| Title | Analytics as a service architecture for cloud-based CDN: Case of video popularity prediction |
| Publication Type | Conference Paper |
| Year of Publication | 2018 |
| Authors | Aloui, M., Elbiaze, H., Glitho, R., Yangui, S. |
| Conference Name | 2018 15th IEEE Annual Consumer Communications Networking Conference (CCNC) |
| Keywords | Analytical models, analytics as a service architecture, cache storage, CDN logs, cloud computing, cloud-based CDN, Computer architecture, dynamic model training, end-user behaviour, end-user content delivery network requests, highly variable UGV popularity, k-means clustering prediction model, Metrics, NoSQL database, NoSQL databases, pattern clustering, prediction services, Predictive models, pubcrawl, quality of service, Resiliency, RESTful Web services, Scalability, scattered caches, Streaming media, Training, user generated videos, video popularity prediction, Web Caching, web services |
| Abstract | User Generated Videos (UGV) are the dominating content stored in scattered caches to meet end-user Content Delivery Networks (CDN) requests with quality of service. End-User behaviour leads to a highly variable UGV popularity. This aspect can be exploited to efficiently utilize the limited storage of the caches, and improve the hit ratio of UGVs. In this paper, we propose a new architecture for Data Analytics in Cloud-based CDN to derive UGVs popularity online. This architecture uses RESTful web services to gather CDN logs, store them through generic collections in a NoSQL database, and calculate related popular UGVs in a real time fashion. It uses a dynamic model training and prediction services to provide each CDN with related popular videos to be cached based on the latest trained model. The proposed architecture is implemented with k-means clustering prediction model and the obtained results are 99.8% accurate. |
| DOI | 10.1109/CCNC.2018.8319248 |
| Citation Key | aloui_analytics_2018 |
Analytics as a service architecture for cloud-based CDN: Case of video popularity prediction