Point-to-Point Mesh Trading System with Sequencer
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current electronic trading systems face performance degradation due to increasing transaction volumes and high-frequency trading, leading to challenges in maintaining low latency, fairness, and fault tolerance, especially under high loads and high-speed market conditions.
Innovation Solution
The implementation of a point-to-point mesh system with a sequencer interposed between gateways and core compute nodes, using direct connections with non-shared bandwidths to ensure deterministic ordering of messages through sequence marking, enabling efficient matching of trade orders and maintaining system reliability and availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a central matching engine is used to process trade orders, then order matching functionality is provided, but latency increases and performance degrades under high transaction volumes
Solution Approach 1:
The system segments the centralized matching engine into distributed core compute nodes that operate independently. Each node processes trade orders locally without needing to communicate with a central authority, thereby reducing latency and increasing overall transaction processing capacity through parallel processing across multiple nodes.
Solution Approach 2:
The patent transitions from a two-dimensional centralized architecture (single matching engine processing all orders) to a three-dimensional distributed mesh architecture where core compute nodes are arranged in a point-to-point mesh network. This dimensional change enables simultaneous order processing across multiple paths, reducing latency and increasing throughput.
2Reliability
If messages are transmitted through shared network infrastructure, then system complexity is reduced, but message ordering becomes non-deterministic under high loads
Solution Approach 1:
The patent introduces sequencers as intermediary components between gateways and core compute nodes. These sequencers assign sequence numbers to messages and manage the point-to-point mesh connections, ensuring deterministic message ordering without requiring complex distributed consensus protocols. The sequencer acts as a local mediator that simplifies the ordering problem while maintaining reliability.
3Loss of time
If gateways transmit messages directly to core compute nodes without sequencing, then latency is reduced, but message ordering cannot be guaranteed under high-frequency trading conditions
Solution Approach 1:
The system performs preliminary sequencing actions at the gateway level before messages are transmitted to core compute nodes. Sequencers pre-assign sequence numbers and organize messages in deterministic order prior to transmission, eliminating the need for complex ordering logic at the compute node level and maintaining low latency while ensuring ordering guarantees.
4Reliability
If a centralized system architecture is used, then ease of operation is maintained, but system availability decreases under high loads
Solution Approach 1:
The patent segments the centralized system into independent core compute nodes that can operate autonomously. This segmentation provides fault isolation where failures in one node do not propagate to others, maintaining high system availability. The modular architecture allows individual nodes to be managed, updated, or replaced without affecting the entire system, preserving operational simplicity.
Data Source
AI summary
An electronic trading system and corresponding method are based on a point-to-point mesh architecture. The electronic trading system comprises a gateway, core compute node, and sequencer. The core compute node performs an electronic trading matching function. The gateway transmits a message to the core compute node via a first direct connection. The gateway transmits the message via a second direct connection to the sequencer which, in turn, transmits a sequence-marked message to the core compute node via a third direct connection. The core compute node determines relative ordering of the message among other messages in the electronic trading system based on the sequence-marked message to complete the electronic trading matching function, deterministically. The gateway, core compute node, sequencer, and respective direct connections form at least a portion of the point-to-point mesh architecture and enable the electronic trading system to perform high-speed, deterministic, electronic trading of financial instruments while exhibiting low latency, fairness, and fault tolerance, among other features.