On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach
This addresses scalability issues in video dispatch systems for service providers, though it appears incremental in its neural network approach.
The paper tackles the problem of improving peak service quality for video on demand by predicting hot videos and dispatching them to content delivery networks, achieving an average prediction accuracy of 17% compared to a baseline of 3%.
We design a dispatch system to improve the peak service quality of video on demand (VOD). Our system predicts the hot videos during the peak hours of the next day based on the historical requests, and dispatches to the content delivery networks (CDNs) at the previous off-peak time. In order to scale to billions of videos, we build the system with two neural networks, one for video clustering and the other for dispatch policy developing. The clustering network employs autoencoder layers and reduces the video number to a fixed value. The policy network employs fully connected layers and ranks the clustered videos with dispatch probabilities. The two networks are coupled with weight-sharing temporal layers, which analyze the video request sequences with convolutional and recurrent modules. Therefore, the clustering and dispatch tasks are trained in an end-to-end mechanism. The real-world results show that our approach achieves an average prediction accuracy of 17%, compared with 3% from the present baseline method, for the same amount of dispatches.