
Adaptive Resource Management for Analyzing Video Streams from Globally Distributed Network Cameras
Abstract
For a wide range of scientific studies such as weather, wildlife, and traffic, the visual data generated by network cameras can be valuable. For some of these studies, the resource demands for data analysis may fluctuate significantly (e.g., seasonal or only rush hours). Adaptive Resource Management for Analyzing Video Streams from Globally Distributed Network Cameras The pay-per-use of cloud computing may be a preferred solution to analyze large amounts of data from these network cameras. There are few studies on how many video streams from network cameras can be analysed using cloud resources.
Introduction
System Configuration
Platform : cloud computing
Conclusion
In this paper we present an automated resource allocation system for analyzing a large amount of streaming data. First, we find that the performance-cost ratio of instances with fewer cores is better. We then propose two resource allocation strategies: linear increment method and predictive method and predictive method.