Edge Computing Content Preprocessing for Latency Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multi-access edge computing (MEC) devices face challenges in optimizing the provision of high latency content, as existing methods fail to effectively reduce latency for certain applications like augmented reality and virtual reality, despite being geographically closer to user equipment (UEs), due to inherent limitations in content delivery mechanisms.
Innovation Solution
An MEC device processes historical content data using a machine learning model to identify and cache high latency content, generating intermediary content formats that can be quickly streamed to UEs, thereby conserving resources and improving content delivery efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If MEC devices provision computing resources at the network edge to reduce latency, then latency is reduced for most content, but high latency content remains slow due to inherent content delivery limitations
Solution Approach 1:
The system performs preliminary actions by identifying high-latency content in advance using historical data analysis and machine learning models. This content is pre-processed and cached at the MEC device before actual user requests, enabling faster delivery when needed without compromising performance reliability
Solution Approach 2:
The system segments content delivery by distinguishing between high-latency and low-latency content through machine learning classification. Different delivery strategies are applied to each segment: pre-processing and caching for high-latency content, and standard edge computing for low-latency content, thereby resolving the contradiction through differentiated handling
2Speed
If MEC devices cache and pre-process high latency content, then content delivery speed is improved, but computing and networking resources are consumed
Solution Approach 1:
The system applies partial action by selectively caching only high-latency content identified through machine learning analysis, rather than caching all content. This partial approach improves delivery speed for critical content while consuming computing and networking resources only when necessary, avoiding excessive resource consumption
Solution Approach 2:
The system changes the parameter of content delivery by transforming high-latency content into optimized intermediary formats with different characteristics. This parameter change enables faster delivery speed while the machine learning model ensures resource consumption is optimized by only processing content that benefits from this transformation
3Productivity
If MEC devices use machine learning models to identify and cache content, then content delivery efficiency is improved, but device complexity increases
Solution Approach 1:
The MEC device performs self-service by autonomously analyzing historical content data and using machine learning models to identify which content requires caching. This self-service capability improves content delivery efficiency through intelligent decision-making while minimizing the need for external control systems, thereby managing device complexity through automation rather than added complexity
Data Source
AI summary
A multi-access edge computing device may receive historical content data associated with a content application of a user equipment and may process the historical content data, with a machine learning model, to identify content to cache for the user equipment. The multi-access edge computing device may provide, to a content provider device, a request for the content to cache and may receive, from the content provider device, the content to cache based on the request for the content to cache. The multi-access edge computing device may process the content to cache, with a document object model and a browser object model, to generate intermediary content that corresponds to the content to cache. The multi-access edge computing device may store the intermediary content in a data structure associated with the multi-access edge computing device.