TCP BBR: Transforming ‘The Waiting’ into Efficient Medical Imaging Data Transmission
In the world of data transfer, echoing the sentiment of Tom Petty’s timeless song, “The Waiting,” the challenges of patience come to the forefront. Much like the song’s narrative, the internet has grappled with congestion control difficulties since the late 1980s when the internet primarily used loss-based congestion control, relying only on indications of lost packets as the signal to slow down. This method worked well for many years because the small buffers of internet switches and routers were well-matched to the low bandwidth of internet links. As a result, buffers tended to fill up and drop excess packets right when senders began sending data too fast. However, this conventional method has proven problematic in today’s diverse networks due to a few factors:
- In shallow buffers, packet loss happens before congestion. With today’s high-speed, long-haul links that use commodity switches with shallow buffers, loss-based congestion control can result in abysmal throughput because it overreacts, halving the sending rate upon packet loss, even if the packet loss comes from transient traffic bursts (this kind of packet loss can be frequent even when the link is primarily idle).
- In deep buffers, congestion happens before packet loss. At the edge of today’s internet, loss-based congestion control causes the infamous “buffer bloat” problem by repeatedly filling the deep buffers in many last-mile links and causing seconds of needless queuing delay.
The song “The Waiting” conveys the emotional struggle of anticipation when Tom Petty sings, “The waiting is the hardest part..” BBR addresses this sentiment by considering real-time network conditions. From the traditional loss-based approach, BBR adapts transmission rates based on the network’s bandwidth and round-trip time, reducing latency. BBR (“Bottleneck Bandwidth and Round-trip propagation time”) is a congestion control algorithm initially developed at Google. These congestion control algorithms, found in every computer, phone, or tablet connected to a network, are crucial in determining the transmission speed of data.
Departing from traditional methods, BBR adopts a novel paradigm: instead of reacting to packet loss, it assesses how swiftly the network delivers data. To construct a comprehensive model, BBR uses recent measurements of the network’s delivery rate and round-trip time for a given network connection. This model incorporates the maximum recent bandwidth available to the connection and its minimum recent round-trip delay. BBR then utilizes this model to intelligently regulate the speed of data transmission and determine the maximum amount of data permitted in the network at any given time.
TCP before BBR and after. Image Source: Google
Unifier platform leverages TCP BBR congestion control to neutralize image processing latency and downtime and improve throughput
Efficient access to medical imaging data is critical in healthcare, and one way Dicom Systems addresses this need is by leveraging TCP BBR protocol. High latency can delay access and processing of medical images, disrupting the patient care continuum. Leveraging technologies such as TCP BBR minimizes these delays to ensure that data transmits as close to real-time as possible, improving imaging system performance and supporting timely medical decisions. This robust protocol continuously monitors and adapts data transfer rates to match the network’s bandwidth and round-trip time to improve image transfer speed, particularly for remote locations with high-latency data transmission.
Dicom Systems uses TCP BBR for unparalleled medical imaging data transmission. Our benchmark testing of the Unifier platform showed remarkable transmission speed improvements, reaching 39.6 Mbit/s (an 1800% increase) with a latency of 100-250 ms and 1% packet loss, compared to the usual 2.2 Mbit/s with cubic congestion control. With higher latency (250-500 ms) and no packet loss, the speed increases from 13.4 to 31.6 Mbit/s (a 235% improvement). Through strategic alliances with various Cloud providers and the implementation of TCP BBR, Dicom Systems offers fast, dependable medical imaging data transfer to boost performance for healthcare organizations.
Benefits of Embracing TCP BBR for Medical Imaging Data Transfer
- Rapid Data Transfer and Throughput: Integration of TCP BBR by Dicom Systems ensures swift data transfer rates, enabling healthcare professionals to access crucial medical images promptly. This capability is vital for time-sensitive medical decisions, expediting the transmission and ingestion of patient data and accelerating the diagnostic process.
- Reduced Latency and downtime: Effective utilization of TCP BBR addresses latency issues, ensuring real-time data transmission. This improvement enhances medical image viewing and analysis across cloud, on-premise, or hybrid solutions.
- Improved TAT (Patient Read Turn Around Time) Optimization of workflow processes, including the integration of TCP BBR, results in an impressive average turnaround time (TAT). The rapid delivery of results facilitates timely interventions, enhancing the overall patient experience and satisfaction.
Read more about how Dicom Systems generated a 10X performance improvement in delivering studies across the Vision Radiology Network, or listen to the Optimizing Teleradiology Workflows Webinar with Vision Radiology and Dicom Systems to learn more about the implementation and results.
Dicom Systems TCP BBR Congestion Control Protocol
Integrating TCP BBR into Dicom Systems Unifier provides unprecedented speed, reliability, and security for accessing critical medical imaging data. Our platform, which is adaptable to any environment, streamlines workflows, solves interoperability challenges, and enhances overall performance.
Unifier’s workflow engine and data migration tools effectively remedy healthcare organizations facing latency issues, downtime, or delays in image processing due to cloud infrastructure. Like the anticipation in ‘The Waiting,’ Dicom Systems Unifier, powered by TCP BBR, ends the healthcare data transfer wait swiftly, securely, and reliably. It specializes in large enterprises, boosts cloud performance, minimizes disruptions, and ensures patient data safety. In the words of Tom Petty, waiting is the hardest part. With the Unifier, there is no more waiting—the medical imaging song now plays seamlessly with accelerated access and efficient workflows.
Dicom Systems and Pure Storage conducted testing to evaluate if high-performance data storage affects medical image transmission latency and transfer speed. The testing focused on the routing functionality of the Dicom Systems Unifier enterprise imaging platform. When the Unifier platform runs on Pure Storage® hardware, the combined solution can migrate over 800,000* imaging studies daily.