DeepNFV: A Lightweight Framework for Intelligent Edge Network Functions Virtualization
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Traditional Network Functions Virtualization (NFV) implementations are somehow too heavy and do not have enough functionality to conduct complex tasks. In this work, we propose a lightweight NFV framework named DeepNFV, which is based on the Docker container running on the network edge, and integrates state-of-the-art deep learning models with NFV containers to address some complicated problems, such as traffic classification, link analysis, and so on. We compare the DeepNFV framework with several existing works, and detail its structures and functions. The most significant advantage of DeepNFV is its lightweight design, resulting from the virtualization and low-cost nature of the container technology. Also, we design this framework to be compatible with edge devices, in order to decrease the computational overhead of the central servers. Another merit is its strong analysis ability brought by deep learning models, which make it suitable for many more scenarios than traditional NFV approaches. In addition, we also describe some typical application scenarios, regarding how the NFV container works and how to utilize its learning ability. Simulations demonstrate its high efficiency, as well as the outstanding recognition performance in a typical use case.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep packet: a novel approach for encrypted traffic classification using deep learning
Lotfollahi, M., Jafari Siavoshani, M., Shirali Hossein Zade, R., & Saberian, M. (2020) · Soft Computing · doi:10.1007/s00500-019-04030-2 · Cited by 1,190
End-to-end encrypted traffic classification with one-dimensional convolution neural networks
Wang, W., Zhu, M., Wang, J., Zeng, X., & Yang, Z. (2017) · 2017 IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi.2017.8004872 · Cited by 991 · cited 1×
“We built our solution on top of several well developed theories in relevant areas [14, 15], and design an efficient model for traffic recognition.”
MethodCollaborative Mobile Edge Computing in 5G Networks: New Paradigms, Scenarios, and Challenges
Tran, T. X., Hajisami, A., Pandey, P., & Pompili, D. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1600863 · Cited by 874 · cited 1×
“The other one is that cloud resources are optimized by enabling the edge devices with computing ability [9].”
BackgroundFadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2707140 · Cited by 810 · cited 1×
“Due to their superior abilities of automatic feature extraction, deep learning models can find the hidden patterns in raw data, and based on that, infer the possible relationships between the input and the pre-defined labels [3], that is, the classification.”
BackgroundDesigning Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Yang, T.-J., Chen, Y.-H., & Sze, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.643 · Cited by 732 · cited 1×
“, [12] designed an energy-aware pruning method to decrease the energy cost of convolutional neural network (CNN) models.”
MethodRodrigues, T. G., Suto, K., Nishiyama, H., & Kato, N. (2017) · IEEE Transactions on Computers · doi:10.1109/tc.2016.2620469 · Cited by 374 · cited 1×
“There are also several works focused on network delay for the edge computing environment [11].”
BackgroundArkian, H. R., Diyanat, A., & Pourkhalili, A. (2017) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2017.01.012 · Cited by 247 · cited 1×
“The authors in [10] present an edge computing based scheme to support crowdsensing applications.”
BackgroundTang, F., Mao, B., Fadlullah, Z. M., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2018) · IEEE Wireless Communications · doi:10.1109/mwc.2017.1700244 · Cited by 247 · cited 1×
“For example, the authors in [13] adopt the CNN model, and design an intelligent traffic control system.”
MethodPerformance Guaranteed Computation Offloading for Mobile-Edge Cloud Computing
Tao, X., Ota, K., Dong, M., Qi, H., & Li, K. (2017) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2017.2740927 · Cited by 218 · cited 1×
“To resolve this problem, edge computing is proposed to move the computing ability from the centralized servers to the devices near the user-end [8].”
Self-citationContainer Network Functions: Bringing NFV to the Network Edge
Cziva, R., & Pezaros, D. P. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1601039 · Cited by 134 · cited 3×
“GNF is proposed in [6] for container-based vNF implementation, which can take control of the vNF containers and publish the vNFs to the users.”
BackgroundInfluential
Research works printed but not linked: 1
- chiosi, 0, Network Functions Virtualisation: An Introduction, Benefits, Enablers, Challenges and Call for Action, SDN and OpenFlow World Congress, 22
Cited by
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498
“On the other hand, both VNFs and Edge DL services can be hosted on a lightweight NFV framework (deployed on the edge) [74], thus reusing the infrastructure and infrastructure management of NFV to the largest extent possible [75].”
BackgroundCyber security meets artificial intelligence: a survey
Li, J.-H. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1800573 · Cited by 329
Zhou, Z., Wang, B., Dong, M., & Ota, K. (2020) · IEEE Transactions on Systems, Man, and Cybernetics: Systems · doi:10.1109/tsmc.2019.2896323 · Cited by 290
“We consider a V2G energy trading scenario which involves three major entities: 1) local energy aggregators (LEAGs); 2) EVs; and 3) edge computing service provider (ESP) [22], [23].”
BackgroundSelf-citationGyamfi, E., & Jurcut, A. (2022) · Sensors · doi:10.3390/s22103744 · Cited by 171
“MEC-based NIDS for the IoT system is implemented based on virtualized platforms that use modern technology improvement in network functions virtualization (NFV) [106], information-centric networks (ICN) [107], and software-defined networks (SDN) [108–110].”
MethodEmerging Trends, Techniques and Open Issues of Containerization: A Review
Watada, J., Roy, A., Kadikar, R., Pham, H., & Xu, B. (2019) · IEEE Access · doi:10.1109/access.2019.2945930 · Cited by 204
“Traditional NFV approaches adopted full-fledged VMs which made them extremely heavy and were unable to perform complex tasks [100].”
BackgroundNetworking Systems of AI: On the Convergence of Computing and Communications
Song, L., Hu, X., Zhang, G., Spachos, P., Plataniotis, K. N., & Wu, H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3172270 · Cited by 143
“Li et al. [104] proposed a lightweight NFV framework named DeepNFV, which was based on the Docker container running on the network edge, and integrated state-of-the-art deep learning models with NFV containers to address some complicated problems, such as traffic clas-sification, link analysis, etc.…”
BackgroundWu, J., Dong, M., Ota, K., Li, J., Yang, W., & Wang, M. (2019) · IEEE Communications Magazine · doi:10.1109/mcom.2019.1800778 · Cited by 104
“Since the modern router size is limited, the content store size is shown in many research studies as the key element that influences the total delay and impedes the progress of the information-centric future Internet [3][4].”
BackgroundSelf-citationAdoga, H. U., & Pezaros, D. P. (2022) · Future Internet · doi:10.3390/fi14020059 · Cited by 92
“DeepNFV is built on the GNF framework [19], which uses lightweight docker containers to build network functions for the edge.”
BackgroundInfluentialA Theoretical Discussion and Survey of Network Automation for IoT: Challenges and Opportunity
Arzo, S. T., Serugunda, C. N., Granelli, F., Bassoli, R., Devetsikiotis, M., & Fitzek, F. H. P. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3075901 · Cited by 85
Preserving Edge Knowledge Sharing Among IoT Services: A Blockchain-Based Approach
Li, G., Dong, M., Yang, L. T., Ota, K., Wu, J., & Li, J. (2020) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2019.2952587 · Cited by 69
“Literature [35] envisioned that the ECI may enable computation-oriented multiple access for ultra-fast data aggregation, importance-”
BackgroundSelf-citationLiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices
He, Z., Zhang, X., Cao, Y., Liu, Z., Zhang, B., & Wang, X. (2018) · Sensors · doi:10.3390/s18041229 · Cited by 65
“To address this situation, some research [19,20] has focused on how to perform optimal resource allocations on resource-constrained mobile devices, and conducted MEC in various scenarios [21–23].”
NFV Platforms: Taxonomy, Design Choices and Future Challenges
Zhang, T., Qiu, H., Linguaglossa, L., Cerroni, W., & Giaccone, P. (2020) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2020.3045381 · Cited by 70
“NetBricks [18] facilitates the VNF development process by implementing a small set of core processing elements that are highly optimized and customizable through user-defined functions.”
Improved QoS at the Edge Using Serverless Computing to Deploy Virtual Network Functions
Chaudhry, S. R., Palade, A., Kazmi, A., & Clarke, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3011057 · Cited by 60
Liu, H., Long, X., Li, Z., Long, S., Ran, R., & Wang, H. (2022) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2022.3180105 · Cited by 53
“There is also a corresponding boot time for both VMs and containers during the instance deployment [7].”
BackgroundData Transformation Schemes for CNN-Based Network Traffic Analysis: A Survey
Krupski, J., Graniszewski, W., & Iwanowski, M. (2021) · Electronics · doi:10.3390/electronics10162042 · Cited by 56
“Li et al. removed the L2 headers and modified the L4+ headers to form the CNN input [110].”
Energy Efficient Hybrid Edge Caching Scheme for Tactile Internet in 5G
Xu, J., Ota, K., & Dong, M. (2019) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2019.2905225 · Cited by 49
“Li et al. [17] and [18] apply MEC into deep learning and network function virtualization.”
BackgroundSelf-citationOnline multimedia traffic classification from the QoS perspective using deep learning
Wu, Z., Dong, Y., Qiu, X., & Jin, J. (2022) · Computer Networks · doi:10.1016/j.comnet.2021.108716 · Cited by 46
Gupta, N., Anantharaj, K., & Subramani, K. (2020) · 2020 International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci48352.2020.9104073 · Cited by 23
Ni, Z., Chen, H., Li, Z., Wang, X., Yan, N., Liu, W., & Xia, F. (2021) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2021.3131177 · Cited by 27
“Moreover, with the development of Network Function Virtualization (NFV) technology, the construction of virtual resource pool becomes feasible [13].”
BackgroundFrom MPLS to SD-WAN to ensure QoS and QoE in cloud-based applications
Borgianni, L., Troìa, S., Adami, D., Maier, G. A., & Giordano, S. (2023) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft57336.2023.10175470 · Cited by 22
“There has been a growing interest in using machine learning techniques in networking, particularly in traffic classification for automated intrusion detection systems [4].”
BackgroundTEST: an End-to-End Network Traffic Classification System With Spatio-Temporal Features Extraction
Zeng, Y., Qi, Z., Chen, W., & Huang, Y. (2019) · IEEE International Conference on Smart Cloud (SmartCloud) · doi:10.1109/smartcloud.2019.00032 · Cited by 19
“However, traditional ML-based methods like KNN [6] or SVM [7], their efficiency and 1 Wencheng Chen is the corresponding author. accuracy extremely rely on manually selected features, where some features are privacy-related now [8].”
MethodChen, J., Cheng, X., Chen, J., & Zhang, H. (2021) · IEEE Systems Journal · doi:10.1109/jsyst.2021.3111972 · Cited by 21
“…and docker is a lightweight implementation of the NFV system, since the container-based NFV virtualization is a lightweight implementation for consuming less resource and time, compared with virtual-machine-based virtualization, which consumes more resources in the underlying hardware [13], [14].”
BackgroundWu, J., Dong, M., Ota, K., Li, J., & Yang, W. (2019) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2019.2913317 · Cited by 14
“Many advanced computing and networking technologies can be introduced into smart manufacturing to improve the efficiency and performance, such as software-defined networking (SDN), information-centric networking (ICN), and fog computing [3], [4], [5], [6].”
BackgroundSelf-citationDeep Reinforcement Learning for AoI Aware VNF Placement in Multiple Source Systems
Chen, Z., Li, H., Ota, K., & Dong, M. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001066 · Cited by 12
“To realize required network services, multiple VNFs should be chained in a specific order as a Service Function Chaining (SFC) and then placed over the NFV infrastructure [3].”
BackgroundSelf-citationA Novel Approach to Multi-Provider Network Slice Selector for 5G and Future Communication Systems
da Silva, D. C., Batista, J. O. R., de Sousa, M. A. F., Mostaço, G. M., Monteiro, C. D. C., Bressan, G., Cugnasca, C. E., & Silveira, R. M. (2022) · Sensors · doi:10.3390/s22166066 · Cited by 11
Xuan, H., Zhou, Y., Zhao, X., & Liu, Z. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110189 · Cited by 11
Intelligent QoS Agent Design for QoS Monitoring and Provisioning in 6G Network
Arzo, S. T., Tshakwanda, P. M., Worku, Y. M., Kumar, H., & Devetsikiotis, M. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10279078 · Cited by 11
“Recently, several studies have explored the application of machine learning in networking [8].”
BackgroundAssessing the Efficacy of Reinforcement Learning in Enhancing Quality of Service in SD-WANs
Borgianni, L., Troìa, S., Adami, D., Maier, G. A., & Giordano, S. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437333 · Cited by 10
Data Driven Resource Allocation for NFV-Based Internet of Things
Tian, X., Huang, W., Yu, Z., & Wang, X. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2916865 · Cited by 10
Multimedia Traffic Classification for Imbalanced Environment
Wu, Z., Dong, Y., Jin, J., Wei, H., & Xie, G. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3153925 · Cited by 9
Edge resource slicing approaches for latency optimization in AI-edge orchestration
Chandrika, P. K., Mekala, M. S., & Srivastava, G. (2022) · Cluster Computing · doi:10.1007/s10586-022-03817-7 · Cited by 11
“A double-DQL [56] has been employed to allot CAC resources for ED to minimize the offloading cost.”
MethodAn optimal container update method for edge‐cloud collaboration
Zhang, H., Lin, W., Xie, R., Li, S., Dai, Z., & Wang, J. Z. (2023) · Software Practice and Experience · doi:10.1002/spe.3232 · Cited by 10
Edge Computing Based Traffic Analysis System Using Broad Learning
Peng, X., Ota, K., & Dong, M. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-22971-9_20 · Cited by 8
Self-citationMultiple-Walrasian Auction Mechanism for Tree Valuation Service in NFV Market
Borjigin, W., Ota, K., & Dong, M. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3151693 · Cited by 9
“A S ONE of emerging methods, the strength of network function virtualization (NFV) lies in to schedule network service resource and improve the expandability and flexibility of such resources [1]–[4].”
MethodSelf-citationPerson re‐identification in the edge computing system: A deep square similarity learning approach
Chen, X., Li, Z., Tang, C., Xiao, S., & Chen, Y. (2019) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.5360 · Cited by 8
“f(l ) =α (l )h(l ),∀l = 0, · · · , L h(l ) = δ(W (l )h(l−1)),∀l = 1, · · · , L, (10)”
MethodInfluentialXu, N., & Li, Q. (2019) · Minerals · doi:10.3390/min9050259 · Cited by 8
A New Ontology Convolutional Neural Network for Extorting Essential Elements in Video Mining
Ganesh, R. K., Kanthavel, R., Dhaya, R., Robinson, H., Julie, E. G., Kumar, R., Duong, P., Thong, P. H., & Sơn, L. H. (2023) · Journal of Signal Processing Systems · doi:10.1007/s11265-023-01864-w · Cited by 6
“In the second stage, testing analyzes a classifier utilizing testing data for its capacity to classify vague records or objects for prediction and accuracy [7].”
MethodMachine Learning-based Service Function Chain over UAVs: Resource Profiling and Framework
Kiên, N. T., Anh, V. H., Phong, V. D., Minh, N. N., & Thanh, N. H. (2021) · International Telecommunication Networks and Applications Conference (ITNAC) · doi:10.1109/itnac53136.2021.9652156 · Cited by 5
V-PSC: A Perturbation-Based Causative Attack Against DL Classifiers' Supply Chain in VANET
Zeng, Y., Qiu, M., Niu, J., Long, Y., Xiong, J., & Liu, M. (2019) · IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC) · doi:10.1109/cse/euc.2019.00026 · Cited by 2
“[3] presented a light-weight DLBased classification method which transforms communication traffic of On-Board Units (OBUs) and Road Side Units (RSUs) into traffic-graphs, then using a 4-layer CNN model to complete the classification.”
MethodDealer: An Efficient Pricing Strategy for Deep-Learning-as-a-Service
Borjigin, W., Ota, K., & Dong, M. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761086 · Cited by 1
Self-citationFundamentals of Edge Computing
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_2 · Cited by 2
da Silva, D. C. (2023) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.3.2023.tde-13122023-100943
Gadouh, K. A., & Koubaa, H. (2024) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa63423.2024.10912551
“NFV is attracting significant interest for the application of machine learning techniques within the research domain, as indicated by recent studies [1]- [2].”
Design of lightweight neural networks for resource-constrained devices
Mohsin, Z. K., Alshammari, R. F. N., & Alsaadi, E. M. T. A. (2025) · Sustainable Engineering and Innovation · doi:10.37868/sei.v7i2.id542
“…huge storage and RAM [11], being prohibitively costly using energy that drains the batteries of portable devices in a matter of no time [12], to increasing inference latencies due to billions of FLOPs, making them unsuitable for real-time applications where instant responses count [13], [14].”
Metadata
- Authors
- Li, L., Ota, K., & Dong, M.
- Affiliations
- Muroran Institute of Technology (JP)
- Venue
- IEEE Network
- Published
- 2019-01
- Volume
- 33
- Issue
- 1
- Pages
- 136-141
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W2888263775
- Cited by
- 43
- References
- 15
- Citations by year
- 2024: 1 · 2023: 7 · 2022: 10 · 2021: 5 · 2020: 6 · 2019: 12
- FWCI
- 3.87
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- IEEE Network (publishedVersion)
- Institutional Repositories DataBase (IRDB) (acceptedVersion)
- Muroran Institute of Technology Academic Resources Archieve (Muroran Institute of Technology) (submittedVersion)
- Funders
- Japan Society for the Promotion of Science (16K00117)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Software-Defined Networks and 5G
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Keywords
- network function virtualization, edge computing, Docker containers, network traffic classification, link analysis, container-based virtualization, computational overhead reduction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.