CN105723667A - Path calculation method and apparatus - Google Patents
Path calculation method and apparatus Download PDFInfo
- Publication number
- CN105723667A CN105723667A CN201480057546.9A CN201480057546A CN105723667A CN 105723667 A CN105723667 A CN 105723667A CN 201480057546 A CN201480057546 A CN 201480057546A CN 105723667 A CN105723667 A CN 105723667A
- Authority
- CN
- China
- Prior art keywords
- flow
- max
- business
- link
- sourcesink node
- 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.)
- Granted
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present invention relates to the field of network communications. Specifically disclosed is a path calculation method. The method comprises: after it is detected that a fault occurs on a network, determining all affected services; acquiring traffics, allocated on each link in the network, of a largest stream between a source node and a destination node of each service affected by the fault; acquiring a cost value of each link, wherein the cost value of any link is a rounded-up value of a result obtained by dividing a traffic of the any link by a remaining bandwidth of the any link, and a sum of the traffics of the any link is a sum of traffics, allocated on the any link, of largest streams between source nodes and destination nodes of all affected services; and calculating, for a service affected by the fault, a shortest path satisfying bandwidth requirements according to the cost value of each link. Also disclosed is a path calculation apparatus.
Description
A kind of method and apparatus technical field of path computing
The present invention relates to the network communications technology, more particularly to a kind of method and apparatus of path computing.Background technology
With software defined network（Software Defined Network, SDN), the appearance of network function virtualization (Network Function Virtualization, NFV) etc. new technology, central controlled application is more and more wider.
Centralized Control requires that Centralized Controller has very strong dispatch deal ability to the whole network resource, it is necessary to which Centralized Controller provides quick response particularly when network failure, as often as possible recovers impaired business.In the prior art, when network failure, Centralized Controller still continues to use distributed Constraint Shortest Path First（Constrained Shorest Path Tree, CSPF) path calculation method is that each business by fault impact individually calculates road.Network utilization is higher, Internet resources it is more nervous in the case of, this CSPF path calculation methods easily cause resource and striven unexpectedly, cause to calculate road failure, calculate road success rate low.The content of the invention
The embodiment provides a kind of method and apparatus of path computing, the whole network resource can not effectively be utilized, calculate the low success rate of problem in road by solving existing route calculating.
Embodiments of the invention are adopted the following technical scheme that：
First aspect present invention provides a kind of method of path computing, including：
Detect after network failure, determine all business by fault impact；
Obtain each flow shared by the max-flow between the sourcesink node of the business of fault impact in the network in each of the links；
Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up, any link
Flow and be all flow sums shared by the max-flow between the sourcesink node of the business of fault impact on any link；
It is the shortest path that bandwidth demand is met by the service computation of fault impact according to the cost value of each of the links.
In the first possible implementation, it is described detect network failure before, methods described also includes：
Max-flow in the network between the sourcesink node of each business is calculated according to the remaining bandwidth of the link in network, the flow that the max-flow between the sourcesink node of each business is shared in each of the links is determined.
With reference to the first possible implementation of first aspect, in second of possible implementation, the flow that the max-flow between the sourcesink node for determining each business is shared in each of the links is specifically included：
If the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.
With reference to second of possible implementation of first aspect, in the third possible implementation, the max-flow distribution by between the sourcesink node of any business is specifically included on the multilink of carrying max-flow：
Max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.
With reference to the first possible implementation, second of possible implementation or the third possible implementation of first aspect, in the 4th kind of possible implementation, it is described detect network failure before, methods described also includes：
If the remaining bandwidth of the link in network changes, the max-flow between the sourcesink node of each business is recalculated.
Second aspect of the present invention provides a kind of device of path computing, including：
Business determining unit, for detecting after network failure, determines all business by fault impact；
Acquiring unit, for obtaining each flow shared by the max-flow between the sourcesink node of the business of fault impact in the network in each of the links that the business determining unit is determined；Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up；The flow of any link and the flow sums shared described in all by the max-flow between the sourcesink node of the business of fault impact on any link；
Path-calculating element, the cost value of each of the links obtained according to the acquiring unit is the shortest path that bandwidth demand is met by the service computation of fault impact.
In the first possible implementation, described device also includes：
Max-flow computing unit, before detecting network failure for the business determining unit, the max-flow in the network between the sourcesink node of each business is calculated according to the remaining bandwidth of the link in network;
Flow determining unit, for determining that the max-flow computing unit calculates the flow that the max-flow between the sourcesink node of obtained each business is shared in each of the links.
With reference to the first possible implementation of second aspect, in second of possible implementation, the flow determining unit specifically for, if the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.
With reference to second of possible implementation of second aspect, in the third possible implementation, the flow determining unit is specifically included：
First subelement, if not unique for the link that max-flow is carried between the sourcesink node of any business, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；
Second subelement, the flow that the max-flow between sourcesink node for calculating any business is shared in each of the links.
With reference to the third possible implementation of second aspect, in the 4th kind of possible implementation, first subelement specifically for, if the link that max-flow is carried between the sourcesink node of any business is not unique, the max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.
With reference to the first any one possible implementation into the 4th kind of possible implementation of second aspect, in the 5th kind of possible implementation, the max-flow computing unit is additionally operable to before the business determining unit detects network failure, if the remaining bandwidth of the link in network changes, the max-flow between the sourcesink node of each business is recalculated.
A kind of method and apparatus of path computing provided in an embodiment of the present invention, consider the flow that the max-flow between the sourcesink node of all business by fault impact is shared in each of the links in a network, by the service computation path of fault impact, effectively using the whole network resource, to calculate road success rate height.Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, the required accompanying drawing used in embodiment will be briefly described below, apparently, drawings in the following description are only some embodiments of the present invention, for those of ordinary skill in the art, without having to pay creative labor, other accompanying drawings can also be obtained according to these accompanying drawings.
A kind of flow chart of the method for path computing that Fig. 1 provides for embodiments of the invention；
The network organizing schematic diagram that Fig. 2 provides for embodiments of the invention；
The flow schematic diagram that max-flow between node A and node C that Fig. 3 provides for embodiments of the invention is shared in each of the links；
The flow schematic diagram that max-flow between node A and node D that Fig. 4 provides for embodiments of the invention is shared in each of the links；
A kind of one structured flowchart of the device for path computing that Fig. 5 provides for embodiments of the invention；
A kind of another structured flowchart of the device for path computing that Fig. 6 provides for embodiments of the invention.The structured flowchart of the device for another path computing that Fig. 7 provides for embodiments of the invention.Embodiment
The embodiments of the invention provide a kind of method and apparatus of path computing.In order to be better understood from technical scheme, the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings.
It will be appreciated that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, all other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made belongs to the scope of protection of the invention.
The embodiments of the invention provide a kind of flow of the method for path computing as shown in figure 1, this method comprises the following steps：
Step S101, is detected after network failure, determines all business by fault impact.
Step S102, obtains each by the flow shared in the max-flow between the sourcesink node of the business of fault impact in a network each of the links.
Step S103, obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up, the flow sum shared on any link of max-flow between the flow of any link and the sourcesink node for being all business by fault impact.
Step S104, is the shortest path that bandwidth demand is met by the service computation of fault impact according to the cost value of each of the links.
Further, detect before network failure, this method can also include step S100:According to the max-flow between the sourcesink node of each business in the remaining bandwidth calculating network of link in network, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links.
Specifically, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links, can be specifically included：If the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Meter
Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.Specifically, the max-flow distribution between the sourcesink node of any business can be specifically included on the multilink of carrying max-flow：Max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.
Further, step S100 can also include：If the remaining bandwidth of link in network changes, the max-flow between the sourcesink node of each business is recalculated.A kind of method and apparatus of path computing provided in an embodiment of the present invention are described in detail below in conjunction with the accompanying drawings.
It will be appreciated that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, all other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made belongs to the scope of protection of the invention.
Executive agent in the embodiment of the present invention can be central controlled device, the central controlled device can be Centralized Controller, such as webmaster, path-calculating element, network controller, SDN controllers, the central controlled device can also be the device being built in above-mentioned Centralized Controller.
The embodiments of the invention provide a kind of method of path computing, executive agent is by taking Centralized Controller as an example.5 nodes A, B, C, D and E are had in network organizing schematic diagram as shown in Figure 2, network, are controlled by a Centralized Controller.Business in network has：Business 1, it is A-E-D-C that it, which route,;Business 2, it is A-E-D that it, which route,;Business 3, it is A-B that it, which route,.
The remaining bandwidth of each link is in network shown in Fig. 2：
Link A-B remaining bandwidth is 3 bandwidth units；
Link A-D remaining bandwidth is 3 bandwidth units；
Link A-E remaining bandwidth is 6 bandwidth units；
Link E-D remaining bandwidth is 6 bandwidth units；
Link D-C remaining bandwidth is 3 bandwidth units；
Link B-C remaining bandwidth is 3 bandwidth units.
Wherein, the remaining bandwidth of link is relative value, represents how many bandwidth units.For example, tape remaining width values are 3,3 bandwidth units are represented；Tape remaining width values are 6, represent 6 bandwidth units.3MHz bandwidth and 6MHz bandwidth can be represented respectively, and 30MHz bandwidth and 60MHz bandwidth can also be represented respectively.
The method of the path computing specifically includes following steps：
Step S201, is detected after network failure, determines all business by fault impact.
In the present embodiment, detect after link in network A-E breaks down, it is determined that being business 1 and business 2 by the business of fault impact.
Step S202, obtains each by the flow shared in the max-flow between the sourcesink node of the business of fault impact in the network each of the links, wherein, max-flow is source node to the maximum stream flow that can be carried between destination node.
In the present embodiment, the flow that max-flow between the sourcesink node of acquisition business 1 and business 2 is shared in each of the links in the network.The sourcesink node of business 1 is respectively node A and node C, and the sourcesink node of business 2 is respectively node A and node D.
The flow that max-flow in network between the sourcesink node of every business is shared in each of the links, can be pre-configured with before network failure, acquisition can also be precalculated before network failure, ^1 is not limited the present embodiment to this.
Therefore, in the present embodiment, in the flow that max-flow that can be in the network being obtained ahead of time between the sourcesink node of every business is shared in each of the links, directly obtain the flow shared in each of the links of max-flow between node A and node C, and the flow that the max-flow between node A and node D is shared in each of the links.
The flow that max-flow between node A and node C is shared in each of the links, as shown in Figure 3：The flow shared on link A-B is 3 bandwidth units；
The flow shared on link A-D is 3 bandwidth units；
The flow shared on link A-E is 0 bandwidth unit；
The flow shared on link E-D is 0 bandwidth unit；
The flow shared on link D-C is 3 bandwidth units；
The flow shared on link B-C is 3 bandwidth units.
The flow that max-flow between node A and node D is shared in each of the links, as shown in Figure 4：The flow shared on link A-B is 0 bandwidth unit；
The flow shared on link A-D is 3 bandwidth units；
The flow shared on link A-E is 6 bandwidth units；
The flow shared on link E-D is 6 bandwidth units；
The flow shared on link D-C is 0 bandwidth unit；
The flow shared on link B-C is 0 bandwidth unit.
Step S203, obtains the cost of each of the links（Metric) value.
For any link in network, the Metric values of the link for the link flow and divided by the link remaining bandwidth result the value that rounds up；The flow of the link and the flow sum shared on the link for the max-flow between all sourcesink nodes by fault impact business.
In the present embodiment, by taking link A-B as an example, the flow that max-flow between sourcesink the node A and C of business 1 is shared on link A-B is 3 bandwidth units, the flow that max-flow between sourcesink the node A and D of business 2 is shared on link A-B is 0, the flow sum then shared by the max-flow between the business 1 of fault impact and the sourcesink node of business 2 on link A-B is 3 bandwidth units, i.e. link A-B flow and is 3 bandwidth units.
Other links are similar with link A-B, the flow sum shared by the max-flow between the business 1 of fault impact and the sourcesink node of business 2 on each link, i.e., the flow of each link and be：
Link A-B flow and be 3 bandwidth units；
Link A-D flow and be 6 bandwidth units；
Link A-E flow and be 6 bandwidth units；
Link E-D flow and be 6 bandwidth units；
Link D-C flow and be 3 bandwidth units；
Link B-C flow and be 3 bandwidth units.
By taking link A-B as an example, link A-B flow and be 3 bandwidth units, tape remaining width values are 3 bandwidth units, then link A-B cost value for 3 divided by 3 result the value that rounds up, i.e., 1.
Other links are similar with link A-B, according to the flow of above-mentioned each link and and each link tape remaining width values, obtain the cost value of each link：Link A-B cost value is 1;Link A-D cost value is 2, and link A-E cost value is 1, and link E-D cost value is 1, and link D-C cost value is 1, and link B-C cost value is 1.
Step S204, according to the cost value of each of the links to being met the shortest path of bandwidth demand by the service computation of fault impact.
In the present embodiment, the shortest path that meets bandwidth demand is calculated the business 1 by fault impact and business 2 according to the cost value of each of the links obtained in step S203.
Calculating shortest path according to the cost value of link can not limited using the methods such as dijkstra algorithm, bellman-ford algorithm or Floyd-Warshall algorithms, the present embodiment.
Calculating obtain after link A-E failures the node A of business 1 to node C path be A-B-C;Calculating obtain after link A-E failures the node A of business 2 to node D path be A-D.In another embodiment, before the step S201 of above-described embodiment, that is, detect before the network failure, this method can also include：
Step S200, the max-flow in the network between the sourcesink node of each business is calculated according to the remaining bandwidth of the link in network, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links.
In the present embodiment, according to the tape remaining width values of each link, max-flow between sourcesink the node A and C of acquisition business 1 is 6 bandwidth units, max-flow between sourcesink the node A and D of business 2 is 9 bandwidth units, and the max-flow between sourcesink the node A and B of business 3 is 3 bandwidth units.The computational methods of max-flow are prior art, are repeated no more in the present embodiment.
Then, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links.Specifically, if the link that max-flow is carried between the sourcesink node of business is not unique, by the business
Sourcesink node between max-flow distribution carrying max-flow multilink on, calculate the flow that the max-flow between the sourcesink node of the business is shared in each of the links；If the link of the max-flow carried between the sourcesink node of business is unique, directly by the max-flow distribution between the sourcesink node of the business on the link, the flow that the max-flow between the sourcesink node of the business is shared in each of the links is calculated.
Specifically, by the max-flow distribution between the sourcesink node of the business on the multilink of carrying max-flow, max-flow between the sourcesink node of the business can be distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth, other methods of salary distribution can also be used, for example max-flow is distributed evenly on multilink, or distributing first-class in the most link of remaining bandwidth by max-flow, the present embodiment is without limitation.
In the present embodiment, the flow that the max-flow between the sourcesink node of acquisition business 1, business 2 and business 3 is shared in each of the links.
Wherein, max-flow between sourcesink the node A and C of business 1 is 6 bandwidth units, the link that max-flow is carried between node A and node C is not unique, link A-D can be substituted mutually with link A-E and E-D, that is link A-D can be with alternate link A-D with alternate link A-E and E-D, link A-E and E-D.
In the present embodiment, so that the max-flow distribution between the sourcesink node by the business is in the multilink of carrying max-flow on the minimum link of remaining bandwidth as an example.Max-flow between node A and node C is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth, link A-D remaining bandwidths are 3 bandwidth units, link A-E and E-D remaining bandwidth is 6 bandwidth units, and the few link A-D of remaining bandwidth is selected between as the link of carrying max-flow.The flow for obtaining sharing on the flow that the max-flow between node A as shown in Figure 3 and node C is shared in each of the links, link A-E and E-D is 0.
Max-flow between sourcesink the node A and D of business 2 is 9 bandwidth units, and the link that max-flow is carried between node A and node D is unique, and the flow shared in each of the links is as shown in Figure 4.
Max-flow between sourcesink the node A and B of business 3 is 3 bandwidth units, and the link that max-flow is carried between node A and node B is unique, and the flow shared on link A-B is 3 bandwidth units,
The flow shared on other links is 0.
Be frequently present of in the network of practical application each node in a large number of services, network may can above and below business.In such cases, calculate the max-flow between the sourcesink node of each business in the network, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links, equivalent to the max-flow in calculating network between any two node is needed, the flow that the max-flow between any two node is shared in each of the links is determined.
Further, before network failure is detected, if the remaining bandwidth of the link in network changes, then recalculate the max-flow between the sourcesink node of each business, then the flow that the max-flow between the sourcesink node of each business is shared in each of the links is redefined, after network failure, to be met the shortest path of bandwidth demand by the service computation of fault impact.In the prior art, when detecting link A-E failures, road is calculated using CSPF again.The whole network resource is effectively utilized because CSPF is no, but each individually to be calculated road by the business of fault impact.If business 1 first calculates path, according to shortest path rule, the path of calculating is A-D-C, then business 2 calculates road failure, and business 2 can not be recovered.
A kind of method of path computing provided in an embodiment of the present invention, consider the flow that the max-flow between the sourcesink node of all business by fault impact is shared in each of the links in a network, by the service computation path of fault impact, effectively using the whole network resource, to calculate road success rate height.
In addition, the method of path computing provided in an embodiment of the present invention, the flow that the max-flow between the sourcesink node for obtaining each business is shared in each of the links can also be precalculated before network failure, and the change of the remaining bandwidth according to link, refresh the flow shared in real time so that path computing is more accurate and effective.The embodiments of the invention provide a kind of device 500 of path computing, as shown in figure 5, including business determining unit 510, acquiring unit 520 and path-calculating element 530:
Business determining unit 510, for detecting after network failure, is determined all by fault impact
Business；
Acquiring unit 520, the flow shared in the max-flow between the sourcesink node for each business by fault impact for obtaining the determination of business determining unit 510 in a network each of the links；Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up；The flow of any link and the flow sum shared for the max-flow between the sourcesink node of all business by fault impact on any link；
Path-calculating element 530, the cost value of each of the links obtained according to acquiring unit 520 is the shortest path that bandwidth demand is met by the service computation of fault impact.
Further, as shown in fig. 6, the device 500 of the path computing can also include：
Max-flow computing unit 540, before detecting network failure for business determining unit 510, according to the max-flow between the sourcesink node of each business in the remaining bandwidth calculating network of link in network；Flow determining unit 550, for determining that max-flow computing unit 540 calculates the flow that the max-flow between the sourcesink node of obtained each business is shared in each of the links.
Further, flow determining unit 550 can be specifically for if the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.
Further, flow determining unit 550 can be specifically included：
First subelement 551, if not unique for the link that max-flow is carried between the sourcesink node of any business, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；
Second subelement 552, the flow that the max-flow between sourcesink node for calculating any business is shared in each of the links.
Further, first subelement 552 can be specifically for, if the link that max-flow is carried between the sourcesink node of any business is not unique, the max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.
Further, max-flow computing unit 540 can be also used for：Business determining unit 510 is detected before network failure, if the remaining bandwidth of link in network changes, and recalculates the max-flow between the sourcesink node of each business.Another embodiment of the present invention provides a kind of device 700 of path computing, as shown in fig. 7, comprises transmitter 710, memory 720 and processor 730:
Transmitter 710, the service computation for sending by fault impact meets the shortest path of bandwidth demand；Memory 720, includes the information of program routine for storing；
Processor 730, couples with memory 720 and transmitter 710, for the execution of control program routine, specifically includes：
Detect after network failure, determine all business by fault impact；
Obtain each by the flow shared in the max-flow between the sourcesink node of the business of fault impact in a network each of the links；
Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up, the flow sum shared on any link of max-flow between the flow of any link and the sourcesink node for being all business by fault impact；
It is the shortest path that bandwidth demand is met by the service computation of fault impact according to the cost value of each of the links.
Further, detect before network failure, processor 730 can be also used for the execution of control program routine：
According to the max-flow between the sourcesink node of each business in the remaining bandwidth calculating network of link in network, it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links.
Wherein it is determined that the flow that the max-flow between the sourcesink node of each business is shared in each of the links, can be specifically included：If the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate
The flow that max-flow between the sourcesink node of any business is shared in each of the links.
Wherein, the max-flow distribution between the sourcesink node of any business can be specifically included on the multilink of carrying max-flow：Max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.
Further, detect before network failure, processor 730 can be also used for the execution of control program routine：
If the remaining bandwidth of link in network changes, the max-flow between the sourcesink node of each business is recalculated.The device of path computing in above-described embodiment can be central controlled device, the central controlled device can be Centralized Controller, such as webmaster, path-calculating element, network controller, SDN controllers, the central controlled device can also be the device being built in above-mentioned Centralized Controller.
In above-described embodiment, the contents such as information exchange, the implementation procedure between each unit in a kind of device of path computing, due to being based on same design with the inventive method embodiment, particular content can be found in the narration in the inventive method embodiment, and here is omitted.
Using a kind of device of path computing provided in an embodiment of the present invention, consider the flow that the max-flow between the sourcesink node of all business by fault impact is shared in each of the links in a network, by the service computation path of fault impact, effectively using the whole network resource, to calculate road success rate height.One of ordinary skill in the art will appreciate that realizing all or part of step in above-described embodiment method, computer program is can be by instruct the hardware of correlation to complete, described program can be stored in a computer read/write memory medium, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic disc, CD, read-only memory（Read-Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any one skilled in the art the invention discloses technical scope in, can be easily
The change or replacement expected, should all be included within the scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.
Claims (1)
- Claims1st, a kind of method of path computing, it is characterised in that including：Detect after network failure, determine all business by fault impact；Obtain each flow shared by the max-flow between the sourcesink node of the business of fault impact in the network in each of the links；Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up, the flow of any link and the flow sums to be shared by the max-flow between the sourcesink node of the business of fault impact on any link described in all；It is the shortest path that bandwidth demand is met by the service computation of fault impact according to the cost value of each of the links.2nd, according to the method described in claim 1, it is characterised in that it is described detect network failure before, methods described also includes：Max-flow in the network between the sourcesink node of each business is calculated according to the remaining bandwidth of the link in network, the flow that the max-flow between the sourcesink node of each business is shared in each of the links is determined.3rd, method according to claim 2, it is characterised in that the flow that the max-flow between the sourcesink node of determination each business is shared in each of the links, is specifically included：If the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.4th, method according to claim 3, it is characterised in that the max-flow distribution by between the sourcesink node of any business is specifically included on the multilink of carrying max-flow：Max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.5th, the method according to claim 2,3 or 4, it is characterised in that described to detect network hair Before raw failure, methods described also includes：If the remaining bandwidth of the link in network changes, the max-flow between the sourcesink node of each business is recalculated.6th, a kind of device of path computing, it is characterised in that including：Business determining unit, for detecting after network failure, determines all business by fault impact；Acquiring unit, for obtaining each flow shared by the max-flow between the sourcesink node of the business of fault impact in the network in each of the links that the business determining unit is determined；Obtain the cost value of each of the links, wherein, the cost value of any link for any link flow and divided by any link remaining bandwidth result the value that rounds up；The flow of any link and the flow sums shared described in all by the max-flow between the sourcesink node of the business of fault impact on any link；Path-calculating element, the cost value of each of the links obtained according to the acquiring unit is the shortest path that bandwidth demand is met by the service computation of fault impact.7th, device according to claim 6, it is characterised in that described device also includes：Max-flow computing unit, before detecting network failure for the business determining unit, the max-flow in the network between the sourcesink node of each business is calculated according to the remaining bandwidth of the link in network;Flow determining unit, for determining that the max-flow computing unit calculates the flow that the max-flow between the sourcesink node of obtained each business is shared in each of the links.8th, device according to claim 7, it is characterized in that, the flow determining unit specifically for, if the link that max-flow is carried between the sourcesink node of any business is not unique, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow；Calculate the flow that the max-flow between the sourcesink node of any business is shared in each of the links.9th, device according to claim 8, it is characterised in that the flow determining unit is specifically included：First subelement, if not unique for the link that max-flow is carried between the sourcesink node of any business, by the max-flow distribution between the sourcesink node of any business on the multilink of carrying max-flow； Second subelement, the flow that the max-flow between sourcesink node for calculating any business is shared in each of the links.10th, device according to claim 9, it is characterized in that, first subelement specifically for, if the link that max-flow is carried between the sourcesink node of any business is not unique, the max-flow between the sourcesink node of any business is distributed in the multilink of carrying max-flow on the minimum link of remaining bandwidth.11st, device according to any one of claims of claim 7-10, it is characterized in that, the max-flow computing unit is additionally operable to before the business determining unit detects network failure, if the remaining bandwidth of the link in network changes, the max-flow between the sourcesink node of each business is recalculated.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2014/081071 WO2015196494A1 (en) | 2014-06-28 | 2014-06-28 | Path calculation method and apparatus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105723667A true CN105723667A (en) | 2016-06-29 |
| CN105723667B CN105723667B (en) | 2019-02-19 |
Family
ID=54936539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201480057546.9A Active CN105723667B (en) | 2014-06-28 | 2014-06-28 | A kind of method and apparatus of path computing |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105723667B (en) |
| WO (1) | WO2015196494A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111479137B (en) * | 2020-04-16 | 2022-02-18 | 广州酷狗计算机科技有限公司 | Method and device for providing line address, server and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100461732C (en) * | 2006-06-16 | 2009-02-11 | 华为技术有限公司 | Ethernet technology switching and forwarding method, system and equipment |
| CN101594555A (en) * | 2008-05-30 | 2009-12-02 | 华为技术有限公司 | A kind of media forwarding method, system and device |
| CN101938424A (en) * | 2010-09-15 | 2011-01-05 | 北京星网锐捷网络技术有限公司 | Method and device for establishing routing table and method and device for transmitting message |
| WO2011009331A1 (en) * | 2009-07-23 | 2011-01-27 | 中兴通讯股份有限公司 | Routing label distribution method and apparatus in virtual private network |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6996065B2 (en) * | 2000-07-06 | 2006-02-07 | Lucent Technologies Inc. | Dynamic backup routing of network tunnel paths for local restoration in a packet network |
| US7609626B2 (en) * | 2004-04-16 | 2009-10-27 | Alcatel-Lucent Usa Inc. | Nodes for managing congestion and traffic flow by considering the minimization of link utilization values |
| CN101399748B (en) * | 2007-09-25 | 2012-07-04 | 华为技术有限公司 | Route computing method and router |
| WO2015021615A1 (en) * | 2013-08-14 | 2015-02-19 | 华为技术有限公司 | Routing traffic adjustment method, device and controller |
| CN103685054B (en) * | 2013-12-18 | 2017-02-01 | 武汉烽火网络有限责任公司 | Multipath load balancing method based on service awareness |
-
2014
- 2014-06-28 CN CN201480057546.9A patent/CN105723667B/en active Active
- 2014-06-28 WO PCT/CN2014/081071 patent/WO2015196494A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100461732C (en) * | 2006-06-16 | 2009-02-11 | 华为技术有限公司 | Ethernet technology switching and forwarding method, system and equipment |
| CN101594555A (en) * | 2008-05-30 | 2009-12-02 | 华为技术有限公司 | A kind of media forwarding method, system and device |
| WO2011009331A1 (en) * | 2009-07-23 | 2011-01-27 | 中兴通讯股份有限公司 | Routing label distribution method and apparatus in virtual private network |
| CN101938424A (en) * | 2010-09-15 | 2011-01-05 | 北京星网锐捷网络技术有限公司 | Method and device for establishing routing table and method and device for transmitting message |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105723667B (en) | 2019-02-19 |
| WO2015196494A1 (en) | 2015-12-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113315700B (en) | Computing resource scheduling method, device and storage medium | |
| US10374956B1 (en) | Managing a hierarchical network | |
| CN109218213B (en) | Flow regulation and control method and device | |
| CN104639639A (en) | Regulating method, device and system for deployment position of virtual machine | |
| CN103650435A (en) | Routing traffic adjusting method, device and controller | |
| US20150327135A1 (en) | Apparatus and method for dynamic hybrid routing in sdn networks to avoid congestion and balance loads under changing traffic load | |
| US9807002B2 (en) | Centralized route determination in communication networks | |
| WO2014064913A1 (en) | Operation management device and operation management method | |
| CN109314652A (en) | Network for formance measuring method and device | |
| CN115514696B (en) | Method, device and equipment for transmitting computing power resource information | |
| US20160065449A1 (en) | Bandwidth-Weighted Equal Cost Multi-Path Routing | |
| CN110636394B (en) | Virtual optical network mapping method, device, equipment and medium | |
| US10044621B2 (en) | Methods and systems for transport SDN traffic engineering using dual variables | |
| CN110661708B (en) | Network optimization method, system and network equipment | |
| CN103188149A (en) | Routing computation method and router | |
| EP3868062A1 (en) | Methods and apparatus for transmitting data over multiple paths in a network | |
| Kawashima et al. | Dynamic placement of virtual network functions based on model predictive control | |
| US10157076B2 (en) | Virtual machine migration device and method | |
| CN105262534A (en) | Route method and route device applicable to satellite communication network | |
| CN105723667A (en) | Path calculation method and apparatus | |
| CN105515981A (en) | Path computation method, tunnel establishment method, PCC, PCE and path computation system | |
| US9450858B2 (en) | Standby bandwidth aware path computation | |
| CN105515714A (en) | Network upgrading perception protection method | |
| CN115883469A (en) | Data flow load balancing method and device, network topology and data center | |
| US8995827B2 (en) | System and method for finding partially disjoint paths for spare capacity allocation in shared backup path protection for dual fiber cuts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |