ML-Based Network Slice Node Selection for Energy-Efficient Slicing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Network slicing lacks energy-efficient solutions, leading to increased energy consumption in telecommunications infrastructure, and there is a need for efficient utilization of renewable energy sources in network infrastructure.

Innovation Solution

An intelligent network entity uses a machine learning model to generate a list of network nodes that can fulfill specific criteria for creating a network slice, prioritizing nodes with renewable energy sources, by analyzing current and historical data from network nodes, and providing a ranked list to the network service provider.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If network slicing is implemented to provide customized networks, then service differentiation is enhanced, but energy consumption of the underlying infrastructure increases

Engineering Contradiction:
Improveservice differentiationVSAvoidenergy consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by pre-identifying and ranking network nodes based on their renewable energy usage and capability to fulfill slice requirements before actual slice deployment. The intelligent network entity proactively evaluates multiple network nodes and creates a ranked list, allowing the network service provider to select pre-qualified nodes that optimize energy efficiency while meeting service differentiation requirements.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the network service provider manually evaluates all network nodes for slice creation, then selection accuracy is improved, but processing overhead and time consumption increase

Engineering Contradiction:
Improveselection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The intelligent network entity acts as an intermediary between the network service provider and the network nodes. It receives slice requirement criteria from the provider, evaluates multiple network nodes against these criteria, and returns a ranked list of suitable nodes. This intermediary approach maintains high selection accuracy by systematically evaluating node capabilities while significantly reducing processing time and overhead at the provider end.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The intelligent network entity performs preliminary evaluation and ranking of network nodes before the final selection is made by the network service provider. By pre-processing the evaluation of multiple nodes against the given criteria and presenting them in a ranked order, the system enables the provider to make informed decisions quickly without manually analyzing each node from scratch.

Inventive Principle:
Principle #10Preliminary action

3Object-affected harmful factors

If renewable energy sources are integrated into the network infrastructure, then carbon footprint is reduced, but complexity of energy management increases

Engineering Contradiction:
Improvecarbon footprintVSAvoidenergy management complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The intelligent network entity autonomously manages the complexity of renewable energy integration by automatically evaluating network nodes based on their renewable energy usage, generating ranked lists, and presenting recommendations to the network service provider. This self-service approach handles the complexity of energy management internally while presenting simplified outputs to the provider, thereby reducing the carbon footprint without proportionally increasing visible system complexity.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4694287A1Network slice creation
Publication Date: 2026.02.11 VODAFONE GROUP SERVICES LTD
  • EP4694287A1 patent drawingFigure 1
  • EP4694287A1 patent drawingFigure 2
  • EP4694287A1 patent drawing

AI summary

The present disclosure provides a method for use in creating a Network Slice in a telecommunications network. The method comprises receiving information from a plurality of network nodes with which the Network Slice can be realised. In response to a request received at the intelligent network entity containing one or more criteria for the Network Slice, a list of one or more network nodes is generated using a machine learning model and the received information, wherein the list indicates a level of confidence that each of the one or more network nodes can fulfil the one or more criteria. The list is provided to a Network Service Provider, NSP, such that the NSP can identify, based on the level of confidence of each one or more network nodes in the list, whether there are suitable network nodes in the telecommunications network for creating the Network Slice.