ISSCS 2009, Iasi, Romania1 Forecasting WiMAX BS Traffic by Statistical Processing in the Wavelet Domain Cristina Stolojescu 1, Alina Cușnir 2, Sorin Moga.

Slides:



Advertisements
Similar presentations
Research Directions Mark Crovella Boston University Computer Science.
Advertisements

Travel Time Estimation on Arterial Streets By Heng Wang, Transportation Analyst Houston-Galveston Area Council Dr. Antoine G Hobeika, Professor Virginia.
On the Trend, Detrend and the Variability of Nonlinear and Nonstationary Time Series A new application of HHT.
A.M. Alonso, C. García-Martos, J. Rodríguez, M. J. Sánchez Seasonal dynamic factor model and bootstrap inference: Application to electricity market forecasting.
© 2005, it - instituto de telecomunicações. Todos os direitos reservados. Pedro Santos Traian Abrudan Ana.
Use of Business Tendency Survey Results for Forecasting Industry Production in Slovakia Use of Business Tendency Survey Results for Forecasting Industry.
May 4, Mobile Computing COE 446 Network Planning Tarek Sheltami KFUPM CCSE COE Principles of Wireless.
Part II – TIME SERIES ANALYSIS C5 ARIMA (Box-Jenkins) Models
Exponential Smoothing Methods
Probabilistic Aggregation in Distributed Networks Ling Huang, Ben Zhao, Anthony Joseph and John Kubiatowicz {hling, ravenben, adj,
On the Self-Similar Nature of Ethernet Traffic - Leland, et. Al Presented by Sumitra Ganesh.
Multi-Scale Analysis for Network Traffic Prediction and Anomaly Detection Ling Huang Joint work with Anthony Joseph and Nina Taft January, 2005.
Building the communication performance model of heterogeneous clusters based on a switched network Alexey Lastovetsky
Total Quality Management BUS 3 – 142 Statistics for Variables Week of Mar 14, 2011.
Energy-efficient Self-adapting Online Linear Forecasting for Wireless Sensor Network Applications Jai-Jin Lim and Kang G. Shin Real-Time Computing Laboratory,
Regression Model Building
Forecast for the solar activity based on the autoregressive desciption of the sunspot number time series R. Werner Solar Terrestrial Influences Institute.
BOX JENKINS METHODOLOGY
Traffic modeling and Prediction ----Linear Models
1 Statistical Tools for Multivariate Six Sigma Dr. Neil W. Polhemus CTO & Director of Development StatPoint, Inc.
Chapter 11 Simple Regression
A methodology for developing new technology ideas to avoid
Communications-2010, Bucharest, June 11 A Second Order Statistical Analysis of the 2D Discrete Wavelet Transform Corina Nafornita 1, Ioana Firoiu 1,2,
Intelligent Database Systems Lab Advisor : Dr. Hsu Graduate : Chien-Shing Chen Author : Byoung-Kee Yi N.D.Sidiropoulos Theodore Johnson 國立雲林科技大學 National.
Forecasting Professor Ahmadi.
CSDA Conference, Limassol, 2005 University of Medicine and Pharmacy “Gr. T. Popa” Iasi Department of Mathematics and Informatics Gabriel Dimitriu University.
Communication Networks (Kommunikationsnetværk) Specialisations: Distributed Application Engineering Network Planning & Management Ole Brun Madsen Professor.
Time series data: each case represents a point in time. Each cell gives a value for each variable for each time period. Stationarity: Data are stationary.
Experimental Design If a process is in statistical control but has poor capability it will often be necessary to reduce variability. Experimental design.
Planning and Executing a Flexible Coverage Plan Bernard Breton Director, Wireless Development Northwood Technologies Inc.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
May 20-22, 2010, Brasov, Romania 12th International Conference on Optimization of Electrical and Electronic Equipment OPTIM 2010 Electrocardiogram Baseline.
Integration of WiMAX and WiFi Optimal Pricing for Bandwidth Sharing Dusit Niyato and Ekram Hossain, TRLabs and University of Manitoba IEEE Communications.
Time Series Analysis and Forecasting
Week 11 Introduction A time series is an ordered sequence of observations. The ordering of the observations is usually through time, but may also be taken.
P. Wielgosz and A. Krankowski IGS AC Workshop Miami Beach, June 2-6, 2008 University of Warmia and Mazury in Olsztyn, Poland
Doc.: IEEE /0065r0 Submission January 2014 William Carney, SONYSlide 1 Comments on Draft HEW PAR Date: Authors:
LE DEBRUITAGE DES IMAGES SONAR EN UTILISANT LA THEORIE DES ONDELETTES SORIN MOGA ET ALEXANDRU ISAR ISETc 2010, Timisoara, November 11, 2010 A Study of.
1 1 Slide Forecasting Professor Ahmadi. 2 2 Slide Learning Objectives n Understand when to use various types of forecasting models and the time horizon.
SADC Course in Statistics Forecasting and Review (Sessions 04&05)
Computer networks are a series of two or more computers that are connected together to share information. There are three types of computer networks:
Big Data at Home Depot KSU – Big Data Survey Course Steve Einbender Advanced Analytics Architect.
VI. Regression Analysis A. Simple Linear Regression 1. Scatter Plots Regression analysis is best taught via an example. Pencil lead is a ceramic material.
Conference on Medium Term Economic Assessment (CMTEA) 39 TH Edition, Iaşi, September 25–27, 2008 PROGNOSIS USING THE MULTIVARIATE STATISTICAL ANALYSIS.
Quality of model and Error Analysis in Variational Data Assimilation François-Xavier LE DIMET Victor SHUTYAEV Université Joseph Fourier+INRIA Projet IDOPT,
1 Network Tomography Using Passive End-to-End Measurements Venkata N. Padmanabhan Lili Qiu Helen J. Wang Microsoft Research DIMACS’2002.
The Box-Jenkins (ARIMA) Methodology
1 1 Chapter 6 Forecasting n Quantitative Approaches to Forecasting n The Components of a Time Series n Measures of Forecast Accuracy n Using Smoothing.
Forecasting is the art and science of predicting future events.
MBF1413 | Quantitative Methods Prepared by Dr Khairul Anuar 8: Time Series Analysis & Forecasting – Part 1
ISEN 315 Spring 2011 Dr. Gary Gaukler. Forecasting for Stationary Series A stationary time series has the form: D t =  +  t where  is a constant.
Comparison of Wavelet Families with Application to WiMAX Traffic Forecasting Cristina Stolojescu, Ion Railean, Sorin Moga and Alexandru Isar Faculty of.
Subodh Kant. Auto-Regressive Integrated Moving Average Also known as Box-Jenkins methodology A type of linear model Capable of representing stationary.
SUBJECT : POWER DISTRIBUTION AND UTILIZATION (PRESENTATION) INSTRUCTOR:KASHIF MEHMOOD.
1 A latent information function to extend domain attributes to improve the accuracy of small-data-set forecasting Reporter : Zhao-Wei Luo Che-Jung Chang,Der-Chiang.
Class Seven Turn In: Chapter 18: 32, 34, 36 Chapter 19: 26, 34, 44 Quiz 3 For Class Eight: Chapter 20: 18, 20, 24 Chapter 22: 34, 36 Read Chapters 23 &
ISSCS 2009, Iasi, Romania1 On the Choice of the Mother Wavelet for Perceptual Data Hiding Corina Nafornita, Alexandru Isar Politehnica University of Timisoara.
Forecasting. Model with indicator variables The choice of a forecasting technique depends on the components identified in the time series. The techniques.
Welcome to MM305 Unit 5 Seminar Dr. Bob Forecasting.
Lecture 9 Forecasting. Introduction to Forecasting * * * * * * * * o o o o o o o o Model 1Model 2 Which model performs better? There are many forecasting.
A Spectral Approach for Large Scale Data Traffic Load: Analysis and Application HONGZHI SHI, YONG LI (TSINGHUA UNIVERSITY) DI WU (HUNAN UNIVERSITY) YING.
Belinda Boateng, Kara Johnson, Hassan Riaz
Jinseok Choi, Brian L. Evans and *Alan Gatherer
System Control based Renewable Energy Resources in Smart Grid Consumer
Prediction as Data Mining Task
CHAPTER 29: Multiple Regression*
Chapter 11: Inference for Distributions of Categorical Data
Time series forecasting
A Second Order Statistical Analysis of the 2D Discrete Wavelet Transform Corina Nafornita1, Ioana Firoiu1,2, Dorina Isar1, Jean-Marc Boucher2, Alexandru.
Andrew Karl, Ph.D. James Wisnowski, Ph.D. Lambros Petropoulos
Presentation transcript:

ISSCS 2009, Iasi, Romania1 Forecasting WiMAX BS Traffic by Statistical Processing in the Wavelet Domain Cristina Stolojescu 1, Alina Cușnir 2, Sorin Moga 3, Alexandru Isar 1 1 Politehnica University, Timisoara, Romania, 2 Alcatel-Lucent, Timisoara, Romania, 3 Telecom Bretagne, Brest, France.

ISSCS 2009, Iasi, Romania2 Goal predict where and when BS upgrading must take place in a WiMAX network statistical data processing in the wavelets domain

ISSCS 2009, Iasi, Romania3 Papagiannaki & alls, 2003 Wire network 1.5 years of data with 15 minutes granularity

ISSCS 2009, Iasi, Romania4 Potential of generalization Pros & cons Accurate forecasting Stationary network High volume of data required

ISSCS 2009, Iasi, Romania5 Proposed Method Wireless network containing 64 BSs, 11 weeks of data with 15 minutes granularity.

ISSCS 2009, Iasi, Romania6 Initial Observations The weekly traffic for a BS (arbitrarily selected). The corresponding power spectral density. Analyzing the first week of the considered period for all the 64 BSs we have found a periodicity of 24 hours in 77% of cases.

ISSCS 2009, Iasi, Romania7 MRA d 3 and d 4 – variability.c 6 – long term trend

ISSCS 2009, Iasi, Romania8 ANOVA

ISSCS 2009, Iasi, Romania9 Validation

ISSCS 2009, Iasi, Romania10 Parameters Extraction

ISSCS 2009, Iasi, Romania11 ARIMA MODELING

ISSCS 2009, Iasi, Romania12 Long Term Trend Estimation Applying the Box-Jenkins methodology for the first difference of the time series c 6 in our example we have obtained an ARIMA(011) model for the overall tendency:

ISSCS 2009, Iasi, Romania13 Where and when an upgrading must take place ?

ISSCS 2009, Iasi, Romania14 Saturation Risk BS μ [Mb/w] BS μ [Mb/w] BS μ [Mb/w]

ISSCS 2009, Iasi, Romania15 Conclusions The proposed methodology is capable to isolate the overall long term trend and to identify those components that significantly contribute to its variability. Predictions based on approximations of those components provide accurate estimates with a minimal computational overhead.

ISSCS 2009, Iasi, Romania16 Metcalfe’s Law “The value of any communication network grows as the square of the number of users of the network” Andrew J. Viterbi, Four Laws of Nature and Society: The Governing Principles of Digital Wireless Communication Networks, in: H. Vincent POOR, Gregory W. WORNELL, Wireless Communications-Signal Processing Perspectives, Prentice Hall, 1998