Slide 119/10/2015 INTERMON Advanced architecture for INTER-domain quality of service MONitoring,...
-
Upload
estella-cross -
Category
Documents
-
view
214 -
download
0
Transcript of Slide 119/10/2015 INTERMON Advanced architecture for INTER-domain quality of service MONitoring,...
Slide 104/21/23
INTERMONAdvanced architecture for INTER-domain quality of service
MONitoring, modelling and visualisation
http://www.ist-intermon.org
U. Hofmann*, I.Miloucheva, T.Pfeiffenberger, F. StrohmeierSalzburg Research,*Univ. of Applied Sciences, Salzburg Austria
{ulrich.hofmann,ilka.miloucheva,thomas.pfeiffenberger,felix.strohmeier}
@salzburgresearch.at
Slide 204/21/23
1. INTERMON Overview
2. CM Toolset active QoS monitoring and analysis
toolkit
- Motivation
- Components
- Scenario
- Results
3. Future Work
Slide 304/21/23
Motivation : ISP wants to enhance the inter-domain Quality of Service (QoS) analysis in large-scale, multi-domain to offer stabile inter-domain services
D iffe re n tS o u rc e A S
IS P S 1
S o u rc ee n dsy ste m
T ra n s it A S
P e e rin gp o ss ib il ity
IS P T 2 D e st in a tio ne n dsy ste m
IS P T 1
IS P T 3IS P S 2
IS P D 1
IS P D 2
IS P D 3
IS P D 4
D iffe re n tD e s tin a tio n A S
IN T E R M O N to o lk itw ith in t e g ra t e d d a t ab a se
T ra ff ic s tu d y a tb o rd e r ro u te r A lt e r n a t iv e
to p o lo g ie s
E n d - to -e n dQ o S
E n d -to -e n dQ o S
• ISP S1/2 are competitors
• ISP* offers SourceEndSystem
• the aggregate QoS
• best_of {ISP T1/T2}
•...ISP D*
1. Overview
Slide 404/21/23
=> scalable inter-domain QoS monitoring and analysis
effect of inter-domain routing and BGP-4 protocol behaviour
monitoring : IPFIX
modelling load <=> QoS : simulation ( fluid, hybrid
analytical M/G/*
visual data mining architecture
measurement based simulation technologies IPFIX => Simulation
pattern detection, outlier elimination
pattern compression PLA
using
common QoS database with
policy-controlled interworking of components
Slide 504/21/23
Q oS measurement and modelling
„w hat if“analys is
A nalys is o fT raffic &T opo logyImpact onE nd-to -end Q oS
S im ulationtoo lk it-flu id-tim e series-hybrid-analyt ica l
Q oS Patternanalyser-outliers- linearapproxim at ion
IN T E RM O N D B:- QoS param. M eas.(delay, lo ss),-SN M P data per router-IPFIX traffic-BG P-4 protoco l data-T raceroute topo logy
BG P-4Protoco lA nalyser- H eurist icsfo r BG P-4Patterns
Act ive Q oSm easurem entand traffic flowemulat ion(CM T oo lset)
T rafficflow s(IPFIX )
T rafficm atrix
M RCollecto r
Act ivetopo logy(traceroute)A nalys is o fCM T oo lset
Passivedelaym easurem ent too l
Slide 604/21/23
QoS is different for different paths : s->A->B->d , s->A->C->d
QoS is different for different SLS : VoIP (160 Byte), FTP (1500 Byte)
ISP_A
ISP_C
ISP_B
source destination
QoS offer S->D
Salzburg-Madrid
t=20ms
2. CM Toolset active QoS monitoring and analysis toolkit
Motivation
Slide 704/21/23
IP Network
Measurement Flows(TCP/UDP)
MeasurementClient Station
MeasurementManagement Station
GUI(WWW-Browser)
WebServer
CMCaller
CMDaemon
GPSEquipment
MDB
MeasurementClient Station
CMDaemon
GPSEquipment
Components
Slide 804/21/23
CM Toolset Scenario for complex QoS analysis and data mining
-capacity planning-patterns dependent on topology change-application emulation and QoS study - VoIP
Spatio temporal QoS Analyser -Pattern detection (generic patterns for data mining rules)-Outlier-Similarity detection
Spatio temporal QoS Analyser -Pattern detection (generic patterns for data mining rules)-Outlier-Similarity detection
QoS measurement for secified scenario
QoS measurement for secified scenario QoS monitoring
data base
Pattern data base
detect router anomaly
• define pattern owd>2s & singular
• specify measurements rate, p_size, duration, source, destination,..
• measurements
• analysis if(owd>2s & singular) then anomaly else path_change
Scenario:
Slide 904/21/23
Results (1): Active Topology discovery using traceroute data base
Objective: study of topology properties of the connection number hops, availability of the routers long term reporting : per hour, day BGP issues ( security,...)
Separation of measurement results per path
Salzburg-Madridred: router not respondingbrightness: RTTblue: some RTT > e2e_RTT
Slide 1004/21/23
Results (2) Piecewise linear approximation
• data as sequences of straight lines,
• optimise the tradeoff between
• high level of aggregation of measurement results• „pieces“: set of consecutive measurement points
with „similar“ gradient d_measurement(t)/dt• plain : gradient =0
• increasing : gradient >0
• decreasing: gradient <0
• „similarity“ : tolerance parameter d
•Pattern Description Language (PDL)
Slide 1104/21/23
Salzburg-Sao Paulo: router anomaly ?
Slide 1204/21/23
• improved outlier analysis e.g. prediction optimised (ARIMA)
• symbolic representation for pattern detection {R} -> {a,b,c,..}
• evaluation tradeoff : information loss, compression
• InterDomain Forum Cluster
• audio QoS pattern analysis ( ITU E.855, perceptual QoS )
• prototype for global controller ( GEANT ?)
• MOME cluster
• anomaly detection for network security
• monitoring and modelling for network planning
3. Future Work