Network Switch Load Management for Financial Data Streams
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing electronic financial exchange systems face challenges in efficiently processing and transmitting information, leading to increased computational and network loads due to excessive data feeds and unnecessary updates.
Innovation Solution
The system implements load management by using load messages and coincidental peak messages to adjust message flows and timing, allowing recipients to adjust their message handling in response to aggregate message volumes, thereby reducing the overall load on the system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all information is transmitted to subscribers automatically, then subscribers receive complete data feeds, but computational and network loads increase significantly
Solution Approach 1:
The system extracts and transmits only the specific information that subscribers actually need, rather than sending complete data feeds. The exchange identifies and delivers only relevant updates based on individual subscriber requirements, filtering out unnecessary data to reduce network and computational load while maintaining information completeness for needed data.
Solution Approach 2:
The system applies different information delivery strategies to different subscribers based on their specific needs. Each subscriber receives a customized information stream tailored to their requirements, rather than a uniform approach. This allows the system to optimize resource allocation by sending detailed information only to those who need it while providing summarized or reduced information to others.
2Speed
If frequent updates are sent for particular values, then subscribers receive real-time information, but unnecessary data transmission increases system load
Solution Approach 1:
The system sends updates at appropriate frequencies based on actual need rather than uniformly frequent updates to all subscribers. Information is transmitted when changes occur that are significant to subscribers, avoiding unnecessary frequent transmissions of unchanged or irrelevant data. This partial action approach maintains real-time delivery for critical information while reducing overall transmission volume.
3Loss of information
If complete data feeds are distributed to all subscribers, then information availability is maximized, but bandwidth and processing time are consumed
Solution Approach 1:
The system extracts and transmits only the specific information that subscribers actually need, rather than sending complete data feeds. The exchange identifies and delivers only relevant updates based on individual subscriber requirements, filtering out unnecessary data to reduce network and computational load while maintaining information completeness for needed data.
Solution Approach 2:
The system changes the parameters of information delivery by adjusting the level of detail and frequency based on subscriber needs and market conditions. During high-volatility periods, more frequent and detailed updates are sent, while during stable periods, less frequent summaries are transmitted. This dynamic parameter adjustment optimizes both information availability and resource consumption.
Data Source
AI summary
An apparatus and a computer implemented method for managing data streams to a terminal device according to peak levels is disclosed. A streaming device (e.g., exchange device) may provide the data streams in response to requests received from the terminal devices. A network device in the communication path between the streaming device and the terminal device may route the data streams. At least one of the exchange device, the network device, and the terminal device is configured to identify an extended time period for a data stream between a streaming device and a terminal device, determine at least one representative time period within the extended time period, determine a quantity of discrete messages for the at least one representative time period, and calculate the coincident value for the streaming device and the terminal device over the extended time period based on the quantity of discrete messages, for the at least one representative time period, from the exchange device to at least the terminal device.