MEC Application Pre-Emption for Resource-Constrained 5G Edge Hosts

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The impracticality of dimensioning MEC hosts with sufficient resources to run all possible applications due to increasing application demands, necessitating careful resource management to ensure desired applications are available at a particular MEC host location when resources are constrained.

Innovation Solution

A mechanism is defined to provide the MEC orchestrator with information to select which existing application instances should be pre-empted to free up resources for new application instantiations, involving either removing or changing the operational state of applications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If MEC hosts are dimensioned with sufficient resources to run all possible applications, then application availability is improved, but resource cost and device complexity increase significantly

Engineering Contradiction:
Improveapplication availabilityVSAvoidhost resource capacity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic resource allocation where MEC hosts adjust their application portfolio based on real-time resource availability and demand. The orchestrator dynamically selects which applications to instantiate or terminate, allowing the system to adapt its capacity rather than maintaining static over-provisioned resources for all possible applications simultaneously

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary actions by pre-selecting candidate applications for instantiation based on predicted demand and resource availability. The orchestrator proactively manages the application portfolio by identifying which applications should be instantiated in advance, rather than reacting only when resources are exhausted

Inventive Principle:
Principle #10Preliminary action

2Loss of energy

If application instances are located only where necessary, then resource usage is optimized, but system complexity and management difficulty increase

Engineering Contradiction:
Improveresource usage efficiencyVSAvoidapplication management complexity
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The patent implements self-service mechanisms where the orchestrator autonomously monitors resource levels and automatically makes instantiation decisions without manual intervention. The system self-manages the complex task of selecting which applications to deploy based on predefined policies and real-time conditions, reducing the operational burden while maintaining optimization

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system employs feedback loops where the orchestrator continuously monitors resource availability, application performance, and demand signals. This feedback drives automatic adjustments in application instantiation decisions, allowing the system to optimize resource usage dynamically while managing complexity through closed-loop control rather than static configurations

Inventive Principle:
Principle #23Feedback

3Quantity of substance

If existing applications are pre-empted to free up resources for new instances, then resource availability for new applications is improved, but service continuity and reliability of existing applications deteriorate

Engineering Contradiction:
Improveavailable resourcesVSAvoidapplication service continuity
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent changes the parameter of application priority dynamically. The orchestrator adjusts the priority status of applications based on current resource conditions, service level agreements, and demand urgency. This allows the system to legitimately pre-empt lower-priority applications while protecting critical services, making the pre-emption mechanism more reliable and predictable rather than arbitrary

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12625726B2Method and apparatus for improving a multi-access edge computing (MEC) network
Publication Date: 2026.05.12 SAMSUNG ELECTRONICS CO LTD
  • US12625726B2 patent drawing
  • US12625726B2 patent drawing
  • US12625726B2 patent drawing

AI summary

The present disclosure relates to a communication method and system for converging a 5th-Generation (5G) communication system for supporting higher data rates beyond a 4th-Generation (4G) system with a technology for Internet of Things (IoT). The present disclosure may be applied to intelligent services based on the 5G communication technology and the IoT-related technology, such as smart home, smart building, smart city, smart car, connected car, health care, digital education, smart retail, security and safety services. Disclosed is a method of operating a MEC system, comprising the step of instantiating a first application in the MEC system, which comprises the step of a first entity transmitting an application instantiation request to a second entity, wherein the application instantiation request comprises pre-emption information concerning the first application, such that the pre-emption information may be used to pre-empt the first application in the future, if required.