Dynamic Ethernet Packet Classification for Industrial Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial control systems face challenges in adapting to multiple communication protocols and achieving real-time data packet classification with low latency and high performance, particularly in industrial Ethernet environments where protocols like EtherCAT and Profinet require efficient parsing and forwarding of data packets.
Innovation Solution
The proposed solution involves a network communications interface, memory, and processing units that classify data packets based on factors like rate and time of receipt, allowing for selection between cut-through and store-and-forward operations, and utilizing hardware accelerators and programmable real-time units (PRUs) to enable deterministic and flexible communication, including the use of broadside interfaces for efficient data transfer and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If store-and-forward operation is used for packet processing, then data integrity is improved, but latency increases
Solution Approach 1:
The system dynamically selects between store-and-forward and cut-through operations based on real-time classification of incoming packets. Different packet types receive different processing modes, allowing the system to optimize between reliability and latency on a per-packet basis rather than using a fixed approach for all packets.
Solution Approach 2:
The invention changes the operational parameter of packet processing from a static mode to a dynamic mode that can switch between store-and-forward and cut-through operations. This parameter change enables the system to adapt processing intensity and method based on packet classification, resolving the contradiction between data integrity and latency.
2Loss of time
If cut-through operation is used for packet processing, then latency is reduced, but data integrity may be compromised
Solution Approach 1:
Different quality levels of processing are applied to different packets based on their classification. Critical packets receive full store-and-forward processing with maximum integrity checks, while less critical packets use cut-through processing for speed. This local differentiation resolves the contradiction by applying appropriate rigor to each packet type.
Solution Approach 2:
The system dynamically adjusts processing mode based on real-time packet classification, allowing it to switch between conservative (store-and-forward) and aggressive (cut-through) processing strategies. This dynamic adaptation enables the system to minimize latency where safe and maximize integrity where critical.
3Adaptability or versatility
If multiple communication protocols are supported, then adaptability is improved, but device complexity increases
Solution Approach 1:
The packet classification engine is designed with universal functionality to handle multiple industrial communication protocols (EtherCAT, Profinet, Modbus TCP, etc.) through a single unified architecture. Rather than implementing separate processing paths for each protocol, the system uses a common classification and processing framework that adapts to different protocol types, maintaining adaptability while controlling complexity.
Solution Approach 2:
The system segments protocol handling into distinct classification stages and processing layers. The packet classification engine divides incoming packets into categories based on protocol type and characteristics, then routes them through appropriate processing paths. This segmentation allows multiple protocols to be supported through modular, organized handling rather than monolithic complexity.
4Productivity
If real-time packet classification is implemented, then productivity is improved, but processing requirements increase
Solution Approach 1:
The system performs preliminary classification of packets based on easily identifiable features such as protocol type and packet structure before full processing. This preliminary action quickly sorts packets into categories, enabling subsequent processing to be optimized for each category. The classification engine examines only essential header information initially, reducing processing requirements while maintaining high productivity.
Solution Approach 2:
The classification engine performs partial processing on all packets (examining basic headers and identifiers) and excessive processing only on packets that require it (detailed inspection of specific packet types). This selective approach to processing intensity maintains high overall throughput while avoiding unnecessary processing overhead on packets that don't require full analysis.
Data Source
AI summary
An ultra-high speed electronic communications device includes: a network communications interface; a memory; and one or more processing units, communicatively coupled to the memory and the network communications interface, wherein the memory stores instructions configured to cause the one or more processing units to: receive a data packet using the network communications interface; determine a classification of the data packet based, at least in part, on a plurality of factors, wherein the plurality of factors comprises a rate at which the data packet was received and a time at which the data packet was received; select, based at least in part, on the classification, an operation from a plurality of operations, wherein the plurality of operations comprises a cut-through operation and a store-and-forward operation; and perform the selected operation.