VGPrio: Visually-Guided HTTP/3 Prioritization
Abstract
HTTP prioritization allows browsers to signal the priority of web resources to aid and speed up the webpage loading process. However, setting optimal resource priorities is challenging. Browser vendors use different, generalized priority strategies to achieve good performance for most websites, but a clear one-size-fits-all solution does not exist and the strategies struggle in certain scenarios reducing human-perceivable performance. Thus, we propose VGPrio, an approach that automatically optimizes HTTP prioritization w.r.t. visual metrics / human-perceivable performance. VGPrio uses a Bayesian optimization–based method to learn prioritization strategies for websites that specifically improve the human-perceivable SpeedIndex. Through its sample-efficient method, our approach only requires few iterations while our evaluation on a public website corpus shows that VGPrio can improve the SpeedIndex by up to 50% compared to default strategies evading strong detriments and being more widely applicable than related work aiming at similar goals. As such, VGPrio represents a promising option to improve human-perceivable web performance for website providers beyond manual optimization.
Constantin Sander, M.Sc.
Researcher
Ike Kunze, M.Sc.
Researcher
Dario Veltri
