| Title | : | Application Prioritization Engine for Enhancing Real-time Performance in Smartphones |
| Speaker | : | Madhan Raj Kanagarathinam (IITM) |
| Details | : | Tue, 16 May, 2023 3:30 PM @ MR-1(SSB-233) |
| Abstract: | : | Smartphone consumers use various applications (apps), including online gaming, chat, streaming, video calling, and social networking. In its send-and-receive queues, the smartphone processes the packets in a
first-in-first-out (FIFO) fashion. The smartphone relies on the network
backhaul, such as a Wi-Fi access point, to provide the required Quality
of Service (QoS). Many people worldwide started using video calling apps daily during the pandemic and post-pandemic periods. With many working remotely, video calling applications have become crucial for the
smoother operation of various businesses. On the other hand, gaming apps skyrocketed during the pandemic and continue to engage people. Online and multi-player gaming boomed to engage people across the globe. When real-time (RT) video calling and gaming apps race with non-real-time (NRT) traffic, we found a serious degradation in the performance. We can not completely block the NRT traffic in the smartphone. This also could severely hamper the user experience.
In this work, we propose an Application Prioritization Engine (APE) framework that will improve user experience by dynamically allocating bandwidth to the different apps in the smartphone. APE helps improve the end-user experience by detecting and prioritizing real-time traffic over concurrent best-effort traffic. We introduced an eBPF (extended Berkeley Packet filter) that can control the NRT traffic to the extent that it does not affect the RT traffic. The performance of top-chart video calling and gaming apps in a live-air scenario has been evaluated. It is shown that, in poor network conditions, APE enhances video calling performance by improving the bitrate to 110%. Furthermore, it provided a four-fold gaming latency reduction despite download traffic. APE is an app-agnostic server-independent solution enabled in Samsung S22 and all the latest Samsung flagship smartphones. |
