational complexity

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20230189086A1Method and device for determining handover target

Publication Date: 2023.06.15 LITE ON TECH CORP

AI summary

A method for determining a handover target is provided. The method includes receiving a measurement report transmitted by a user equipment (UE). The method includes obtaining a handover priority list according to the measurement report. The method includes instructing the UE to execute a handover procedure according to the handover priority list and obtaining a handover result. The method includes obtaining handover parameters according to the handover result. The method includes training a handover model according to the measurement report, the handover parameters and neighborhood information to update the handover priority list.