Method and system for classifying network devices in virtual LANs

• US 6,578,021 B1
• Filed: 10/05/1999
• Issued: 06/10/2003
• Est. Priority Date: 12/29/1998
• Status: Expired due to Term

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Barillaud, Franck
• Primary Examiner(s): Follansbee, John
• Assistant Examiner(s): Hirl, Joseph P.
• Application Number:
  US09/412,686
• Time in Patent Office: 1,344 Days
• Field of Search: 706/20, 706/21, 706/26
• US Class Current: 706/20
• CPC Class Codes: H04L 12/4641 Virtual LANs, VLANs, e.g. virtual private networks [VPN] LAN interconnection over a bridge based backbone H04L12/462; encapsulation techniques H04L12/4633; routing of packets H04L45/00; packet switches H04L49/00; virtual private networks for security H04L63/0272
• CPC Class Codes: H04L 41/08 Configuration management of networks or network elements address allocation H04L61/50
• CPC Class Codes: H04L 41/0853 by actively collecting configuration information or by backing up configuration information
• CPC Class Codes: H04L 41/0866 Checking the configuration
• CPC Class Codes: H04L 41/0895 Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• CPC Class Codes: H04L 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities

Abstract

Network management information stored by network devices in a switched network is obtained at a network management workstation. This is information that relates to the activity of the network devices on the network, such as the logical address of the network devices in communication with other devices. For TCP/IP networks utilizing the NMP protocol, this information is stored in the MIB or the RMON matrix group variables. This information feeds a neural network. The output of the neural network is a list of network devices grouped in virtual LANs (VLANs) such that network devices communicating, or having recently communicated, are grouped in the same VLAN. The network management information is periodically updated so the VLAN grouping can also be periodically refreshed to reflect current network device activity and thus optimize the network bandwidth.

Claims

1. A method for classifying network devices into VLANs at switches in a switched network having a network management application managing said network devices, said method being characterized in that it comprises the steps of:

collecting network logical addresses and communication activity therebetween, stored on said network devices using said network management applications;

applying the collected network logical addresses and communication activity therebetween to a neural network operating on a computer, and

running said neural network, to produce an output list of network devices grouped in VLANs according to the pattern presented by the network logical addresses communicating together, and

sending the VLAN groupings from said computer to the switches.

2. The method of claim 1 characterized in that the neural network is a Self-Organizing Feature Map (SOFM) Artificial neural network.

3. The method of claim 2 characterized in that the network is TCP/IP network and the network logical addresses are the IP addresses of the other network devices which are communicating with said network devices.

4. The method of claim 3 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs.

5. The method of claim 3 characterized in that the said network management application supports the single Network Management Protocol (SNMP).

6. The method of claim 5 characterized in that the IP addresses of the other network devices which are communicating with said network devices are obtained by said network management application reading a MIB stored in said network devices.

7. The method of claim 6 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs, using said network management application.

8. The method of claim 5 characterized in that the IP addresses of the other network devices which are communicating with said network devices are obtained by said network management application reading a RMON Matrix Group stored in said network devices.

9. The method of claim 8 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs, using said network management application.

10. The method of claim 2 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs.

11. The method of claim 1 characterized in that the neural network is an Adaptive Resonance Theory (ART) Artificial neural network.

12. The method of claim 11 characterized in that the network is TCP/IP network and the network logical addresses are the IP addresses of the other network devices which are communicating with said network devices.

13. The method of claim 12 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs.

14. The method of claim 12 characterized in that said network management application supports the Single Network Management Protocol (SNMP).

15. The method of claim 14 characterized in that the IP addresses of the other network devices which are communicating with said network devices are obtained by said network management application reading a MIB stored in said network devices.

16. The method of claim 15 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs, using said network management application.

17. The method of claim 14 characterized in that the IP addresses of the other network devices which are communicating with said network devices are obtained by said network management application reading a RMON Matrix Group stored in said network devices.

18. The method of claim 17 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANs, using said network management application.

19. The method of claim 11 further comprising the step of reading said output list of network devices grouped in VLANs and updating the network devices using this information with said list of network devices grouped in VLANS.

20. A method according to claim 1 wherein the step of collecting communication activity includes a step of selectively discarding communication activity according to age.

21. A system for classifying network devices in VLANs at switches in a network comprising:

a main processor,

a storage unit accessed by said main processor,

a network interface to the network devices allowing collection of network logical addresses and communication traffic of said network devices by the main processor and storage of the collection in said storage unit,

a neural network component activated by the main processor and fed by the main processor with said network logical addresses and communication traffic stored in said storage unit, said neural network providing an output list of VLANs classified according to the network logical addresses communicating together, said output list being stored in the storage unit by the main processor and sent to the switches of the network.

22. The system of claim 21 further comprising a user interface with said main processor allowing users to request VLAN classification to be activated, said user interface accessing also said output list of classified VLANs stored in said storage unit.

23. The system of claim 21 further comprising a network management component providing said network interface to said network devices, said network management component using the main processor for collecting network information and for updating the network devices with said output list of classified VLANs.

24. An article of manufacture comprising a computer usable medium having a computer program embedded in said medium, wherein the computer readable program when executed on a computer connected to a network including network devices switched by one or more LAN switches, causes the computer to:

collect, from the network devices, network logical addresses and intercommunication activity records stored on said network devices;

create an emulation of a neural network;

apply the collected network logical addresses and intercommunication records to the neural network emulation;

run the neural network emulation to produce an output list of network devices grouped in VLANs according to the pattern of the network logical addresses communicating together, and

send the list to the LAN switches.

25. The article of manufacture of claim 24 wherein said emulation of a neural network is an emulation of a Self-Organizing Feature Map (SOFM) Artificial neural network.

26. The article of manufacture of claim 24 wherein said emulation of a neural network is an emulation of an Adaptive Resonance Theory (ART) Artificial neural network.