On Data-Driven Delay Estimation for Media Cloud

Abstract

It is well known that delay announcement is an economical and efficient way to improve the user satisfaction since the waiting time (delay) is an important performance metric for media cloud. However, how to accurately estimate the delay in an online-implementation manner is still an open and challenging problem. In this study, we study the data-driven delay estimation in a practical cloud media with heavy traffic, and propose an accurate estimation strategy only with a small amount of dataset. Importantly, we explicitly model the subjective announcement-dependent user response via an objective response function through the elaborate data analysis and model. On the theoretical end, the user response in terms of the estimated delay is characterized by the time window data-cleaning, where an appropriate dataset is set up through the window function analysis. On the technical end, we analyze the conditions for data-driven delay estimation, and prove that the proposed method is able to obtain a near-optimal solution within a finite time period. Extensive simulation results demonstrate the efficiency of the proposed delay estimation method.