A novel network traffic combination prediction model

Tian, Zhongda; Song, Pengfei

doi:10.1002/dac.5097

Cited by 10 publications

(4 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the same time, it can also effectively suppress or eliminate complex environments under the influence of noise. It has certain research prospects in complex neural networks [27,28], traffic prediction models [29][30][31], and network security [32][33][34].…”

Section: Eemd Algorithmmentioning

confidence: 99%

Retracted: Anomaly detection with ensemble empirical mode decomposition and approximate entropy for quick user datagram protocol internet connection‐based distributed Blockchain systems

Cao

et al. 2023

IET Software

View full text Add to dashboard Cite

With the vigorous development of mobile Internet and Blockchain, the rapid and secure interaction of high-frequency data in the era of data explosion has gradually become an urgent need for people. Quick User Datagram Protocol Internet Connection Protocol (QUIC) can be perfectly integrated into the Blockchain due to its low latency and high security, providing a safe and reliable transmission service for the Blockchain system. However, QUIC-based distributed Blockchain systems are vulnerable to cyberattacks due to asymmetric encryption and timestamp, which seriously impacts security and fairness. Therefore, based on the self-similarity of QUIC network traffic, this study proposes an anomaly detection model for QUIC network traffic based on Ensemble Empirical Mode Decomposition and Approximate Entropy. The model obtains several intrinsic mode functions and a residual term by decomposing the network traffic, introducing Approximate Entropy to judge the complexity of each component, and using the Hurst parameter to determine the generation of abnormal traffic. Compared with traditional detection methods, the model can effectively overcome the problems of poor adaptive ability and low efficiency and has high accuracy, which can be used for attack detection and prevention of network nodes. K E Y W O R D S computer network security, data flow analysis, software reliability, transport protocols 1 | INTRODUCTION Blockchain technology is an integrated and innovative application of various IT technologies. It is a technical solution for storing, verifying, transmitting, and exchanging network data without relying on a third party and its distributed nodes. It has two core characteristics: data is difficult to tamper with and decentralisation. Based on these two characteristics, the information recorded by the Blockchain is more authentic and reliable, which can help solve the problem of people's mutual distrust [1, 2]. It solves the problem of data trust and security through distributed ledgers, consensus mechanisms, smart contracts, authorisation, and encryption [3]. In recent years, Blockchain technology is continuously empowering various fields. Figure 1 shows a 5G wireless network and Blockchainbased network architecture. The architecture collects real-time data through the Internet of Things and uploads the data and events to the Blockchain platform, enabling secure scheduling of terminal devices connected to the 5G network [4]. Integrating 5G and Blockchain technology will open the era of inter-chain integration, which can provide an efficient, safe, and fast service experience. With the continuous development This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Eemd Algorithmmentioning

confidence: 99%

Retracted: Anomaly detection with ensemble empirical mode decomposition and approximate entropy for quick user datagram protocol internet connection‐based distributed Blockchain systems

Cao

et al. 2023

IET Software

View full text Add to dashboard Cite

show abstract

“…e experiments of many neural network methods to predict the network traffic data show that in a real-time network data set, LSTM is of better performance than Recurrent Neural Network (RNN), the Feed-forward Neural Network (FFN), and other classic methods. LSTM neural network can more accurately simulate time series and its long-term dependencies than the traditional RNN, in large network traffic matrix prediction, and obtain a faster convergence rate [25]. e variants of LSTM neural network, GRU neural network, and identity-RNN (IRNN) have comparable performance with LSTM [26].…”

Section: Nonparametric Modelmentioning

confidence: 99%

A Hybrid Approach by CEEMDAN-Improved PSO-LSTM Model for Network Traffic Prediction

Shao

Song

Bian

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

As an important part of data management, network traffic evaluation and prediction can not only find network anomalies but also judge the future trends of the network. To predict network traffic more accurately, a novel hybrid model, integrating Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) with long short-term memory neural network (LSTM) optimized by the improved particle swarm optimization (IPSO) algorithm, is established for network traffic prediction. Firstly, an LSTM prediction model for the real-time mutation and dependence of network traffic is constructed, and the IPSO is applied to optimize the hyperparameters. Then, CEEMDAN is introduced to decompose sequences of raw network traffic data into several different modal components containing different information to reduce the complexity of the network traffic sequence. Finally, the evaluation of the experiments shows the feasibility and effectiveness of the proposed method by comparing it with other deep neural architectures and regression models. The results show that the proposed model CEEMDAN-IPSO-LSTM produced a significantly superior performance with a reduction of the prediction error.

show abstract

“…The difference in the network environment or the use of encryption protocol [31] will significantly impact the time interval of data packets [32], and the arrival time interval of data packets is far from the exponential distribution. Since Tor is a low-latency anonymous communication system, it affects the time-related characteristics, such as the number of data packets and the arrival time of data packets, so these time-related flow statistics can be used as an effective way [33][34][35] to distinguish Tor flow.…”

Section: Subsection Tor Flow Characteristicsmentioning

confidence: 99%

Bidirectional Statistical Feature Extraction Based on Time Window for Tor Flow Classification

Hong-ping

Song

et al. 2022

Symmetry

View full text Add to dashboard Cite

The anonymous system Tor uses an asymmetric algorithm to protect the content of communications, allowing criminals to conceal their identities and hide their tracks. This malicious usage brings serious security threats to public security and social stability. Statistical analysis of traffic flows can effectively identify and classify Tor flow. However, few features can be extracted from Tor traffic, which have a weak representational ability, making it challenging to combat cybercrime in real-time effectively. Extracting and utilizing more accurate features is the key point to improving the real-time detection performance of Tor traffic. In this paper, we design an efficient and real-time identification scheme for Tor traffic based on the time window method and bidirectional statistical characteristics. In this paper, we divide the network traffic by sliding the time window and then calculate the relative entropy of the flows in the time window to identify Tor traffic. We adopt a sequential pattern mining method to extract bidirectional statistical features and classify the application types in the Tor traffic. Finally, extensive experiments are carried out on the UNB public dataset (ISCXTor2016) to validate our proposal’s effectiveness and real-time property. The experiment results show that the proposed method can detect Tor flow and classify Tor flow types with an accuracy of 93.5% and 91%, respectively, and the speed of processing and classifying a single flow is 0.05 s, which is superior to the state-of-the-art methods.

show abstract

A novel network traffic combination prediction model

Cited by 10 publications

References 51 publications

Retracted: Anomaly detection with ensemble empirical mode decomposition and approximate entropy for quick user datagram protocol internet connection‐based distributed Blockchain systems

Retracted: Anomaly detection with ensemble empirical mode decomposition and approximate entropy for quick user datagram protocol internet connection‐based distributed Blockchain systems

A Hybrid Approach by CEEMDAN-Improved PSO-LSTM Model for Network Traffic Prediction

Bidirectional Statistical Feature Extraction Based on Time Window for Tor Flow Classification

Contact Info

Product

Resources

About