Parallel Scheduling for Network Data Transmission
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In peer-to-peer (P2P) network topologies, especially in multimedia streaming, the inefficient utilization of upload bandwidth leads to suboptimal network performance due to leaf nodes in tree-based topologies and data transmission delays in mesh topologies, where nodes with insufficient upload bandwidth cannot fully contribute to data sharing and may experience delays in data chunk delivery.
Innovation Solution
A parallel scheduling method and system that generates modulus condition sets based on weight ratios to define sequence numbers for data chunks, allowing multiple transmitting nodes to send sub-streams in parallel, ensuring complete stream formation without redundancy and optimizing bandwidth utilization by integrating sub-streams at receiving nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If tree-based topology is used for data transmission, then transmission delay is reduced, but upload bandwidth utilization is inefficient due to leaf nodes unable to contribute
Solution Approach 1:
The patent segments the data stream into multiple sub-streams (first sub-stream, second sub-stream, third sub-stream) and distributes them to different transmitting nodes. This allows internal nodes to transmit multiple sub-streams simultaneously, enabling leaf nodes to contribute their upload bandwidth while maintaining low transmission delay through the segmented push-based delivery mechanism.
Solution Approach 2:
The patent introduces a multi-dimensional scheduling approach by assigning different weights (w1, w2, w3) to different sub-streams and using weighted fair queuing mechanisms. This dimensional expansion in the scheduling space allows the system to optimize both delay and bandwidth utilization simultaneously by treating different sub-streams with different priorities and allocation ratios.
2Productivity
If mesh topology is used for data exchange, then upload bandwidth contribution is improved, but data transmission delay increases due to pull manner and non-ordered chunk arrival
Solution Approach 1:
The patent segments the data transmission into multiple sub-streams with different weights, allowing the system to adopt a hybrid approach where internal nodes push multiple sub-streams in parallel while maintaining ordered delivery through the weighted scheduling mechanism, thus reducing the delay penalty of mesh topology.
Solution Approach 2:
The patent performs preliminary scheduling decisions by pre-calculating weight ratios (w1, w2, w3) and assigning sub-streams to transmitting nodes before actual data transmission begins. This preliminary action ensures that data chunks arrive in the correct order and optimizes bandwidth utilization, mitigating the inherent delays of pull-based mesh topology.
3Productivity
If sub-stream scheduling method is used, then upload bandwidth waste is alleviated, but computational complexity increases when determining value of k
Solution Approach 1:
The patent changes the parameter k to a fixed value of 3, dividing the data stream into three sub-streams with predetermined weights (w1, w2, w3). This parameter simplification reduces the computational complexity of determining optimal k values while maintaining effective bandwidth utilization through the weighted fair queuing mechanism.
Solution Approach 2:
The patent uses a partial action approach by only considering three sub-streams instead of optimizing for any possible number of sub-streams. This partial action simplifies the scheduling computation while achieving sufficient bandwidth utilization, avoiding the excessive computational complexity of exhaustive optimization.
Data Source
AI summary
According to one exemplary embodiment, a parallel scheduling method for network data transmission is provided. This method generates a corresponding modulus condition set for each weight in a weight set, with each modulus condition of the modulus condition set having a modulus operation, and a divisor and a remainder for the modulus operation, uses a network node to transmit the modulus condition set corresponding to said each weight to a transmitting node corresponding to the weigh. Based on the modulus condition set, the transmitting node transmits a plurality of data chunks, and at least one receiving node receives the plurality of data chunks, wherein each data chunk corresponding to a sequence number, and the sequence number matches a corresponding modulus condition in the modulus condition set.