Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN
In information-centric networking, accurately predicting content popularity can improve the performance of caching. Therefore, based on software defined network (SDN), this paper proposes Deep-Learning-based Content Popularity Prediction (DLCPP) to achieve the popularity prediction. DLCPP adopts the...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8172025/ |
id |
doaj-9423ef2347644d3a9a72c58dead15aa6 |
---|---|
record_format |
Article |
spelling |
doaj-9423ef2347644d3a9a72c58dead15aa62021-03-29T20:29:17ZengIEEEIEEE Access2169-35362018-01-0165075508910.1109/ACCESS.2017.27817168172025Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDNWai-Xi Liu0https://orcid.org/0000-0002-7343-4948Jie Zhang1Zhong-Wei Liang2Ling-Xi Peng3Jun Cai4Department of Electronic and Information Engineering, Guangzhou University, Guangzhou, ChinaDepartment of Electrical Engineering and Automation, Guangzhou University, Guangzhou, ChinaDepartment of Electrical Engineering and Automation, Guangzhou University, Guangzhou, ChinaDepartment of Electronic and Information Engineering, Guangzhou University, Guangzhou, ChinaSchool of Electronic and Information, Guangdong Polytechnic Normal University, Guangzhou, ChinaIn information-centric networking, accurately predicting content popularity can improve the performance of caching. Therefore, based on software defined network (SDN), this paper proposes Deep-Learning-based Content Popularity Prediction (DLCPP) to achieve the popularity prediction. DLCPP adopts the switch's computing resources and links in the SDN to build a distributed and reconfigurable deep learning network. For DLCPP, we initially determine the metrics that can reflect changes in content popularity. Second, each network node collects the spatial-temporal joint distribution data of these metrics. Then, the data are used as input to stacked auto-encoders (SAE) in DLCPP to extract the spatiotemporal features of popularity. Finally, we transform the popularity prediction into a multi-classification problem through discretizing the content popularity into multiple classifications. The Softmax classifier is used to achieve the content popularity prediction. Some challenges for DLCPP are also addressed, such as determining the structure of SAE, realizing the neuron function on an SDN switch, and deploying DLCPP on an OpenFlow-based SDN. At the same time, we propose a lightweight caching scheme that integrates cache placement and cache replacement-caching based on popularity prediction and cache capacity (CPC). Abundant experiments demonstrate good performance of DLCPP, and it achieves close to 2.1%~15% and 5.2%~40% accuracy improvements over neural networks and auto regressive, respectively. Benefitting from DLCPP's better prediction accuracy, CPC can yield a steady improvement of caching performance over other dominant cache management frameworks.https://ieeexplore.ieee.org/document/8172025/Information-centric networkingSDNdeep learningcontent popularity predictioncaching scheme |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Wai-Xi Liu Jie Zhang Zhong-Wei Liang Ling-Xi Peng Jun Cai |
spellingShingle |
Wai-Xi Liu Jie Zhang Zhong-Wei Liang Ling-Xi Peng Jun Cai Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN IEEE Access Information-centric networking SDN deep learning content popularity prediction caching scheme |
author_facet |
Wai-Xi Liu Jie Zhang Zhong-Wei Liang Ling-Xi Peng Jun Cai |
author_sort |
Wai-Xi Liu |
title |
Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN |
title_short |
Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN |
title_full |
Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN |
title_fullStr |
Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN |
title_full_unstemmed |
Content Popularity Prediction and Caching for ICN: A Deep Learning Approach With SDN |
title_sort |
content popularity prediction and caching for icn: a deep learning approach with sdn |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
In information-centric networking, accurately predicting content popularity can improve the performance of caching. Therefore, based on software defined network (SDN), this paper proposes Deep-Learning-based Content Popularity Prediction (DLCPP) to achieve the popularity prediction. DLCPP adopts the switch's computing resources and links in the SDN to build a distributed and reconfigurable deep learning network. For DLCPP, we initially determine the metrics that can reflect changes in content popularity. Second, each network node collects the spatial-temporal joint distribution data of these metrics. Then, the data are used as input to stacked auto-encoders (SAE) in DLCPP to extract the spatiotemporal features of popularity. Finally, we transform the popularity prediction into a multi-classification problem through discretizing the content popularity into multiple classifications. The Softmax classifier is used to achieve the content popularity prediction. Some challenges for DLCPP are also addressed, such as determining the structure of SAE, realizing the neuron function on an SDN switch, and deploying DLCPP on an OpenFlow-based SDN. At the same time, we propose a lightweight caching scheme that integrates cache placement and cache replacement-caching based on popularity prediction and cache capacity (CPC). Abundant experiments demonstrate good performance of DLCPP, and it achieves close to 2.1%~15% and 5.2%~40% accuracy improvements over neural networks and auto regressive, respectively. Benefitting from DLCPP's better prediction accuracy, CPC can yield a steady improvement of caching performance over other dominant cache management frameworks. |
topic |
Information-centric networking SDN deep learning content popularity prediction caching scheme |
url |
https://ieeexplore.ieee.org/document/8172025/ |
work_keys_str_mv |
AT waixiliu contentpopularitypredictionandcachingforicnadeeplearningapproachwithsdn AT jiezhang contentpopularitypredictionandcachingforicnadeeplearningapproachwithsdn AT zhongweiliang contentpopularitypredictionandcachingforicnadeeplearningapproachwithsdn AT lingxipeng contentpopularitypredictionandcachingforicnadeeplearningapproachwithsdn AT juncai contentpopularitypredictionandcachingforicnadeeplearningapproachwithsdn |
_version_ |
1724194742818832384 |