Microservice Latency Budgeting for MEC Edge Deployment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The management of wireless communication networks, particularly with the integration of 5G technologies and Multi-Access Edge Computing (MEC), faces challenges due to limited resources and inefficiencies in deploying microservices, as traditional virtualization methods like virtual machines are costly and complex, and not all microservices require latency reduction.
Innovation Solution
A system and method for determining which microservices to deploy in a Multi-Access Edge Computing (MEC) network based on specific requirements and capabilities, using container-based virtualization to select and deploy microservices that meet latency and computational needs, while considering security and data workflow dependencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional virtualization methods like virtual machines are used to deploy microservices, then service functionality is provided, but resource costs and system complexity increase
Solution Approach 1:
The patent employs container-based virtualization instead of traditional virtual machines, using lightweight, ephemeral containers that can be rapidly created and destroyed. This approach provides the necessary service functionality while significantly reducing resource overhead and system complexity compared to full VM instances.
Solution Approach 2:
The patent segments microservices deployment by selecting only specific microservices that require latency reduction for edge deployment, while other microservices remain in the cloud. This segmentation allows the system to maintain service functionality without the complexity of deploying all services at the edge.
2Loss of time
If all microservices are deployed in MEC network, then latency is reduced, but resource consumption increases
Solution Approach 1:
The patent applies local quality by deploying only those microservices that specifically benefit from low latency at the MEC edge, while leaving other microservices in the cloud. This selective approach ensures latency reduction for time-sensitive services without the resource consumption of deploying all microservices locally.
Solution Approach 2:
The patent implements partial action by deploying a subset of microservices at the edge rather than all microservices. This partial deployment achieves the necessary latency reduction for critical services while avoiding the excessive resource consumption that would result from deploying the entire microservice suite at the edge.
3Productivity
If selective microservice deployment is implemented, then resource usage is optimized, but deployment complexity increases
Solution Approach 1:
The patent implements feedback mechanisms that monitor latency requirements and resource usage to dynamically determine which microservices should be deployed at the edge. This feedback-driven approach optimizes resource efficiency by continuously adapting the deployment selection based on actual performance metrics and changing service requirements.
Solution Approach 2:
The system employs self-service capabilities where the deployment management automatically identifies and deploys appropriate microservices based on predefined criteria and real-time conditions, reducing the need for manual intervention and simplifying the overall deployment process despite the selective nature of the deployment strategy.
Data Source
AI summary
A device may include a processor configured to determine latency budgets for particular microservices for an application associated with a user equipment (UE) device, wherein the microservices are deployed in a cloud computing center. The processor may be further configured to determine that a measured latency for a particular microservice has exceeded a latency budget for the particular microservice by at least a latency budget threshold; deploy the particular microservice on a Multi-Access Edge Computing (MEC) network associated with a base station servicing the UE device, based on determining that the measured latency for the particular microservice has exceeded the latency budget for the particular microservice by at least the latency budget threshold; and send a recommendation to the UE device to use the particular microservice deployed at the MEC network.