Bandwidth Packing Rate Controller for Resource Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing rate control mechanisms in communication systems lead to poor resource utilization and reduced throughput due to blanket reduction factors applied across all flows, counteracting the benefits of over-subscription techniques without considering underlying flow characteristics.
Innovation Solution
A method that dynamically adjusts bandwidth allocation among flows to achieve a target utilization rate by transferring bandwidth from underutilized flows to overutilized ones, using a feedback mechanism that considers TCP behavior and buffer occupancy to optimize resource utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If a blanket reduction factor is applied to over-subscribed flows to prevent exceeding bandwidth capacity, then link stability is improved, but resource utilization deteriorates
Solution Approach 1:
The patent applies different reduction factors to different flows based on their individual characteristics and current utilization levels, rather than applying a uniform reduction factor. This local differentiation allows the system to maintain stability while preserving resource utilization by being selective about which flows receive bandwidth reductions.
Solution Approach 2:
The reduction factor is dynamically adjusted based on real-time flow characteristics, current bandwidth utilization, and link conditions. This dynamic approach allows the system to adapt to changing conditions and optimize both stability and resource utilization continuously, rather than using a static blanket reduction factor.
2Productivity
If over-subscription is used to achieve higher throughput, then productivity is improved, but system complexity increases
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors flow utilization and link conditions, then adjusts bandwidth allocations accordingly. This feedback loop enables the system to manage over-subscription effectively by detecting when flows are exceeding their fair share and applying targeted reduction factors, thereby maintaining throughput while managing complexity through automated control.
Solution Approach 2:
The system changes key parameters such as reduction factors and bandwidth allocations based on observed flow characteristics and link conditions. By dynamically adjusting these parameters, the system can achieve higher throughput through over-subscription while managing complexity through parameter-based control rather than structural complexity.
3Productivity
If bandwidth allocation is increased for all flows to improve resource utilization, then throughput is improved, but bandwidth capacity constraints are violated
Solution Approach 1:
The patent applies partial action by selectively increasing bandwidth allocation only to flows that need it, rather than uniformly increasing allocation for all flows. Combined with the feedback mechanism, this allows the system to push beyond traditional capacity constraints for individual flows while ensuring that the total bandwidth usage remains within acceptable limits, thereby improving resource utilization without violating overall capacity compliance.
Data Source
AI summary
A bandwidth packing rate control technique includes altering bandwidth allocations of existing flows on a link depending on a current utilization of a current bandwidth allocation for a flow. A disclosed example decreases the bandwidth allocation for flows that are utilizing a current bandwidth allocation below a selected target utilization rate. Flows with higher utilization can receive increased bandwidth allocation, which provides increased throughput for such flows. One overall result of a disclosed example is increased utilization and increased throughput using existing bandwidth resources.