Self-Adaptive Computation Management in Edge Cloud

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing computation management solutions in edge environments are inadequate due to their reliance on static objective functions and predefined strategies, failing to consider the dynamic nature of cloud, edge, and IoT devices, leading to poor performance and quality of service.

Innovation Solution

A self-adaptive architecture for computation management in edge cloud domains that dynamically selects and adapts strategies based on real-time status of cloud and edge systems, using a computation management system comprising a computation analyzer, discovery engine, computation manager, and computation agent to generate adaptive management strategies through reinforcement learning and Markov Decision Processes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If static objective functions and predefined strategies are used for computation management, then the system structure is simple and easy to implement, but the system cannot adapt to dynamic conditions leading to poor performance and quality of service

Engineering Contradiction:

Improveadaptability to dynamic conditionsVSAvoidsystem structure complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic computation management strategies that adapt to changing network conditions, task characteristics, and resource availability. The system transitions from static predefined strategies to dynamic decision-making processes that continuously adjust based on real-time status of cloud, edge, and IoT devices, thereby resolving the contradiction between adaptability and complexity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where computation management decisions are continuously refined based on performance outcomes and changing conditions. The management system receives feedback about network stability, resource status, and task completion, then adjusts strategies accordingly, enabling adaptability while maintaining manageable complexity through learned patterns.

Inventive Principle:

Principle #23Feedback

2Reliability

If computation management decisions consider multiple factors such as task characteristics, network conditions, and platform differences, then the quality of service improves, but the decision-making complexity increases

Engineering Contradiction:

Improvequality of serviceVSAvoiddecision-making complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the computation management system into distinct functional components: computation analyzer for assessing conditions, discovery engine for gathering information, computation manager for decision-making, and computation agent for execution. This segmentation allows each component to handle specific factors independently, improving quality of service while managing overall decision-making complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary components that mediate between multiple factors and final decisions. The computation manager acts as an intermediary that synthesizes information about task characteristics, network conditions, and platform differences, then translates this complex information into actionable computation offloading decisions, thereby improving service quality while managing complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Use of energy by moving object

If computation offloading is performed in unstable network conditions, then energy consumption is reduced, but the reliability of computation completion deteriorates

Engineering Contradiction:

Improveenergy consumptionVSAvoidcomputation completion reliability

Core Design Contradiction:

Use of energy by moving objectVSReliability

Solution Approach 1:

The patent dynamically changes the parameter of computation offloading decisions based on network condition parameters. When network stability parameters indicate poor conditions, the system adjusts the offloading decision parameter to execute locally despite higher energy consumption, thereby maintaining computation completion reliability. When network conditions improve, the system changes parameters to enable offloading for energy savings, resolving the contradiction between energy efficiency and reliability.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250023943A1An architecture for self-adaptive computation management in edge cloud

Publication Date: 2025.01.16 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

Methods and systems are described for computation management of requests in edge cloud domains. A user equipment can send a computation management request. The network can determine the criteria for completing the computation management request, determine static and dynamic status of network resources, assess historical data on performance success and failure and use all of these factors to assign a network resource to respond to the computation management request.