Whitepaper Constrained Connectivity This Dell Whitepaper addresses the concept of constrained environments created over existing connectivity interfaces due to concurrent workloads in an evolving edge computing architecture paradigm, and the new set of problems to solve in these environments. October 2019 Author(s) Michael Gatson Vivek Viswanathan © 2019 Dell Inc. or its subsidiaries.
Table of contents Introduction.............................................................................................................................................................................. 3 Forward and Back Channel..................................................................................................................................................... 3 Bandwidth Requirements ..........................................................................................................
Introduction Substantial changes will take place in information and communications technology as we migrate to the next generation compute platform. This platform will likely include elements of several adjacent technologies. These adjacent technologies include 5G Networks, Edge Cloud Computing, IoT, AI and Machine Learning, and Augmented and Virtual Reality (AR/VR).
a virtual image to the headset. This image presented, that is, what the user sees, is based on the user’s most recent position and direction within the defined virtual space. As the user changes head or body position, there is a need to update this positional information to the host, or through the back channel, so that future video frames present an updated virtual image based on the user’s most recent position.
Extending the example to broader use cases, not all data or information must conform to this extreme limit. In fact, various levels of processing and latency requirements may exist within the same ecosystem. For example, the closed loop processing required of 20ms—ultra low latency, or ULL-- as discussed for AR/VR and other interactive devices, may need to be maintained between the headset and the end user system, or alternatively, may be offloaded through acceleration within the headset.
Figure 2: Multi-prong latency model for AR Use Case Example While the multi-prong model described above accommodates different roundtrip latency requirements for different use cases and their resulting workloads, the I/O requirements introduced with services enabled by Scalable Edge Cloud Compute further add to the constrained connectivity problem.
• Back Channel transmissions (BC-BC): Similar to forward channel transmissions, back channel information such as video capture and motion tracking, may require tight synchronization to other context and control information, such as other sensor data or audio. Conclusion: Solution Space & Areas of Focus As discussed, emerging technologies will create new demands for bandwidth and lower latency applications.