Base Station AI Configuration for Adaptive Handover Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing mobile communication systems face challenges in optimizing various key performance indicators (KPIs) such as delay, reliability, connection density, and energy efficiency across different communication states due to limited application of AI/ML in use cases beyond network energy saving and load balancing.

Innovation Solution

A communication system incorporating AI/ML to enable a base station to determine optimal configurations for communication terminals based on training data from connected terminals and neighboring stations, allowing terminals to switch configurations dynamically for effective processing in varying states.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Use of energy by moving object

If AI/ML is applied only to network energy saving and load balancing, then energy efficiency and load distribution are improved, but other key performance indicators such as delay, reliability, and connection density cannot be optimized

Engineering Contradiction:
Improveenergy efficiencyVSAvoidapplication scope of AI/ML
Core Design Contradiction:
Use of energy by moving objectVSAdaptability or versatility

Solution Approach 1:

The patent extends AI/ML application beyond energy saving and load balancing to cover multiple communication states including RRC connection establishment, handover, and data transmission. The base station uses AI/ML models to determine optimal configurations for various KPIs (delay, reliability, connection density) across different communication scenarios, making the system multi-functional in its AI/ML applications.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements dynamic configuration adjustment based on communication states. The base station determines AI/ML-based configurations adaptively for different scenarios (RRC setup, handover, data transmission) and the terminal switches configurations dynamically according to current communication state, enabling optimization of multiple KPIs across varying operational conditions.

Inventive Principle:
Principle #15Dynamics

2Productivity

If the base station determines configuration using AI/ML model trained on data from multiple sources, then communication processing effectiveness is improved, but system complexity increases

Engineering Contradiction:
Improvecommunication processing effectivenessVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces an AI/ML model as an intermediary between raw communication data and configuration decisions. The base station collects data from multiple sources (connected terminals, neighboring base stations), processes it through the AI/ML model to generate optimized configurations, and applies these configurations. This intermediary structure systematizes the complexity while maintaining effectiveness.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent employs pre-trained AI/ML models that are prepared in advance with training data from multiple sources. The model is trained beforehand to recognize patterns and determine optimal configurations, so when actual communication events occur (RRC establishment, handover, data transmission), the base station can quickly apply pre-computed configurations without real-time complex calculations, reducing operational complexity.

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If the communication terminal switches configurations dynamically for different base stations, then adaptability to varying communication states is improved, but processing overhead increases

Engineering Contradiction:
Improveconfiguration adaptabilityVSAvoidprocessing overhead
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent enables the communication terminal to dynamically switch between different AI/ML-based configurations determined for different base stations. The terminal receives configurations from serving and neighboring base stations and selectively applies them based on current communication state (which base station is being served, handover status), achieving high adaptability while managing processing through state-based decision rules.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4723718A1Communication system, base station, and communication terminal
Publication Date: 2026.04.08 MITSUBISHI ELECTRIC CORP
  • EP4723718A1 patent drawingFigure 1
  • EP4723718A1 patent drawingFigure 2
  • EP4723718A1 patent drawingFigure 3

AI summary

A communication system includes a base station and a communication terminal configured to establish connection to the base station, the base station being configured to, using a model on which training using pieces of information acquired from the communication terminal already connected to the base station and another neighboring base station has been performed, determine a configuration to be used in communication processing performed by the communication terminal and notify the communication terminal of the determined configuration determined, and the communication terminal notified of the configuration by a first base station, which is the base station having determined the configuration, being configured to use the configuration to perform communication processing on the first base station or communication processing on a second base station.