Latency Management Component for MEC Edge Applications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques are inadequate for automated, near-real-time proactive and reactive identification and resolution of latency issues affecting applications that rely on multi-access edge (MEC) server instances, leading to potential application malfunction due to varying network latency between client devices and MEC platforms.
Innovation Solution
Implementing a component that measures and manages latency by transmitting synthetic traffic, collecting end-to-end latency measurements, and applying latency management policies to identify and mitigate latency issues through proactive and reactive management strategies, such as creating new MEC server instances or applying throttling policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques are used for latency management, then device complexity is reduced, but latency measurement precision and automated resolution capability deteriorate
Solution Approach 1:
The patent introduces an intermediary latency management component that acts as a mediator between the application and the network infrastructure. This component captures latency measurements, evaluates them against policies, and triggers resolution actions without requiring complex logic in the end devices themselves, thus achieving precise measurement while keeping device complexity manageable.
Solution Approach 2:
The system implements continuous feedback loops where latency measurements are constantly monitored, compared against thresholds, and used to trigger automated resolution actions. This feedback mechanism enables precise latency management through systematic evaluation and response without requiring complex manual intervention at each device.
2Reliability
If proactive latency evaluation is implemented, then application reliability is improved, but use of energy increases due to continuous synthetic traffic transmission
Solution Approach 1:
The system performs preliminary latency evaluations using synthetic traffic before actual application traffic experiences latency issues. By proactively measuring latency conditions in advance and evaluating them against policies, the system can prevent reliability problems before they occur, ensuring application reliability while managing energy through targeted evaluation rather than continuous monitoring.
Solution Approach 2:
Instead of continuously transmitting synthetic traffic at full intensity, the system applies partial action by transmitting synthetic traffic only when necessary for evaluation purposes and at controlled rates. This approach provides sufficient latency measurement capability to ensure application reliability while avoiding excessive energy consumption from constant synthetic traffic transmission.
3Productivity
If automated management resolution functions are implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The latency management system implements self-service automation where the management component autonomously evaluates latency measurements, determines policy violations, and executes resolution actions without human intervention. This automated self-service approach increases productivity by rapidly responding to latency issues while centralizing complexity in the management component rather than distributing it across multiple devices.
Solution Approach 2:
The system segments latency management functionality into distinct modular components: latency measurement, policy evaluation, and resolution execution. This segmentation allows each component to perform its specific function efficiently while keeping individual component complexity manageable, thereby enabling automated high-productivity management without excessive overall system complexity.
4Measurement precision
If segment latency measurements are implemented, then latency issue identification accuracy is improved, but measurement precision requirements increase
Solution Approach 1:
The system divides the end-to-end latency measurement into multiple segment measurements along the communication path. By measuring latency in discrete segments rather than as a single aggregate value, the system can identify which specific network segments are causing latency issues, improving identification accuracy while making the measurement process more manageable and less demanding of extreme precision in any single measurement.
Data Source
AI summary
One or more computing devices, systems, and/or methods for latency evaluation and management resolution are provided. A fingerprint for traffic flow over a communication network from an application executing on a device to a multi-access edge (MEC) server instance hosted by a MEC platform may be identified. The fingerprint may be used to track the traffic flow between the application and the MEC server in order to measure round trip time latencies of the traffic flow. In response to a round trip time latency violating a latency management policy, segment latencies along segments of a communication travel path of the traffic flow from the device to the MEC platform may be measured. A management resolution function may be performed based upon one or more of the segment latencies exceeding a threshold.