Signiant’s patent uses machine learning to evaluate anonymized historical transfer information collected by its SaaS products.
Signiant has received a patent for a new architecture that leverages machine learning to adapt to network conditions in real-time. “Cloud-Based Authority To Enhance Point-To-Point Data Transfer With Machine Learning,” describes methods and systems that incorporate machine learning to evaluate anonymized historical transfer information collected by its SaaS products.
This history is used as training data to build a model that predicts the fastest possible way to move or access media. Signiant’s intelligent transport chooses the optimal number of parallel transport streams and selects either standard TCP or Signiant’s proprietary UDP-based acceleration protocol based on a variety of inputs including current and historical network conditions, available compute, storage type and the characteristics of the data set. The new architecture is capable of multiple Gbps transfer speeds and is already deployed in Signiant’s SDCX (Software-Defined Content Exchange) SaaS platform for transfers between public and/or private cloud services and/or storage. The platform is capable of working with any size file, data sets with an unlimited number of files as well as growing files and streams.
“When early transfer tests showed speeds greater than 10 Gbps using settings derived through machine learning that weren’t intuitive or obvious, we knew we were onto something disruptive,” said Ian Hamilton, CTO at Signiant. “As networks evolve and increase in bandwidth, Signiant’s transport becomes even more valuable and is now capable of speeds of 10s of Gbps. Standard transfer tools simply aren’t designed to take advantage of available bandwidth and so with today’s fatter pipes, this new architecture becomes even more critical as datasets get bigger and workflows are increasingly globally distributed.”
In order to take full advantage of available bandwidth, Signiant’s machine learning algorithm examines past history and optimally configures application-level and transport-level parameters for both file and live media transfers.
The company said that not only does this ensure the best result without expensive and error prone manual tuning and tooling, but results improve over time as the system learns. In addition to Signiant’s patent-pending intelligent transport, Signiant’s core UDP-acceleration protocol offers distinct advantages. Signiant isolates different sources of congestion by looking at latency and packet loss, and also by constantly examining the rate of change in these observations. As such it can differentiate between edge and core network congestion and react accordingly.
“We’re in a world where new network technologies are being deployed for different use cases and the storage landscape has become far more complex,” Hamilton said. “With all these enhancements in infrastructure technology, Signiant’s unique SDCX SaaS platform acts as an important abstraction layer to adapt any type of IP network for the modern media enterprise. Content can be anywhere within a global mesh of SDCX-enabled storage and services, and our platform will provide fast seamless location-independent access to media assets for people and systems.”
You might also like...
The arrival of 5G brings both opportunities and challenges to communications, media and entertainment companies, as well as the original equipment manufacturers (OEMs) working to support them.
The Sponsors Perspective: SRG-SSR, R&S - Virtualized Multiviewers At Revolutionary Production Centre
Rohde and Schwarz has evolved a heritage in the broadcast and media industry stretching over 70 years. Throughout this period, the company has developed a reputation as one of the leading developers of hardware-based technology solutions worldwide. However, recent years have…
Will alternative immersive channels create an imperative for broadcasters? Veronique Larcher, Director of AMBEO Immersive Audio, Sennheiser, explores immersive content outside of the commercial broadcast space, including virtual, augmented, and mixed realities.
Local broadcasters are used to mission-critical because everything is mission-critical. Moving critical data may be the right move.
HRTF stands for Head Related Transfer Function and, simply put, is a catch-all term for the characteristics a human head imparts on sound before it enters the ear canal. Everything from level tonal changes caused by our head, shoulders, and…