PREDICTING CHARACTERISTICS OF SELF SIMILAR TRAFFIC BY SPLINE-EXTRAPOLATION

2019 ◽  
Author(s):  
Irina Strelkovskay ◽  
Irina Solovskaya ◽  
Anastasija Makoganjuk ◽  
Nikolaj Severin
Keyword(s):  
Quality Characteristics ◽  
Traffic Prediction ◽  
Normative Values ◽  
Spline Functions ◽  
Network Nodes ◽  
Traffic Forecasting ◽  
Network Equipment ◽  
Self Similar ◽  
Accuracy Of Prediction

The problem of forecasting self-similar traffic, which is characterized by a considerable number of ripples and the property of long-term dependence, is considered. It is proposed to use the method of spline extrapolation using linear and cubic splines. The results of self-similar traffic prediction were obtained, which will allow to predict the necessary size of the buffer devices of the network nodes in order to avoid congestion in the network and exceed the normative values ​​of QoS quality characteristics. The solution of the problem of self-similar traffic forecasting obtained with the Simulink software package in Matlab environment is considered. A method of extrapolation based on spline functions is developed. The proposed method has several advantages over the known methods, first of all, it is sufficient ease of implementation, low resource intensity and accuracy of prediction, which can be enhanced by the use of quadratic or cubic interpolation spline functions. Using the method of spline extrapolation, the results of self-similar traffic prediction were obtained, which will allow to predict the required volume of buffer devices, thereby avoiding network congestion and exceeding the normative values ​​of QoS quality characteristics. Given that self-similar traffic is characterized by the presence of "bursts" and a long-term dependence between the moments of receipt of applications in this study, given predetermined data to improve the prediction accuracy, it is possible to use extrapolation based on wavelet functions, the so-called wavelet-extrapolation method. Based on the results of traffic forecasting, taking into account the maximum values ​​of network node traffic, you can give practical guidance on how traffic is redistributed across the network. This will balance the load of network objects and increase the efficiency of network equipment.

scholarly journals Spline-Extrapolation Method in Traffic Forecasting in 5G Networks

2019 ◽  
Vol 3 ◽  
pp. 8-16 ◽  
Author(s):  
Irina Strelkovskaya ◽  
Irina Solovskaya ◽  
Anastasiya Makoganiuk
Keyword(s):  
Research Work ◽  
Mobile Network ◽  
Spline Functions ◽  
B Splines ◽  
Traffic Forecasting ◽  
Short And Long Term ◽  
Self Similar ◽  
Comparison Of The Results ◽  
Packet Data Transmission

This paper considers the problem of predicting self-similar traffic with a significant number of pulsations and the property of long-term dependence, using various spline functions. The research work focused on the process of modeling self-similar traffic handled in a mobile network. A splineextrapolation method based on various spline functions (linear, cubic and cubic B-splines) is proposed to predict selfsimilar traffic outside the period of time in which packet data transmission occurs. Extrapolation of traffic for short- and long-term forecasts is considered. Comparison of the results of the prediction of self-similar traffic using various spline functions has shown that the accuracy of the forecast can be improved through the use of cubic B-splines. The results allow to conclude that it is advisable to use spline extrapolation in predicting self-similar traffic, thereby recommending this method for use in practice in solving traffic prediction-related problems.

scholarly journals Using spline-extrapolation in the research of self-similar traffic characteristics

2019 ◽  
Vol 70 (4) ◽  
pp. 310-316 ◽  
Author(s):  
Irina Strelkovskaya ◽  
Irina Solovskaya
Keyword(s):  
Traffic Management ◽  
Cubic Splines ◽  
Short Term ◽  
Traffic Forecasting ◽  
Traffic Characteristics ◽  
Packet Data ◽  
Self Similar ◽  
Comparison Of The Results ◽  
Packet Data Transmission

Abstract The problem of predicting self-similar traffic is considered, the solution of which modeling of self-similar traffic was performed using the Simulink software package in MATLAB environment. For the simulation, the queuing system WB/M/1/K with Weibull distribution was used. The use of the spline-extrapolation method made it possible to predict self-similar traffic outside the considered period of time on which packet data transmission is considered. Extrapolation of traffic for short-term and long-term forecasts is considered. Comparison of the results of the prediction of self-similar traffic using various spline functions has shown that the accuracy of the forecast can be improved through the use of cubic splines. A method is proposed for estimating the error of traffic prediction for each variant of traffic forecasting using linear, cubic splines. The results of the research will allow you to perform effective traffic management with the support of quality characteristics, by providing the required parameters of network hardware and software in order to avoid overloads in the network.

DEEP LEARNING WITH LONG-TERM SHORT-TERM MEMORY FOR IOT TRAFFIC PREDICTION

2021 ◽  
Author(s):  
А.С. БОРОДИН ◽  
А.Р. АБДЕЛЛАХ ◽  
А.Е. КУЧЕРЯВЫЙ
Keyword(s):  
Deep Learning ◽  
Communication Networks ◽  
Short Term Memory ◽  
Traffic Prediction ◽  
Short Term ◽  
Term Memory ◽  
Traffic Forecasting ◽  
Long Short Term Memory ◽  
Iot Devices

Использование искусственного интеллекта в сетях связи пятого (5G) и последующих поколений дает новые возможности, в том числе для прогнозирования трафика. Это особенно важно для трафика интернета вещей (IoT - Internet of Things), поскольку число устройств IoT очень велико. Предлагается для прогнозирования трафика IoT применить глубокое обучение с использованием нейронной сети долговременной краткосрочной памяти LSTM (Long Short-Term Memory). The use of artificial intelligence in communication networks of the 5G and subsequent generations provides completely new opportunities, including for traffic forecasting. This is especially important for IoT traffic because the number of IoT devices is very large. The article proposes to apply deep learning to predict IoT traffic using a neural network of longterm short-term memory (LSTM).

scholarly journals Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1151
Author(s):  
Carolina Gijón ◽  
Matías Toril ◽  
Salvador Luna-Ramírez ◽  
María Luisa Marí-Altozano ◽  
José María Ruiz-Avilés
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Data Traffic ◽  
Medium Term ◽  
Short Term ◽  
Traffic Forecasting ◽  
Series Analysis ◽  
Radio Planning

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

scholarly journals Network Bandwidth Utilization Prediction Based on Observed SNMP Data

2018 ◽  
Vol 13 (1) ◽  
pp. 160-168
Author(s):  
Nandalal Rana ◽  
Krishna P Bhandari ◽  
Surendra Shrestha
Keyword(s):  
Linear Time ◽  
Arima Model ◽  
Real Data ◽  
Service Planning ◽  
Bandwidth Utilization ◽  
Network Nodes ◽  
Network Bandwidth ◽  
Bandwidth Requirement ◽  
Logit Transformation

 Bandwidth requirement prediction is an important part of network design and service planning. The natural way of predicting bandwidth requirement for existing network is to analyze the past trends and apply appropriate mathematical model to predict for the future. For this research, the historical usage data of FWDR network nodes of Nepal Telecom is subject to univariate linear time series ARIMA model after logit transformation to predict future bandwidth requirement. The predicted data is compared to the real data obtained from the same network and the predicted data has been found to be within 10% MAPE. This model reduces the MAPE by 11.71% and 15.42% respectively as compared to the non-logit transformed ARIMA model at 99% CI. The results imply that the logit transformed ARIMA model has better performance compared to non-logit-transformed ARIMA model. For more accurate and longer term predictions, larger dataset can be taken along with season adjustments and consideration of long term variations.Journal of the Institute of Engineering, 2017, 13(1): 160-168

Introducing Automation in Service Delivery Procedures

2015 ◽  
pp. 409-430
Author(s):  
Isabel Borges
Keyword(s):  
Information Technologies ◽  
High Volume ◽  
Resource Provisioning ◽  
Network Services ◽  
Network Nodes ◽  
Network Equipment ◽  
Standard Information ◽  
Network Functions ◽  
And Storage ◽  
Data Centres

The combination of Software-Defined Networking (SDN) with Network Functions Virtualization (NFV) approaches is gaining momentum in the Industry as a new way of implementing, managing and controlling telecommunications networks. This chapter aims to go through SDN and lightly over NFV, presenting main characteristics and the standardization work on that technologies. SDN enables programming networks together with the ability to adapt to applications requirements and network dynamics. NFV aims at virtualizing network services by merging several network equipment types onto standard Information Technologies (IT) high volume virtualization technology (switches, servers and storage) located either in data centres, customer premises or network nodes. SDN and NFV interworking ambition is to bring on-demand resource provisioning, resource elasticity, among others with a centralized view of the overall network, able to automatically and dynamically honor service requirements.

Sign in / Sign up

Export Citation Format

Share Document