Transport Accelerator Chunk Request Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current content delivery technologies, particularly for high-resolution video streaming, face challenges in maintaining accurate download rate estimates and minimizing buffering delays due to the sequential availability of media segments and network congestion, leading to suboptimal user experiences during live streaming.
Innovation Solution
A transport accelerator on a client device subdivides fragment requests into chunk requests, managed by a request manager and connection manager to optimize network transfer rates independently of server congestion, utilizing multiple connections to ensure continuous content delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a client requests content fragments sequentially over a single connection, then the server's network congestion avoidance operation can maintain stable transmission, but the client's network transfer rate is limited and download accuracy deteriorates
Solution Approach 1:
The patent segments a single fragment request into multiple chunk requests and distributes them across multiple connections. Each connection requests a portion of the total content, allowing parallel downloads that increase overall transfer rate while maintaining accurate rate estimation through aggregated feedback from all connections.
Solution Approach 2:
The patent transitions from a single-dimension approach (one connection, sequential requests) to a multi-dimensional approach (multiple connections, parallel requests). By adding the connection dimension, the system achieves higher throughput while maintaining measurement accuracy through coordinated management of all connections.
2Loss of time
If a streaming client operates on a request-download-estimate loop with sequential fragment requests, then the system complexity remains simple, but buffering delays increase and user experience deteriorates
Solution Approach 1:
The transport accelerator segments the content delivery process into multiple parallel chunk requests across multiple connections, enabling overlapping downloads that reduce buffering delays. The segmentation allows the client to build buffers more quickly by simultaneously retrieving content from multiple sources.
Solution Approach 2:
The transport accelerator performs preliminary actions by pre-requesting content chunks across multiple connections before they are needed for playback. This proactive approach builds content buffers in advance, reducing buffering delays during live streaming while the coordinated management handles the increased complexity.
3Productivity
If multiple connections are used to increase network transfer rate, then the download speed improves, but the coordination and management complexity increases
Solution Approach 1:
The transport accelerator merges multiple chunk requests into coordinated operations across multiple connections. By combining the management functions and synchronizing requests, the system achieves high content delivery speed while the merging of control functions prevents complexity from scaling linearly with the number of connections.
Solution Approach 2:
The transport accelerator implements a universal connection manager that handles multiple connections with a single coordinated control mechanism. This multi-functional component manages chunk requests, rate estimation, and buffer management across all connections simultaneously, improving delivery speed while containing complexity through functional consolidation.
Data Source
AI summary
Transport accelerator (TA) systems and methods for delivery of content to a user agent (UA) of the client device from a content server are provided according to embodiments of the present disclosure. Embodiments of a TA operate to subdivide, by a request manager (RM) of the TA, fragment requests provided by the UA each into a plurality of chunk requests for requesting chunks of the content and to provide, by the RM to a connection manager (CM) of the TA, chunk requests of the plurality of chunk requests for requesting chunks of the content. Requests may thus be made, by the CM, for the chunks of the content from the content server via a plurality of connections established between the CM and the content server.