Presentation is loading. Please wait.

Presentation is loading. Please wait.

August 10, 2005 (Week 1) 1 CS 5224 High Speed Networks and Multimedia Networking Dr. Chan Mun Choon Semester 1, 2005/2006 School of Computing National.

Similar presentations


Presentation on theme: "August 10, 2005 (Week 1) 1 CS 5224 High Speed Networks and Multimedia Networking Dr. Chan Mun Choon Semester 1, 2005/2006 School of Computing National."— Presentation transcript:

1 August 10, 2005 (Week 1) 1 CS 5224 High Speed Networks and Multimedia Networking Dr. Chan Mun Choon Semester 1, 2005/2006 School of Computing National University of Singapore

2 Aug 10, 2005 (Week 1) 2Introduction/Basic Concept Organization Lecturer: Lecturer: Dr. Chan Mun Choon (chanmc@comp.nus.edu.sg) Dr. Chan Mun Choon (chanmc@comp.nus.edu.sg)chanmc@comp.nus.edu.sg Homepage: http://www.comp.nus.edu.sg/~chanmc Homepage: http://www.comp.nus.edu.sg/~chanmchttp://www.comp.nus.edu.sg/~chanmc Office: S14 #06-09 Office: S14 #06-09 Tel: 6874-7372 Tel: 6874-7372 Course Information Course Information Web-site: http://www.comp.nus.edu.sg/~cs5224 Web-site: http://www.comp.nus.edu.sg/~cs5224http://www.comp.nus.edu.sg/~cs5224 IVLE IVLE Class Venue: S16 #04-05 (SR1) Class Venue: S16 #04-05 (SR1) Class Time: 6:30pm – 8:30pm, Wednesday Class Time: 6:30pm – 8:30pm, Wednesday Office Hours: 3:30pm – 5:30pm Wednesday Office Hours: 3:30pm – 5:30pm Wednesday

3 Aug 10, 2005 (Week 1) 3Introduction/Basic Concept Course Description Introduce graduate students to fundamental networking problems and concepts Introduce graduate students to fundamental networking problems and concepts For students interested in the area of networking, this course will be rewarding For students interested in the area of networking, this course will be rewarding Emphasis on problem solving and performance evaluation (queuing theory, graph algorithms etc.) Emphasis on problem solving and performance evaluation (queuing theory, graph algorithms etc.) Long homework Long homework Midterm + Finals Midterm + Finals

4 Aug 10, 2005 (Week 1) 4Introduction/Basic Concept Course Pre-requisites Assume students have taken undergraduate networking classes like CS2105/CS3103 Assume students have taken undergraduate networking classes like CS2105/CS3103 Basic background on probability and algorithms Basic background on probability and algorithms Textbooks: Textbooks: S. Keshav, "An Engineering Approach to Computer Networking", Addison-Wesley. S. Keshav, "An Engineering Approach to Computer Networking", Addison-Wesley. Reference Books Reference Books Bertsekas and Gallager, "Data Networks", 2nd Edition, Prentice Hall Bertsekas and Gallager, "Data Networks", 2nd Edition, Prentice Hall

5 Aug 10, 2005 (Week 1) 5Introduction/Basic Concept (Tentative) Outline/Schedule 110/8Introduction and basic concepts 217/8Multiplexing, Queuing Theory 324/8Traffic Engineering(HW1 Assign) 431/8Simulation (HW1 Due) 57/9Scheduling and Buffer Management(Hw 2 Assign) 614/9Scheduling and Buffer Management (HW 2 Due) 21/8Mid-Semester Break 728/9Midterm Exam 85/10Routing 912/10Routing (HW3 Assign) 1019/10End-to-end Performance (HW3 Due) 1126/10Transport 122/11Wireless Networks(HW4 Assign) 139/11Access/High Speed Networks 16/11Reading Day(HW 4 Due)

6 Aug 10, 2005 (Week 1) 6Introduction/Basic Concept (Tentative) Grading Policy Homework35% (4 Assignments) Homework35% (4 Assignments) Class Participation5% Class Participation5% Mid-Term Exam25% Mid-Term Exam25% Final Exam35% Final Exam35%

7 August 10, 2005 (Week 1) 7 Introduction and Basic Concepts

8 Aug 10, 2005 (Week 1) 8Introduction/Basic Concept Outline Types of Communication Networks Types of Communication Networks Quality of Service Measure and Classes Quality of Service Measure and Classes Design issues/principles Design issues/principles

9 Aug 10, 2005 (Week 1) 9Introduction/Basic Concept Speed and Distance of Communications Networks

10 Aug 10, 2005 (Week 1) 10Introduction/Basic Concept Characteristics of WANs Covers large geographical areas Covers large geographical areas Circuits provided by a common carrier Circuits provided by a common carrier Consists of interconnected switching nodes Consists of interconnected switching nodes Legacy WANs provide modest connection capacity Legacy WANs provide modest connection capacity 64 kbps were common 64 kbps were common Business subscribers uses T1 (1.544Mbps) Business subscribers uses T1 (1.544Mbps) Current WAN connections Current WAN connections Higher-speed WANs use optical fiber and transmission technique known as asynchronous transfer mode (ATM) or SONET Higher-speed WANs use optical fiber and transmission technique known as asynchronous transfer mode (ATM) or SONET T1/DS3(45Mbps)/OC3(155Mbps)/OC12, Ethernet T1/DS3(45Mbps)/OC3(155Mbps)/OC12, Ethernet 10, 100 of Mbps or more are common 10, 100 of Mbps or more are common

11 Aug 10, 2005 (Week 1) 11Introduction/Basic Concept Characteristics of LANs Like WAN, LAN interconnects a variety of devices and provides a means for information exchange among them Like WAN, LAN interconnects a variety of devices and provides a means for information exchange among them Legacy LANs Legacy LANs Provide data rates of 1 to 20 Mbps Provide data rates of 1 to 20 Mbps High-speed LANS High-speed LANS Provide data rates of 100 Mbps to 10 Gbps Provide data rates of 100 Mbps to 10 Gbps

12 Aug 10, 2005 (Week 1) 12Introduction/Basic Concept Switching Terms Switching Nodes: Switching Nodes: Intermediate switching device that moves data Intermediate switching device that moves data Not concerned with content/payload of data Not concerned with content/payload of data Switch based on timing or header information Switch based on timing or header information Stations: Stations: End devices that wish to communicate End devices that wish to communicate Each station is connected to a switching node Each station is connected to a switching node Communications Network: Communications Network: A collection of switching nodes A collection of switching nodes

13 Aug 10, 2005 (Week 1) 13Introduction/Basic Concept Switched Network

14 Aug 10, 2005 (Week 1) 14Introduction/Basic Concept Observations of Figure 3.3 Some nodes connect only to other nodes (e.g., 5 and 7) Some nodes connect only to other nodes (e.g., 5 and 7) Some nodes connect to one or more stations Some nodes connect to one or more stations Node-station links usually dedicated point-to-point links Node-station links usually dedicated point-to-point links Node-node links usually multiplexed links Node-node links usually multiplexed links Shared among difference source-destination pairs Shared among difference source-destination pairs Not a direct link between every node pair Not a direct link between every node pair Directly connecting all pairs requires N(N-1) or O(N 2 ) links Directly connecting all pairs requires N(N-1) or O(N 2 ) links

15 Aug 10, 2005 (Week 1) 15Introduction/Basic Concept Techniques Used in Switched Networks Circuit switching Circuit switching Dedicated communications path between two stations Dedicated communications path between two stations E.g., public telephone network E.g., public telephone network Packet switching Packet switching Message is broken into a series of packets Message is broken into a series of packets Each node determines next leg of transmission for each packet Each node determines next leg of transmission for each packet

16 Aug 10, 2005 (Week 1) 16Introduction/Basic Concept Phases of Circuit Switching Circuit establishment Circuit establishment An end to end circuit is established through switching nodes An end to end circuit is established through switching nodes Information Transfer Information Transfer Information transmitted through the network Information transmitted through the network Data may be analog voice, digitized voice, or binary data Data may be analog voice, digitized voice, or binary data Circuit disconnect Circuit disconnect Circuit is terminated Circuit is terminated Each node deallocates dedicated resources Each node deallocates dedicated resources

17 Aug 10, 2005 (Week 1) 17Introduction/Basic Concept Characteristics of Circuit Switching Can be inefficient Can be inefficient Channel capacity dedicated for duration of connection Channel capacity dedicated for duration of connection Utilization not 100% Utilization not 100% Delay prior to signal transfer for establishment Delay prior to signal transfer for establishment Once established, network is transparent to users Once established, network is transparent to users Information transmitted at fixed data rate with only (fixed) propagation delay Information transmitted at fixed data rate with only (fixed) propagation delay Best known circuit switched network is the Public Switch Telephone Network (PSTN) Best known circuit switched network is the Public Switch Telephone Network (PSTN)

18 Aug 10, 2005 (Week 1) 18Introduction/Basic Concept How Packet Switching Works Data is transmitted in blocks, called packets Data is transmitted in blocks, called packets Before sending, the message is broken into a series of packets Before sending, the message is broken into a series of packets Packets consists of a portion of data plus a packet header that includes control information Packets consists of a portion of data plus a packet header that includes control information At each node en route, packet is received, stored briefly and passed to the next node At each node en route, packet is received, stored briefly and passed to the next node The store and forward mode of operation incurred both (variable) queuing delay and propagation delay The store and forward mode of operation incurred both (variable) queuing delay and propagation delay

19 Aug 10, 2005 (Week 1) 19Introduction/Basic Concept Packet Switching

20 Aug 10, 2005 (Week 1) 20Introduction/Basic Concept Packet Switching Advantages Line efficiency is greater Line efficiency is greater Many packets over time can dynamically share the same node to node link Many packets over time can dynamically share the same node to node link Packet-switching networks can carry out data-rate conversion Packet-switching networks can carry out data-rate conversion Two stations with different data rates can exchange information Two stations with different data rates can exchange information Unlike circuit-switching networks that block calls when traffic is heavy, packet-switching still accepts packets, but with increased delivery delay Unlike circuit-switching networks that block calls when traffic is heavy, packet-switching still accepts packets, but with increased delivery delay Priorities can be used at the packet level Priorities can be used at the packet level

21 Aug 10, 2005 (Week 1) 21Introduction/Basic Concept Disadvantages of Packet Switching Each packet switching node introduces a delay Each packet switching node introduces a delay Overall packet delay can vary substantially Overall packet delay can vary substantially This is referred to as jitter This is referred to as jitter Caused by differing packet sizes, routes taken and varying delay in the switches Caused by differing packet sizes, routes taken and varying delay in the switches Each packet requires overhead information Each packet requires overhead information Includes destination and sequencing information Includes destination and sequencing information Reduces communication capacity Reduces communication capacity More processing required at each node More processing required at each node

22 Aug 10, 2005 (Week 1) 22Introduction/Basic Concept Packet Switching Networks - Virtual Circuit Preplanned route established before packets sent Preplanned route established before packets sent All packets between source and destination follow this route All packets between source and destination follow this route Routing decision not required by nodes for each packet Routing decision not required by nodes for each packet Emulates a circuit in a circuit switching network but is not a dedicated path Emulates a circuit in a circuit switching network but is not a dedicated path Packets still buffered at each node and queued for output over a line Packets still buffered at each node and queued for output over a line

23 Aug 10, 2005 (Week 1) 23Introduction/Basic Concept Packet Switching Networks – Virtual Circuit Advantages: Advantages: Packets arrive in original order Packets arrive in original order Packets arrive correctly Packets arrive correctly Packets transmitted more rapidly without routing decisions made at each node Packets transmitted more rapidly without routing decisions made at each node This is how ATM network works This is how ATM network works

24 Aug 10, 2005 (Week 1) 24Introduction/Basic Concept Packet Switching Networks - Datagram Each packet treated independently, without reference to previous packets Each packet treated independently, without reference to previous packets Each node chooses next node on packet’s path Each node chooses next node on packet’s path Packets don’t necessarily follow same route and may arrive out of sequence Packets don’t necessarily follow same route and may arrive out of sequence Exit node restores packets to original order Exit node restores packets to original order Responsibility of exit node or destination to detect loss of packet and how to recover Responsibility of exit node or destination to detect loss of packet and how to recover

25 Aug 10, 2005 (Week 1) 25Introduction/Basic Concept Packet Switching Networks – Datagram Advantages: Advantages: Call setup phase is avoided Call setup phase is avoided Because it’s more primitive, it’s more flexible Because it’s more primitive, it’s more flexible Datagram delivery is more “reliable” Datagram delivery is more “reliable” This is how the Internet works This is how the Internet works

26 Aug 10, 2005 (Week 1) 26Introduction/Basic Concept Example Imagine a postal system implemented in the following ways: Imagine a postal system implemented in the following ways: 1. All mails coming from zip code 123456 will be delivered to 654321. This is ____________ 1. All mails coming from zip code 123456 will be delivered to 654321. This is ____________ 2. The zip code of all mails coming from zip code 123456 will be changed to 654321 and sent to the post office in Kent Ridge. This is ____________ 2. The zip code of all mails coming from zip code 123456 will be changed to 654321 and sent to the post office in Kent Ridge. This is ____________ 3. The zip code of all mails coming from zip code 123456 will be delivered to Kent Ridge. This is ____________ 3. The zip code of all mails coming from zip code 123456 will be delivered to Kent Ridge. This is ____________

27 Aug 10, 2005 (Week 1) 27Introduction/Basic Concept Recap: different types of networks A network is defined by its “switching mode” and its “networking mode” A network is defined by its “switching mode” and its “networking mode” Circuit switching vs. packet switching Circuit switching vs. packet switching Circuit-switching: switching based on position (space, time, ) of arriving bits Circuit-switching: switching based on position (space, time, ) of arriving bits Packet-switching: switching based on information in packet headers Packet-switching: switching based on information in packet headers Connectionless vs. connection-oriented networking: Connectionless vs. connection-oriented networking: CL: Packets routed based on address information in headers CL: Packets routed based on address information in headers CO: Connection set up (resources reserved) prior to data transfer CO: Connection set up (resources reserved) prior to data transfer Packet-switching Circuit-switching Switching modes Connectionless Connection-oriented Networking modes ATM, X.25 IP, SS7 MPLS IP + RSVP Telephone network, SONET/SDH, WDM

28 Aug 10, 2005 (Week 1) 28Introduction/Basic Concept Types of data transfers Sending end Consuming end Live Stored Live Stored Interactive/ Live streaming Recording Stored streamingFile transfers An application could consist of different types of data transfers —An http session has an interactive component, but could also have a non-real-time transfer

29 Aug 10, 2005 (Week 1) 29Introduction/Basic Concept Matching applications & networks Non-real-time (stored at sender and receiver ends) Real-time (consumed or sent live) Interactive (two-way) (consumed/sent live) e.g. telephony, on-line interactive games Streaming (one-way) (consumed live; sent from live or stored source) e.g. radio/TV broadcasts Recording (one-way) (stored at receiver end; sent from live source); e.g. Replay Short transfers (e.g. short email) Connectionless networks Circuit-switched networks Packet-switched CO networks Data transfers Interactive (two-way) (consumed/sent live) e.g. telnet, http, games Long transfers (e.g. large image, audio, video or data)

30 Aug 10, 2005 (Week 1) 30Introduction/Basic Concept Outline Types of Communication Networks Types of Communication Networks Quality of Service Measure and Classes Quality of Service Measure and Classes Design issues and Scalability Requirements of Networks Design issues and Scalability Requirements of Networks

31 Aug 10, 2005 (Week 1) Introduction/Basic Concept “Quality of Service” Measure How is level of service measured in the network? How is level of service measured in the network? Measure can be deterministic or statistical Measure can be deterministic or statistical Common parameters are Common parameters are bandwidth bandwidth delay delay delay-jitter delay-jitter loss loss

32 Aug 10, 2005 (Week 1) Introduction/Basic Concept Bandwidth Specified as minimum bandwidth measured over a pre-specified interval Specified as minimum bandwidth measured over a pre-specified interval E.g. > 5Mbps over intervals of > 1 sec E.g. > 5Mbps over intervals of > 1 sec Meaningless without an interval! Meaningless without an interval! Can be a bound on average (sustained) rate or peak rate Can be a bound on average (sustained) rate or peak rate Peak is measured over a ‘small’ inteval Peak is measured over a ‘small’ inteval Average is asymptote as intervals increase without bound Average is asymptote as intervals increase without bound

33 Aug 10, 2005 (Week 1) Introduction/Basic Concept Packet Loss Specified ratio of packet loss over some interval Specified ratio of packet loss over some interval Like bandwidth, meaningless without some reference to a measurement interval Like bandwidth, meaningless without some reference to a measurement interval Common to use an average loss rate measured over a “sufficiently long” interval Common to use an average loss rate measured over a “sufficiently long” interval Consecutive packet loss can be of interest to some applications, e.g. those with error- correction capability Consecutive packet loss can be of interest to some applications, e.g. those with error- correction capability

34 Aug 10, 2005 (Week 1) Introduction/Basic Concept Delay and delay-jitter Bound on some parameter of the delay distribution curve Bound on some parameter of the delay distribution curve

35 Aug 10, 2005 (Week 1) 35Introduction/Basic Concept How do loss and delay occur? Packets queue in router buffers packet arrival rate to link exceeds output link capacity packet arrival rate to link exceeds output link capacity packets queue, wait for turn packets queue, wait for turn A B packet being transmitted (delay) packets queueing (delay) free (available) buffers: arriving packets dropped (loss) if no free buffers

36 Aug 10, 2005 (Week 1) 36Introduction/Basic Concept Four sources of packet delay 1. nodal processing: check bit errors determine output link A B propagation transmission nodal processing queueing 2. queueing 2. queueing time waiting at output link for transmission time waiting at output link for transmission depends on congestion level of router depends on congestion level of router

37 Aug 10, 2005 (Week 1) 37Introduction/Basic Concept Delay in packet-switched networks 3. Transmission delay: R=link bandwidth (bps) R=link bandwidth (bps) L=packet length (bits) L=packet length (bits) time to send bits into link = L/R time to send bits into link = L/R 4. Propagation delay: d = length of physical link s = propagation speed in medium (~2x10 8 m/sec) propagation delay = d/s A B propagation transmission nodal processing queueing Note: s and R are very different quantities!

38 Aug 10, 2005 (Week 1) 38Introduction/Basic Concept Nodal delay d proc = processing delay d proc = processing delay typically a few microsecs or less typically a few microsecs or less d queue = queuing delay d queue = queuing delay depends on congestion depends on congestion d trans = transmission delay d trans = transmission delay = L/R, significant for low-speed links = L/R, significant for low-speed links d prop = propagation delay d prop = propagation delay a few microsecs to hundreds of msecs a few microsecs to hundreds of msecs

39 Aug 10, 2005 (Week 1) 39Introduction/Basic Concept Queueing delay (revisited) R=link bandwidth (bps) R=link bandwidth (bps) L=packet length (bits) L=packet length (bits) a=average packet arrival rate a=average packet arrival rate traffic intensity = La/R La/R ~ 0: average queueing delay small La/R ~ 0: average queueing delay small La/R -> 1: delays become large La/R -> 1: delays become large La/R > 1: more “work” arriving than can be serviced, average delay infinite! La/R > 1: more “work” arriving than can be serviced, average delay infinite!

40 Aug 10, 2005 (Week 1) 40Introduction/Basic Concept Packet loss queue (aka buffer) preceding link in buffer has finite capacity queue (aka buffer) preceding link in buffer has finite capacity when packet arrives to full queue, packet is dropped (aka lost) when packet arrives to full queue, packet is dropped (aka lost) lost packet may be retransmitted by previous node, by source end system, or not retransmitted at all lost packet may be retransmitted by previous node, by source end system, or not retransmitted at all

41 Aug 10, 2005 (Week 1) 41Introduction/Basic Concept Outline Types of Communication Networks Types of Communication Networks Quality of Service Measure and Classes Quality of Service Measure and Classes Design issues/principles Design issues/principles

42 Aug 10, 2005 (Week 1) 42Introduction/Basic Concept Common design techniques Key concept: bottleneck Key concept: bottleneck the most constrained element in a system the most constrained element in a system System performance improves by removing bottleneck System performance improves by removing bottleneck but creates new bottlenecks but creates new bottlenecks In a balanced system, all resources are simultaneously bottlenecked In a balanced system, all resources are simultaneously bottlenecked this is optimal this is optimal but nearly impossible to achieve but nearly impossible to achieve in practice, bottlenecks move from one part of the system to another in practice, bottlenecks move from one part of the system to another

43 Aug 10, 2005 (Week 1) 43Introduction/Basic Concept Top level goal Use unconstrained resources to alleviate bottleneck Use unconstrained resources to alleviate bottleneck How to do this? How to do this? Several standard techniques allow us to trade off one resource for another Several standard techniques allow us to trade off one resource for another

44 Aug 10, 2005 (Week 1) 44Introduction/Basic Concept Multiplexing Another word for sharing Another word for sharing Trades time and space for money Trades time and space for money Users see an increased response time, and take up space when waiting, but the system costs less Users see an increased response time, and take up space when waiting, but the system costs less economies of scale economies of scale

45 Aug 10, 2005 (Week 1) 45Introduction/Basic Concept Multiplexing (contd.) Examples Examples multiplexed links multiplexed links shared memory shared memory Another way to look at a shared resource Another way to look at a shared resource unshared virtual resource unshared virtual resource Server controls access to the shared resource Server controls access to the shared resource uses a schedule to resolve contention uses a schedule to resolve contention choice of scheduling critical in proving quality of service guarantees choice of scheduling critical in proving quality of service guarantees

46 Aug 10, 2005 (Week 1) 46Introduction/Basic Concept Statistical multiplexing Suppose resource has capacity C Suppose resource has capacity C Shared by N identical tasks Shared by N identical tasks Each task requires capacity c Each task requires capacity c If Nc <= C, then the resource is underloaded If Nc <= C, then the resource is underloaded If at most 10% of tasks active, then C >= Nc/10 is enough If at most 10% of tasks active, then C >= Nc/10 is enough we have used statistical knowledge of users to reduce system cost we have used statistical knowledge of users to reduce system cost this is statistical multiplexing gain this is statistical multiplexing gain

47 Aug 10, 2005 (Week 1) 47Introduction/Basic Concept Statistical multiplexing (contd.) Two types: spatial and temporal Two types: spatial and temporal Spatial Spatial we expect only a fraction of tasks to be simultaneously active we expect only a fraction of tasks to be simultaneously active Temporal Temporal we expect a task to be active only part of the time we expect a task to be active only part of the time e.g silence periods during a voice call e.g silence periods during a voice call

48 Aug 10, 2005 (Week 1) 48Introduction/Basic Concept Example of statistical multiplexing gain Consider a 100 room hotel Consider a 100 room hotel How many external phone lines does it need? How many external phone lines does it need? each line costs money to install and rent each line costs money to install and rent tradeoff tradeoff What if a voice call is active only 40% of the time? What if a voice call is active only 40% of the time? can get both spatial and temporal statistical multiplexing gain can get both spatial and temporal statistical multiplexing gain but only in a packet-switched network (why?) but only in a packet-switched network (why?) Remember Remember to get SMG, we need good statistics! to get SMG, we need good statistics! Will cover statistical multiplexing in more detail in the queuing theory section Will cover statistical multiplexing in more detail in the queuing theory section

49 Aug 10, 2005 (Week 1) 49Introduction/Basic Concept Optimizing the common case 80/20 rule 80/20 rule 80% of the time is spent in 20% of the code 80% of the time is spent in 20% of the code Optimize the 20% that counts Optimize the 20% that counts need to measure first! need to measure first! RISC RISC How much does it help? How much does it help? Amdahl’s law Amdahl’s law Execution time after improvement = (execution affected by improvement / amount of improvement) + execution unaffected Execution time after improvement = (execution affected by improvement / amount of improvement) + execution unaffected beyond a point, speeding up the common case doesn’t help beyond a point, speeding up the common case doesn’t help

50 Aug 10, 2005 (Week 1) 50Introduction/Basic Concept Hierarchy Recursive decomposition of a system into smaller pieces that depend only on parent for proper execution Recursive decomposition of a system into smaller pieces that depend only on parent for proper execution No single point of control No single point of control Highly scaleable Highly scaleable Leaf-to-leaf communication can be expensive Leaf-to-leaf communication can be expensive shortcuts help shortcuts help Most network naming schemes are hierarchical Most network naming schemes are hierarchical

51 Aug 10, 2005 (Week 1) 51Introduction/Basic Concept More… Extensibility Extensibility Always a good idea to leave hooks that allow for future growth Always a good idea to leave hooks that allow for future growth Examples: version field in header, Modem negotiation Examples: version field in header, Modem negotiation Separation of Control and Data Path Separation of Control and Data Path Divide actions that happen once per data transfer from actions that happen once per packet Divide actions that happen once per data transfer from actions that happen once per packet Can increase throughput by minimizing actions in data path Can increase throughput by minimizing actions in data path

52 Aug 10, 2005 (Week 1) 52Introduction/Basic Concept Acknowledgements Slides are taken from the following sources: Slides are taken from the following sources: W. Stallings, “Wireless Communications and Networks”, Chapter 3 W. Stallings, “Wireless Communications and Networks”, Chapter 3 S. Keshav, “An Engineering Approach to Computer Networking” S. Keshav, “An Engineering Approach to Computer Networking” Kurose and Ross, “Computer Networking: A Top- Down Approach Featuring the Internet”, Chapter 1 Kurose and Ross, “Computer Networking: A Top- Down Approach Featuring the Internet”, Chapter 1


Download ppt "August 10, 2005 (Week 1) 1 CS 5224 High Speed Networks and Multimedia Networking Dr. Chan Mun Choon Semester 1, 2005/2006 School of Computing National."

Similar presentations


Ads by Google