WO1999067886A1 - Compression de donnees pour un train de donnees multi-flux - Google Patents

Compression de donnees pour un train de donnees multi-flux Download PDF

Info

Publication number
WO1999067886A1
WO1999067886A1 PCT/IL1999/000347 IL9900347W WO9967886A1 WO 1999067886 A1 WO1999067886 A1 WO 1999067886A1 IL 9900347 W IL9900347 W IL 9900347W WO 9967886 A1 WO9967886 A1 WO 9967886A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
compression
data flows
flows
data stream
Prior art date
Application number
PCT/IL1999/000347
Other languages
English (en)
Inventor
Marco Talmon
Original Assignee
Infit Communications Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Infit Communications Ltd. filed Critical Infit Communications Ltd.
Priority to AU43892/99A priority Critical patent/AU4389299A/en
Publication of WO1999067886A1 publication Critical patent/WO1999067886A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/40—Conversion to or from variable length codes, e.g. Shannon-Fano code, Huffman code, Morse code
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/3084—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction using adaptive string matching, e.g. the Lempel-Ziv method

Definitions

  • the present invention relates to data compression and, more specifically, to compressing a stream of data by separately compressing data flows in the stream.
  • Packet-based communication networks transfer information between computers and other equipment using a data transmission format known as packetized data.
  • the stream of data from a data source e.g., a host computer
  • a data source e.g., a host computer
  • switches e.g., routers
  • Switches e.g., routers
  • the packets may be relayed through several routers before they reach their destination. Once the packets reach their destination, they are reassembled to regenerate the stream of data.
  • the routers receive and transmit streams of data over multiplexed lines. That is, each line transmits packets from several sources by sending the packets for each source over the line at different periods of time.
  • each line transmits packets from several sources by sending the packets for each source over the line at different periods of time.
  • the flow of packets from a given data source to a given data destination may be referred to as a data flow.
  • a multiplexed line typically supports many data flows.
  • IP Internet Protocol
  • IP defines procedures for routing data through a network.
  • IP specifies that the data is organized into frames, each of which includes an IP header and associated data.
  • the routers in the network use the information in the IP header to forward the packet through the network.
  • each router-to-router (or switch-to-router, etc.) link is referred to as a hop.
  • a hop As the demand for data services grows, so too does the need for more bandwidth on data networks.
  • One solution to this problem is to add more capacity. That is, add more lines and routers. This, however, is a relatively expensive proposition.
  • Another solution is to increase the throughput on existing lines.
  • One method of accomplishing increased throughput involves compressing the data being routed over the line.
  • Data compression algorithms convert data defined in a given format to another format so that the resulting format contains fewer data bits (i.e., the ones and zeros that define digital data) than the original format. Hence, the data is compressed into a smaller representation.
  • the compressed data is decompressed using an algorithm that is complementary to the compression algorithm.
  • Many compression schemes use what are known as history files.
  • a history file contains a series of mappings between the original data and the compressed representations of the actual data.
  • the compressor and decompressor use identical history files.
  • the history files may be supplied to each component or dynamically created by each component using known algorithms.
  • Some data compression schemes have been proposed for data networks.
  • all packets routed over a given path in the network are compressed as they enter the path and decompressed as they exit the path.
  • a compressor may be installed at one end of the path. The compressor compresses all of the packets being routed over that path.
  • a decompressor at the other end of the path decompresses all of the packets it receives from the path. The decompressor then routes the packets to their destination.
  • a single history file may be used for all of the data at each end of the path.
  • each packet routed over a given path in the network is individually compressed. In this case, a new history file may be used for each packet.
  • data routed over a multiplexed path is compressed before it is sent over the path and is decompressed on the other end of the path.
  • the system may separately compress data flows or groups of data flows that are routed over the path.
  • the system analyses the data to be sent over the path to identify the data flows associated with that data. Then, a data compressor uses a history file associated with each flow or group of flows to compress the data. In addition, the system associates an indicator with the data. The indicator uniquely identifies the flow or flow group. The system then sends the compressed data and the (non-encoded) associated indicator together over the path.
  • the system reads the indicator accompanying the compressed data to identify the flow or flow group associated with that data.
  • a data decompressor uses a history file associated with the flow or flow group to decompress the compressed data.
  • the invention is implemented in a pair of devices installed on each end of an IP hop.
  • the devices may be installed between a pair of routers in the network.
  • the device on the sending end of the hop intercepts each packet that the router sends over the hop.
  • the device identifies the session associated with the packet (in the case of a TCP packet) and uses a history file associated with that session (or a group of sessions that includes that session) to compress the packet.
  • the device generates the history file at the start of each session (or at the start of the first in a group of sessions) and uses the same history file for all of the packets in that session (or session group).
  • the compressed packet and an associated identifier are then sent over the hop.
  • the device on the other end of the hop intercepts each inbound packet from the hop.
  • the device identifies the session (or session group) associated with the packet (in the case of a TCP packet) by reading the identifier and uses a history file associated with that session (or session group) to decompress the packet.
  • a separate history file may be used for each session (or session group).
  • the method of the invention is implemented by installing appropriate software modules in the equipment (e.g., routers) on the ends of the path.
  • the equipment is configured so that packets are processed as above and stored in the internal memory of the equipment, as necessary.
  • a system or method implementing the teachings of the invention may provide more efficient compression than conventional systems or methods that compress different types of data using a common history file.
  • the system or method of the invention may use separate history files for each type of flow. This increases the probability that each of the history files will contain data that it specifically adapted to the corresponding flows.
  • the history file for Japanese e-mail messages may contain some frequently used Japanese words, or dates and headers similar to "From" and "To" which are likely to be found in e-mail messages.
  • HTML data may contain typical HTML strings such as " ⁇ html>" or " ⁇ center>".
  • a history file will contain data related to the other flows.
  • the e-mail history file probably will not include the " ⁇ html>" string.
  • the presence of the specifically adapted data and the absence of the unrelated data in each history file may, in many circumstances, significantly improve the effectiveness of the compression.
  • a system or method implemented according to the invention may provide a higher degree of compression in comparison to conventional compression systems or methods.
  • FIGURE 1 is a block diagram of one embodiment of a data network incorporating a compression system in accordance with the invention
  • FIGURE 2 is a block diagram of a flow compressor constructed according to the invention
  • FIGURE 3 is a block diagram of a flow decompressor constructed according to the invention
  • FIGURE 4 is a flowchart of operations that may be performed by a compression system implemented according to the invention.
  • FIGURE 5 is a flowchart of operations that may be performed by a decompression system implemented according to the invention.
  • FIGURE 6 is a block diagram of another embodiment of a data network incorporating compression and decompression in accordance with the invention.
  • FIGURE 1 illustrates a single IP hop in a data network system S employing one embodiment of the invention.
  • a router 20 at one end of the hop sends packets to another router 22 on the other end of the hop.
  • the link between the routers 20 and 22 may be either a permanent or temporary link. It is used to transfer unmodified layer 3 protocol packets.
  • Layer 3 is a network layer protocol and encompasses, for example, the Internet Protocol and those that conform to the Open System Interconnection ("OSI") reference model.
  • OSI Open System Interconnection
  • a flow compressor 28 extracts individual flows and/or groups of flows from the inbound packets. Each individual flow or group of flows may then be separately compressed by a compressor 30. The compressed flows are sent to the other end of the hop where a flow decompressor 32 separately decompresses each flow or flow group.
  • a flow identifier 34 analyzes an inbound packet to identify the layer 4 flow associated with the packet.
  • Layer 4 is a transport layer protocol and encompasses, for example, the Transmission Control Protocol ("TCP") and those that conform to the Open System Interconnection ("OSI") reference model.
  • TCP Transmission Control Protocol
  • OSI Open System Interconnection
  • the flow identifier 34 associates the flow with an identifier (ID 36). This identifier 36 uniquely identifies the associated flow or flow group.
  • the flow compressor 28 uses the ID 36 sent by the flow identifier 34 to retrieve a compression history file. As illustrated in FIGURE 1 , several history files 38 are stored in the flow compressor 28, each of the history files 38 is associated with an active flow or an active flow group.
  • the compressor 30 uses the retrieved history file to compress the packet.
  • the flow compressor 28 associates an indicator with the packet.
  • the indicator uniquely identifies a flow or flow group.
  • the flow compressor 28 sends this indicator with the compressed data to the flow decompressor 32 on the other end of the hop so that the flow decompressor 32 can determine with which flow or flow group the compressed packet is associated.
  • a flow identifier 40 reads the indicator accompanying the compressed packet to identify the flow or flow group associated with the packet. The flow identifier then sends an identifier (ID 42) to a decompressor 44 to enable the decompressor 44 to retrieve the appropriate compression history file 46.
  • ID 42 an identifier
  • the compressor 30 and the decompressor 44 are implemented in a manner that ensures that each of them maintains analogous state information (compression history) for a given flow. In other words, for a given state in a particular flow, the corresponding history files in both the flow compressor 28 and the flow decompressor 32 will contain identical state information.
  • the decompressor 44 uses the retrieved history file 46 to decompress the packet. After the packet is decompressed, the flow decompressor 32 forwards the packet, which is now in its original, uncompressed state, to its destination.
  • Adaptive compression methods are based on the idea that if the stream of data elements to be encoded is x-i, x 2 , x 3 , etc., then the encoding of x is based on information extracted from x-i, x 2 , ... Xt-i- Typically, each of the elements is a character. However in some applications each element may be a word or some other character string.
  • the first t-1 data elements are referred to as the history data at stage t.
  • the use of the history data enables the compression/decompression system to be adaptive. In other words, there is no need to transfer statistical distribution tables between the compressor and decompressor.
  • the decompressor Before the decompressor starts decompressing the compressed element x t , the decompressor knows the values of x 1 t ... x t- ⁇ .
  • the decompressor can evaluate the code from which the code-word for x t is extracted in exactly the same way as the compressor.
  • the extracted information may be, for example, the distribution of the various characters, i.e., their relative frequencies, which are necessary to derive a variable length code (e.g., Huffman's code) or an arithmetic code.
  • FIGURES 2 and 3 are block diagrams of compressor and decompressor sections, respectively, of a device that is installed in the network.
  • FIGURES 4 and 5 are flowcharts that describe operations that may be performed by the compressor and decompressor sections depicted in FIGURE 2 and 3, respectively, or by other embodiments of the invention.
  • a flow compressor 28 processes an inbound stream of packets.
  • a network input interface 50 terminates the physical layer and provides layer 2 packets to a processor 52 .
  • the network interface 50 connects to a wide area network ("WAN") as described above.
  • the device may be installed farther up the link (i.e., before the router 20 ).
  • one or more of the network interfaces (50 and 54) may connect to a local area network ("LAN").
  • the network interface in this type of system will include a LAN-type interface such as an Ethernet interface.
  • the details of the operation and implementation of network input interfaces are well known in the IP data networking art.
  • the processor 52 illustrated in FIGURE 2 includes several logical components. The operations of these components are described in conjunction with FIGURE 4 beginning at block 100.
  • the processor 52 receives a layer 2 packet from the interface 50.
  • a layer 3 packet identifier 56 reads the packet header to identify the layer 3 protocol of the packet.
  • the level 3 protocol is the Internet Protocol.
  • the packet identifier 56 then sends the protocol information to a session handler 58 via line 60. This enables the session handler 58 to separate the flows. That is, once the session handler 58 knows the protocol of the incoming level 3 packet, the session handler 58 will know how to identify the flow within the packet.
  • the flow compressor 28 may be configured to compress all packets. In other embodiments, however, the flow compressor 28 may selectively compress packets. The latter scenario is treated at block 106.
  • a compression bypass component 62 determines whether this packet is to be compressed. If the packet should not be compressed, the compression bypass component 62 routes the packet directly to a packet assembler 64 via line 66 so that the packet bypasses the compression stage.
  • the decision of whether to compress a packet may be based on various criteria. For example, the bypass component 62 may reroute all non-IP packets (e.g., RIP packets) so they bypass the compression stage. In one embodiment, the compression bypass component 62 analyzes the inbound packet to determine whether it is encrypted. If it is encrypted, the bypass component 62 may skip the compression process for this packet.
  • non-IP packets e.g., RIP packets
  • bypass component 62 may cooperate with the session handler
  • a session identifier 70 identifies the layer 4 flow associated with the packet (block 108). For TCP packets, the session identifier 70 may identify a session based on the combination of the source IP address, the destination IP address, the source port and the destination port. All of this information is contained in the header of the packet.
  • the session identifier 70 may also identify a particular session or member of a session group by analyzing the packet data. For example, the session identifier may look for certain strings, or a particular distribution of characters.
  • the session handler 58 maintains a session table 72 of all sessions and session groups associated with the packets that have passed through this node of the network.
  • the session table 72 is stored in a data memory 74 as illustrated in FIGURE 2.
  • the table entries may include an identifier for each session and session group along with information that identifies the flow.
  • an identifier for a session 76 may be associated with a source IP address, a destination IP address, a source port and a destination port.
  • An identifier for a session group 78 may be associated, for example, with a source IP address and a destination IP address, with a port, or with a source IP address. It should be appreciated by one skilled in the art that many other methods of identifying flows may be used in accordance with the teachings of the invention.
  • a new session identifier 80 determines whether the packet is associated with a new session or session group. For example, the new session identifier 80 may compare the current session information with the entries in the session table 72.
  • the session handler 58 passes the session information of the packet to a dictionary maintenance component 82 that creates an entry in the session table 72.
  • the dictionary maintenance component 82 may generate an identifier that is associated with a session.
  • the dictionary maintenance component 82 may create an entry 76 in the session table 72 for the identifier and the source IP address, the destination IP address, the source port and the destination port.
  • the dictionary maintenance component 82 may generate an identifier that is associated with the source IP address of the current session. In this case, the dictionary maintenance component 82 would store this information in the session table 72.
  • the dictionary maintenance component 82 creates a dictionary entry 84 for the new session or session group. Depending on the compression scheme, the new dictionary entry 84 may or may not initially contain information.
  • some adaptive compression schemes generate the dictionary entries on-the-fly.
  • the newly created compression dictionary information 84 is stored in the data memory 74 (e.g., as dictionary 1 84A) and the corresponding ID is sent to a compressor 86.
  • the session handler 58 sends the session identifier (ID) to the compressor 86 via line 88 .
  • the compressor 86 uses the ID to fetch the corresponding compression dictionary (e.g., dictionary 1 84A) from the data memory 74 (block 116).
  • the packet compressor 86 compresses the packet using the compression dictionary 84.
  • Various packet compression algorithms may be used at this stage.
  • the compressor 86 may implement a compression scheme based on Lempel-Ziv algorithms.
  • LZ77 is discussed in U.S. Patent Nos. 5,016,009 and 5,126,739 (both of which are entitled Data Compression Apparatus and Method), the contents of which are hereby incorporated herein by reference.
  • Another algorithm, known as LZW (which is a variant of LZ78), is discussed in U.S. Patent No. 4,558,302, the contents of which is hereby incorporated herein by reference.
  • Compression software also may be commercially available.
  • a packet compressor is sold under the name "STAC LZS" by Stac Electronics.
  • the packets associated with a given flow or flow group may be compressed separately or collectively.
  • the compression is performed independently for each packet.
  • each packet may, in effect, have its own dictionary.
  • the packet is compressed using a static algorithm. For example, the algorithm may first scan the packet to gather statistics, then build a Huffman code based on these statistics, and finally rescan the packet to compress it.
  • the algorithm compresses each packet independently using an adaptive algorithm, like any Lempel-Ziv algorithm.
  • a global compression algorithm may be used that acts on all the packets with the same auxiliary data.
  • the algorithm uses the statistics of not only the packet t itself, but of all the packets 1 , 2, up to and including t.
  • the algorithm may base the compression of packet t only on the statistics gathered from packets 1 , 2, up to including packet t-1 , but not packet t itself.
  • the compressor 86 may be implemented as several compressors so that several packets may be compressed simultaneously. In this case, the session handler 58 would distribute the packets to the compressors 86 as necessary.
  • the compressors 86 may be implemented as several compression processes. The compression processes may run on one or more processors 52. Alternatively, the compressor 86 could be implemented in hardware using application specific integrated circuits or other logic circuits.
  • an end session identifier 92 checks the inbound packet to determine whether the current packet is the last packet that will be sent in the session. For example, in TCP, the packet type "FIN" indicates that this is the last packet in a session.
  • the end of a session may serve as an indication that the dictionary 84 and session table entries 76 and 78 may be cleared.
  • the entries may be cleared after the last packet for that session is sent over the hop.
  • the process proceeds to block 122.
  • the dictionary maintenance component 82 deletes the ID and associated information from the session table 72 and deletes the corresponding dictionary entry 84 from the data memory 74.
  • the session handler 58 may use a time-out mechanism to ensure that obsolete dictionaries 84 and session table entries 76 and 78 are deleted.
  • the time-out may be predefined or dynamic, depending on system resources.
  • a compressed packet identifier 94 marks the compressed packet to indicate that it is compressed.
  • the compressed packet identifier 94 prefixes a one bit tag to each packet that indicates whether the packet is compressed.
  • the compressed packet identifier 94 attaches the indicator to the packet.
  • the indicator identifies the flow or flow group for the packet.
  • the indicator may consist of, for example, a non-encoded index of the flow.
  • the packet assembler 64 assembles the packet
  • the processor 52 sends the packets to the network output interface 54.
  • the network output interface 54 processes the network layer (e.g., IP) packets and provides the appropriate physical and data link layers to interface to the network. Details of the operation and implementation of a network output interface are also well known in the IP data networking art.
  • the process then ends at block 130.
  • packets from the flow compressor 28 are routed over the network to the flow decompressor 32 on the other end of the hop.
  • the flow decompressor 32 includes a network input interface 150 that terminates the physical and data link layers and provides network layer (e.g., IP) packets to a processor 152.
  • FIGURE 5 beginning at block 200, the operation of the processor will now be treated in detail. Many of the components and operations depicted in FIGURES 3 and 5 are similar to those discussed above in conjunction with FIGURES 2 and 4. Consequently, these operations will only be treated briefly here.
  • the processor 152 receives a packet from the network input interface 150.
  • the network input interface 150 terminates the physical layer and provides layer 2 packets to the processor 152.
  • a layer 3 packet identifier 156 reads the packet header to determine the layer 3 protocol of the packet.
  • a compressed packet identifier 162 determines whether the inbound packet is compressed. As discussed above, this may involve checking a one bit tag prefixed to the packet that indicates whether the packet is compressed. If the packet is not compressed, the process proceeds to block 226 and the packet is forwarded to a packet assembler 164 via line 166. The operations of the packet assembler 164 are discussed below.
  • the packet and associated indicator are sent to a session handler 158 via lines 168 and 160, respectively.
  • a session identifier 170 reads the indicator that accompanied the packet (block 208). In one embodiment, this process may simply consist of reading an index number assigned to the flow.
  • a new session identifier 180 determines whether the packet is associated with a new session.
  • the session handler 158 may maintain a session table 172 for the active sessions and session groups.
  • the process proceeds to block 212 and the dictionary maintenance component 182 enters the session or session group information into the session table 172.
  • the dictionary maintenance component 182 creates a compression dictionary entry 184 for the new session or session group.
  • the process proceeds to block 216. Then, the flow decompressor 32 uses the ID received via line 188 to fetch the compression dictionary 184 associated with the session or session group.
  • the packet decompressor 186 uses the retrieved compression dictionary 184 to decompress the packet that was received via line 190.
  • the decompression algorithms used by the decompressor 186 are compatible with the compression algorithm used by the compressor 86 in
  • FIGURE 2 is a diagrammatic representation of FIGURE 1
  • the compressor 86 and the decompressor 186 may use dictionary schemes as are known in the art.
  • dictionaries may be pre-loaded into the data memories in the flow compressor 28 and the flow decompressor 32 or the dictionaries may initially be empty.
  • the compression and decompression algorithms will use the same procedures to adaptively update the dictionaries 84 and 184 on-the-fly.
  • an end session identifier 192 determines whether the dictionary 184 for the current session or session group is still needed. As discussed above in conjunction with FIGURE 2, if the current packet is the last packet in the session or session group, the process proceeds to block 222.
  • the dictionary maintenance component 182 deletes the session information (176 or 178) from the session table 172, then it deletes the dictionary entry 184 for that session from the data memory 174. Again, these operations may be initiated by some form of background (e.g., time-out) routine.
  • the packet assembler 164 assembles the packet
  • the processor 152 sends the packets to the network output interface 154.
  • the network output interface 154 processes the network layer (e.g., IP) packets and provides the appropriate physical and data link layers to interface to the network.
  • the details of the operation and implementation of the network output interface 154 may be similar to those of the interfaces discussed above in conjunction with FIGURE 2.
  • the process then ends at block 230.
  • FIGURE 6 illustrates an embodiment of the invention that is implemented by integrating software modules 250 into equipment 252 installed at each end of a predefined path in the network N.
  • the equipment 252 may consist of routers, bridges, switches, modems or any other equipment in the network N that handle packet traffic.
  • the packet compression and decompression operations performed by the embodiment of FIGURE 6 are similar to those described above in conjunction with FIGURES 2-5.
  • the compressor software modules 254 and decompressor software modules 256 are linked in with software modules 258 in the equipment in a manner that enables the compressor and decompressor software modules 254 and 256 to intercept and process packets.
  • a data memory 260 in the equipment may be used to store the packet data.
  • the compressor and decompressor software modules 254 and 256 may be implemented along the transmission path in the equipment 252 where the packets are fully visible. For example, some of the packets flowing through the network N may be encrypted. Thus, the compressor and decompressor software modules 254 and 256 may be linked in to the switch modules 258 so that the compressor and decompressor software modules 254 and 256 have access to decrypted data.
  • a compressor 254 and a decompressor 256 are installed on both sides of a duplex link. Accordingly, packet traffic that flows in either direction over the path is compressed on a per session or session group basis.
  • FIGURE 6 also illustrates that the invention may be used on more than a single IP hop.
  • the packets are routed through the network 262 and, as a result, they may be routed over several hops. For example, another hop between two routers 264 and 266 is shown.
  • appropriate routing provisions should be made to ensure that all compressed packets are routed to the same receive module at the other end of the path. This may include, for example, defining static routes using IP tunneling.
  • various initialization procedures may be performed. For example, all dictionaries may be erased and various compression parameters may be exchanged between the flow compressor and the flow decompressor.
  • the invention provides an effective method of compressing transmitted packets.
  • the invention may provide a higher degree of compression and use data memory more efficiently than many conventional systems. While certain specific embodiments of the invention are disclosed as typical, the invention is not limited to these particular forms, but rather is applicable broadly to all such variations as fall within the scope of the appended claims. To those skilled in the art to which the invention pertains many modifications and adaptations will occur.
  • the devices may be installed at various locations within the network.
  • the invention may be implemented using a variety of hardware and software architectures.
  • the teachings of the invention are applicable to numerous protocols in addition to those described above.
  • a number of compression algorithms and compression history techniques may be used to compress or decompress data.
  • the system may compress and decompress various types of flows of various types of data.
  • other forms of flow identifiers may be used.

Abstract

Pour comprimer des données multiplexées, un compresseur de données (28) comprime des données multiplexées en comprimant séparément chacun des flux de données ou groupes de flux de données (F1...F3). Les données comprimées sont acheminées à un décompresseur de données (32) qui décomprime séparément les flux ou groupes de flux (F1.. F3). Le compresseur (28) et le décompresseur (32) produisent à la demande des historiques de compression (38, 42) pour chaque flux et groupe de flux (F1...F3). Selon une réalisation, le compresseur de données (28) et le décompresseur de données (32) équipent les extrémités opposées d'un chemin de données dans un réseau informatique.
PCT/IL1999/000347 1998-06-23 1999-06-23 Compression de donnees pour un train de donnees multi-flux WO1999067886A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU43892/99A AU4389299A (en) 1998-06-23 1999-06-23 Data compression for a multi-flow data stream

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US10334598A 1998-06-23 1998-06-23
US09/103,345 1998-06-23

Publications (1)

Publication Number Publication Date
WO1999067886A1 true WO1999067886A1 (fr) 1999-12-29

Family

ID=22294682

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IL1999/000347 WO1999067886A1 (fr) 1998-06-23 1999-06-23 Compression de donnees pour un train de donnees multi-flux

Country Status (2)

Country Link
AU (1) AU4389299A (fr)
WO (1) WO1999067886A1 (fr)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1049350A1 (fr) * 1999-04-30 2000-11-02 Teles AG Informationstechnologien Méthode et système de communication pour la transmission de données d'un raccordement d'abonné
WO2003050641A3 (fr) * 2001-12-10 2004-02-26 Virtual Locality Ltd Appareil et procede de reflexion optimisee et securisee de services de reseau vers des emplacements a distance
US7321322B2 (en) 2003-05-08 2008-01-22 Sap Portals Israel Ltd. Pattern-driven, message-oriented compression apparatus and method
WO2008112777A3 (fr) * 2007-03-12 2009-12-30 Citrix Systems, Inc. Systèmes et procédés pour utiliser des historiques de compression pour améliorer la performance de réseau
US7774323B2 (en) 2006-03-27 2010-08-10 Sap Portals Israel Ltd. Method and apparatus for delivering managed applications to remote locations
GB2454133B (en) * 2006-08-15 2011-10-26 Celtro Ltd Method and system for saving bandwidth during broadcasting/multicasting
US8396214B2 (en) 2006-11-02 2013-03-12 SAP Portals Israel Limited Method and apparatus for centrally managed encrypted partition
US9325762B2 (en) 2012-12-11 2016-04-26 Qualcomm Incorporated Method and apparatus for efficient signaling for compression
US9350676B2 (en) 2012-12-11 2016-05-24 Qualcomm Incorporated Method and apparatus for classifying flows for compression

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5654703A (en) * 1996-06-17 1997-08-05 Hewlett-Packard Company Parallel data compression and decompression
US5701302A (en) * 1995-10-25 1997-12-23 Motorola, Inc, Method and apparatus for adaptively companding data packets in a data communication system
US5831558A (en) * 1996-06-17 1998-11-03 Digital Equipment Corporation Method of compressing and decompressing data in a computer system by encoding data using a data dictionary

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5701302A (en) * 1995-10-25 1997-12-23 Motorola, Inc, Method and apparatus for adaptively companding data packets in a data communication system
US5654703A (en) * 1996-06-17 1997-08-05 Hewlett-Packard Company Parallel data compression and decompression
US5831558A (en) * 1996-06-17 1998-11-03 Digital Equipment Corporation Method of compressing and decompressing data in a computer system by encoding data using a data dictionary

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1049350A1 (fr) * 1999-04-30 2000-11-02 Teles AG Informationstechnologien Méthode et système de communication pour la transmission de données d'un raccordement d'abonné
WO2003050641A3 (fr) * 2001-12-10 2004-02-26 Virtual Locality Ltd Appareil et procede de reflexion optimisee et securisee de services de reseau vers des emplacements a distance
US7321322B2 (en) 2003-05-08 2008-01-22 Sap Portals Israel Ltd. Pattern-driven, message-oriented compression apparatus and method
US7774323B2 (en) 2006-03-27 2010-08-10 Sap Portals Israel Ltd. Method and apparatus for delivering managed applications to remote locations
GB2454133B (en) * 2006-08-15 2011-10-26 Celtro Ltd Method and system for saving bandwidth during broadcasting/multicasting
US8094607B2 (en) 2006-08-15 2012-01-10 Celtro Ltd Method and system for saving bandwidth during broadcasting/multicasting
US8396214B2 (en) 2006-11-02 2013-03-12 SAP Portals Israel Limited Method and apparatus for centrally managed encrypted partition
WO2008112777A3 (fr) * 2007-03-12 2009-12-30 Citrix Systems, Inc. Systèmes et procédés pour utiliser des historiques de compression pour améliorer la performance de réseau
EP2651090A3 (fr) * 2007-03-12 2014-01-22 Citrix Systems, Inc. Systèmes et procédés pour ameliorer les couples de historiques de compression en supprimant des entetes de la couche d'applkication
US9325762B2 (en) 2012-12-11 2016-04-26 Qualcomm Incorporated Method and apparatus for efficient signaling for compression
US9350676B2 (en) 2012-12-11 2016-05-24 Qualcomm Incorporated Method and apparatus for classifying flows for compression

Also Published As

Publication number Publication date
AU4389299A (en) 2000-01-10

Similar Documents

Publication Publication Date Title
EP1330720B1 (fr) Architecture de reseau et procedes de codage transparent de sessions croisees en ligne et de transport de donnees de communications reseau
EP1334560B1 (fr) Procede de communication pour une compression de contexte partage
US6711164B1 (en) Method and apparatus for performing IP-ID regeneration to improve header compression efficiency
US5446736A (en) Method and apparatus for connecting a node to a wireless network using a standard protocol
US6134245A (en) System and method for the compression and transportation of non frame relay data over a frame relay network
US8934343B2 (en) Method and apparatus for Ethernet data compression
US7126955B2 (en) Architecture for efficient utilization and optimum performance of a network
US7630394B2 (en) Method, apparatus and computer-readable code for data compression of network packets
JP3900435B2 (ja) データパケットのルーティング方法およびルーティング装置
US20060075134A1 (en) Routing data packets in a compressed-header domain
US8539062B1 (en) Method and system for managing network traffic
EP0836780B1 (fr) Agencement d'adressage de reseau destine a l'acheminement retro-compatible d'un espace d'adressage elargi
EP1216539B1 (fr) Manipulation des champs d'en-tete visant a ameliorer les performances de la communication par paquets
US7027450B2 (en) Frame batching and compression for IP transmission
JP3972038B2 (ja) データ通信用セル・ヘッダの圧縮
US7640362B2 (en) Adaptive compression in an edge router
WO1999067886A1 (fr) Compression de donnees pour un train de donnees multi-flux
US6229823B1 (en) System and method for the compression of proprietary encapsulations
US20020095513A1 (en) Multilayer lossless data compression across a network
US6963568B2 (en) Method for transmitting data packets, method for receiving data packets, data packet transmitter device, data packet receiver device and network including such devices
US7450586B2 (en) Network header compression arrangement
WO2002045309A1 (fr) Procede pour comprimer les en-tetes de paquets dans un protocole de jonction pour l'agregation de multiples canaux d'informations dans un reseau
US20110116503A1 (en) Technique For Packet Compression In An Application Level Multicast
US7319697B2 (en) Data communication system according to a packet-switching principle
Neupane IP payload compression for higher throughput

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AE AL AM AT AU AZ BA BB BG BR BY CA CH CN CU CZ DE DK EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MD MG MK MN MW MX NO NZ PL PT RO RU SD SE SG SI SK SL TJ TM TR TT UA UG US UZ VN YU ZA ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW SD SL SZ UG ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE BF BJ CF CG CI CM GA GN GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
REG Reference to national code

Ref country code: DE

Ref legal event code: 8642

122 Ep: pct application non-entry in european phase