Cloud Financial Trade Ordering with Delivery Clocks for Latency Fairness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing networks face challenges in providing fair and deterministic latency to market participant computers in financial exchanges, leading to unfairness and increased costs when migrating CES computers from on-premises data centers, as they do not guarantee equal latency due to heterogeneous environments and variable network conditions.
Innovation Solution
Implementing a delivery-time-based ordering (DBO) system that uses release buffers to maintain delivery clocks and control pacing, ensuring trades are ordered based on the time taken by market participant computers to react to financial market data, independent of equal latency, and incorporating ordering buffers to handle variable latency conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If cloud computing networks are used to host CES computers, then scalability and cost efficiency are improved, but latency fairness and determinism deteriorate due to heterogeneous environments and variable network conditions
Solution Approach 1:
The system performs preliminary actions by maintaining delivery clocks at market participant computers that track virtual time independently of actual network latency. These delivery clocks are updated in advance based on scheduled data deliveries, allowing the system to prepare trade ordering decisions before actual network conditions manifest, thus achieving fairness without requiring real-time latency equalization
Solution Approach 2:
The patent introduces delivery clocks as intermediary time-tracking mechanisms between the CES computer and market participant computers. These delivery clocks act as mediators that translate variable network latency into a standardized virtual time framework, enabling fair trade ordering without directly controlling actual network latency. The delivery clocks mediate between the scheduling system and the trading system, decoupling them from each other
2Reliability
If delivery clocks are maintained at market participant computers, then trade ordering fairness is improved, but system complexity increases due to additional timing infrastructure
Solution Approach 1:
The delivery clocks are maintained self-service at market participant computers using their own local clocks and received timestamps. Each market participant computer independently tracks its own delivery time without requiring external synchronization or complex coordination. The system leverages the existing resources at each computer rather than adding centralized control mechanisms
Solution Approach 2:
The system implements partial timing infrastructure only where necessary - delivery clocks are maintained at market participant computers but not at the CES computer. This selective implementation achieves the required fairness functionality while minimizing overall system complexity by adding timing mechanisms only to the points where they are directly needed for trade ordering
3Reliability
If trades are ordered based on delivery clock timestamps, then response time fairness is improved, but measurement precision requirements increase
Solution Approach 1:
The system changes the time parameter from actual wall-clock time to virtual delivery time tracked by delivery clocks. This parameter transformation allows the system to measure response times consistently across different network conditions. The delivery clock timestamps provide a standardized time scale that compensates for network latency variations, making precise measurement of actual network performance unnecessary
Data Source
AI summary
Examples are disclosed that relate to fairly ordering financial market trades received from different market participant computers via a cloud computing network. In one example, a plurality of trades generated by a plurality of market participant computers are received. The trades are generated based at least on a financial market data point received by the plurality of market participant computers. Each trade is tagged with a delivery clock time stamp that tracks time in relation to financial market events that occur at a corresponding market participant computer. The trades are ordered based on the delivery clock time stamps and sent to a central exchange server computer. The central exchange server computer processes the trades.