A method for operating a network

Patent metadata

Field	Value
Publication number	US-2016014229-A1
Application number	US-201414769821-A
Country	US
Kind code	A1
Filing date	Feb 21, 2014
Priority date	Feb 27, 2013
Publication date	Jan 14, 2016
Grant date	—

Abstract

A method operates a network, wherein multiple clients are connected to a server for accessing an application that is provided or running on the server. The application is tunneled within one or more corresponding flows between the clients and the server. A device for per flow scheduling of the flows prioritizes the flows based on at least one of application characteristics, application requirements, flow characteristics or flow requirements. The prioritizing by the device takes into consideration a change or a variation, over time, of at least one of an application characteristic, an application requirement, a flow characteristic or a flow requirement.

First claim

1 . A method for operating a network, wherein multiple clients are connected to a server for accessing an application that is provided or running on the server, wherein the application is tunneled within one or more corresponding flows between the clients and the server, the method comprising:
prioritizing, by a device for per flow scheduling of the flows, the flows based on at least one of application characteristics, application requirements, flow characteristics or flow requirements, and wherein the prioritizing by the device takes into consideration a change or a variation, over time, of at least one of an application characteristic, an application requirement, a flow characteristic or a flow requirement.

2 . The method according to claim 1 , wherein the application requirement or the flow requirement that is used includes at least one of a Quality of Experience, QoE, requirement, a QoF, threshold, a bandwidth requirement or a bandwidth threshold.

3 . The method according to claim 1 , wherein an the application characteristic or the flow characteristic that is used comprises a Round-Trip Time, RTT.

4 . The method according to claim 1 , wherein the device prioritizes a flow with a delay-sensitive application.

5 . The method according to claim 1 , wherein the flows traverse the device.

6 . The method according to claim 1 , wherein connections between the clients and the server are thin client connections.

7 . The method according to claim 1 , wherein the application or connections between the clients and the server are encrypted.

8 . The method according to claim 1 , wherein a per flow application identification is available to the device.

9 . The method according to claim 8 , wherein the per flow application identification is statistical.

10 . The method according to claim 8 , wherein the per flow application identification is based on an estimation of at least one of application type, RTT of each flow, QoE expectation for the flow or bandwidth requirement for the flow.

11 . The method according to claim 1 , wherein scheduling or the prioritizing is performed periodically or dynamically.

12 . The method according to claim 1 , wherein, during the scheduling or, the prioritizing, the flows are assigned to queue classes based on at least one of current application characteristics, current application requirements, current flow characteristics or current flow requirements.

13 . The method according to claim 12 , wherein during the scheduling or the prioritizing, individual weights are assigned to the queue classes based on their current characteristics or requirements.

14 . The method according to claim 12 , wherein during the scheduling or the prioritizing, the queue classes are assigned a bandwidth corresponding to the characteristics or the requirements of the flows within each individual queue class.

15 . The method according to claim 1 , wherein the prioritizing by the device is based on a Delay Budget, DB, which is a difference between an optimal time a Flow requires to be within the application requirements or the flow requirements for an application type and its current average RTT.

16 . The method according to claim 15 , wherein during the scheduling or the prioritizing, the flows are classified into m queue classes C=c 1 , c 2 , . . . , c m depending on the respective Delay Budgets, wherein m is a positive integer.

17 . The method according to claim 16 , wherein each class c k that belongs to C has a maximum Delay Budget, DB max (c k ), and classes are ordered such that if k<h, then DB max (c k )<DB max (c h ), wherein h and k are positive integers.

18 . The method according to claim 17 , wherein each flow f i is allocated to the class c k with the lowest DB max (c k ) that is higher than DB(f i ; t j ), such that flows get allocated to a lowest class which has a higher maximum Delay Budget than the current Delay Budget of the flow, wherein i, j and k are positive integers and t is a point of time.

19 . The method according to claim 18 , wherein each flow f i is allocated periodically.

20 . The method according to claim 16 , wherein during the scheduling or the prioritizing, each class c k is assigned a weight w(c k , t j ), which is calculated based on the Delay Budgets of the flows in that class and on the bandwidth requirements of the flows in that class for all f i in c k , wherein i, j and k are positive integers and t is a point of time.

21 . The method according to claim 20 , wherein each class c k is assigned periodically.

22 . The method according to claim 13 , wherein for each queue class, there is a scheduling queue and an outgoing bandwidth of each queue is proportional to a weight of the respective queue class.

23 . The method according to claim 15 , wherein during the scheduling or the prioritizing, weights are assigned to queue classes proportional to a number of the flows currently allocated to that queue class and inversely proportional to the Delay Budgets of the flows.

24 . The method according to claim 1 , wherein accessing the application comprises accessing a content that is provided on the server.

25 . The method according to claim 1 , wherein the device is realized close to the server or within the server.

26 . A network comprising:
multiple clients connected to a server for accessing an application that is provided and/or running on the server, wherein the application is tunneled within corresponding flows between the clients and the server; and a device for per flow scheduling of the flows configured to prioritize the flows based on at least one of application characteristics, application requirements, flow characteristics or flow requirements, and wherein, the device is further configured to prioritize the flows based on a change or a variation, over time, of at least one of an application characteristic, an application requirement, a flow characteristic or a flow requirement.

Assignees

• Nec Europe Ltd

Inventors

• Seedorf Jan
• Arumaithurai Mayutan
• Monticelli Edo

Classifications

• H04L47/6275

  based on priority · CPC title

• H04L47/2441

  relying on flow classification, e.g. using integrated services [IntServ] · CPC title

• H04L47/6215

  Individual queue per QOS, rate or priority · CPC title

• H04L67/322 Primary

  Electricity · mapped topic

• H04L65/80 Primary

  Responding to QoS · CPC title