Network Device Burst Parameter Extraction for Elephant Flows
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network devices face challenges in efficiently extracting flow characteristics from packet flows that include burst traffic, leading to increased processing overheads and inaccurate representation of actual traffic patterns, which affects network performance and service quality.
Innovation Solution
A method and apparatus for extracting flow characteristics by determining burst parameters of burst traffic segments within packet flows, allowing for the representation of flow characteristics in real-time, reducing bandwidth and resource consumption, and enabling differentiated processing of packet flows based on Service-Level Agreements (SLAs).
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a transmit end periodically sends a large quantity of packets to reduce processing overheads, then processing overheads and CPU load are reduced, but traffic burst occurs causing inaccurate flow characteristic extraction
Solution Approach 1:
The patent segments the packet flow into multiple flow segments based on time intervals, where each segment contains a subset of packets. This segmentation allows the system to process packets in manageable chunks rather than all at once, reducing instantaneous processing overhead while maintaining accurate flow characteristic extraction through aggregated statistics from multiple segments.
2Measurement precision
If all packets in a packet flow are processed to extract flow characteristics, then extraction accuracy is improved, but processing overheads and resource consumption increase
Solution Approach 1:
The patent applies partial action by processing packets in multiple time segments rather than all at once. Each segment processes a portion of the total packets, and the results are aggregated to achieve accurate flow characteristics. This approach reduces instantaneous processing overhead and resource consumption while maintaining extraction accuracy through cumulative statistical analysis.
3Ease of operation
If packet flows with burst traffic are processed using conventional methods, then processing is simplified, but actual traffic patterns are not accurately represented
Solution Approach 1:
The patent introduces dynamic time interval adjustment based on detected burst patterns. When burst traffic is detected, the system adapts its processing intervals and aggregation methods to capture the burst characteristics accurately. This dynamic approach maintains processing simplicity while significantly improving traffic pattern representation accuracy compared to static conventional methods.
Data Source
AI summary
The technology of this application relates to a flow characteristic extraction method and apparatus, and belongs to the field of network technologies. The method includes a network device that determines a burst parameter of a burst traffic segment of a received first packet flow, and determines a burst parameter of the first packet flow based on the burst parameter of the burst traffic segment of the first packet flow. The first packet flow is an elephant flow, the burst traffic segment indicates a burst degree of traffic within one period of time, the burst parameter of the burst traffic segment is a parameter used to describe the burst traffic segment, and the burst parameter of the first packet flow is a parameter used to describe at least one burst traffic segment included in the first packet flow.