A General Approach for Traffic Classification in Wireless Networks Using Deep Learning

Camelo, Miguel; Soto, Paola; Latré, Steven

doi:10.1109/tnsm.2021.3130382

Cited by 16 publications

(31 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traffic classification in wired as well as wireless networks has been researched well over the past two decades. Both machine learning [134], [135] and conventional traffic classification techniques [136], [137] have been studied and promising results have been achieved. Recently, traffic classification studies have focused on IoT networks due to different characteristics of IoT traffic and diverse QoS requirements [138], [139].…”

Section: Role Of Ai and ML In Distributed Network Management And Edge...mentioning

confidence: 99%

“…Therefore, statistics based traffic classification are well suited at edge devices considering their limited computational powers as well. AI & ML algorithms have shown promising results in classifying IoT traffic with higher accuracy (up to 83.3% [127] with Decision Trees and up to 94% [135] with CNNs) and their employment at the edge devices can build highly reliable IoT networks with diverse QoS needs. Readers are referred to [127], [134], [135] for detailed surveys of AI & ML techniques for traffic classification.…”

Section: Role Of Ai and ML In Distributed Network Management And Edge...mentioning

confidence: 99%

See 1 more Smart Citation

AI-Enabled Reliable QoS in Multi-RAT Wireless IoT Networks: Prospects, Challenges, and Future Directions

Zia

Chiumento

Havinga

2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Wireless IoT networks have seen an unprecedented rise in number of devices, heterogeneity and emerging use cases which led to diverse throughput, reliability and latency (Quality of Service) requirements. Fulfilling these diverse requirements in a rapidly changing and dynamic wireless environment is a complex and challenging task. On top of including new technologies and wireless standards, one solution is to deploy cross-layer Design (CLD) and multiple Radio Access Technologies (Multi-RAT) to develop scalable QoS-aware IoT networks. However, the complexity of such solutions is high as it involves complex inter-layer interactions and dependencies and inter-application dependencies in multi-RAT networks. Moreover, the wireless environment is very dynamic, so having an optimal constellation of parameters is a challenging task. In this paper, we address the possibilities of using Artificial Intelligence (AI) and Machine Learning (ML) to address these high dimensional and dynamic problems. Based on our findings, we have proposed a distributed network management framework employing AI & ML for studying inter-layer dependencies and developing cross-layer design, traffic classification and traffic prediction at the edge devices for reliable QoS in multi-RAT IoT networks. A thorough discussion on future directions and emerging challenges related to our proposed framework has also been provided for further research in this field.INDEX TERMS QoS in IoT networks, AI & ML for cross-layer design, cross-layer optimization, reliable QoS, multi-RAT networks, edge intelligence.

show abstract

Section: Role Of Ai and ML In Distributed Network Management And Edge...mentioning

confidence: 99%

Section: Role Of Ai and ML In Distributed Network Management And Edge...mentioning

confidence: 99%

AI-Enabled Reliable QoS in Multi-RAT Wireless IoT Networks: Prospects, Challenges, and Future Directions

Zia

Chiumento

Havinga

2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…There are, however, a slew of additional options. However, they can all be utilized to calculate classification and, as a result, to judge the model's quality in classification procedures [33].…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…The authors of [33] introduced a novel framework to carry out traffic classification at any layer on the radio network stack. An RNN-based baseline architecture was described, and its performance was benchmarked on three TC workloads at different radio stack layers.…”

Section: Introductionmentioning

confidence: 99%

VPN and Non-VPN Network Traffic Classification Using Time-Related Features

Al-Fayoumi¹,

Al-Fawa’reh²,

Nashwan³

2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The continual growth of the use of technological appliances during the COVID-19 pandemic has resulted in a massive volume of data flow on the Internet, as many employees have transitioned to working from home. Furthermore, with the increase in the adoption of encrypted data transmission by many people who tend to use a Virtual Private Network (VPN) or Tor Browser (dark web) to keep their data privacy and hidden, network traffic encryption is rapidly becoming a universal approach. This affects and complicates the quality of service (QoS), traffic monitoring, and network security provided by Internet Service Providers (ISPs), particularly for analysis and anomaly detection approaches based on the network traffic's nature. The method of categorizing encrypted traffic is one of the most challenging issues introduced by a VPN as a way to bypass censorship as well as gain access to geo-locked services. Therefore, an efficient approach is especially needed that enables the identification of encrypted network traffic data to extract and select valuable features which improve the quality of service and network management as well as to oversee the overall performance. In this paper, the classification of network traffic data in terms of VPN and non-VPN traffic is studied based on the efficiency of time-based features extracted from network packets. Therefore, this paper suggests two machine learning models that categorize network traffic into encrypted and non-encrypted traffic. The proposed models utilize statistical features (SF), Pearson Correlation (PC), and a Genetic Algorithm (GA), preprocessing the traffic samples into net flow traffic to accomplish the experiment's objectives. The GA-based method utilizes a stochastic method based on natural genetics and biological evolution to extract essential features. The PC-based method performs well in removing different features of network traffic. With a microsecond perpacket prediction time, the best model achieved an accuracy of more than 95.02 percent in the most demanding traffic classification task, a drop in accuracy of only 2.37 percent in comparison to the entire statistical-based machine learning approach. This is extremely promising for the development of real-time traffic analyzers.

show abstract

“…1) A methodology that leverages the latest advancements in MTL and lightweight ML algorithms to provide an efficient and effective solution for this problem. To the best knowledge of the authors, this is the first work proposing a detailed methodology to design tailor-made DNN for TC at the spectrum level, providing both STL and MTL models that can run on constrained devices such as the NVIDIA Jetson TX2 4 , removing the limitations of state-of-the-art works that are resource hungry such as our previous one [8].…”

Section: Introductionmentioning

confidence: 99%

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Góez,

Aycan Beyazit,

Fletscher

et al. 2024

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

Traffic Classification (TC) systems are designed to identify the applications generating network traffic. Recent advancements in TC leverage Deep Learning (DL) techniques, surpassing traditional methods in complex scenarios, including those with encrypted traffic. Notably, state-of-the-art DL-based TC systems have been developed for wireless networks using Physical Layer (L1) packets. This approach overcomes the common limitation in TC research that assumes traffic flows within a wired network under a single network management domain. Despite their benefits, DL-based TC systems often demand significant computational resources, typically available only in cloud environments. Consequently, deploying models at the edge is often infeasible due to their resource-intensive nature, given their original training and optimization for high-resource environments. The inherent challenge lies in adapting these systems for edge computing scenarios, including deployment at access points. In this paper, we propose a novel methodology that exploits expert knowledge in combination with recent advances in Multi-Task Learning (MTL) and Deep Neural Network (DNN) optimization to allow spectrum-based TC systems to run on constrained devices. Performance evaluations on an NVIDIA Jetson TX2 demonstrate that our most optimized MTL model, handling four TC tasks, can reduce memory requirements by a factor of 2.65x and improve execution time by 3.6x compared to sequential execution of four Single-Task Learning (STL) models in a servergrade configuration, with minimal accuracy impact (less than a 0.5% drop) and energy efficiency of 0.97 millijoules per sample at inference. Compared to other edge platforms such as the Raspberry Pi model 3B+ (RPI3B+) with a low-power Artificial Intelligence (AI)-accelerator such as the Coral Tensor Processing Unit (TPU), the NVIDIA Jetson achieves a 12-fold improvement in energy efficiency with no impact on accuracy. These are the first available results to provide a benchmark for different performance metrics (memory, computing, energy) over heterogeneous constrained devices for this type of TC system.

show abstract

A General Approach for Traffic Classification in Wireless Networks Using Deep Learning

Cited by 16 publications

References 47 publications

AI-Enabled Reliable QoS in Multi-RAT Wireless IoT Networks: Prospects, Challenges, and Future Directions

AI-Enabled Reliable QoS in Multi-RAT Wireless IoT Networks: Prospects, Challenges, and Future Directions

VPN and Non-VPN Network Traffic Classification Using Time-Related Features

Resource-Efficient Spectrum-Based Traffic Classification on Constrained Devices

Contact Info

Product

Resources

About