Abstract
In this paper, we present Deepcache a novel Framework for content caching, which can significantly boost cache performance. Our Framework is based on powerful deep recurrent neural network models. It comprises of two main components: i) Object Characteristics Predictor, which builds upon deep LSTM Encoder-Decoder model to predict the future characteristics of an object (such as object popularity) - to the best of our knowledge, we are the first to propose LSTM Encoder-Decoder model for content caching; ii) a caching policy component, which accounts for predicted information of objects to make smart caching decisions. In our thorough experiments, we show that applying Deepcache Framework to existing cache policies, such as LRU and k-LRU, significantly boosts the number of cache hits.
- Cisco visual networking index: Forecast and methodology, 2016--2021, 2017.Google Scholar
- Bahdanau, D., Cho, K., and Bengio, Y. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014).Google Scholar
- Basu, S., Sundarrajan, A., Ghaderi, J., Shakkottai, S., and Sitaraman, R. Adaptive ttl-based caching for content delivery. vol. 45, ACM, pp. 45--46. Google ScholarDigital Library
- Che, H., Wang, Z., and Tung, Y. Analysis and design of hierarchical web caching systems. In Proceedings IEEE INFOCOM 2001. (2001), vol. 3, pp. 1416--1424 vol.3.Google ScholarCross Ref
- Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).Google Scholar
- Ferragut, A., Rodriguez, I., and Paganini, F. Optimizing ttl caches under heavy-tailed demands. vol. 44, ACM, pp. 101--112. Google ScholarDigital Library
- Graves, A., and Jaitly, N. Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 (2014), ICML'14, JMLR.org, pp. II-1764--II-1772. Google ScholarDigital Library
- Gregor, K., Danihelka, I., Graves, A., Rezende, D. J., and Wierstra, D. Draw: A recurrent neural network for image generation. arXiv preprint arXiv:1502.04623 (2015).Google Scholar
- Hashemi, M., et al. Learning memory access patterns. arXiv preprint arXi:1803.02329 (2018).Google Scholar
- Hochreiter, S., and Schmidhuber, J. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780. Google ScholarDigital Library
- Jacobson, V., Smetters, D. K., Thornton, J. D., Plass, M. F., Briggs, N. H., and Braynard, R. L. Networking named content. In Proceedings of CoNEXT 2019 (New York, NY, USA, 2009), CoNEXT '09, ACM, pp. 1--12. Google ScholarDigital Library
- Koponen, T., Chawla, M., Chun, B.-G., Ermolinskiy, A., Kim, K. H., Shenker, S., and Stoica, I. A data-oriented (and beyond) network architecture. In Proceedings of the 2007 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications (New York, NY, USA, 2007), SIGCOMM '07, ACM, pp. 181--192. Google ScholarDigital Library
- Mao, H., Netravali, R., and Alizadeh, M. Neural adaptive video streaming with pensieve. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication (2017), ACM. Google ScholarDigital Library
- Martina, V., Garetto, M., and Leonardi, E. A unified approach to the performance analysis of caching systems. In IEEE INFOCOM 2014 - IEEE Conference on Computer Communications (April 2014), pp. 2040--2048.Google ScholarCross Ref
- Mikolov, T., Karafiát, M., Burget, L., Černockỳ, J., and Khudanpur, S. Recurrent neural network based language model. In Eleventh Annual Conference of the International Speech Communication Association (2010).Google ScholarCross Ref
- Ramadan, E., Narayanan, A., and Zhang, Z. L. CONIA: Content (provider)- oriented, namespace-independent architecture for multimedia information delivery. In 2015 IEEE ICMEW (June 2015), pp. 1--6.Google ScholarCross Ref
- Sadeghi, A., Sheikholeslami, F., and Giannakis, G. B. Optimal and scalable caching for 5g using reinforcement learning of space-time popularities. IEEE Journal of Selected Topics in Signal Processing 12, 1 (Feb 2018), 180--190.Google ScholarCross Ref
- Shafiq, M. Z., Liu, A. X., and Khakpour, A. R. Revisiting caching in content delivery networks. vol. 42, ACM, pp. 567--568. Google ScholarDigital Library
- Sutskever, I., Vinyals, O., and Le, Q. V. Sequence to sequence learning with neural networks. NIPS'14, MIT Press. Google ScholarDigital Library
- Tang, W., Fu, Y., Cherkasova, L., and Vahdat, A. Medisyn: A synthetic streaming media service workload generator. In NOSSDAV (2003), ACM. Google ScholarDigital Library
Index Terms
- Making content caching policies 'smart' using the deepcache framework
Recommendations
DeepCache: A Deep Learning Based Framework For Content Caching
NetAI'18: Proceedings of the 2018 Workshop on Network Meets AI & MLIn this paper, we present DEEPCACHE a novel Framework for content caching, which can significantly boost cache performance. Our Framework is based on powerful deep recurrent neural network models. It comprises of two main components: i) Object ...
Criticality aware tiered cache hierarchy: a fundamental relook at multi-level cache hierarchies
ISCA '18: Proceedings of the 45th Annual International Symposium on Computer ArchitectureOn-die caches are a popular method to help hide the main memory latency. However, it is difficult to build large caches without substantially increasing their access latency, which in turn hurts performance. To overcome this difficulty, on-die caches ...
Mitigating Prefetcher-Caused Pollution Using Informed Caching Policies for Prefetched Blocks
Many modern high-performance processors prefetch blocks into the on-chip cache. Prefetched blocks can potentially pollute the cache by evicting more useful blocks. In this work, we observe that both accurate and inaccurate prefetches lead to cache ...
Comments