US20060253607A1 - Method for adapting link weights in ralation to optimized traffic distribution - Google Patents
Method for adapting link weights in ralation to optimized traffic distribution Download PDFInfo
- Publication number
- US20060253607A1 US20060253607A1 US10/550,229 US55022905A US2006253607A1 US 20060253607 A1 US20060253607 A1 US 20060253607A1 US 55022905 A US55022905 A US 55022905A US 2006253607 A1 US2006253607 A1 US 2006253607A1
- Authority
- US
- United States
- Prior art keywords
- link
- accordance
- traffic
- paths
- determined
- Prior art date
- Legal status (The legal status 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 status listed.)
- Abandoned
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
Definitions
- the invention relates to a method for adapting link weights in a communication network formed from links for an optimized distribution of traffic within the communication network as regards the volume of traffic expected for the communication network and in relation to a parameter relating to link usage.
- the invention lies within the area of communication technology and in particular deals with the transmission of data over packet-oriented networks.
- IP Internet Protocol
- the best possible distribution of the traffic routed over a communication network is important, on the one hand in relation to avoiding overload situations, on the other hand good traffic distribution is the requirement for a good utilization of the existing resources and especially the bandwidth available.
- the traffic distribution within a communication network depends on the routing within the network or the paths on which the traffic is routed through the network.
- OSPF Open Shortest Path First
- link weight or link weights which are normally employed by specialists as synonymous with link costs are also referred to below.
- the link costs or link weights are values administratively assigned to the links, said values representing a measure of how well the relevant link is being used. In the simplest case the link costs are equal to 1 for each link, i.e. all links are treated in the same way. For routing which minimizes the link costs this method automatically determines the shortest path between two nodes as regards the number of links or the number of hops. Changing the link costs allows the determination of the routes and thus the distribution of the traffic within a communication network to be influenced. Controlling the traffic distribution by adapting the link costs is generally possible with routing methods which operate using a metric and the allocation of link costs, e.g.
- IS-IS Intermediate System-Intermediate System
- ECMP Equal Cost Multiple
- the object of the invention is to specify a simple method for determining the link costs in a communication network as regards optimized traffic distribution
- the thinking behind the invention is that the link costs or link weights of heavily loaded links should be increased to reduce the traffic load on these links.
- a parameter is used for the optimization which represents the measure of the loading of the individual links. Preferably this parameter is specified by the traffic load of the individual links. Other options are the relative traffic load in relation to the link bandwidth, any traffic-dependent costs arising for link usage (possibly even in the form of real charges arising), the availability of the links, the run time on the individual links or the load-bearing capabilities of the end nodes of the links concerned.
- the starting point of the invention is that the volume of traffic to be carried by the network is known or at least an estimate of said volume exists. In traffic theory what is known as the traffic matrix is usually used to specify the traffic volume more precisely.
- the traffic matrix specifies the volume of traffic to be transported between pairs of source and destination nodes.
- a source node for example corresponds to an ingress node and a destination node to an egress node, so that the traffic matrix features an entry in relation to these two nodes for the traffic transported between them.
- the procedure is as follows. First the link costs of the individual links are initialized, i.e. start values are assigned to them. For the links a distinction is preferably made between the two directions, i.e. a connection between two nodes corresponds to two directed links, each of which transports the traffic once from the first node to the second and once in the other direction. The invention can then be further developed so that, especially for symmetrical traffic matrices, the optimization of the link costs is performed for both directions simultaneously. After the assignment of start values for the link costs paths for the routing of traffic within a communication network are computed with the aid of the routing protocol (for example OSPF or IS-IS).
- OSPF OSPF
- IS-IS the routing protocol
- the traffic carried on these paths and thereby the traffic volume on the individual links can be calculated or determined.
- the link is then determined for which the parameter, for example the traffic volume, has the highest value.
- the value of the link costs for the link determined is increased, by 1 for example.
- Calculating the paths, defining the values of the parameter, determining the link for which the parameter has the highest value and increasing the value of the link costs for the link determined is performed as a loop which is run until such time as the value of the parameter for the link with the highest parameter value determined in a step is higher than the parameter determined in the previous step or sequence for the link with the highest parameter value. If this abort criteria is fulfilled, the values for the link costs defined in the step before last and the associated paths for routing within the communication network are determined.
- An improved or optimized traffic distribution is obtained through the invention by increasing the link costs of heavily loaded links.
- the inventive method is simpler and can be implemented without any problems.
- For determining paths within the framework of the ECMP (Equal Cost Multiple) method it is useful to operate in the method with whole-number link costs or whole-number increases in the link costs, since in this way it is more likely that alternative paths with the same accumulated costs for the connection of two nodes are produced, so that, as provided for in the ECMP method, traffic can be distributed to the various equivalent paths.
- ECMP Equal Cost Multiple
- the inventive method can be performed using central or distributed computing capacity.
- parts thereof e.g. path calculation, there can be recourse to conventional methods (which for example are defined within the framework of the OPSF or IS-IS protocol).
- FIG. 1 shows an exemplary flowchart according to the invention.
- the exemplary embodiment starts from the assumption that the communication network is an IP network which is formed with nodes and links and that paths are to be determined for routing within the framework of the ECMP concept.
- the link costs LK are initialized with the value 1.
- the ECMP paths P(LK) are then calculated. The calculation is undertaken by determining the paths with the lowest accumulated link costs LK for routing between two nodes, as is provided for in the OSPF protocol.
- Least-cost paths to a destination node can for example be determined in the following way. All neighboring nodes of the destination node are initially determined and these neighboring nodes are assigned the link costs as node costs. This defines the routing for this first ring of nodes around the destination node. The procedure below is undertaken ring-by-ring, moving up from a ring to the next higher ring in each case. A ring in this case is specified by the fact that a specific number of links at least have to be passed through to reach the destination node. The costs of the individual paths are successively calculated ring-by-ring.
- the path costs are made up of the sum of the link costs and the node costs, with link costs being the current costs of the outgoing link in each case and the node costs being the actual costs of the relevant end node of this link in each case.
- the costs of the paths calculated in this way are then compared and only those paths are retained which have minimal path costs (as is also provided for within the framework of the OSPF concept).
- a number of paths with the minimum path costs are frequently found which are retained for traffic distribution in the sense of the ECMP concept.
- Other methods of determining least-cost paths for example the Dijkstra algorithm, can be used just as well.
- the above procedure can be used for re-determining the paths as part of the iterations for which the inventive method makes provision.
- the traffic matrix VM is used to determine the traffic volume V(L) of the individual links.
- the link L(Vmax,n) with the highest or maximum traffic volume Vmax,n is identified and the maximum traffic volume Vmax,n in this step is compared with the maximum traffic volume Vmax,n ⁇ 1 in the previous step If the maximum traffic volume Vmax,n for the current step is less than the maximum traffic volume Vmax,n ⁇ 1 for the previous step, the link costs LK(L(Vmax,n)) of the link L(Vmax,n) with the maximum traffic volume Vmax,n are increased by 1 and the paths P(LK) are recalculated as a function of the changed link costs LK. The loop is then executed once more. Otherwise, i.e.
- the link costs LK determined in the previous step are used as optimized link costs LKOpt and the associated paths P(LK) are used as the paths P(LKopt) determined for an optimized traffic distribution for routing.
Abstract
Description
- This application is the US National Stage of International Application No. PCT/EP2005/050149, filed Jan. 14, 2005 and claims the benefits thereof. The International Application claims the benefits of German application No. 10 2004 004 793.6 filed Jan. 30, 2004, both applications are incorporated by reference herein in their entirety.
- The invention relates to a method for adapting link weights in a communication network formed from links for an optimized distribution of traffic within the communication network as regards the volume of traffic expected for the communication network and in relation to a parameter relating to link usage.
- The invention lies within the area of communication technology and in particular deals with the transmission of data over packet-oriented networks.
- The optimization of data transmission over packet-oriented networks, especially over IP (Internet Protocol)-based networks is currently an important area of activity in the field of network technologies. the transmission of data with different quality-of-service requirements in particular being a prerequisite for the provision of new services, such as for example the transmission of real-time traffic over packet-oriented networks. To optimize transmission as much as possible, different parameters, such as delay, noise susceptibility or traffic distribution must be taken into account.
- The best possible distribution of the traffic routed over a communication network is important, on the one hand in relation to avoiding overload situations, on the other hand good traffic distribution is the requirement for a good utilization of the existing resources and especially the bandwidth available. The traffic distribution within a communication network depends on the routing within the network or the paths on which the traffic is routed through the network. By far the most widespread routing method for packet-oriented networks based on an IP protocol is what is known as the OSPF (Open Shortest Path First) method or protocol. In this method, for traffic to be routed between two nodes, the shortest path in the sense of a metric between the two nodes is defined. The path is normally determined with the aid of what are known as link costs. The terms link weight or link weights which are normally employed by specialists as synonymous with link costs are also referred to below. The link costs or link weights are values administratively assigned to the links, said values representing a measure of how well the relevant link is being used. In the simplest case the link costs are equal to 1 for each link, i.e. all links are treated in the same way. For routing which minimizes the link costs this method automatically determines the shortest path between two nodes as regards the number of links or the number of hops. Changing the link costs allows the determination of the routes and thus the distribution of the traffic within a communication network to be influenced. Controlling the traffic distribution by adapting the link costs is generally possible with routing methods which operate using a metric and the allocation of link costs, e.g. in the IS-IS (Intermediate System-Intermediate System) protocol or for example the ECMP (Equal Cost Multiple) method, which was defined within the framework of the OSPF protocol and makes provision for the use of a number of paths determined by means of OSPF for routing between two nodes.
- Conventional methods for optimizing traffic distribution by adapting the link costs are comparatively complicated. Usually the link costs are optimized globally by optimizing a target function which reflects the topology of the network. Because of the complexity of this method the link costs are currently frequently not optimized. Unavoidable adaptations of the link costs are frequently performed manually, which entails a high risk of errors. Thus the traffic optimization in real networks is likely to be less than optimal.
- The object of the invention is to specify a simple method for determining the link costs in a communication network as regards optimized traffic distribution
- The object is achieved by the claims.
- The thinking behind the invention is that the link costs or link weights of heavily loaded links should be increased to reduce the traffic load on these links. A parameter is used for the optimization which represents the measure of the loading of the individual links. Preferably this parameter is specified by the traffic load of the individual links. Other options are the relative traffic load in relation to the link bandwidth, any traffic-dependent costs arising for link usage (possibly even in the form of real charges arising), the availability of the links, the run time on the individual links or the load-bearing capabilities of the end nodes of the links concerned. The starting point of the invention is that the volume of traffic to be carried by the network is known or at least an estimate of said volume exists. In traffic theory what is known as the traffic matrix is usually used to specify the traffic volume more precisely. The traffic matrix specifies the volume of traffic to be transported between pairs of source and destination nodes. For traffic routed through the communication network a source node for example corresponds to an ingress node and a destination node to an egress node, so that the traffic matrix features an entry in relation to these two nodes for the traffic transported between them.
- For optimization as regards the parameter the procedure is as follows. First the link costs of the individual links are initialized, i.e. start values are assigned to them. For the links a distinction is preferably made between the two directions, i.e. a connection between two nodes corresponds to two directed links, each of which transports the traffic once from the first node to the second and once in the other direction. The invention can then be further developed so that, especially for symmetrical traffic matrices, the optimization of the link costs is performed for both directions simultaneously. After the assignment of start values for the link costs paths for the routing of traffic within a communication network are computed with the aid of the routing protocol (for example OSPF or IS-IS). With the aid of the assumed traffic volume the traffic carried on these paths and thereby the traffic volume on the individual links can be calculated or determined. The link is then determined for which the parameter, for example the traffic volume, has the highest value. Subsequently the value of the link costs for the link determined is increased, by 1 for example. Calculating the paths, defining the values of the parameter, determining the link for which the parameter has the highest value and increasing the value of the link costs for the link determined is performed as a loop which is run until such time as the value of the parameter for the link with the highest parameter value determined in a step is higher than the parameter determined in the previous step or sequence for the link with the highest parameter value. If this abort criteria is fulfilled, the values for the link costs defined in the step before last and the associated paths for routing within the communication network are determined.
- An improved or optimized traffic distribution is obtained through the invention by increasing the link costs of heavily loaded links. In comparison to conventional methods the inventive method is simpler and can be implemented without any problems. For determining paths within the framework of the ECMP (Equal Cost Multiple) method it is useful to operate in the method with whole-number link costs or whole-number increases in the link costs, since in this way it is more likely that alternative paths with the same accumulated costs for the connection of two nodes are produced, so that, as provided for in the ECMP method, traffic can be distributed to the various equivalent paths. As a start point it is useful to initialize all link costs with the same value, for example with 1.
- The inventive method can be performed using central or distributed computing capacity. For parts thereof, e.g. path calculation, there can be recourse to conventional methods (which for example are defined within the framework of the OPSF or IS-IS protocol).
- The object of the invention is explained in more detail below within the context of an exemplary embodiment which refers to a flowchart.
- The sole FIGURE shows an exemplary flowchart according to the invention.
- The exemplary embodiment starts from the assumption that the communication network is an IP network which is formed with nodes and links and that paths are to be determined for routing within the framework of the ECMP concept. To begin with the link costs LK are initialized with the
value 1. On the basis of these link costs LK the ECMP paths P(LK) are then calculated. The calculation is undertaken by determining the paths with the lowest accumulated link costs LK for routing between two nodes, as is provided for in the OSPF protocol. - Least-cost paths to a destination node can for example be determined in the following way. All neighboring nodes of the destination node are initially determined and these neighboring nodes are assigned the link costs as node costs. This defines the routing for this first ring of nodes around the destination node. The procedure below is undertaken ring-by-ring, moving up from a ring to the next higher ring in each case. A ring in this case is specified by the fact that a specific number of links at least have to be passed through to reach the destination node. The costs of the individual paths are successively calculated ring-by-ring. In this case in each step the path costs are made up of the sum of the link costs and the node costs, with link costs being the current costs of the outgoing link in each case and the node costs being the actual costs of the relevant end node of this link in each case. The costs of the paths calculated in this way are then compared and only those paths are retained which have minimal path costs (as is also provided for within the framework of the OSPF concept). A number of paths with the minimum path costs are frequently found which are retained for traffic distribution in the sense of the ECMP concept. Other methods of determining least-cost paths, for example the Dijkstra algorithm, can be used just as well.
- The above procedure can be used for re-determining the paths as part of the iterations for which the inventive method makes provision. After calculation of the paths P(LK) as a function of the link costs, the traffic matrix VM is used to determine the traffic volume V(L) of the individual links. The link L(Vmax,n) with the highest or maximum traffic volume Vmax,n is identified and the maximum traffic volume Vmax,n in this step is compared with the maximum traffic volume Vmax,n−1 in the previous step If the maximum traffic volume Vmax,n for the current step is less than the maximum traffic volume Vmax,n−1 for the previous step, the link costs LK(L(Vmax,n)) of the link L(Vmax,n) with the maximum traffic volume Vmax,n are increased by 1 and the paths P(LK) are recalculated as a function of the changed link costs LK. The loop is then executed once more. Otherwise, i.e. if the maximum traffic load Vmax,n is greater than in the previous step, the link costs LK determined in the previous step are used as optimized link costs LKOpt and the associated paths P(LK) are used as the paths P(LKopt) determined for an optimized traffic distribution for routing.
Claims (20)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/367,802 US7933206B2 (en) | 2004-01-30 | 2009-02-09 | Method for adapting link weights in relation to optimized traffic distribution |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102004004793.6 | 2004-01-30 | ||
DE102004004793A DE102004004793B3 (en) | 2004-01-30 | 2004-01-30 | Method for adapting the link weights with regard to an optimized traffic distribution |
PCT/EP2005/050149 WO2005074196A1 (en) | 2004-01-30 | 2005-01-14 | Method for adapting link-weights in relation to optimised traffic distribution |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2005/050149 A-371-Of-International WO2005074196A1 (en) | 2004-01-30 | 2005-01-14 | Method for adapting link-weights in relation to optimised traffic distribution |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/367,802 Continuation US7933206B2 (en) | 2004-01-30 | 2009-02-09 | Method for adapting link weights in relation to optimized traffic distribution |
Publications (1)
Publication Number | Publication Date |
---|---|
US20060253607A1 true US20060253607A1 (en) | 2006-11-09 |
Family
ID=34745206
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/550,229 Abandoned US20060253607A1 (en) | 2004-01-30 | 2005-01-14 | Method for adapting link weights in ralation to optimized traffic distribution |
US12/367,802 Expired - Fee Related US7933206B2 (en) | 2004-01-30 | 2009-02-09 | Method for adapting link weights in relation to optimized traffic distribution |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/367,802 Expired - Fee Related US7933206B2 (en) | 2004-01-30 | 2009-02-09 | Method for adapting link weights in relation to optimized traffic distribution |
Country Status (5)
Country | Link |
---|---|
US (2) | US20060253607A1 (en) |
EP (1) | EP1588531B1 (en) |
CN (1) | CN100574269C (en) |
DE (2) | DE102004004793B3 (en) |
WO (1) | WO2005074196A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090161673A1 (en) * | 2007-12-21 | 2009-06-25 | Lee Breslau | Method and System For Computing Multicast Traffic Matrices |
US20130343396A1 (en) * | 2012-06-22 | 2013-12-26 | Fujitsu Limited | Information processing system, relay device, information processing device, and information processing method |
US9137162B2 (en) | 2013-07-23 | 2015-09-15 | Sap Se | Network traffic routing optimization |
US10027571B2 (en) * | 2016-07-28 | 2018-07-17 | Hewlett Packard Enterprise Development Lp | Load balancing |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102008029825A1 (en) | 2008-06-25 | 2009-12-31 | Medi Gmbh & Co. Kg | knee Support |
US8798034B2 (en) * | 2009-03-31 | 2014-08-05 | Motorola Solutions, Inc. | System and method for selecting a route based on link metrics incorporating channel bandwidth, spatial streams and/or guard interval in a multiple-input multiple-output (MIMO) network |
CN104883696B (en) * | 2015-04-15 | 2019-07-26 | 国家电网公司 | Power information physics system wireless communication networks equal cost multipath dynamic control method |
CN109034657A (en) * | 2018-08-22 | 2018-12-18 | 泰康保险集团股份有限公司 | Process path finding method, device, medium and electronic equipment based on block chain |
CN111953606B (en) * | 2020-07-14 | 2022-06-21 | 锐捷网络股份有限公司 | Routing iteration loop detection method and device, electronic equipment and storage medium |
CN114048160A (en) * | 2021-11-08 | 2022-02-15 | 上海兆芯集成电路有限公司 | Link balance adjusting system and link balance adjusting method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030028670A1 (en) * | 2001-07-31 | 2003-02-06 | Byoung-Joon Lee | Network resource allocation methods and systems |
US6535923B1 (en) * | 1999-03-30 | 2003-03-18 | International Business Machines Corporation | Method and system for defining an efficient and reliable meshing of CP-CP sessions in an advanced peer to peer network |
US6584071B1 (en) * | 1999-08-03 | 2003-06-24 | Lucent Technologies Inc. | Routing with service level guarantees between ingress-egress points in a packet network |
US20030156536A1 (en) * | 2002-02-21 | 2003-08-21 | Eiji Oki | Node, an optical/electrical path integrated network using the node, and a program which controls the node |
US6611874B1 (en) * | 1998-09-16 | 2003-08-26 | International Business Machines Corporation | Method for improving routing distribution within an internet and system for implementing said method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002046947A1 (en) * | 2000-12-04 | 2002-06-13 | Rensselaer Polytechnic Institute | System for proactive management of network routing |
-
2004
- 2004-01-30 DE DE102004004793A patent/DE102004004793B3/en not_active Withdrawn - After Issue
-
2005
- 2005-01-14 DE DE502005000029T patent/DE502005000029D1/en active Active
- 2005-01-14 WO PCT/EP2005/050149 patent/WO2005074196A1/en not_active Application Discontinuation
- 2005-01-14 CN CNB2005800000867A patent/CN100574269C/en not_active Expired - Fee Related
- 2005-01-14 US US10/550,229 patent/US20060253607A1/en not_active Abandoned
- 2005-01-14 EP EP05701519A patent/EP1588531B1/en not_active Expired - Fee Related
-
2009
- 2009-02-09 US US12/367,802 patent/US7933206B2/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611874B1 (en) * | 1998-09-16 | 2003-08-26 | International Business Machines Corporation | Method for improving routing distribution within an internet and system for implementing said method |
US6535923B1 (en) * | 1999-03-30 | 2003-03-18 | International Business Machines Corporation | Method and system for defining an efficient and reliable meshing of CP-CP sessions in an advanced peer to peer network |
US6584071B1 (en) * | 1999-08-03 | 2003-06-24 | Lucent Technologies Inc. | Routing with service level guarantees between ingress-egress points in a packet network |
US20030028670A1 (en) * | 2001-07-31 | 2003-02-06 | Byoung-Joon Lee | Network resource allocation methods and systems |
US20030156536A1 (en) * | 2002-02-21 | 2003-08-21 | Eiji Oki | Node, an optical/electrical path integrated network using the node, and a program which controls the node |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090161673A1 (en) * | 2007-12-21 | 2009-06-25 | Lee Breslau | Method and System For Computing Multicast Traffic Matrices |
US7792057B2 (en) | 2007-12-21 | 2010-09-07 | At&T Labs, Inc. | Method and system for computing multicast traffic matrices |
US20130343396A1 (en) * | 2012-06-22 | 2013-12-26 | Fujitsu Limited | Information processing system, relay device, information processing device, and information processing method |
US9479423B2 (en) * | 2012-06-22 | 2016-10-25 | Fujitsu Limited | Information processing system, relay device, information processing device, and information processing method |
US9137162B2 (en) | 2013-07-23 | 2015-09-15 | Sap Se | Network traffic routing optimization |
US9397930B2 (en) | 2013-07-23 | 2016-07-19 | Sap Se | Network traffic routing optimization |
US10027571B2 (en) * | 2016-07-28 | 2018-07-17 | Hewlett Packard Enterprise Development Lp | Load balancing |
Also Published As
Publication number | Publication date |
---|---|
EP1588531A1 (en) | 2005-10-26 |
EP1588531B1 (en) | 2006-06-28 |
US20090141633A1 (en) | 2009-06-04 |
CN1765091A (en) | 2006-04-26 |
DE502005000029D1 (en) | 2006-08-10 |
DE102004004793B3 (en) | 2005-08-11 |
US7933206B2 (en) | 2011-04-26 |
WO2005074196A1 (en) | 2005-08-11 |
CN100574269C (en) | 2009-12-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7933206B2 (en) | Method for adapting link weights in relation to optimized traffic distribution | |
US7948899B2 (en) | Method and apparatus for communications traffic engineering | |
KR100788762B1 (en) | Method and system for controlling data traffic in a network | |
US7903563B2 (en) | Shortest-path routing optimized for network utilization | |
EP1443722B1 (en) | Transmission bandwidth control device | |
US8175006B2 (en) | Multi-path load balancing using route controller | |
Xu et al. | DEFT: Distributed exponentially-weighted flow splitting | |
US20080253290A1 (en) | Optimization of Traffic Distribution in Multipath Routing | |
JP5235622B2 (en) | Method for routing and load balancing in a communication network | |
Rocha et al. | Quality of service constrained routing optimization using evolutionary computation | |
US20060126625A1 (en) | Method for distributing traffic using hash-codes corresponding to a desired traffic distribution in a packet-oriented network comprising multipath routing | |
US20040233850A1 (en) | Device and a method for determining routing paths in a communication network in the presence of selection attributes | |
Szviatovszki et al. | Minimizing re-routing in MPLS networks with preemption-aware constraint-based routing | |
US20030231599A1 (en) | Optimum route calculation method and storage medium which stores optimum route calculation program | |
US8259742B2 (en) | Hybrid channel assignment method and router thereof | |
Lee et al. | Traffic engineering with constrained multipath routing in MPLS networks | |
US8331233B2 (en) | Communication path control apparatus for evenly distributing packets between adjacent nodes and a method therefor | |
KR100684453B1 (en) | Method and system for communication of data via an optimum data path in a network | |
Hendling et al. | A new bandwidth guaranteed routing approach for online calculation of LSPs for MPLS traffic engineering | |
Dort-Golts et al. | Load balancing algorithm exploiting overlay techniques | |
Hendling et al. | Interference minimizing bandwidth guaranteed on-line routing algorithm for traffic engineering | |
Modi et al. | Refinements to minimum interference routing for traffic engineering | |
CN113676406A (en) | Network flow control method and device | |
Honma et al. | Load-balanced shortest-path-based routing with even traffic splitting | |
Kotti et al. | Bandwidth Constrained Least Delay Least Cost Routing Algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SIEMENS AKTIENGESELLSCHAFT, GERMANY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SCHOLLMEIER, GERO;WINKLER, CHRISTIAN;REEL/FRAME:018128/0281;SIGNING DATES FROM 20050819 TO 20050827 |
|
AS | Assignment |
Owner name: NOKIA SIEMENS NETWORKS GMBH & CO KG, GERMANY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SIEMENS AKTIENGESELLSCHAFT;REEL/FRAME:021786/0236 Effective date: 20080107 Owner name: NOKIA SIEMENS NETWORKS GMBH & CO KG,GERMANY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SIEMENS AKTIENGESELLSCHAFT;REEL/FRAME:021786/0236 Effective date: 20080107 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |