Sentinel: Scheduling Live Streams with Proactive Anomaly Detection in Crowdsourced Cloud-Edge Platforms

TL;DR

Sentinel tackles revenue optimization for live streaming on Crowdsourced Cloud-edge Platforms by introducing a proactive anomaly-aware scheduling framework. It adopts a two-stage, Pre-Post-Scheduling ($P^2S$) paradigm that precomputes anomaly-informed strategies and applies them in real time, enabling faster decisions and resilience to failures. The approach combines a two-stage device anomaly detector with a service-effect predictor to produce a revenue-optimized strategy pool, and uses linear relaxations and Branch-and-Cut to solve the pre-scheduling problem. Across real CCP datasets, Sentinel reduces anomaly frequency by about 70%, boosts revenue by about 74%, and doubles scheduling speed, demonstrating strong practical impact for large-scale, unstable CCP environments.

Abstract

With the rapid growth of live streaming services, Crowdsourced Cloud-edge service Platforms (CCPs) are playing an increasingly important role in meeting the increasing demand. Although stream scheduling plays a critical role in optimizing CCPs' revenue, most optimization strategies struggle to achieve practical results due to various anomalies in unstable CCPs. Additionally, the substantial scale of CCPs magnifies the difficulties of anomaly detection in time-sensitive scheduling. To tackle these challenges, this paper proposes Sentinel, a proactive anomaly detection-based scheduling framework. Sentinel models the scheduling process as a two-stage Pre-Post-Scheduling paradigm: in the pre-scheduling stage, Sentinel conducts anomaly detection and constructs a strategy pool; in the post-scheduling stage, upon request arrival, it triggers an appropriate scheduling based on a pre-generated strategy to implement the scheduling process. Extensive experiments on realistic datasets show that Sentinel significantly reduces anomaly frequency by 70%, improves revenue by 74%, and doubles the scheduling speed.

Figures (11)

• Figure 1: Crowdsourced Cloud-edge service Platform.
• Figure 2: Server utilization analysis.
• Figure 3: Analysis of the anomalies.
• Figure 4: Resource revenue metric.
• Figure 5: The system overview of Sentinel.