About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Blogs

AWS, SGX and Aquis POC Demonstrates Feasibility of Cloud-Based Matching

Subscribe to our newsletter

AWS, the Singapore Exchange (SGX) and Aquis Exchange recently completed a proof of concept (POC) that confirmed the viability of situating an exchange matching engine in a cloud environment.

The POC – which focused on evaluating the core functions and connectivity latencies of Aquis’s order-matching platform in the AWS cloud – demonstrated respectable order turnaround latency and jitter measures, compared with standard optimized data centre set-ups, indicating that cloud could present a feasible hosting option for both start-up and established exchanges and execution venues.

The POC made use of AWS’s Transit Gateway facility to handle the multicast requirement that is so often cited as a barrier to migrating high-performance trading functions to the cloud.

Using Transit Gateway, the POC was able to produce matching latencies on the Aquis platform of 100-200 microseconds, compared with 13 microseconds in a fully optimized environment. After some work to reduce variability, AWS and Aquis were able to reduce jitter on the POC to just 4 microseconds, making the approach viable for trading firms accustomed to tuning their trading strategies to venues’ jitter measures.

Adrian Ip, director of product management at Aquis, calls the jitter measure “an amazing result” that supports the possibility of operating exchange matching engines in the cloud. While cloud is slower than a fully optimized data centre implementation, high-performance market participants would be able to use AWS’s Direct Connect facility – or other cloud operators’ equivalents – to create a high-bandwidth uplink from FIX engines, smart order routers and other trading algorithms hosted within traditional data centres like those operated by Equinix, Interxion and CenturyLink.

By setting access parameters based on, say, number of network hops, operators of cloud-based exchanges could ensure a level playing field while eradicating the need and expense of operating colocation facilities. Ip reckons the set-up costs for establishing matching in the cloud could represent an 80%-90% savings versus traditional platform implementations within data centres. He also suggests that cloud’s higher levels of resilience could go some way to reduce the outages experienced by such high-profile markets as Australian Stock Exchange, Japan Exchange Group and Euronext.

To facilitate the POC, says Ip, the partners created multiple virtual private clouds (VPCs) that used the Transit Gateway facility to handle connections to trading entities’ FIX engines situated within those entities’ AWS instances. Through this connection, the POC was able to control access to the matching engine, ensuring security and resilience.

Subscribe to our newsletter

Related content

WEBINAR

Recorded Webinar: The Role of Data Fabric and Data Mesh in Modern Trading Infrastructures

The demands on trading infrastructure are intensifying. Increasing data volumes, the necessity for real-time processing, and stringent regulatory requirements are exposing the limitations of legacy data architectures. In response, firms are re-evaluating their data strategies to improve agility, scalability, and governance. Two architectural models central to this conversation are Data Fabric and Data Mesh. This...

BLOG

The AI Co-Pilot: How Wall Street is Really Using AI for a Competitive Edge

The headlines paint a dramatic picture: autonomous AI traders making split-second decisions, rendering human portfolio managers obsolete. But for technology professionals on the ground, the reality of artificial intelligence in capital markets is proving to be both more pragmatic and, in many ways, more powerful. Discussions at A-Team Group’s recent TradingTech Briefing New York revealed...

EVENT

AI in Data Management Summit New York City

Following the success of the 15th Data Management Summit NYC, A-Team Group are excited to announce our new event: AI in Data Management Summit NYC!

GUIDE

Entity Data Management Handbook – Fifth Edition

Welcome to the fifth edition of A-Team Group’s Entity Data Management Handbook, sponsored for the fourth year running by entity data specialist Bureau van Dijk, a Moody’s Analytics Company. The past year has seen a crackdown on corporate responsibility for financial crime – with financial firms facing draconian fines for non-compliance and the very real...