Dynamic Buffer Depth Adjustment for Network Delay Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In Optical Transport Networks (OTNs), buffers face challenges in maintaining consistent data transmission rates, leading to buffer overflow or underflow due to bursty read rates and constant write rates, resulting in varying and increased average delays.
Innovation Solution
Implementing a buffer system with adjustable depth, where the initial depth is set to accommodate variations, and then reduced based on monitored minimum depth to minimize excess buffering and delay, using read and write pointers to manage memory entries and optimize buffer operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the buffer depth is set to a large initial value to accommodate bursty read rates, then buffer overflow and underflow are prevented, but the average delay increases
Solution Approach 1:
The buffer depth is made dynamic by continuously monitoring the actual minimum depth required to prevent overflow/underflow and adjusting the buffer depth accordingly. This resolves the contradiction by transitioning from a static large buffer (which causes delay) to a dynamic buffer that maintains only the necessary depth (preventing overflow/underflow while minimizing delay).
Solution Approach 2:
The buffer depth parameter is changed from a fixed large value to a variable value that adapts based on monitored traffic characteristics. By changing this parameter dynamically, the system prevents buffer overflow/underflow while reducing the excessive delay caused by maintaining a consistently large buffer depth.
2Loss of time
If the buffer depth is reduced to minimize delay, then average delay decreases, but buffer overflow or underflow may occur
Solution Approach 1:
The system implements feedback by monitoring the buffer depth and traffic characteristics, then using this information to adjust the buffer depth dynamically. This feedback mechanism ensures the buffer depth is sufficient to prevent overflow/underflow while being minimized to reduce delay, resolving the contradiction between these two requirements.
Solution Approach 2:
The buffer system performs self-adjustment by autonomously monitoring its own depth and traffic patterns, then automatically adjusting the buffer depth without external intervention. This self-service capability allows the system to maintain optimal buffer depth that prevents overflow/underflow while minimizing delay.
3Ease of operation
If a fixed buffer depth is used to simplify operation, then ease of operation increases, but delay variation increases
Solution Approach 1:
The buffer depth transitions from a fixed value to a dynamic value that adapts to traffic conditions. This dynamic adjustment reduces delay variation by responding to actual traffic characteristics, while the automation of this process maintains ease of operation despite the increased complexity of the buffer behavior.
Solution Approach 2:
The buffer system automatically adjusts its own depth based on monitored traffic characteristics, eliminating the need for manual configuration and maintaining ease of operation. This self-adjustment capability simultaneously reduces delay variation by adapting to actual traffic patterns.
Data Source
AI summary
There are disclosed systems and methods for reducing the average delay and the average delay variation of network communication data in a buffer. The buffer comprises a plurality of memory entries, and associated with the buffer is a read point and a write pointer. The buffer has a depth defined as the number of memory entries in the buffer between the memory entry pointed to by the read pointer and the memory entry pointed to by the write pointer. In one embodiment, at least one of the read pointer and the write pointer is initially set to establish the depth of the buffer to be a first value. The variation of the depth of the buffer is then monitored for a predetermined period of time as network communication data flows through the buffer. The depth of the buffer is then reduced based upon this monitoring.