An Intelligent Resource Reservation for Crowdsourced Live Video Streaming Applications in Geo-Distributed Cloud Environment

TL;DR

This paper proposes a machine-learning based predictive resource allocation framework for geo-distributed cloud-based live video streaming, aiming to optimize QoS and reduce costs through offline optimization, forecasting, and a greedy allocation algorithm.

Contribution

It introduces a novel predictive resource allocation framework combining offline optimization, machine learning forecasting, and a greedy algorithm for real-time video streaming in cloud environments.

Findings

GNCA achieves over 20% cost reduction compared to existing methods.

The framework effectively balances QoS and cost in geo-distributed cloud streaming.

Simulations demonstrate improved performance and lower latency.

Abstract

Crowdsourced live video streaming (livecast) services such as Facebook Live, YouNow, Douyu and Twitch are gaining more momentum recently. Allocating the limited resources in a cost-effective manner while maximizing the Quality of Service (QoS) through real-time delivery and the provision of the appropriate representations for all viewers is a challenging problem. In our paper, we introduce a machine-learning based predictive resource allocation framework for geo-distributed cloud sites, considering the delay and quality constraints to guarantee the maximum QoS for viewers and the minimum cost for content providers. First, we present an offline optimization that decides the required transcoding resources in distributed regions near the viewers with a trade-off between the QoS and the overall cost. Second, we use machine learning to build forecasting models that proactively predict the approximate transcoding resources to be reserved at each cloud site ahead of time. Finally, we develop a Greedy Nearest and Cheapest algorithm (GNCA) to perform the resource allocation of real-time broadcasted videos on the rented resources. Extensive simulations have shown that GNCA outperforms the state-of-the art resource allocation approaches for crowdsourced live streaming by achieving more than 20% gain in terms of system cost while serving the viewers with relatively lower latency.