PROJECT TITLE :
On Data-Driven Delay Estimation for Media Cloud
It is well known that delay announcement is a cost-effective and efficient method 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 continues to be an open and difficult problem. During this study, we study the data-driven delay estimation in a sensible cloud media with significant traffic, and propose an correct estimation strategy only with a small quantity of dataset. Importantly, we have a tendency to explicitly model the subjective announcement-dependent user response via an objective response function through the flowery information analysis and model. On the theoretical end, the user response in terms of the estimated delay is characterized when window knowledge-cleaning, where an acceptable dataset is founded through the window operate analysis. On the technical finish, we tend to analyze the conditions for knowledge-driven delay estimation, and prove that the proposed method is in a position to obtain a close to-optimal resolution within a finite time amount. In depth simulation results demonstrate the potency of the proposed delay estimation method.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here