Adaptive Flow Table Processing for SDN Delay Reduction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current Software-Defined Networking (SDN) technologies face delays in data processing due to the time-consuming flow table rule matching process, especially in future wireless communications networks with millions of data connections, which cannot meet the requirements for efficient data processing.

Innovation Solution

An adaptive flow table processing method is introduced, where resource scheduling determines the terminal device or data stream for uplink data transmission, and the corresponding flow rule is queried and updated in the flow table, allowing for efficient matching and processing of data packets, reducing the delay by maintaining a smaller scale flow table.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a large quantity of flow rules are stored in a flow table to handle millions of data connections, then the data stream matching capability is improved, but the data processing delay increases to millisecond level

Engineering Contradiction:

Improvedata stream matching capabilityVSAvoiddata processing delay

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent segments the flow table into multiple partitions, each handling a subset of flow rules. This allows the matching process to be distributed across multiple smaller tables rather than searching through one large table, reducing the time complexity from O(N) to O(N/M) where M is the number of partitions.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary classification of data streams into different categories (e.g., by source/destination IP, port ranges) before the actual flow rule matching. This pre-grouping reduces the search space for subsequent matching operations, enabling faster processing of millions of data connections.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If flow table rule matching is performed for all data packets, then accurate data processing is achieved, but the processing time reaches five milliseconds which cannot meet wireless communications requirements

Engineering Contradiction:

Improvedata processing accuracyVSAvoiddata processing throughput

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent implements partial matching by identifying and processing high-priority or time-sensitive data packets through expedited paths with simplified matching rules, while applying full matching to other packets. This allows critical communications to meet timing requirements without sacrificing overall accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent dynamically adjusts matching parameters such as rule priority weights, time thresholds, and packet classification criteria based on network conditions and service types. This enables the system to adapt between thorough matching for reliability and faster matching for throughput based on real-time requirements.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP3223474B1Method and device for processing adaptive flow table

Publication Date: 2020.06.17 HUAWEI TECH CO LTD

Figure 1A~1C
Figure 1D
Figure 2A

AI summary

A method and an apparatus for processing an adaptive flow table are disclosed. When resource scheduling is performed, a terminal device or a data stream that performs uplink data transmission in a scheduled time period is determined; a corresponding flow rule of the terminal device or the data stream is queried, and the found flow rule is updated to a flow table; and when a data packet is received, corresponding processing is performed on the data packet according to a flow rule in the flow table. This reduces a delay of data processing in a flow table matching process.