Feng Gang National Laboratory of Communication,UESTC Aug 2017 Ver 1.4 Traffic models To align services,need to have some idea of how users or aggregates of users behave traffic model e.g.how long a user uses a modem e.g.average size of a file transfer 、 Models change with network usage We can only guess about the future ·Two types of models measurements educated guesses 2616009:Network Traffic Engineering 8:Traffic Management and Modeling Page.16
2616009: Network Traffic Engineering Feng Gang National Laboratory of Communication, UESTC Aug 2017 Ver 1.4 8: Traffic Management and Modeling Page.16 Traffic models • To align services, need to have some idea of how users or aggregates of users behave = traffic model - e.g. how long a user uses a modem - e.g. average size of a file transfer • Models change with network usage • We can only guess about the future • Two types of models - measurements - educated guesses
Feng Gang National Laboratory of Communication,UESTC Aug 2017 Ver 1.4 Telephone traffic models ·How are calls placed? call arrival model studies show that time between calls is drawn from an exponential distribution call arrival process is therefore Poisson memoryless:the fact that a certain amount of time has passed since the last call gives no information of time to next call How long are calls held? usually modeled as exponential however,measurement studies show it to be heavy tailed - means that a significant number of calls last a very long time 2616009:Network Traffic Engineering 8:Traffic Management and Modeling Page.17
2616009: Network Traffic Engineering Feng Gang National Laboratory of Communication, UESTC Aug 2017 Ver 1.4 8: Traffic Management and Modeling Page.17 Telephone traffic models • How are calls placed? - call arrival model - studies show that time between calls is drawn from an exponential distribution - call arrival process is therefore Poisson - memoryless: the fact that a certain amount of time has passed since the last call gives no information of time to next call • How long are calls held? - usually modeled as exponential - however, measurement studies show it to be heavy tailed - means that a significant number of calls last a very long time
Feng Gang National Laboratory of Communication,UESTC Aug 2017 Ver 1.4 Internet traffic modeling A few apps account for most of the traffic -W FTP telnet A common approach is to model apps (this ignores distribution of destination!) time between app invocations - connection duration -bytes transferred packet interarrival distribution Little consensus on models But two important features 2616009:Network Traffic Engineering 8:Traffic Management and Modeling Page.18
2616009: Network Traffic Engineering Feng Gang National Laboratory of Communication, UESTC Aug 2017 Ver 1.4 8: Traffic Management and Modeling Page.18 Internet traffic modeling • A few apps account for most of the traffic - WWW - FTP - telnet • A common approach is to model apps (this ignores distribution of destination!) - time between app invocations - connection duration - # bytes transferred - packet interarrival distribution • Little consensus on models • But two important features
Feng Gang National Laboratory of Communication,UESTC Aug 2017 Ver 1.4 Internet traffic models:features LAN connections differ from WAN connections -Higher bandwidth(more bytes/call) longer holding times Many parameters are heavy-tailed examples s bytes in call s call duration means that a few calls are responsible for most of the traffic - these calls must be well-managed also means that even aggregates with many calls not be smooth can have long bursts New models appear all the time,to account for rapidly changing traffic mix 2616009:Network Traffic Engineering 8:Traffic Management and Modeling Page.19
2616009: Network Traffic Engineering Feng Gang National Laboratory of Communication, UESTC Aug 2017 Ver 1.4 8: Traffic Management and Modeling Page.19 Internet traffic models: features • LAN connections differ from WAN connections - Higher bandwidth (more bytes/call) - longer holding times • Many parameters are heavy-tailed - examples § # bytes in call § call duration - means that a few calls are responsible for most of the traffic - these calls must be well-managed - also means that even aggregates with many calls not be smooth - can have long bursts • New models appear all the time, to account for rapidly changing traffic mix
Feng Gang National Laboratory of Communication,UESTC Aug 2017 Ver 1.4 Outline Introduction 。 Economic principles Traffic classes ·Time scales ·Mechanisms Some open problems on traffic management Traffic modeling-----self-similar traffic 2616009:Network Traffic Engineering 8:Traffic Management and Modeling Page.20
2616009: Network Traffic Engineering Feng Gang National Laboratory of Communication, UESTC Aug 2017 Ver 1.4 8: Traffic Management and Modeling Page.20 Outline • Introduction • Economic principles • Traffic classes • Time scales • Mechanisms • Some open problems on traffic management • Traffic modeling-----self-similar traffic