MEC Application Logic Distribution for Low-Latency Service Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining which network operations to distribute to mobile edge computing (MEC) nodes are costly, time-consuming, and prone to human error, lacking an intelligent system to optimize cost, resource allocation, and user experience.
Innovation Solution
An automated system using an application recommendation module with machine learning algorithms to dynamically offload application logic to MEC servers, optimizing network resource allocation by processing usage data and user profiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual evaluation methods are used to determine which network operations to distribute to MEC nodes, then operators can make informed decisions about resource allocation, but the process becomes costly and time-consuming
Solution Approach 1:
The patent replaces manual evaluation processes with an automated machine learning system that uses neural networks to analyze usage data and determine optimal MEC node distribution. This substitution of mechanical/manual operations with automated computational systems directly resolves the contradiction by eliminating time-consuming manual evaluation while maintaining or improving decision accuracy through algorithmic analysis of multiple factors simultaneously.
Solution Approach 2:
The system enables self-service by allowing the network to automatically evaluate and distribute operations to MEC nodes without human intervention. The machine learning model continuously analyzes usage data, user profiles, and network conditions to make autonomous decisions about resource allocation, thereby eliminating the time loss associated with manual evaluation while preserving decision quality through automated optimization.
2Measurement precision
If more computational resources are allocated to analyze usage data and user profiles for distribution decisions, then the accuracy of function selection improves, but operating costs increase
Solution Approach 1:
The patent applies partial action by implementing a machine learning system that processes only the most relevant features from usage data and user profiles rather than analyzing all available data comprehensively. This selective approach maintains high function selection accuracy while reducing computational resource consumption and associated operating costs by focusing processing power on the most impactful variables.
Solution Approach 2:
The system dynamically adjusts the complexity of analysis based on network conditions, traffic patterns, and available computational resources. By changing parameters such as the depth of neural network processing, the number of features analyzed, and the frequency of re-evaluation, the system maintains high selection accuracy when resources are abundant while reducing computational overhead during periods of constrained resources, thereby resolving the cost-accuracy trade-off.
3Speed
If network operations are distributed to MEC nodes closer to user equipment, then latency is reduced and user experience improves, but determining optimal distribution becomes complex and costly
Solution Approach 1:
The patent replaces complex manual distribution planning with an automated machine learning system that uses neural networks to optimize the placement of network operations at MEC nodes. This substitution handles the complexity of evaluating multiple factors including user profiles, usage patterns, and network conditions, thereby maintaining high operation execution speed through automated decision-making while managing distribution system complexity through algorithmic optimization rather than manual processes.
Solution Approach 2:
The machine learning model serves as an intermediary between raw network data and distribution decisions. It mediates the complex relationship between usage data, user profiles, and optimal MEC node selection by translating these inputs into actionable distribution recommendations. This intermediary layer simplifies the overall system complexity by encapsulating the decision-making logic in a trained model that can be deployed and executed efficiently.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Techniques for distribution of application logic in digital networks are disclosed. In one embodiment, the techniques may be realized as a method that includes receiving a request from a first device to initiate a service instance associated with a service. The service instance is associated with application logic. The method further includes determining one or more parameters associated with the request, identifying at least a portion of the application logic to distribute to a mobile edge server based on the one or more parameters, and distributing the at least a portion of the application logic to the mobile edge server to cause the mobile edge server to provide the service instance to the first device.