scholarly journals SELF-SIMILARITY TECHNIQUES FOR CHAOTIC ATTRACTORS WITH MANY SCROLLS USING STEP SERIES SWITCHING

2021 ◽  
Vol 26 (4) ◽  
pp. 591-611
Author(s):  
Emile Franc Doungmo Goufo ◽  
Chokkalingam Ravichandran ◽  
Gunvant A. Birajdar
Keyword(s):  
Chaos Theory ◽  
Network Traffic ◽  
Chaotic Systems ◽  
Switching Process ◽  
Traffic Prediction ◽  
Chaotic Attractors ◽  
Numerical Techniques ◽  
Self Similarity ◽  
Mathematical Concepts ◽  
Natural Way

Highly applied in machining, image compressing, network traffic prediction, biological dynamics, nerve dendrite pattern and so on, self-similarity dynamic represents a part of fractal processes where an object is reproduced exactly or approximately exact to a part of itself. These reproduction processes are also very important and captivating in chaos theory. They occur naturally in our environment in the form of growth spirals, romanesco broccoli, trees and so on. Seeking alternative ways to reproduce self-similarity dynamics has called the attention of many authors working in chaos theory since the range of applications is quite wide. In this paper, three combined notions, namely the step series switching process, the Julia’s technique and the fractal-fractional dynamic are used to create various forms of self-similarity dynamics in chaotic systems of attractors, initially with two, five and seven scrolls. In each case, the solvability of the model is addressed via numerical techniques and related graphical simulations are provided. It appears that the initial systems are able to trigger a self-similarity process that generates the exact or approximately exact copy of itself or part of itself. Moreover, the dynamics of the copies are impacted by some model’s parameters involved in the process. Using mathematical concepts to re-create features that usually occur in a natural way proves to be a prowess as related applications are many for engineers.

DELAYED FEEDBACK CONTROL OF CHAOTIC SYSTEMS WITH DRY FRICTION

2002 ◽  
Vol 12 (08) ◽  
pp. 1877-1883 ◽  
Author(s):  
UGO GALVANETTO
Keyword(s):  
Dry Friction ◽  
Chaotic Systems ◽  
Control Method ◽  
Delayed Feedback ◽  
Delayed Feedback Control ◽  
Chaotic Attractors ◽  
Unstable Periodic Orbits ◽  
Numerical Techniques ◽  
The Stability ◽  
Time Delayed Feedback

This paper describes some numerical techniques to control unstable periodic orbits embedded in chaotic attractors of a particular discontinuous mechanical system. The control method is a continuous time delayed feedback that modifies the stability of the orbit but does not affect the orbit itself.

Network traffic prediction based on wavelet FARIMA model

2011 ◽  
Vol 31 (4) ◽  
pp. 901-903
Author(s):  
Yong SUN ◽  
Guang-wei BAI ◽  
Lu ZHAO
Keyword(s):  
Network Traffic ◽  
Traffic Prediction

scholarly journals Attention based multi-component spatiotemporal cross-domain neural network model for wireless cellular network traffic prediction

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Qingtian Zeng ◽  
Qiang Sun ◽  
Geng Chen ◽  
Hua Duan
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Network Traffic ◽  
Cellular Network ◽  
Critical Issue ◽  
Traffic Prediction ◽  
Weekly Cycle ◽  
Cross Domain ◽  
Cellular Traffic

AbstractWireless cellular traffic prediction is a critical issue for researchers and practitioners in the 5G/B5G field. However, it is very challenging since the wireless cellular traffic usually shows high nonlinearities and complex patterns. Most existing wireless cellular traffic prediction methods lack the abilities of modeling the dynamic spatial–temporal correlations of wireless cellular traffic data, thus cannot yield satisfactory prediction results. In order to improve the accuracy of 5G/B5G cellular network traffic prediction, an attention-based multi-component spatiotemporal cross-domain neural network model (att-MCSTCNet) is proposed, which uses Conv-LSTM or Conv-GRU for neighbor data, daily cycle data, and weekly cycle data modeling, and then assigns different weights to the three kinds of feature data through the attention layer, improves their feature extraction ability, and suppresses the feature information that interferes with the prediction time. Finally, the model is combined with timestamp feature embedding, multiple cross-domain data fusion, and jointly with other models to assist the model in traffic prediction. Experimental results show that compared with the existing models, the prediction performance of the proposed model is better. Among them, the RMSE performance of the att-MCSTCNet (Conv-LSTM) model on Sms, Call, and Internet datasets is improved by 13.70 ~ 54.96%, 10.50 ~ 28.15%, and 35.85 ~ 100.23%, respectively, compared with other existing models. The RMSE performance of the att-MCSTCNet (Conv-GRU) model on Sms, Call, and Internet datasets is about 14.56 ~ 55.82%, 12.24 ~ 29.89%, and 38.79 ~ 103.17% higher than other existing models, respectively.

scholarly journals Autoregressive models of network traffic prediction

2021 ◽  
Vol 1864 (1) ◽  
pp. 012099
Author(s):  
T. Tatarnikova ◽  
B. Sovetov ◽  
V. Chehanovsky
Keyword(s):  
Network Traffic ◽  
Autoregressive Models ◽  
Traffic Prediction

scholarly journals Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1578
Author(s):  
Daniel Szostak ◽  
Adam Włodarczyk ◽  
Krzysztof Walkowiak
Keyword(s):  
Machine Learning ◽  
Optical Networks ◽  
Network Traffic ◽  
Optical Network ◽  
Optimization Methods ◽  
Supervised Machine Learning ◽  
Traffic Prediction ◽  
Machine Learning Classification ◽  
Classification And Regression ◽  
Network Technologies

Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.

Sign in / Sign up

Export Citation Format

Share Document