DEEPCACHE: A deep learning based framework for content caching

Arvind Narayanan; Saurabh Verma; Eman Ramadan; Pariya Babaie; Zhi-Li Zhang

doi:10.1145/3229543.3229555

DEEPCACHE: A deep learning based framework for content caching

Arvind Narayanan, Saurabh Verma, Eman Ramadan, Pariya Babaie, Zhi-Li Zhang

Computer Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

121 Scopus citations

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.

Original language	English (US)
Title of host publication	NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018
Publisher	Association for Computing Machinery, Inc
Pages	48-53
Number of pages	6
ISBN (Electronic)	9781450359115
DOIs	https://doi.org/10.1145/3229543.3229555
State	Published - Aug 7 2018
Event	2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018 - Budapest, Hungary Duration: Aug 24 2018 → …

Publication series

Name	NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018

Other

Other	2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018
Country/Territory	Hungary
City	Budapest
Period	8/24/18 → …

Bibliographical note

Publisher Copyright:
© 2018 Association for Computing Machinery.

Keywords

Cache hit
Caching
Deep learning
DeepCache
Fake requests
Lstm
Machine learning
Popularity prediction
Prefetching
Proactive caching
Seq2seq
Smart caching policies
Video object caches

Publisher link

10.1145/3229543.3229555

Find It

Find It at U of M Libraries

Cite this

Narayanan, A., Verma, S., Ramadan, E., Babaie, P., & Zhang, Z.-L. (2018). DEEPCACHE: A deep learning based framework for content caching. In NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018 (pp. 48-53). (NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018). Association for Computing Machinery, Inc. https://doi.org/10.1145/3229543.3229555

DEEPCACHE: A deep learning based framework for content caching. / Narayanan, Arvind; Verma, Saurabh; Ramadan, Eman et al.
NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, 2018. p. 48-53 (NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Narayanan, A, Verma, S, Ramadan, E, Babaie, P & Zhang, Z-L 2018, DEEPCACHE: A deep learning based framework for content caching. in NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018, Association for Computing Machinery, Inc, pp. 48-53, 2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018, Budapest, Hungary, 8/24/18. https://doi.org/10.1145/3229543.3229555

Narayanan A, Verma S, Ramadan E, Babaie P, Zhang ZL. DEEPCACHE: A deep learning based framework for content caching. In NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc. 2018. p. 48-53. (NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018). doi: 10.1145/3229543.3229555

Narayanan, Arvind ; Verma, Saurabh ; Ramadan, Eman et al. / DEEPCACHE : A deep learning based framework for content caching. NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018. Association for Computing Machinery, Inc, 2018. pp. 48-53 (NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018).

@inproceedings{b0c43bc7f8344339a4b09313abdca563,

title = "DEEPCACHE: A deep learning based framework for content caching",

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.",

keywords = "Cache hit, Caching, Deep learning, DeepCache, Fake requests, Lstm, Machine learning, Popularity prediction, Prefetching, Proactive caching, Seq2seq, Smart caching policies, Video object caches",

author = "Arvind Narayanan and Saurabh Verma and Eman Ramadan and Pariya Babaie and Zhi-Li Zhang",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018 ; Conference date: 24-08-2018",

year = "2018",

month = aug,

day = "7",

doi = "10.1145/3229543.3229555",

language = "English (US)",

series = "NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018",

publisher = "Association for Computing Machinery, Inc",

pages = "48--53",

booktitle = "NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018",

}

TY - GEN

T1 - DEEPCACHE

T2 - 2018 ACM SIGCOMM Workshop on Network Meets AI and ML, NetAI 2018

AU - Narayanan, Arvind

AU - Verma, Saurabh

AU - Ramadan, Eman

AU - Babaie, Pariya

AU - Zhang, Zhi-Li

PY - 2018/8/7

Y1 - 2018/8/7

N2 - 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.

AB - 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.

KW - Cache hit

KW - Caching

KW - Deep learning

KW - DeepCache

KW - Fake requests

KW - Lstm

KW - Machine learning

KW - Popularity prediction

KW - Prefetching

KW - Proactive caching

KW - Seq2seq

KW - Smart caching policies

KW - Video object caches

UR - http://www.scopus.com/inward/record.url?scp=85056891888&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056891888&partnerID=8YFLogxK

U2 - 10.1145/3229543.3229555

DO - 10.1145/3229543.3229555

M3 - Conference contribution

AN - SCOPUS:85056891888

T3 - NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018

SP - 48

EP - 53

BT - NetAI 2018 - Proceedings of the 2018 Workshop on Network Meets AI and ML, Part of SIGCOMM 2018

PB - Association for Computing Machinery, Inc

Y2 - 24 August 2018

ER -

DEEPCACHE: A deep learning based framework for content caching

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this