Bandwidth Allocation via Token Bucket Count Threshold
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current queuing systems in networks often distribute excess bandwidth unfairly among users, leading to an uneven allocation of resources, and existing solutions like traffic shaping introduce complexity and latency.
Innovation Solution
Implementing a bandwidth allocation system with a phantom scheduler and rate limiter that maintains counts of non-committed information rate (non-CIR) packets for each user, preventing forwarding of excess packets when a threshold is reached, thereby ensuring fair distribution of excess bandwidth.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traffic shaping is used to distribute excess bandwidth fairly among users, then bandwidth allocation fairness is improved, but system complexity and latency increase
Solution Approach 1:
The patent extracts the bandwidth allocation control logic from complex traffic shaping mechanisms and implements it through a simplified token bucket approach. The token bucket algorithm maintains a count of transmitted packets and compares it against a threshold, providing fair bandwidth distribution without the complexity of traditional traffic shaping systems.
Solution Approach 2:
The patent changes the control parameter from complex traffic shaping rules to a simple token count threshold. By monitoring the number of packets transmitted in the token bucket and comparing it against a predefined threshold, the system achieves fair bandwidth allocation through parameter-based control rather than complex scheduling algorithms.
2Manufacturing precision
If traffic shaping is implemented to ensure fair bandwidth distribution, then bandwidth allocation fairness is improved, but transmission latency increases
Solution Approach 1:
The patent implements preliminary action by pre-calculating and storing the token threshold value before transmission begins. The system proactively manages the token bucket count and preemptively prevents excessive packet transmission by comparing the current count against the pre-set threshold, thereby avoiding latency caused by reactive packet queuing and retransmission.
Solution Approach 2:
The patent allows packets to be transmitted immediately when the token count is below the threshold, skipping the complex scheduling and queuing processes of traditional traffic shaping. This direct transmission approach reduces latency while maintaining fairness through the simple count-threshold comparison mechanism.
3Productivity
If excess bandwidth is allocated to users who send more packets, then packet transmission volume is improved, but bandwidth allocation fairness deteriorates
Solution Approach 1:
The patent implements feedback control by continuously monitoring the token bucket packet count and comparing it against the threshold. When the count approaches or exceeds the threshold, the system provides feedback to limit further packet transmission from the same user, ensuring that no single user can monopolize excess bandwidth regardless of their transmission volume.
Solution Approach 2:
The patent introduces dynamic bandwidth allocation through the token threshold mechanism. The effective bandwidth available to each user dynamically adjusts based on their current transmission rate and the token bucket state, preventing any user from consistently obtaining disproportionate bandwidth while allowing high transmission volumes when resources are available.
Data Source
AI summary
Methods, systems, and computer program products for allocating excess bandwidth of an output among network users are disclosed. According to one method, packets associated with a plurality of network users for forwarding to an output are received. The packets can include a first non-committed information rate (CIR) packet associated with a first network user. The method can include a step for maintaining a count of non-CIR packets sent for the first network user. Further, the method can include preventing the first non-CIR packet from being forwarded to the output in response to the count having a predetermined relationship with respect to a threshold level.