Dimas S. Lima
Paulo Renato C. Mendes
ABSTRACT
Content caching is a well-known promising solution to address large demands for streaming companies. This paper presents an ongoing work towards improving CDN network traffic focusing on users' quality of experience (QoE) by anticipating which videos will be popular on Globo's platform. To do so, a deep neural network approach was chosen to model video's popularity based on its metadata and a near real-time framework is presented describing how to make content caching in a preemptive way. Additionally, a threshold selection approach is presented defining whether a video should be cached or not. The presented approach allows making content cache without any user interaction, aiming to decide about the admission of the content before it starts to receive requests. This approach is important to most of the daily published videos at Globo, especially for breaking news. Using Globo's real-world data, we demonstrate the popularity predictor results and conclude with some directions for future works.
Supplemental Material
- Charu C Aggarwal et al. 2016. Recommender Systems. Springer.Google Scholar
- Parnia Bahar, Tobias Bieschke, and Hermann Ney. 2019. A comparative study on end-to-end speech to text translation. In 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU). IEEE, 792--799.Google ScholarCross Ref
- Daniel S Berger, Ramesh K Sitaraman, and Mor Harchol-Balter. 2017. Adaptsize: Orchestrating the hot object memory cache in a content delivery network. In 14th {USENIX} Symposium on Networked Systems Design and Implementation ({NSDI} 17). 483--498.Google Scholar
- Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics 5 (2017), 135--146.Google ScholarCross Ref
- Fangfei Chen, Ramesh K Sitaraman, and Marcelo Torres. 2015. End-user mapping: Next generation request routing for content delivery. ACM SIGCOMM Computer Communication Review 45, 4 (2015), 167--181.Google ScholarDigital Library
- Ludmila Cherkasova. 1998. Improving WWW proxies performance with greedy-dual-size-frequency caching policy. Hewlett-Packard Laboratories.Google Scholar
- Mattia Antonino Di Gangi, Matteo Negri, Roldano Cattoni, Dessi Roberto, and Marco Turchi. 2019. Enhancing transformer for end-to-end speech-to-text translation. In Machine Translation Summit XVII. European Association for Machine Translation, 21--31.Google Scholar
- Fernando Ferraz do Nascimento, Dani Gamerman, and Hedibert Freitas Lopes. 2012. A semiparametric Bayesian approach to extreme value estimation. Statistics and Computing 22, 2 (2012), 661--675.Google ScholarDigital Library
- Nathan Hartmann, Erick Fonseca, Christopher Shulby, Marcos Treviso, Jessica Rodrigues, and Sandra Aluisio. 2017. Portuguese word embeddings: Evaluating on word analogies and natural language tasks. arXiv preprint arXiv:1708.06025 (2017).Google Scholar
- Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani. 2013. An introduction to Statistical Learning. Vol. 112. Springer.Google ScholarDigital Library
- Vadim Kirilin, Aditya Sundarrajan, Sergey Gorinsky, and Ramesh K Sitaraman. 2020. RL-Cache: Learning-based cache admission for content delivery. IEEE Journal on Selected Areas in Communications 38, 10 (2020), 2372--2385.Google ScholarCross Ref
- Samuel Kotz and Saralees Nadarajah. 2000. Extreme value distributions: theory and applications. World Scientific.Google Scholar
- Donghee Lee, Jongmoo Choi, Jong-Hun Kim, Sam H Noh, Sang Lyul Min, Yookun Cho, and Chong Sang Kim. 2001. LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies. IEEE transactions on Computers 50, 12 (2001), 1352--1361.Google Scholar
- Bruce M Maggs and Ramesh K Sitaraman. 2015. Algorithmic nuggets in content delivery. ACM SIGCOMM Computer Communication Review 45, 3 (2015), 52--66.Google ScholarDigital Library
- Jose L Martinez-Rodriguez, Aidan Hogan, and Ivan Lopez-Arevalo. 2020. Information extraction meets the semantic web: a survey. Semantic Web 11, 2 (2020), 255--335.Google ScholarDigital Library
- Iacopo Masi, Yue Wu, Tal Hassner, and Prem Natarajan. 2018. Deep face recognition: A survey. In 2018 31st SIBGRAPI conference on graphics, patterns and images (SIBGRAPI). IEEE, 471--478.Google ScholarCross Ref
- Paulo Renato C Mendes, Antonio José G Busson, Sérgio Colcher, Daniel Schwabe, Álan Lívio V Guedes, and Carlos Laufer. 2020. A Cluster-Matching-Based Method for Video Face Recognition. In Proceedings of the Brazilian Symposium on Multimedia and the Web. 97--104.Google ScholarDigital Library
- Kathlene Morales and Byeong Kil Lee. 2012. Fixed segmented LRU cache replacement scheme with selective caching. In 2012 IEEE 31st International Performance Computing and Communications Conference (IPCCC). IEEE, 199--200.Google ScholarCross Ref
- Diego Moussallem, Ricardo Usbeck, Michael Röeder, and Axel-Cyrille Ngonga Ngomo. 2017. MAG: A multilingual, knowledge-base agnostic and deterministic entity linking approach. In Proceedings of the Knowledge Capture Conference. 1--8.Google ScholarDigital Library
- R Gary Parker and Ronald L Rardin. 2014. Discrete optimization. Elsevier.Google Scholar
- Rafael Pena, Felipe A Ferreira, Frederico Caroli, Luiz José Schirmer Silva, and Hélio Lopes. 2020. Globo Face Stream: A System for Video Meta-data Generation in an Entertainment Industry Setting.. In ICEIS (1). 350--358.Google Scholar
- Mirco Ravanelli, Titouan Parcollet, and Yoshua Bengio. 2019. The pytorch-kaldi speech recognition toolkit. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6465--6469.Google ScholarCross Ref
- Ozge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, and Chris Biemann. 2020. Neural entity linking: A survey of models based on deep learning. arXiv preprint arXiv:2006.00575 (2020).Google Scholar
- SM Shahrear Tanzil, William Hoiles, and Vikram Krishnamurthy. 2017. Adaptive scheme for caching YouTube content in a cellular network: Machine learning approach. Ieee Access 5 (2017), 5870--5881.Google ScholarCross Ref
Index Terms
- An ML-Based Approach for Near Real-Time Content Caching
Recommendations
CoPUP: content popularity and user preferences aware content caching framework in mobile edge computing
AbstractMobile edge computing (MEC) enables intelligent content caching at the network edge to reduce traffic and enhance content delivery efficiency. In MEC architecture, popular content can be deployed at the MEC server to improve users’ quality of ...
Cooperative caching for adaptive bit rate streaming in content delivery networks
IMCOM '15: Proceedings of the 9th International Conference on Ubiquitous Information Management and CommunicationThis work proposes a cooperative caching model which supports adaptive bit-rate streaming in content delivery networks. A linear program (LP) problem is applied to maximize the total user satisfaction. The optimal content placement and content fetching ...
Popularity prediction caching based on logistic regression in vehicular content centric networks
To improve the network performance caused by mobility and sporadic connectivity in the vehicular network, vehicular content centric network (VCCN) is proposed by applying CCN into the vehicular network. The open in-network caching of CCN makes nodes cache ...
Comments