Multi-Scale Analysis for Network Traffic Prediction and Anomaly Detection Ling Huang Joint work with Anthony Joseph and Nina Taft January, 2005.

Slides:



Advertisements
Similar presentations
Characteristics of Network Traffic Flow Anomalies Paul Barford and David Plonka University of Wisconsin – Madison SIGCOMM IMW, 2001.
Advertisements

Noise & Data Reduction. Paired Sample t Test Data Transformation - Overview From Covariance Matrix to PCA and Dimension Reduction Fourier Analysis - Spectrum.
Detecting DDoS Attacks on ISP Networks Ashwin Bharambe Carnegie Mellon University Joint work with: Aditya Akella, Mike Reiter and Srinivasan Seshan.
Detectability of Traffic Anomalies in Two Adjacent Networks Augustin Soule, Haakon Ringberg, Fernando Silveira, Jennifer Rexford, Christophe Diot.
A Flexible Model for Resource Management in Virtual Private Networks Presenter: Huang, Rigao Kang, Yuefang.
What role should probabilistic sensitivity analysis play in SMC decision making? Andrew Briggs, DPhil University of Oxford.
Sensitivity of PCA for Traffic Anomaly Detection Evaluating the robustness of current best practices Haakon Ringberg 1, Augustin Soule 2, Jennifer Rexford.
1 Communication-Efficient Online Detection of Network-Wide Anomalies Ling Huang* XuanLong Nguyen* Minos Garofalakis § Joe Hellerstein* Michael Jordan*
© 2005 The McGraw-Hill Companies, Inc., All Rights Reserved. Chapter 14 Using Multivariate Design and Analysis.
Probabilistic Aggregation in Distributed Networks Ling Huang, Ben Zhao, Anthony Joseph and John Kubiatowicz {hling, ravenben, adj,
1 In-Network PCA and Anomaly Detection Ling Huang* XuanLong Nguyen* Minos Garofalakis § Michael Jordan* Anthony Joseph* Nina Taft § *UC Berkeley § Intel.
Time-Frequency and Time-Scale Analysis of Doppler Ultrasound Signals
1 Toward Sophisticated Detection With Distributed Triggers Ling Huang* Minos Garofalakis § Joe Hellerstein* Anthony Joseph* Nina Taft § *UC Berkeley §
1 Distributed Online Simultaneous Fault Detection for Multiple Sensors Ram Rajagopal, Xuanlong Nguyen, Sinem Ergen, Pravin Varaiya EECS, University of.
Probabilistic Data Aggregation Ling Huang, Ben Zhao, Anthony Joseph Sahara Retreat January, 2004.
Traffic Matrix Estimation: Existing Techniques and New Directions A. Medina (Sprint Labs, Boston University), N. Taft (Sprint Labs), K. Salamatian (University.
Cumulative Violation For any window size  t  Communication-Efficient Tracking for Distributed Cumulative Triggers Ling Huang* Minos Garofalakis.
1 Using A Multiscale Approach to Characterize Workload Dynamics Characterize Workload Dynamics Tao Li June 4, 2005 Dept. of Electrical.
ECE Spring 2010 Introduction to ECE 802 Selin Aviyente Associate Professor.
EL 933 Final Project Presentation Combining Filtering and Statistical Methods for Anomaly Detection Augustin Soule Kav´e SalamatianNina Taft.
Laurent Itti: CS599 – Computational Architectures in Biological Vision, USC Lecture 7: Coding and Representation 1 Computational Architectures in.
Network Anomography Yin Zhang, Zihui Ge, Albert Greenberg, Matthew Roughan Internet Measurement Conference 2005 Berkeley, CA, USA Presented by Huizhong.
A Signal Analysis of Network Traffic Anomalies Paul Barford, Jeffrey Kline, David Plonka, and Amos Ron.
Computer Science Characterizing and Exploiting Reference Locality in Data Stream Applications Feifei Li, Ching Chang, George Kollios, Azer Bestavros Computer.
RACE: Time Series Compression with Rate Adaptivity and Error Bound for Sensor Networks Huamin Chen, Jian Li, and Prasant Mohapatra Presenter: Jian Li.
Statistical Methods for long-range forecast By Syunji Takahashi Climate Prediction Division JMA.
1 Multivariate Normal Distribution Shyh-Kang Jeng Department of Electrical Engineering/ Graduate Institute of Communication/ Graduate Institute of Networking.
A Signal Analysis of Network Traffic Anomalies Paul Barford with Jeffery Kline, David Plonka, Amos Ron University of Wisconsin – Madison Summer, 2002.
Dr Mark Cresswell Statistical Forecasting [Part 1] 69EG6517 – Impacts & Models of Climate Change.
Tomo-gravity Yin ZhangMatthew Roughan Nick DuffieldAlbert Greenberg “A Northern NJ Research Lab” ACM.
Inference for regression - Simple linear regression
1 Reading Report 9 Yin Chen 29 Mar 2004 Reference: Multivariate Resource Performance Forecasting in the Network Weather Service, Martin Swany and Rich.
Extensions of PCA and Related Tools
Scalable and Efficient Data Streaming Algorithms for Detecting Common Content in Internet Traffic Minho Sung Networking & Telecommunications Group College.
Time Series Data Analysis - I Yaji Sripada. Dept. of Computing Science, University of Aberdeen2 In this lecture you learn What are Time Series? How to.
Generic Approaches to Model Validation Presented at Growth Model User’s Group August 10, 2005 David K. Walters.
1 Impact of IT Monoculture on Behavioral End Host Intrusion Detection Dhiman Barman, UC Riverside/Juniper Jaideep Chandrashekar, Intel Research Nina Taft,
1 Multivariate Linear Regression Models Shyh-Kang Jeng Department of Electrical Engineering/ Graduate Institute of Communication/ Graduate Institute of.
Network Anomography Yin Zhang – University of Texas at Austin Zihui Ge and Albert Greenberg – AT&T Labs Matthew Roughan – University of Adelaide IMC 2005.
Digital Media Lab 1 Data Mining Applied To Fault Detection Shinho Jeong Jaewon Shim Hyunsoo Lee {cinooco, poohut,
Optimal XOR Hashing for a Linearly Distributed Address Lookup in Computer Networks Christopher Martinez, Wei-Ming Lin, Parimal Patel The University of.
Copyright © 2012, SAS Institute Inc. All rights reserved. ANALYTICS IN BIG DATA ERA ANALYTICS TECHNOLOGY AND ARCHITECTURE TO MANAGE VELOCITY AND VARIETY,
1 Distributed Detection of Network-Wide Traffic Anomalies Ling Huang* XuanLong Nguyen* Minos Garofalakis § Joe Hellerstein* Michael Jordan* Anthony Joseph*
The Haar + Tree: A Refined Synopsis Data Structure Panagiotis Karras HKU, September 7 th, 2006.
Big Data at Home Depot KSU – Big Data Survey Course Steve Einbender Advanced Analytics Architect.
Geo479/579: Geostatistics Ch4. Spatial Description.
Mining Anomalies in Network-Wide Flow Data Anukool Lakhina with Mark Crovella and Christophe Diot NANOG35, Oct 23-25, 2005.
Mining Anomalies Using Traffic Feature Distributions Anukool Lakhina Mark Crovella Christophe Diot in ACM SIGCOMM 2005 Presented by: Sailesh Kumar.
DDM Kirk. LSST-VAO discussion: Distributed Data Mining (DDM) Kirk Borne George Mason University March 24, 2011.
ASTUTE: Detecting a Different Class of Traffic Anomalies Fernando Silveira 1,2, Christophe Diot 1, Nina Taft 3, Ramesh Govindan 4 1 Technicolor 2 UPMC.
Taming Internet Traffic Some notes on modeling the wild nature of OD flows Augustin Soule Kavé Salamatian Antonio Nucci Nina Taft Univ. Paris VI Sprintlabs.
EE515/IS523: Security 101: Think Like an Adversary Evading Anomarly Detection through Variance Injection Attacks on PCA Benjamin I.P. Rubinstein, Blaine.
Network Anomography Yin Zhang Joint work with Zihui Ge, Albert Greenberg, Matthew Roughan Internet Measurement.
Jump to first page Inferring Sample Findings to the Population and Testing for Differences.
Distributed Network Monitoring in the Wisconsin Advanced Internet Lab Paul Barford Computer Science Department University of Wisconsin – Madison Spring,
CLASSIFICATION OF ECG SIGNAL USING WAVELET ANALYSIS
Forecasting. Model with indicator variables The choice of a forecasting technique depends on the components identified in the time series. The techniques.
1 Autocorrelation in Time Series data KNN Ch. 12 (pp )
Communication-Efficient Online Detection of Network-Wide Anomalies Ling Huang* XuanLong Nguyen* Minos Garofalakis § Joe Hellerstein* Michael Jordan* Anthony.
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.
Data Transformation: Normalization
RF-based positioning.
Online Conditional Outlier Detection in Nonstationary Time Series
Automatic Picking of First Arrivals
Application of Independent Component Analysis (ICA) to Beam Diagnosis
Feifei Li, Ching Chang, George Kollios, Azer Bestavros
The general linear model and Statistical Parametric Mapping
Multivariate Linear Regression Models
Jia-Bin Huang Virginia Tech
On applying pattern recognition to systems management
Presentation transcript:

Multi-Scale Analysis for Network Traffic Prediction and Anomaly Detection Ling Huang Joint work with Anthony Joseph and Nina Taft January, 2005

January 2005 Problem Statement Accurate network traffic modeling and prediction are important for:  Network provisioning  Problem diagnosis But, network traffic is highly dynamic  Exhibits multi-timescale properties (temporal domain)  Anomalies (failures, attacks) interfere with analysis Need to isolate anomalies from normal traffic variation to achieve better modeling and prediction

January 2005 Our Work We decompose traffic signals into two parts  Normal variations: follow certain law, can be modeled and are predictable  Anomalies: consist of sudden changes and are not predictable Method: Multi-scale signal analysis and modeling for  Network traffic prediction [almost done]  Volume anomaly detection and identification [in progress]

January 2005 Properties of Real Life Data Streams Three real-world data traces and a random trace

January 2005 Observation: Multi-Scale Property Data source: bandwidth measurements for the CUDI network interface on an Abilene router with 5-minute average. Multi-scale property of traffic data in a weekly measurement Long-term trend Transient Variation Sudden Changes (anomalies)

January 2005 Multi-Scale Prediction of Future Data Traditional Approaches  Last seen data as approximation for current estimation  Linear Prediction Exploit and leverage statistical properties of data stream on temporal domain in a window of size T Exploit temporal correlation in different time scale  Long term trend: B-spline estimation  High frequency residual: ARMA modeling  ARMA stands for AutoRegressive and Moving Average model, which is a standard time series technique to model chaotic data stream

January 2005 Two-Level Modeling and Prediction B-spline modeling for long term trend  Piecewise continuous, low-degree B-spline can represent complex shapes  Least-square B-spline regression for two-level decomposition  B-Spline extension for future forecasting ARMA forecasting for transient oscillation  System Identification to determine the order of the model  Parameter estimation by optimization algorithm  Low complexity recursive equation for future forecasting Statistical properties for the calibration of prediction results

January 2005 Complexity of Prediction Algorithms Legend  T: the window size of history data  m: the order of the linear predictor  K: the order of the ARMA model  d: the degree of B-spline curve  c: the increase in storage due to multi-level data representation

January 2005 Performance of Prediction Algorithms Performance of Prediction Algorithms On Network Traffic Mean Relative Increment

January 2005 Unpredictability: Anomalies in Data Signal The data stream can be decomposed into two layers: the long-term trend, which is the modeled pattern; the residual, high frequency with anomalies Monday Data Long-term trend (modeled) Residual with anomalies

January 2005 Anomalies Detection and Identification Volume anomaly: Sudden change in link/flow’s traffic count  Network failures, attacks, flash crowds  Measurement anomalies Anomalies are not normal variations of network traffic and are not predictable  Worse yet, anomalies skew the prediction models!  For better modeling and prediction, need to detect and isolate anomalies from data The rest of the talk focuses on anomaly detection algorithms  Existing algorithms: single-link vs. network-wide analysis  New directions

January 2005 Single-link Anomalies Detection Multi-scale analysis to capture temporal correlation  Use wavelets for multi-scale data decomposition  Isolate characteristics of traffic signal on different timescales  Expose the details of both ambient (modeled) and anomalous traffic  Detection of sharp increase in the local variance in a moving time window on different time-scale Disadvantages  Diagnose on single link or at single router, and is impractical to do analysis for large network  Many anomalies are across multiple links, and is not obvious on single link

January 2005 Network-Wide Anomalies Detection Diagnose traffic anomalies spanning multiple links  Capture the spatial correlation cross links  Analyze origin-destination flows with known traffic matrix  Principle Component Analysis (PCA) for dimension reduction and signal decomposition  Separate traffic signal into modeled and residual space  Scoring/prediction method to detect abnormal changes in residual space Disadvantages  Need ISP support  Single time scale analysis  Centralized algorithm

January 2005 New Direction (1): Multi-Scale PCA PCA analysis on wavelets representation of traffic data  Wavelets capture correlation within a single link  PCA captures the correlation across links and transforms the multivariate space into a subspace which preserves maximum variance of the original space  PCA analyzes data on single time-scale and can not utilize the information pertaining to the frequency  Multi-scale PCA combines two extremes of wavelets and PCA based analysis of multivariate data Benefits: detection of multi-timescale anomalies

January 2005 New Direction (2): Distributed Algorithm Distributed anomalies detection based on partial flow information  No ISP support, no information about OD flows and traffic matrix  Diagnose volume anomalies based on network monitoring data – flow and link information from a subset of places in the network Network-wide traffic modeling, inference and prediction improve measured data  Distributed algorithms for network-wide data reduction, decomposition and anomaly detection Collective PCA Benefit: local analysis and low cost

January 2005 Conclusion and Future Work Summary  Apply statistical algorithms to network traffic analysis  Multi-scale analysis is effective in traffic modeling and prediction  Contribution: using multi-scale network-wide analysis to capture both temporal correlation within single link and spatial correlation cross links Future Work  Develop distributed algorithms based on multi-scale PCA  Exploit tradeoff between detection accuracy, false positive and computation cost  Build real system for applications in traffic analysis and network health monitoring