# On-Demand Video Dispatch Networks: A Scalable End-to-End Learning Approach

## TL;DR

This paper presents an end-to-end neural network system for predicting and dispatching popular videos to CDNs during peak hours, significantly improving prediction accuracy over baseline methods.

## Contribution

It introduces a scalable, coupled neural network architecture with autoencoder and sequence analysis for on-demand video dispatch prediction.

## Key findings

- Achieves 17% prediction accuracy for hot videos, outperforming 3% baseline.
- Employs end-to-end training of clustering and dispatch networks.
- Scales to billions of videos with neural network-based approach.

## Abstract

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.