WO2015021615A1 - 路由流量调整方法、装置及控制器 - Google Patents
路由流量调整方法、装置及控制器 Download PDFInfo
- Publication number
- WO2015021615A1 WO2015021615A1 PCT/CN2013/081459 CN2013081459W WO2015021615A1 WO 2015021615 A1 WO2015021615 A1 WO 2015021615A1 CN 2013081459 W CN2013081459 W CN 2013081459W WO 2015021615 A1 WO2015021615 A1 WO 2015021615A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- traffic
- transmitted
- nodes
- path
- bandwidth
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000005540 biological transmission Effects 0.000 claims abstract description 156
- 229920006395 saturated elastomer Polymers 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 12
- 238000013507 mapping Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/64—Hybrid switching systems
- H04L12/6418—Hybrid transport
Definitions
- Embodiments of the present invention relate to communication technologies, and in particular, to a method, device, and controller for routing traffic adjustment. Background technique
- each router calculates the route through the Interior Gateway Protocol (IGP) or the Border Gateway Protocol (BGP). Generate your own forwarding table, which requires each router to have powerful computing resources and storage capabilities. Because routers work together through protocols, network fault awareness and router operation and maintenance have great difficulties, network negotiation will lead to inefficiency; in addition, because each router is an individual, router software update and feature development are based on The specific equipment needs to be completed by the equipment manufacturer, which is not conducive to the rapid response and cost reduction of the network application.
- IGP Interior Gateway Protocol
- BGP Border Gateway Protocol
- SDN Software Defined Network
- the router only needs to perform the forwarding table according to the controller.
- the core of the SDN is the centralized routing algorithm.
- the linear programming algorithm For example, the linear programming algorithm.
- the fairness algorithm the linear programming algorithm needs to establish the corresponding objective function, set up an initial solution, and exhaust all feasible solutions through the computer, and finally get the optimal solution; the fair algorithm refers to all the services on the saturated link. Streams all allocate a certain amount of bandwidth without pursuing the optimal goal of the entire network.
- the calculation amount of the linear programming algorithm is related to the network scale. When the network scale is large, the calculation amount will be very large, and the network traffic path cannot be quickly adjusted. In the fair algorithm, the saturation of the bandwidth demand of each service flow is not satisfied.
- the sub-optimal path of the link calculation may cause the sub-optimal path to be far from the cost of the optimal path, thus affecting the network efficiency, making the stability of the service flow poor and the user experience jitter increased.
- the embodiment of the invention provides a method, a device and a controller for adjusting a routing traffic, so as to implement network traffic path adjustment and ensure the stability of the service flow when the network is faulty or the network traffic is abrupt.
- an embodiment of the present invention provides a method for adjusting a route traffic, including:
- the first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes is adjusted according to the path cost difference between the nodes to be transmitted, and the first The second bandwidth allocation scheme includes:
- the bandwidth allocated by the high priority transmission path is adjusted to the bandwidth of the lower priority transmission path to form a second bandwidth allocation scheme, where each node
- the bandwidth adjustment order between the transmission paths in the to-be-transmitted traffic is inversely related to the path cost difference.
- the traffic to be transmitted between the at least two nodes, and the inter-node chain in the topology And obtaining a transmission path of the to-be-transmitted traffic between each of the nodes, and forming a first bandwidth allocation scheme for the to-be-transmitted traffic to be allocated in each transmission path, including: according to at least two nodes to be transmitted Traffic, and the cost of the link between nodes in the topology, obtaining an optimal path for the traffic to be transmitted between each of the nodes;
- the traffic to be transmitted between the nodes is allocated, and the bandwidth is allocated in the corresponding optimal path;
- the available bandwidth and the generation value of the inter-point link are respectively obtained as sub-optimal paths of the to-be-transmitted traffic between the nodes;
- the traffic to be transmitted between the nodes is adjusted, and the bandwidth is allocated in the corresponding sub-optimal path.
- the bandwidth allocation scheme of the optimal path and the sub-optimal path is used as the first bandwidth allocation solution.
- calculating a cost difference between the two transmission paths includes: :
- a cost value difference between the optimal path and the suboptimal path is calculated for each of the nodes to be transmitted.
- the path to be transmitted between the nodes is adjusted according to a path value difference between the nodes to be transmitted.
- the first bandwidth allocation scheme, forming the second bandwidth allocation scheme includes:
- the first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes is separately adjusted to form a second bandwidth allocation scheme.
- the traffic to be transmitted between the nodes is determined according to the first setting rule, and the corresponding optimal path is
- the bandwidth allocation in the middle includes:
- the available bandwidth of the saturated link is allocated to the traffic to be transmitted between the nodes according to a preset weight.
- the traffic to be transmitted according to the at least two nodes And the available bandwidth and the cost of the link between the nodes in the topology, respectively, obtaining a transmission path of the traffic to be transmitted between each of the nodes, and forming a first bandwidth allocation scheme to be allocated in each transmission path. Also includes:
- the embodiment of the present invention provides a routing traffic adjustment apparatus, including:
- a first allocation module configured to perform traffic according to at least two nodes, and a topology And obtaining a transmission path of the to-be-transmitted traffic between the nodes, and forming a first bandwidth allocation scheme to be allocated in each transmission path;
- a calculation module configured to: Calculating a cost difference between the two transmission paths for each of the nodes to be transmitted, wherein the value of each transmission path is equal to the sum of the value of the links between all the nodes in the transmission path;
- a second allocation module configured to adjust a first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to a path value difference between the nodes to be transmitted, to form a second bandwidth allocation scheme.
- the second allocation module is specifically configured to:
- the bandwidth allocated by the high priority transmission path is adjusted to the bandwidth of the lower priority transmission path to form a second bandwidth allocation scheme, where each node
- the bandwidth adjustment order between the transmission paths in the to-be-transmitted traffic is inversely related to the path cost difference.
- a first acquiring unit configured to acquire an optimal path of the to-be-transmitted traffic between each of the nodes according to the to-be-transmitted traffic between the at least two nodes and the value of the link between the nodes in the topology; And for performing, according to the first setting rule, the traffic to be transmitted between the nodes, and performing bandwidth allocation in the corresponding optimal path;
- An adjusting unit configured to adjust an available bandwidth of a link between nodes in the topology according to the allocation result, and adjust a traffic to be transmitted between the nodes;
- a second acquiring unit configured to acquire, according to the adjusted traffic to be transmitted between the nodes, and the available bandwidth and the value of the link between the nodes in the adjusted topology, respectively, to obtain the traffic to be transmitted between the nodes Suboptimal path
- a second allocation unit configured to perform bandwidth allocation in the corresponding sub-optimal path, and the bandwidth allocation scheme of the optimal path and the sub-optimal path as the first bandwidth allocation solution .
- the calculating module is specifically configured to:
- the second allocation module is specifically configured to:
- the first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes is separately adjusted to form a second bandwidth allocation scheme.
- the first allocation unit is specifically configured to:
- the calculating module is further configured to:
- an embodiment of the present invention provides a controller, including:
- a processor configured to acquire, according to the to-be-transmitted traffic between the at least two nodes, and the available bandwidth and the value of the link between the nodes in the topology, respectively, to obtain a transmission path of the to-be-transmitted traffic between the nodes, to form a to-be-transmitted a first bandwidth allocation scheme in which traffic is allocated in each transmission path;
- a calculator configured to calculate a cost difference between the two transmission paths for each to-be-transmitted traffic between the nodes, where the value of each transmission path is equal to the sum of the value of the links between all nodes in the transmission path ;
- the processor is further configured to adjust a first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to a path cost difference between the nodes to be transmitted, to form a second bandwidth allocation scheme.
- the processor is specifically configured to:
- the bandwidth allocated by the high priority transmission path is adjusted to the bandwidth of the lower priority transmission path to form a second bandwidth allocation scheme, where each node
- the bandwidth adjustment order between the transmission paths in the to-be-transmitted traffic is inversely related to the path cost difference.
- the traffic to be transmitted between the nodes is allocated, and the bandwidth is allocated in the corresponding optimal path;
- the traffic to be transmitted between the nodes is adjusted, and the bandwidth is allocated in the corresponding sub-optimal path.
- the bandwidth allocation scheme of the optimal path and the sub-optimal path is used as the first bandwidth allocation solution.
- the calculator is specifically configured to:
- a cost value difference between the optimal path and the suboptimal path is calculated for each of the nodes to be transmitted.
- the processor is specifically configured to:
- the first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes is separately adjusted to form a second bandwidth allocation scheme.
- the processor is specifically configured to:
- the calculator is further configured to: Calculate the cost of each link in the topology based on the network overhead parameters.
- the embodiment of the present invention adjusts the value of the transmission path to be transmitted according to the path of the to-be-transmitted traffic between the nodes in the topology, adjusts the traffic to be transmitted according to the at least two nodes, and the available bandwidth and the value of the link between the nodes in the topology.
- the first bandwidth allocation scheme is formed to form a second bandwidth allocation scheme, so that when the network is faulty or the network traffic is abrupt, the network traffic path can be quickly adjusted, and at the same time, the total network used when the entire network meets the traffic demand is ensured.
- the least cost, that is, the use of the network resources is the least, so that the business flow is transmitted stably.
- FIG. 1 is a flowchart of Embodiment 1 of a method for adjusting routing traffic according to the present invention
- FIG. 2 is a schematic diagram of a topology configuration of a method for adjusting a routing traffic according to the present invention
- FIG. 3 is a schematic flowchart of a method for adjusting a routing traffic according to the present invention.
- FIG. 4 is a schematic flowchart of a method for adjusting a route traffic according to the third embodiment of the present invention.
- FIG. 5 is a schematic diagram of a method for adjusting a routing traffic according to the present invention
- FIG. 6 is a schematic diagram of a method for adjusting a routing traffic according to the third embodiment
- FIG. 6 is a schematic diagram of a method for adjusting a routing traffic according to the present invention
- FIG. 8 is a schematic diagram of bandwidth allocation of a sub-optimal path in Embodiment 3 of a method for adjusting a route traffic according to the present invention
- FIG. 8 is a schematic diagram of a topology configuration of a route flow adjustment method according to the present invention
- FIG. Method ⁇ Bandwidth allocation using fair algorithm in Example 4;
- FIG. 10 is a schematic diagram of another topology in the fourth embodiment of the routing traffic adjustment method of the present invention.
- FIG. 11 is a first embodiment of the routing traffic adjustment apparatus according to the present invention.
- FIG. 12 is a second embodiment of a routing traffic adjustment apparatus according to the present invention.
- FIG. 13 is a diagram showing the structure of the first embodiment of the controller of the present invention. detailed description
- FIG. 1 is a schematic flowchart of Embodiment 1 of a method for adjusting a route traffic according to the present invention.
- Embodiments of the present invention provide a method for adjusting a route traffic, which may be performed by any routed traffic adjustment device, which may be implemented by software and/or hardware.
- the routing traffic adjustment apparatus may be integrated in the controller to manage the forwarding table of each routing node. As shown in FIG. 1, the method of this embodiment includes:
- Step 101 Obtain a transmission path of the to-be-transmitted traffic between each of the nodes according to the to-be-transmitted traffic between the at least two nodes, and the available bandwidth and the cost of the link between the nodes in the topology, to form a traffic to be transmitted.
- connection relationship between the nodes is determined.
- a connection link is formed between the two nodes, and the total bandwidth of each link is constant.
- the traffic to be transmitted needs to be transmitted between the source node and the sink node.
- the upper layer application needs to generate traffic between two nodes, and the traffic to be transmitted is proposed to allocate bandwidth.
- the traffic to be transmitted between nodes is relatively fixed for a certain period of time.
- the information to be transmitted is consumed by the source node to reach the sink node through the intermediate node in the topology.
- the information to be transmitted is mapped to the traffic to be transmitted, according to the traffic to be transmitted, and the available bandwidth of the link between the nodes in the topology. And the generation value, the transmission path of the traffic path to be transmitted between the source node and the sink node can be obtained.
- the transmission path is not unique.
- the transmission paths of the node A to the node E include multiple transmission paths such as A-D-E, A-C-E, A-B-C-E, and A-D-C-E.
- the transmission paths A-D-E and A-C-E can be selected for the transmission of the traffic to be transmitted, that is, the transmission path of the traffic to be transmitted between each of the nodes.
- Step 102 Calculate a generation difference between the two transmission paths for each of the nodes to be transmitted.
- the value of each transmission path is equal to the sum of the value of the links between all nodes in the transmission path. Still taking the node A and the node E in FIG. 2 as an example, in the multiple transmission paths from the node A to the node E, the generation values of the respective transmission paths are respectively calculated, wherein the generation value of each transmission path is equal to the transmission. The sum of the surrogate values of the links in the path.
- the transmission path of the traffic to be transmitted between each node may be one or more. Therefore, the following three specific scenarios exist:
- Scenario 1 There are at least two transmission paths for the traffic to be transmitted between each node. This scenario is a suitable scenario for the present invention.
- Scenario 2 There are at least two transmission paths for the traffic to be transmitted between some nodes, and only one transmission path exists for the traffic to be transmitted between the other nodes.
- the present invention does not adjust the bandwidth allocation, and only adjusts the bandwidth allocation on the transmission path of the to-be-transmitted traffic between the nodes having at least two transmission paths.
- Scenario 3 There is only one transmission path for the traffic to be transmitted between each node. The invention is not applicable to this scenario.
- Step 103 Adjust a first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to a path cost difference between the nodes to be transmitted, to form a second bandwidth allocation scheme.
- step 101 a first bandwidth allocation scheme in which traffic to be transmitted is allocated in each transmission path has been formed, and in some cases, the first bandwidth allocation scheme may not be optimal.
- the traffic to be transmitted between node A and node E is 20G, and there are two transmission paths.
- the traffic to be transmitted between Node B and Node E is 10G, and there are also two transmission paths.
- the cost difference between the two transmission paths of the A-E is compared with the cost difference between the two transmission paths of the B-E, and the bandwidth allocation scheme in the transmission path can be adjusted according to the comparison result. Adjusting the bandwidth usage according to the cost difference can make the network resources occupied by each transmission path more balanced under the condition that the traffic demand is met.
- the path value difference is adjusted according to the path of the traffic to be transmitted between the nodes.
- a first bandwidth allocation scheme for the traffic to be transmitted between the nodes forms a second bandwidth allocation scheme.
- the embodiment of the present invention adjusts the value of the transmission path to be transmitted according to the path of the to-be-transmitted traffic between the nodes in the topology, adjusts the traffic to be transmitted according to the at least two nodes, and the available bandwidth and the value of the link between the nodes in the topology.
- the first bandwidth allocation scheme is formed to form a second bandwidth allocation scheme, so that when the network is faulty or the network traffic is abrupt, the network traffic path can be quickly adjusted, and at the same time, the total network used when the entire network meets the traffic demand is ensured.
- the least cost that is, the use of the network resources is the least, so that the business flow is transmitted stably.
- step 103 adjusting a first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to the path value difference between the nodes to be transmitted, and forming the second bandwidth allocation scheme may include: The transmission bandwidth of the to-be-transmitted traffic is prioritized, and the bandwidth allocated by the high-priority transmission path is adjusted to the bandwidth of the lower-priority transmission path to form a second bandwidth allocation scheme, where the traffic to be transmitted between the nodes The bandwidth adjustment order between the transmission paths is inversely related to the path cost difference.
- each transmission path of the traffic to be transmitted between each node is fixed, and each transmission path is sorted according to the priority, and the optimal path is preferentially used, that is, the bandwidth is preferentially allocated for the optimal path, and then Consider other lower priority transmission paths.
- the bandwidth allocated for the optimal path used by the traffic to be transmitted between the nodes can be adjusted to other lower priority transmission paths to form a second bandwidth allocation scheme.
- the foregoing reverse correspondence specifically means that if the path cost difference is larger, the bandwidth allocated for the optimal path is adjusted to the order of the other lower priority transmission paths, and the optimal path is allocated.
- the order of increasing bandwidth is higher.
- it is preferable to use an optimal path and a transmission path with a small path cost difference from the optimal path for bandwidth allocation for example, using only the optimal path, or A portion of the bandwidth allocated to the optimal path is reassigned to the transmission path having a smaller path cost difference from the optimal path.
- the bandwidth allocation using the optimal path and the path cost difference with the path cost of the optimal path still does not satisfy the traffic demand, consider using a transmission path with a large difference in path cost from the optimal path.
- the optimal path for the traffic to be transmitted between the two nodes includes a common link, and the available bandwidth of the common link is 20G, and is equally distributed to the two.
- the traffic to be transmitted between nodes that is, 10G is used for the traffic to be transmitted between each node, then the link is full. And the link, at this time, forming a first bandwidth allocation scheme.
- the path cost difference between the optimal path of the first node to be transmitted and the suboptimal path is 5, and the path cost difference between the optimal path of the second node to be transmitted and the suboptimal path is 10, in this scenario, preferentially use the sub-optimal path of the traffic to be transmitted between the first node, and adjust the bandwidth of the optimal path to be transmitted to the first node to the sub-optimal path, if the bandwidth at this time
- the adjustment value is 10G, that is, the traffic to be transmitted between the first nodes uses only its own sub-optimal path, and the traffic of the second first node is to be transmitted under the condition that no other nodes are to be transmitted through the common link.
- the traffic demand can be met using only its own optimal path.
- a transmission path with a small increase in network overhead is used to replace a transmission path with a large network overhead, so that the network resource consumption is minimized when the entire network meets the traffic demand, and the maximum difference of different transmission paths of the service flow is minimized, and the same one is reduced.
- the jitter of the traffic flow is used to replace a transmission path with a large network overhead, so that the network resource consumption is minimized when the entire network meets the traffic demand, and the maximum difference of different transmission paths of the service flow is minimized, and the same one is reduced.
- Step 301 According to at least two The traffic to be transmitted between the nodes, and the cost of the links between the nodes in the topology, obtain the optimal path of the traffic to be transmitted between each of the nodes.
- the maximum allowed bandwidth between each adjacent two nodes is fixed in the topology, and the available bandwidth of the links between the nodes is less than or equal to the maximum allowed bandwidth;
- the cost value of the link between nodes is obtained by converting the cost of the network according to the network overhead parameter.
- the network overhead parameter usually refers to delay, bandwidth, link status, and hop count.
- the optimal path of the traffic to be transmitted between each of the nodes may be obtained in various forms, for example, by using the Dijkstra algorithm.
- the known conditions of the Dijkstra algorithm are the entire network topology and the length of each link. If the known link length is changed to link delay or cost, it is equivalent to finding the path with the minimum delay or minimum cost between any two nodes.
- the Dijkstra algorithm can be used to obtain the optimal path set. For example, as shown in FIG. 2, an optimal path for the traffic to be transmitted between the A node and the E node and an optimal path for the traffic to be transmitted between the Node B and the E node are obtained.
- Step 302 Based on the first setting rule, the traffic to be transmitted between the nodes is allocated, and the bandwidth is allocated in the corresponding optimal path.
- the first setting rule is a bandwidth allocation rule that is preset according to user requirements. For example, if the available bandwidth of the link in the optimal path does not meet the traffic demand, the bandwidth allocation ratio or the bandwidth allocation weight may be preset.
- Step 303 Adjust the available bandwidth of the link between the nodes in the topology according to the allocation result, and adjust the traffic to be transmitted between the nodes.
- the bandwidth and cost of the links between the nodes in the topology after the bandwidth is allocated for the optimal path is 20G, which is the optimal path.
- the traffic to be transmitted between the A node and the E node is 20G, which is the optimal path.
- the ACE is allocated 10G bandwidth
- the available bandwidth of the link AC and CE needs to be optimal.
- the available bandwidth before the path allocation bandwidth (10G or more) is reduced by 10G, and the remaining A-to-E-node traffic to be transmitted is 10G.
- Step 304 Acquire a sub-optimal path of the to-be-transmitted traffic between the nodes according to the adjusted to-be-transmitted traffic between the nodes, and the available bandwidth and generation value of the links between the nodes in the adjusted topology.
- the sub-optimal path is obtained in the same manner as the optimal path.
- the Dijkstra algorithm is used as an example to obtain a sub-optimal path.
- Step 305 Perform the bandwidth allocation in the corresponding sub-optimal path, and the bandwidth allocation scheme of the optimal path and the sub-optimal path as the first bandwidth allocation scheme.
- Bandwidth allocation is performed in the corresponding sub-optimal path according to the adjusted traffic to be transmitted between nodes and the available bandwidth of each link in the topology at that time. For example, as shown in the topology shown in FIG. 2, after the bandwidth is allocated for the optimal path, the traffic to be transmitted between the A node and the E node is 10 G, and the available bandwidth of the sub-optimal path from the A node to the E node is greater than or equal to 10 G.
- the available bandwidth of the suboptimal path satisfies the traffic demand between the A node and the E node, allocates 10G bandwidth for the suboptimal path, and forms a first bandwidth allocation scheme of the optimal path and the suboptimal path between the A node and the E node.
- Step 306 Calculate a generation difference between the two transmission paths for each of the nodes to be transmitted.
- Step 307 Adjust a first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to a path value difference between the nodes to be transmitted, to form a second bandwidth allocation scheme.
- step 301 - step 305 is further refinement of step 101 in FIG.
- a centralized routing algorithm is used to quickly calculate an optimal path of the entire network.
- a centralized network such as a Software Defined Network (SDN)
- SDN Software Defined Network
- Finding the method of replacing the saturated link quickly calculating the optimal path of the traffic to be transmitted between the nodes, not only calculating the optimal path for the traffic to be transmitted between all nodes, but also completing in a short time;
- the replacement algorithm uses a path with a small increase in network overhead to replace a path with a large increase in network overhead, so that the total cost of the network used when the entire network meets the traffic demand is minimized, that is, the network resource is used at the minimum, so that the service flow can be different at the same time.
- the maximum difference in the path is minimized, that is, the jitter amplitude of the same stream is reduced, and the network efficiency and user experience are improved.
- the step 307: adjusting the first bandwidth allocation scheme of the to-be-transmitted traffic between the nodes according to the path value difference of the traffic to be transmitted between the nodes, and forming the second bandwidth allocation scheme may include:
- the step 302 is: based on the first setting rule, the traffic to be transmitted between the nodes, and the bandwidth allocation in the corresponding optimal path may include:
- the traffic to be transmitted between the nodes is mapped as the traffic demand to each of the optimal paths, and the saturated link in the network topology is calculated according to the sum of the traffic demands of the links.
- a third embodiment of the present invention provides a preferred example of a method for adjusting a route traffic, which is still in FIG.
- the illustrated topology is described as an example.
- the available bandwidth and cost of each link are as shown in Table 1.
- FIG. 4 is a schematic flowchart diagram of Embodiment 3 of a method for adjusting a route traffic according to the present invention. As shown in FIG. 4, the method may include:
- Step 401 Calculate the cost value of each link in the topology according to the network overhead parameter. Assume that the traffic to be transmitted between the nodes at time ⁇ is: 20G to be transmitted between A-E, and the traffic to be transmitted between B-E is 40G.
- Step 402 Calculate an optimal path of A-E and B-E according to the traffic to be transmitted between the nodes and the value of each link.
- the Dijkstra algorithm is used to obtain the optimal path of A-E and the optimal path of B-E.
- Step 403 At the same time ⁇ , calculate the sum of the estimated occupied bandwidth of each link in all the optimal paths.
- At least one channel to be transmitted may be transmitted on each link at the same time.
- the traffic demand of each channel and the available bandwidth of the link need to be considered.
- the preset weight ratio is 1: 1, and the (CE) available bandwidth 30G is allocated as follows: 10G bandwidth, allocate 20G bandwidth for the BE path to be transmitted.
- Step 401 - Step 403 is the bandwidth allocation of the optimal path in the first bandwidth allocation scheme, as shown in FIG. 6: A-E (10G): (A-C) ⁇ (C-E), B-E (20G): (B-C) (C-E).
- Step 404 Find the optimal path (suboptimal path) in the remaining paths of A-E and B-E.
- the optimal path is the optimal path of the adjusted topology. Compared with the topology before the adjustment, the optimal path obtained in this step can be considered as the suboptimal path.
- This step is the bandwidth allocation of the suboptimal path in the first bandwidth allocation scheme, as shown in Figure 7: A-E (10G): (A-D) ⁇ (D-E), B-E (20G): (B-C) (C-D) (D-E).
- Step 405 Calculate a cost difference between the optimal path and the sub-optimal path corresponding to the to-be-transmitted traffic between the nodes, and perform optimal replacement.
- the generation value of the suboptimal path is increased relative to the optimal path:
- the suboptimal path of A-E is less valuable than the suboptimal path of B-E with respect to its respective optimal path. Therefore, the sub-optimal path of B-E is used less.
- Step 406 Adjust the bandwidth allocation in each of the optimal path and the sub-optimal path according to the order of the generation value difference.
- the A-E optimal path allocation bandwidth is reduced, and the sub-optimal path is used more.
- the B-E optimal path allocation bandwidth is increased, and the sub-optimal path is less used, namely:
- the 20G traffic demand corresponding to the information to be transmitted on the AE road is allocated by two paths: Optimal path: (AC) (CE), adjusted to 10G 5G after optimal replacement bandwidth allocation; Sub-optimal path: (AD) ( DE), after the optimal replacement bandwidth allocation adjustment becomes 10G 15G.
- the 40G traffic demand corresponding to the information to be transmitted on the BE path is allocated by two paths: Optimal path: (BC) (CE), adjusted to 20G 25G after optimal replacement bandwidth allocation; Sub-optimal path: (BC) ⁇ (CD) (DE), after the optimal replacement bandwidth allocation adjustment becomes
- Steps 405 and 406 are steps involved in the second bandwidth allocation scheme, as shown in FIG. 6 and FIG. 7: AE (5G): (AC) ⁇ (CE), BE (25G): (BC) ⁇ (CE); AE ( 15G) : (AD) ⁇ (DE), BE ( 15G) : (BC) ⁇ (CD) ⁇ (DE)o
- the mutual adjustment of the bandwidth allocation on the sub-optimal path and the optimal path is adopted to minimize the total network cost consumed when the entire network meets the traffic demand, and the network can be quickly implemented when the network is faulty or the network traffic is abruptly changed.
- the traffic path is adjusted, and at the same time, the stability of the traffic flow is guaranteed.
- the value-added path is preferentially used to ensure that the path of the entire network is optimal, thereby improving network usage efficiency.
- traffic changes on the customer network are usually completed in a short period of time, from one
- the flow model is transformed into another traffic model.
- China Telecom's 163 network from the morning traffic model to another morning traffic model, can take only about an hour to complete.
- the time requirement can be met by the traditional linear programming algorithm, and the routing traffic adjustment method provided by the present invention can complete the transformation of the traffic model within the time requirement.
- the route traffic adjustment method provided by the present invention can respond quickly and satisfy all the requirements. Network traffic demand.
- the available bandwidth of all links is 40G, and the link identification number is the link distance.
- the flow requirements are: B-E 40G, B-G 40G, A-G 20G.
- B-E shortest path B-C-E 20G (distance 2);
- B-G shortest path B-C-G 20G (distance 2);
- B-G secondary short path B-A-G 20G (distance 2.5)
- A-G Shortest path A-G 20G (distance ⁇ 3).
- routing traffic adjustment method of the present invention is adopted, and the flow is as follows:
- BG sub-optimal path BAG 20G
- B-G third optimal path B-A-F-G 20G;
- B-E optimal path B-C-E 20G;
- A-G Optimal path A-G 20G.
- the routing traffic adjustment method provided by the present invention is as follows:
- Traffic demand A-D (20G) sub-optimal path - optimal path 1, sub-optimal path A-B-D, optimal path A-C-D.
- A-D can be replaced by sub-optimal path A-B-D, and the released bandwidth is allocated to traffic demand A-C and C-D. All traffic requirements in the final bandwidth allocation result are met.
- FIG. 11 is a schematic structural diagram of Embodiment 1 of a routing traffic adjustment apparatus according to the present invention.
- the routing traffic adjustment apparatus of the embodiment of the present invention can be integrated in the controller.
- the routing flow adjustment apparatus of this embodiment includes a first allocation module 110, a calculation module 120, and a second allocation module 130.
- the first allocating module 110 is configured to obtain, according to the to-be-transmitted traffic between the at least two nodes, and the available bandwidth and the cost of the link between the nodes in the topology, respectively, to obtain the transmission of the to-be-transmitted traffic between each of the nodes.
- a path a first bandwidth allocation scheme for allocating traffic to be transmitted in each transmission path;
- a calculation module 120 configured to calculate a value difference between the two transmission paths for each to-be-transmitted traffic between the nodes, where each The value of the transmission path is equal to the sum of the values of the links between all the nodes in the transmission path.
- the second allocation module 130 is configured to adjust the transmission to be transmitted between the nodes according to the path value difference of the traffic to be transmitted between the nodes.
- the first bandwidth allocation scheme of traffic forming The second bandwidth allocation scheme.
- the routing traffic adjustment device of this embodiment may be used in the technical solution of the first embodiment of the routing traffic adjustment method, and the implementation principle and technical effects thereof are similar, and details are not described herein again.
- the second allocation module 130 is specifically configured to: adjust, for each transmission path in which the traffic to be transmitted between each node is prioritized, the bandwidth allocated by the high priority transmission path to the allocation priority low transmission path. Bandwidth, to form a second bandwidth allocation scheme, wherein the bandwidth adjustment order between the transmission paths in the to-be-transmitted traffic between the nodes is inversely related to the path cost difference.
- Embodiment 2 is a schematic structural diagram of Embodiment 2 of a routing traffic adjustment apparatus according to the present invention. As shown in FIG. 12, the apparatus of this embodiment is based on the apparatus structure shown in FIG. 11, and further, the first allocation module.
- the 110 may include: a first acquisition unit 111, a first distribution unit 112, an adjustment unit 113, a second acquisition unit 114, and a second distribution unit 115.
- the first obtaining unit 111 is configured to obtain an optimal path for the traffic to be transmitted between each node according to the to-be-transmitted traffic between the at least two nodes and the cost of the link between the nodes in the topology.
- the second allocating unit 115 is configured to adjust the traffic to be transmitted between the nodes, in the corresponding times Bandwidth allocation is performed in the optimal path, and the bandwidth allocation scheme of the optimal path and the sub-optimal path is used as the first bandwidth allocation scheme.
- the device in this embodiment can be used to implement the technical solution of the method embodiment shown in FIG. 3, and the principle and the technical effect are similar, and details are not described herein again.
- the calculating module 120 is specifically configured to: calculate a cost difference between the optimal path and the sub-optimal path for each to-be-transmitted traffic between the nodes.
- the second allocating module 130 is specifically configured to: sort the path cost difference of the to-be-transmitted traffic between the nodes; determine the bandwidth adjustment order according to the reverse order of the path cost difference; according to the determined bandwidth adjustment order, The first bandwidth allocation scheme for adjusting the traffic to be transmitted between the nodes is separately adjusted to form a second bandwidth allocation scheme.
- the first allocating unit 112 is specifically configured to: map the traffic to be transmitted between the nodes as the traffic demand to each of the optimal paths, and calculate a saturated link in the network topology according to the sum of the traffic requirements of the link; The preset weight allocates the available bandwidth of the saturated link to the traffic to be transmitted between the nodes.
- the calculating module 120 is further configured to calculate a cost value of each link in the topology structure according to the network overhead parameter.
- FIG. 13 is a schematic structural diagram of Embodiment 1 of the controller of the present invention. As shown in FIG. 13, the controller of this embodiment includes: a processor 100 and a calculator 200.
- the processor 100 is configured to acquire, according to the to-be-transmitted traffic between the at least two nodes, and the available bandwidth and the cost of the link between the nodes in the topology, respectively, to obtain a transmission path of the to-be-transmitted traffic between the nodes, and form a transmission path.
- a first bandwidth allocation scheme to be allocated in each transmission path a calculator 200, configured to calculate a cost difference between the two transmission paths for each of the nodes to be transmitted, wherein each transmission path
- the generation value is equal to the sum of the generation values of the links between all the nodes in the transmission path;
- the processor 100 is further configured to adjust the first bandwidth of the to-be-transmitted traffic between the nodes according to the path cost difference between the nodes to be transmitted.
- the allocation scheme forms a second bandwidth allocation scheme.
- the processor 100 may be specifically configured to adjust, for each transmission path in which the traffic to be transmitted is to be transmitted between each node, the bandwidth allocated by the high priority transmission path to the bandwidth of the low priority transmission path.
- a second bandwidth allocation scheme is formed, where a bandwidth adjustment sequence between transmission paths in the to-be-transmitted traffic between the nodes is inversely related to the path cost difference.
- the processor 100 may be further configured to: obtain an optimal path of the to-be-transmitted traffic between each node according to the to-be-transmitted traffic between the at least two nodes, and the cost of the link between the nodes in the topology. And performing, according to the first setting rule, the traffic to be transmitted between the nodes, performing bandwidth allocation in the corresponding optimal path; adjusting the available bandwidth of the link between the nodes in the topology according to the allocation result, and adjusting each The traffic to be transmitted between the nodes; according to the adjusted traffic to be transmitted between the nodes, and the available bandwidth and the value of the link between the nodes in the adjusted topology, respectively, the traffic to be transmitted between the nodes is obtained. And the sub-optimal path; and, the adjusted traffic to be transmitted between the nodes, performing bandwidth allocation in the corresponding sub-optimal path, and the bandwidth allocation scheme of the optimal path and the sub-optimal path as the first bandwidth allocation solution .
- the calculator 200 may be specifically configured to: for each of the nodes to be transmitted traffic, Calculate the cost difference between the optimal path and the suboptimal path.
- the processor 100 may be further configured to: sort a path cost difference of the to-be-transmitted traffic between the nodes; determine a bandwidth adjustment order according to an inverse order of the path cost difference; according to the determined bandwidth adjustment order, The first bandwidth allocation scheme for adjusting the traffic to be transmitted between the nodes is separately adjusted to form a second bandwidth allocation scheme.
- processor 100 can be specifically configured to:
- the calculator 200 can also be configured to calculate the cost value of each link in the topology according to the network overhead parameter.
- the foregoing controller may perform the foregoing method embodiments, and the implementation principles thereof are similar, and details are not described herein again.
- the aforementioned program can be stored in a computer readable storage medium.
- the program when executed, performs the steps including the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
本发明实施例提供一种路由流量调整方法、装置及控制器,该方法包括:根据至少两个节点间的待传输流量,及拓扑结构中各节点间链路的可用带宽和代价值,分别获取每个所述节点间待传输流量的传输路径,形成待传输流量在各传输路径中分配的第一带宽分配方案;针对每个节点间待传输流量,计算两两传输路径之间的代价值差,每个传输路径的代价值等于传输路径中所有节点间链路的代价值之和;根据各所述节点间待传输流量的路径代价值差,调整各节点间待传输流量的第一带宽分配方案,形成第二带宽分配方案。本发明实现在网络出现故障或网络流量发生突变时,能够快速实现网络流量路径调整,使全网流量使用的带宽代价总和最小,并同时保证业务流的稳定性。
Description
路由流量调整方法、 装置及控制器
技术领域
本发明实施例涉及通信技术, 尤其涉及一种路由流量调整方法、 装置及 控制器。 背景技术
在分布式互联网协议(Internet Protocol, 简称: IP) 网络中, 每台路由器 都会通过内部网关协议 (Interior Gateway Protocol, 简称: IGP) 或边界网关 协议 (Border Gateway Protocol, 简称: BGP) 计算路由, 以生成自己的转发 表, 这要求每台路由器都有强大的计算资源和存储能力。 由于路由器之间通 过协议协同工作, 网络的故障感知与路由器运维都有很大的困难, 网络协商 将导致效率低下; 另外, 由于每台路由器都是一个个体, 路由器软件更新与 特性开发都基于具体设备, 需要设备商自己完成, 不利于网络应用的快速响 应和成本降低。
针对上述问题, 业界提出了集中式网络的思想, 即软件定义的网络 (Software Defined Network, 简称: SDN) 。 SDN将路由器需要的计算能力 与路由能力集中起来由控制器统一代为完成, 路由器只需要按照控制器下发 的转发表执行就可以了, 其中, SDN的核心是集中路由算法, 例如, 线性规 划算法和公平算法, 线性规划算法需要建立相应的目标函数, 设立一个初始 解, 并通过计算机穷举所有可行解, 最终比较得到最优解; 公平算法, 是指 在饱和链路上, 对所有的业务流都分配一定的带宽, 而不追求全网最优的目 标。
而线性规划算法的计算量与网络规模相关, 当网络规模较大时, 计算量 将非常大, 不能应对网络流量路径的快速调整; 公平算法中, 对不满足各条 业务流的带宽需求的饱和链路计算次优路径, 可能导致次优路径与最优路径 的代价相差甚远, 从而影响网络效率, 使得该业务流的稳定性较差, 用户体 验抖动加大。
发明内容
本发明实施例提供一种路由流量调整方法、 装置及控制器, 以实现网络 出现故障或网络流量发生突变时, 能够快速实现网络流量路径调整, 并同时 保证业务流的稳定性。
第一方面, 本发明实施例提供一种路由流量调整方法, 包括:
根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的可 用带宽和代价值, 分别获取每个所述节点间待传输流量的传输路径, 形成待 传输流量在各传输路径中分配的第一带宽分配方案;
针对每个所述节点间待传输流量, 计算两两传输路径之间的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路的代价值之和; 根据各所述节点间待传输流量的路径代价值差, 调整各节点间待传输流 量的第一带宽分配方案, 形成第二带宽分配方案。
结合第一方面, 在第一方面的第一种可能的实现方式中, 根据各所述节 点间待传输流量的路径代价值差, 调整各节点间待传输流量的第一带宽分配 方案, 形成第二带宽分配方案包括:
对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
结合第一方面或第一方面的第一种可能的实现方式, 在第一方面的第二 种可能的实现方式中, 根据至少两个节点间的待传输流量, 以及拓扑结构中 各节点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量的 传输路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案包括: 根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的代 价值, 获取每个所述节点间待传输流量的最优路径;
基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中 进行带宽分配;
根据分配结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各 所述节点间待传输流量;
根据调整后的各所述节点间待传输流量, 以及调整后的拓扑结构中各节
点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流量的次优路 径;
将调整后的各所述节点间待传输流量, 在对应的次优路径中进行带宽分 配, 所述最优路径和次优路径的带宽分配方案作为第一带宽分配方案。
结合第一方面的第二种可能的实现方式, 在第一方面的第三种可能的实 现方式中, 针对每个所述节点间待传输流量, 计算两两传输路径之间的代价 值差包括:
针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价 值差。
结合第一方面的第三种可能的实现方式, 在第一方面的第四种可能的实 现方式中, 根据各所述节点间待传输流量的路径代价值差, 调整各节点间待 传输流量的第一带宽分配方案, 形成第二带宽分配方案包括:
将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
结合第一方面的第二种可能的实现方式, 在第一方面的第五种可能的实 现方式中, 基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优 路径中进行带宽分配包括:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。 结合第一方面、 第一方面的第一种至第五种可能的实现方式中的任意一 种, 在第一方面的第六种可能的实现方式中, 根据至少两个节点间的待传输 流量, 以及拓扑结构中各节点间链路的可用带宽和代价值, 分别获取每个所 述节点间待传输流量的传输路径, 形成待传输流量在各传输路径中分配的第 一带宽分配方案之前, 还包括:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
第二方面, 本发明实施例提供一种路由流量调整装置, 包括:
第一分配模块, 用于根据至少两个节点间的待传输流量, 以及拓扑结构
中各节点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量 的传输路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案; 计算模块, 用于针对每个所述节点间待传输流量, 计算两两传输路径之 间的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路 的代价值之和;
第二分配模块, 用于根据各所述节点间待传输流量的路径代价值差, 调 整各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
结合第二方面, 在第二方面的第一种可能的实现方式中, 所述第二分配 模块具体用于:
对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
结合第二方面或第二方面的第一种可能的实现方式, 在第二方面的第二 种可能的实现方式中, 所述第一分配模块包括:
第一获取单元, 用于根据至少两个节点间的待传输流量, 以及拓扑结构 中各节点间链路的代价值, 获取每个所述节点间待传输流量的最优路径; 第一分配单元, 用于基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中进行带宽分配;
调整单元, 用于根据分配结果调整所述拓扑结构中各节点间链路的可用 带宽, 并调整各所述节点间待传输流量;
第二获取单元, 用于根据调整后的各所述节点间待传输流量, 以及调整 后的拓扑结构中各节点间链路的可用带宽和代价值, 分别获取各所述节点间 待传输流量的次优路径;
第二分配单元, 用于将调整后的各所述节点间待传输流量, 在对应的次 优路径中进行带宽分配, 所述最优路径和次优路径的带宽分配方案作为第一 带宽分配方案。
结合第二方面的第二种可能的实现方式, 在第二方面的第三种可能的实 现方式中, 所述计算模块具体用于:
针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价
值差。
结合第二方面的第三种可能的实现方式, 在第二方面的第四种可能的实 现方式中, 所述第二分配模块具体用于:
将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
结合第二方面的第二种可能的实现方式, 在第二方面的第五种可能的实 现方式中, 所述第一分配单元具体用于:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。 结合第二方面、 第二方面的第一种至第五种可能的实现方式中的任意一 种, 在第二方面的第六种可能的实现方式中, 所述计算模块还用于:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
第三方面, 本发明实施例提供一种控制器, 包括:
处理器, 用于根据至少两个节点间的待传输流量, 以及拓扑结构中各节 点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量的传输 路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案;
计算器, 用于针对每个所述节点间待传输流量, 计算两两传输路径之间 的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路的 代价值之和;
所述处理器还用于根据各所述节点间待传输流量的路径代价值差, 调整 各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
结合第三方面, 在第三方面的第一种可能的实现方式中, 所述处理器具 体用于:
对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
结合第三方面或第一方面的第一种可能的实现方式, 在第三方面的第二 种可能的实现方式中, 所述处理器具体用于:
根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的代 价值, 获取每个所述节点间待传输流量的最优路径;
基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中 进行带宽分配;
根据分配结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各 所述节点间待传输流量;
根据调整后的各所述节点间待传输流量, 以及调整后的拓扑结构中各节 点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流量的次优路 径;
将调整后的各所述节点间待传输流量, 在对应的次优路径中进行带宽分 配, 所述最优路径和次优路径的带宽分配方案作为第一带宽分配方案。
结合第三方面的第二种可能的实现方式, 在第三方面的第三种可能的实 现方式中, 所述计算器具体用于:
针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价 值差。
结合第三方面的第三种可能的实现方式, 在第三方面的第四种可能的实 现方式中, 所述处理器具体用于:
将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
结合第三方面的第二种可能的实现方式, 在第三方面的第五种可能的实 现方式中, 所述处理器具体用于:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。 结合第三方面、 第三方面的第一种至第五种可能的实现方式中的任意一 种, 在第三方面的第六种可能的实现方式中, 所述计算器还用于:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
本发明实施例通过计算拓扑结构中各节点间待传输流量的途径传输路径 的代价值差, 调整根据至少两个节点间待传输流量, 以及拓扑结构中各节点 间链路的可用带宽和代价值形成的第一带宽分配方案, 形成第二带宽分配方 案, 以实现网络出现故障或网络流量发生突变时, 能够快速实现网络流量路 径调整, 并同时保证全网满足流量需求的情况下使用的网络总代价最小, 即 使用网络资源最少, 使得业务流稳定传输。 附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案, 下面将对实 施例或现有技术描述中所需要使用的附图作简单地介绍, 显而易见地, 下面 描述中的附图仅仅是本发明的一些实施例, 对于本领域普通技术人员来讲, 在不付出创造性劳动性的前提下, 还可以根据这些附图获得其他的附图。
图 1为本发明路由流量调整方法实施例一的流程
图 2为本发明路由流量调整方法 ^ 施例一中拓扑结构示例图;
图 3为本发明路由流量调整方法 ^ 施例二的流程示意图;
图 4为本发明路由流量调整方法 ^ 施例三的流程示意图;
图 5为本发明路由流量调整方法 ^ 施例三中调整后拓扑结构示例图; 图 6为本发明路由流量调整方法; 施例三中的最优路径的带宽分配示例 图
图 7为本发明路由流量调整方法实施例三中的次优路径的带宽分配示例 图 8为本发明路由流量调整方法 ^ ;施例四中一拓扑结构示例图; 图 9为本发明路由流量调整方法; ^施例四中采用公平算法的带宽分配; 例图;
图 10为本发明路由流量调整方法实施例四中另一拓扑 ^例图; 图 11为本发明路由流量调整装置实施例一的
图 12为本发明路由流量调整装置实施例二的
图 13为本发明控制器实施例一的结构 ^
具体实施方式
下面将结合本发明实施例中的附图, 对本发明实施例中的技术方案进行 清楚、 完整地描述, 显然, 所描述的实施例仅仅是本发明一部分实施例, 而 不是全部的实施例。 基于本发明中的实施例, 本领域普通技术人员在没有做 出创造性劳动前提下所获得的所有其他实施例, 都属于本发明保护的范围。
实施例一
图 1为本发明路由流量调整方法实施例一的流程示意图。 本发明实施例 提供了一种路由流量调整方法,该方法可以由任意路由流量调整装置来执行, 该装置可以通过软件和 /或硬件实现。 本实施例中, 该路由流量调整装置可以 集成在控制器中, 对各路由节点的转发表集中进行管理。 如图 1所示, 本实 施例的方法包括:
步骤 101 : 根据至少两个节点间的待传输流量, 以及拓扑结构中各节点 间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量的传输路 径, 形成待传输流量在各传输路径中分配的第一带宽分配方案。
在拓扑结构中, 各节点之间的连接关系是确定的, 两两节点之间形成连 接链路, 每条链路的总带宽不变, 随着分配流量的占用和释放, 可用带宽在 变化。 通常, 待传输流量是需要在信源节点和信宿节点之间进行传输的, 上 层应用会产生在某两个节点之间进行流量传输的需求, 提出了待传输流量, 以要求分配带宽。 两节点之间的待传输流量需求可能不止一个, 并且通常在 同一时刻可能会出现多个待传输流量的需求。 节点间的待传输流量在一定时 间内是相对固定的。 待传输信息由信源节点经拓扑结构中中间节点到达信宿 节点需要消耗流量, 因此, 将待传输信息映射为待传输流量, 根据该待传输 流量, 以及拓扑结构中各节点间链路的可用带宽和代价值, 可获取信源节点 和信宿节点间待传输流量途径的传输路径。
通常情况下, 该传输路径不是唯一的, 例如, 图 2所示的拓扑结构中, 节点 A到节点 E的传输路径有 A-D-E、 A-C-E、 A-B-C-E和 A-D-C-E等多条 传输路径。 在这里, 可以选择传输路径 A-D-E和 A-C-E, 用于待传输流量的 传输, 即获取每个所述节点间待传输流量的传输路径。
其中, 待传输流量在信源节点和信宿节点之间传输路径的选择取决条件 为: 各传输路径的可用带宽之和应能满足待传输流量的需求。
步骤 102: 针对每个所述节点间待传输流量, 计算两两传输路径之间的 代价值差。
其中, 每个传输路径的代价值等于传输路径中所有节点间链路的代价值 之和。仍以图 2中节点 A和节点 E为例进行说明,在节点 A到节点 E的多条 传输路径中, 分别计算各条传输路径的代价值, 其中, 每条传输路径的代价 值等于该传输路径中各条链路的代价值之和。
根据计算所得的各条传输路径的代价值, 计算每两条传输路径之间的代 价值差, 例如, 传输路径 A-D-E与传输路径 A-C-E的代价值差和与传输路径 A-D-E和传输路径 A-B-C-E的代价值差, 等等。
需要说明的是,每个节点间待传输流量的传输路径可能是 1条或者多条, 因此, 存在以下三种具体场景:
场景一: 每个节点间待传输流量至少存在 2条传输路径。 该场景为本发 明适用场景。
场景二: 一部分节点间待传输流量至少存在 2条传输路径, 另一部分节 点间待传输流量只存在 1条传输路径。 该场景中, 对只存在 1条传输路径的 节点间待传输流量, 本发明不对其进行带宽分配的调整, 仅调整存在至少 2 条传输路径的节点间待传输流量所经传输路径上带宽分配。
场景三: 每个节点间的待传输流量都只存在 1条传输路径。 本发明不适 用于该场景。
步骤 103: 根据各所述节点间待传输流量的路径代价值差, 调整各节点 间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
在步骤 101 中, 已形成待传输流量在各传输路径中分配的第一带宽分配 方案, 在某些情况下, 该第一带宽分配方案有可能不是最优的。
例如, 图 2所示的拓扑结构, 节点 A和节点 E之间待传输流量为 20G, 存在两条传输路径。 节点 B和节点 E之间的待传输流量为 10G, 也存在两条 传输路径。 将 A-E两条传输路径的代价差值, 与 B-E两条传输路径的代价差 值进行比较, 可根据比较结果调整传输路径中的带宽分配方案。 根据代价差 值调整带宽占用, 可以在满足流量需求的条件下, 使得各传输路径占用的网 络资源更加均衡化。
因此, 该步骤中, 根据各所述节点间待传输流量的路径代价值差, 调整
各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
本发明实施例通过计算拓扑结构中各节点间待传输流量的途径传输路径 的代价值差, 调整根据至少两个节点间待传输流量, 以及拓扑结构中各节点 间链路的可用带宽和代价值形成的第一带宽分配方案, 形成第二带宽分配方 案, 以实现网络出现故障或网络流量发生突变时, 能够快速实现网络流量路 径调整, 并同时保证全网满足流量需求的情况下使用的网络总代价最小, 即 使用网络资源最少, 使得业务流稳定传输。
在上述基础上, 步骤 103 : 根据各所述节点间待传输流量的路径代价值 差, 调整各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案 可以包括: 对于每个节点间待传输流量按照优先级排序的各传输路径, 将优 先级高传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成 第二带宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺 序, 与路径代价差值呈反向对应关系。
具体地, 给定拓扑结构中, 每个节点间待传输流量的各传输路径是固定 的, 按照优先级对各传输路径进行排序, 优先使用最优路径, 即优先为最优 路径分配带宽, 然后考虑其它优先级较低的传输路径。 在满足全网流量需求 的条件下, 可以将节点间待传输流量所使用的为最优路径分配的带宽, 调整 至其它优先级较低的传输路径, 形成第二带宽分配方案。
其中, 上述反向对应关系具体是指若路径代价差值越大, 则将为最优路 径分配的带宽调整至其它优先级较低的传输路径的次序越往后, 同时, 最优 路径上分配的带宽增加的次序越靠前。 例如, 在某一个节点间待传输流量的 各传输路径中, 优选使用最优路径和与最优路径的路径代价差值较小的传输 路径进行带宽分配, 例如, 仅使用最优路径, 或将分配给最优路径的部分带 宽重新分配给该与最优路径的路径代价差值较小的传输路径。 在使用最优路 径和该与最优路径的路径代价差值较小的传输路径进行带宽分配仍不满足流 量需求时, 考虑使用与最优路径的路径代价差值较大的传输路径。
举例说明反向对应关系:
1 )假设有两个节点间待传输流量, 均为 20G, 两个节点间待传输流量的 最优路径中包括共同链路, 该共同链路的可用带宽为 20G, 且平均分配给这 两个节点间待传输流量, 即每个节点间待传输流量使用 10G, 则该链路为饱
和链路, 此时, 形成第一带宽分配方案。
2)又假设第一个节点间待传输流量的最优路径和次优路径的路径代价差 值为 5, 第二个节点间待传输流量的最优路径和次优路径的路径代价差值为 10, 该场景下, 优先使用第一个节点间待传输流量的次优路径, 将分配给第 一个节点间待传输流量的最优路径的带宽调整至该次优路径, 若此时的带宽 调整值为 10G时, 即第一个节点间待传输流量仅使用自身的次优路径, 在没 有其它节点间待传输流量途径上述共同链路的条件下, 第二第一个节点间待 传输流量仅使用自身的最优路径即可满足流量需求。
本发明实施例使用网络开销增加小的传输路径替换网络开销增加大的传 输路径, 从而保证全网满足流量需求时网络资源消耗最少, 使得业务流的不 同传输路径的最大差异最小化, 减少同一个业务流的抖动幅度。
实施例二
图 3为本发明路由流量调整方法实施例二的流程示意图, 如图 3所示, 对上述实施例中形成第一带宽分配方案的操作进一步细化,该方法可以包括: 步骤 301 : 根据至少两个节点间的待传输流量, 以及拓扑结构中各节点 间链路的代价值, 获取每个所述节点间待传输流量的最优路径。
具体地, 给定拓扑结构, 则该拓扑结构中, 每相邻两个节点之间的最大 允许带宽是固定的, 各节点间链路的可用带宽小于等于该最大允许带宽; 同 时, 可获取各节点间链路的代价值, 代价值为根据网络开销参数折算转换得 到的, 其中, 网络开销参数通常指延迟、 带宽、 链路状况和跳数等。
其中, 可以通过多种形式获取每个所述节点间待传输流量的最优路径, 例如运用 Dijkstra算法。 Dijkstra算法的已知条件是整个网络拓扑和各链路的 长度。 若将已知的各链路长度改为链路延时或费用, 就相当于求任意两节点 之间具有最小时延或最小费用的路径。
在本实施例, 根据代价值, 可以运用 Dijkstra算法, 得到最优路径集。 例如, 如图 2所示, 获取 A节点到 E节点间待传输流量的最优路径和 B节点 到 E节点间待传输流量的最优路径。
步骤 302: 基于第一设定规则, 将各所述节点间待传输流量, 在对应的 最优路径中进行带宽分配。
经步骤 301计算出最优路径后, 比较最优路径中每条链路的流量需求和
可用带宽, 并根据该比较结果, 在对应的最优路径中进行带宽分配。 其中, 第一设定规则为根据用户需求预先设定的带宽分配规则, 例如, 最优路径中 链路可用带宽不满足流量需求的, 可以预先设定带宽分配比例, 或者带宽分 配权重。
步骤 303: 根据分配结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各所述节点间待传输流量。
计算为最优路径分配带宽之后拓扑结构中各节点间链路的可用带宽和代 价值, 以及剩余的节点间待传输流量。 例如, 如图 2所示的拓扑结构, A节 点到 E节点间待传输流量为 20G, 为其最优路径, 假设为 A-C-E分配 10G带 宽,则链路 A-C和 C-E的可用带宽需在为最优路径分配带宽前的可用带宽 (大 于等于 10G) 上减少 10G, 剩余的 A节点到 E节点间待传输流量为 10G。
步骤 304: 根据调整后的各所述节点间待传输流量, 以及调整后的拓扑 结构中各节点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流 量的次优路径。
其中, 次优路径的获取方式与最优路径的获取方式相同, 可以有多种形 式, 这里, 仍以 Dijkstra算法为例获取次优路径。
步骤 305: 将调整后的各所述节点间待传输流量, 在对应的次优路径中 进行带宽分配, 所述最优路径和次优路径的带宽分配方案作为第一带宽分配 方案。
根据调整后的节点间待传输流量和该时刻拓扑结构中各链路的可用带 宽, 在对应的次优路径中进行带宽分配。 例如, 如图 2所示的拓扑结构, 为 最优路径分配带宽后, A节点到 E节点间待传输流量为 10G, 假设 A节点到 E节点的次优路径的可用带宽大于等于 10G,则该次优路径的可用带宽满足 A 节点到 E节点间的流量需求, 为次优路径分配 10G带宽, 形成 A节点到 E 节点间最优路径和次优路径的第一带宽分配方案。
步骤 306: 针对每个所述节点间待传输流量, 计算两两传输路径之间的 代价值差。
具体地, 针对每个所述节点间待传输流量, 对应着至少两条传输路径, 计算该至少两条传输路径中两两传输路径之间的代价值差, 可以计算最优路 径和次优路径之间的代价值差。
步骤 307: 根据各所述节点间待传输流量的路径代价值差, 调整各节点 间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
经步骤 306计算得到的各节点间待传输流量的路径代价值差, 例如最优 路径和次优路径的路径代价值差, 调整各节点间待传输流量的第一带宽分配 方案。
其中, 步骤 301-步骤 305为对图 1中步骤 101的进一步细化。
本发明实施例通过集中路由算法, 快速计算全网最优路径, 对集中式网 络, 例如软件定义的网络 (Software Defined Network, 简称: SDN网络) , 根据拓扑结构与节点间的待传输流量, 通过查找替换饱和链路的方法, 迅速 计算出节点间的待传输流量的最优路径, 不仅为所有节点间的待传输流量计 算最优路径, 又能在很短的时间内完成; 通过最优路径替换算法, 使用网络 开销增加小的路径来替换网络开销增加大的路径, 可使全网满足流量需求时 使用的网络总代价最小, 亦即使用网络资源最少, 所以可同时使得对业务流 的不同路径的最大差异最小化, 即减少同一个流的抖动幅度, 提升网络效率 与用户体验。
在上述基础上, 步骤 307 : 根据各所述节点间待传输流量的路径代价值 差, 调整各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案 可以包括:
1、 将各所述节点间待传输流量的路径代价差值进行排序。
2、 按照路径代价差值的相反排序确定带宽调整顺序。
3、根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽 分配方案, 形成第二带宽分配方案。
在上述基础上, 步骤 302: 基于第一设定规则, 将各所述节点间待传输 流量, 在对应的最优路径中进行带宽分配可以包括:
1、将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据 链路的流量需求之和计算网络拓扑中的饱和链路。
2、 按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流 实施例三
本发明实施例三提供了一个路由流量调整方法的优选实例, 仍以图 2所
示的拓扑结构为例进行说明, 其中, 在时刻 ^, 该拓扑结构中, 各链路的可 用带宽和成本如表 1所示。
表 1
图 4为本发明路由流量调整方法实施例三的流程示意图。 如图 4所示, 该方法可以包括:
步骤 401 : 根据网络开销参数, 计算拓扑结构中每条链路的代价值。 假设时刻 ^的节点间的待传输流量为: A-E 间的待传输流量 20G, B-E 间的待传输流量是 40G。
步骤 402: 根据该节点间的待传输流量, 以及各链路的代价值, 计算 A-E 和 B-E的最优路径。
该拓扑结构中, A到 E的所有传输路径中, A-E: (A-C) (C-E)这条路 径上,代价值的和最小,为 5+10=15。由 B到 E的所有传输路径中, B-E: (B-C) (C-E)这条路径上, 代价值的和最小, 为 5+10=15。 可见, (A-C) (C-E) 与 (B-C) (C-E)两路待传输信息的传输都经过链路 (C-E)。
根据步骤 401中计算得到的拓扑结构中每条链路的代价值,运用 Dijkstra 算法, 得到 A-E的最优路径和 B-E的最优路径。
步骤 403 : 同一时刻 ^, 计算每条链路在所有最优路径中的预估占用带宽 之和。
每条链路上或许同时有至少一路待传输信息经过, 这时, 需要考虑每一 路的流量需求和该条链路的可用带宽。
考虑途径传输路径上各链路的可用带宽, 如表 1所示: (A-C) 20G, (B-C) 40G, (C-E) 30G。
链路 (A-C)与 (B-C)能满足流量需求,链路 (C-E)不满足流量需求,差额 30G (20+40-30=30) , 则根据权重或其它规则, 将该链路的可用带宽分配给各最 优路径, 并根据此可用带宽的分配结果, 重新调整各链路的可用带宽, 以及 流量需求。因此,链路 (C-E)上按预设权重为两路待传输信息分配带宽,例如, 预设权重比为 1 : 1, 即将 (C-E)可用带宽 30G进行如下分配: 为 A-E路待传 输信息分配 10G带宽, 为 B-E路待传输信息分配 20G带宽。 这样, (A-C)剩 余 10G, (B-C)剩余 20G, (C-E)剩余 0G, 并形成如图 5所示的调整后的拓扑 结构, 如表 2所示的调整后的拓扑结构中各链路的可用带宽和成本, 以及调 整后的 A-E间的待传输流量 10G和 B-E间的待传输流量 20G。
步骤 401-步骤 403为第一带宽分配方案中最优路径的带宽分配, 如图 6 所示: A-E ( 10G) : (A-C) ^ (C-E), B-E (20G) : (B-C) (C-E)。
表 2
步骤 404: 在 A-E和 B-E的剩余路径中查找最优路径 (次优路径) 。 A-E: (A-D) ^ (D-E), 代价值: 10+10=20。
B-E: (B-C) (C-D) ^ (D-E), 代价值: 5+10+10=25。
该最优路径为调整后拓扑结构的最优路径, 相对于调整前的拓扑结构, 可认为该步骤得到的最优路径为次优路径。
该步骤为第一带宽分配方案中次优路径的带宽分配, 如图 7 所示: A-E ( 10G) : (A-D) ^ (D-E), B-E (20G) : (B-C) (C-D) (D-E)。
步骤 405: 计算各节点间待传输流量对应的最优路径与次优路径的代价 值差, 并进行最优替换。
相对于最优路径, 次优路径的代价值增加:
A-E: 20-15=5。
B-E: 25-15=10。
可见, A-E的次优路径比 B-E的次优路径相对于其各自的最优路径增加 的代价值少。 因此, 较少使用 B-E的次优路径。
步骤 406: 根据代价值差的排序, 调整各最优路径和次优路径中带宽分 配。
A-E最优路径分配带宽减少, 较多使用次优路径; B-E最优路径分配带 宽增加, 较少使用其次优路径, 即:
对 A-E路待传输信息对应的 20G流量需求, 由两条路径分配完成: 最优路径: (A-C) (C-E), 经过最优替换带宽分配调整变为 10G 5G; 次优路径: (A-D) (D-E), 经过最优替换带宽分配调整变为 10G 15G。 对 B-E路待传输信息对应的 40G流量需求, 由两条路径分配完成: 最优路径: (B-C) (C-E), 经过最优替换带宽分配调整变为 20G 25G; 次优路径: (B-C)^(C-D) (D-E), 经过最优替换带宽分配调整变为
20G 15G。
步骤 405和步骤 406为第二带宽分配方案涉及的步骤, 如图 6和图 7所 示: A-E (5G) : (A-C) ^ (C-E), B-E (25G) : (B-C) ^ (C-E); A-E ( 15G) : (A-D) ^ (D-E), B-E ( 15G) : (B-C) ^ (C-D) ^ (D-E)o
本发明实施例, 通过次优路径和最优路径上带宽分配的相互调整, 以在 全网满足流量需求时消耗的网络总代价最小, 实现网络出现故障或网络流量 发生突变时, 能够快速实现网络流量路径调整, 并同时保证业务流传输的稳 定性。
有益效果: 快速响应网络流量变化, 路径迅速调整应对流量突变。
1、 流量拓扑双迭代与最优路径替换算法, 采用 Dijkstra算法计算网络最 优路径, 并迅速查找饱和链路, 不需要对网络上各条链路穷举计算, 速度非 常快。
2、 通过拓扑结构路径代价差值的比较, 优先采用增值小的路径, 可以确 保全网路径最优, 从而提升网络使用效率。
在集中式网络里, 客户网络的流量变化通常在短时间内就会完成, 从一
种流量模型转变到另一种流量模型。 例如, 中国电信的 163网络, 从早上的 流量模型变化到上午的另一种流量模型, 只需要约一个小时的时间就可以完 成。 用传统的线性规划算法就可能达不到该时间要求, 而本发明提供的路由 流量调整方法则可以在该时间要求范围内完成流量模型的转变。
另外, 在网络发生故障时, 需要发生故障的链路或者节点上的流量快速 恢复。 若采用现有技术恢复, 可能在时间上达不到响应要求, 或者恢复路径 不佳造成网络资源浪费, 甚至有些业务不能恢复, 而本发明提供的路由流量 调整方法则可以快速响应, 同时满足全网的流量需求。
实施例四
以下比较说明本发明路由流量调整方法相对于公平算法的优势: 一、 解决公平算法缺陷, 避免路径绕圈子。
如图 8所示的拓扑结构, 假设所有链路的可用带宽都为 40G, 链路标识 数字为链路距离。 流量需求为: B-E 40G, B-G 40G, A-G 20G。
1、 若采用公平算法, 由于链路 B-C为饱和链路, B-G与 B-E流量需求 各分配 50%, 得到流量分配路径如图 9所示。
B-E: 最短路径 B-C-E 20G (距离 2) ;
B-E: 次短路径 B-A-D-E 20G (距离 5.5 )
B-G: 最短路径 B-C-G 20G (距离 2) ;
B-G: 次短路径 B-A-G 20G (距离 2.5 )
A-G: 最短路径 A-G 20G (距禺 3 ) 。
由此可以看出, 流量需求 B-E的路径分配有两条, 其次短路径比最短路 径的距离要远很多, 在拓扑结构上绕圈子, 浪费网络资源; 并且同一条流两 条路径相差太大, 导致业务抖动加大, 用户体验很差。
2、 采用本发明路由流量调整方法, 流程如下:
计算路径的代价差, 即路径的距离差异:
B-G: 次优路径代价值-最优路径代价值 =3.5-2=1.5; 第三最优路径代价值 -最优路径代价值 =4.0-2=2;
B-E: 2nd -1st =5.5-2=3.5。
可见, B-G的第三最优路径增加的距离差 2, 比 B-E的次路径增加的距 离差 3.5小, 因此, 优先采用 B-G的第三最优路径, 替换 B-E的次优路径。
B-G: 次优路径 B-A-G 20G;
B-G: 第三最优路径 B-A-F-G 20G;
B-E: 最优路径 B-C-E 20G;
A-G: 最优路径 A-G 20G。
二、 解决公平算法缺陷, 流量需求不能满足。
如图 10所示, 假设各链路的带宽都为 40G, 链路代价 A-C为 1, 其余链 路都为 2。 由于流量需求 A-D的最短路径为 A-C-D, 与流量需求 A-C及 C-D 共路径, 链路 A-C与 C-D为饱和链路。
1、如果采用 Dijkstra算法与公平算法,则流量需求 A-C与 C-D只有一半 (20G) 能满足。
2、 采用本发明提供的路由流量调整方法, 流程如下:
首先, 计算传输路径的代价值差。
流量需求 A-C (20G) 次优路径-最优路径 =无穷大;
流量需求 C-D (20G) 次优路径-最优路径 =无穷大;
流量需求 A-D (20G) 次优路径-最优路径 =1, 次优路径 A-B-D, 最优路 径 A-C-D。
可见, 流量需求 A-C与 C-D都没有其它路径可用, A-D可以采用次优路 径 A-B-D来替换, 释放出来的带宽分配给流量需求 A-C和 C-D。最后的带宽 分配结果中所有流量需求都得到满足。
实施例五
图 11为本发明路由流量调整装置实施例一的结构示意图。本发明实施例 的路由流量调整装置可以集成于控制器中。如图 11所示, 本实施例的路由流 量调整装置包括第一分配模块 110、 计算模块 120和第二分配模块 130。
其中, 第一分配模块 110, 用于根据至少两个节点间的待传输流量, 以 及拓扑结构中各节点间链路的可用带宽和代价值, 分别获取每个所述节点间 待传输流量的传输路径, 形成待传输流量在各传输路径中分配的第一带宽分 配方案; 计算模块 120, 用于针对每个所述节点间待传输流量, 计算两两传 输路径之间的代价值差, 其中每个传输路径的代价值等于传输路径中所有节 点间链路的代价值之和; 第二分配模块 130, 用于根据各所述节点间待传输 流量的路径代价值差, 调整各节点间待传输流量的第一带宽分配方案, 形成
第二带宽分配方案。
本实施例的路由流量调整装置, 可以用于路由流量调整方法实施例一的 技术方案, 其实现原理和技术效果类似, 此处不再赘述。
进一步地, 所述第二分配模块 130具体用于: 对于每个节点间待传输流 量按照优先级排序的各传输路径, 将优先级高传输路径分配的带宽, 调整至 分配优先级低传输路径的带宽, 以形成第二带宽分配方案, 其中, 各节点间 待传输流量中传输路径间的带宽调整顺序,与路径代价差值呈反向对应关系。
实施例六
图 12为本发明路由流量调整装置实施例二的结构示意图,如图 12所示, 本实施例的装置在图 11 所示装置结构的基础上, 进一步地, 第一分配模块
110可以包括: 第一获取单元 111、 第一分配单元 112、 调整单元 113、 第二 获取单元 114和第二分配单元 115。
其中, 第一获取单元 111, 用于根据至少两个节点间的待传输流量, 以 及拓扑结构中各节点间链路的代价值, 获取每个所述节点间待传输流量的最 优路径; 第一分配单元 112, 用于基于第一设定规则, 将各所述节点间待传 输流量, 在对应的最优路径中进行带宽分配; 调整单元 113, 用于根据分配 结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各所述节点间待 传输流量; 第二获取单元 114, 用于根据调整后的各所述节点间待传输流量, 以及调整后的拓扑结构中各节点间链路的可用带宽和代价值, 分别获取各所 述节点间待传输流量的次优路径; 第二分配单元 115, 用于将调整后的各所 述节点间待传输流量, 在对应的次优路径中进行带宽分配, 所述最优路径和 次优路径的带宽分配方案作为第一带宽分配方案。
本实施例的装置, 可以用于执行图 3所示方法实施例的技术方案, 其实 现原理和技术效果类似, 此处不再赘述。
进一步地, 计算模块 120具体用于: 针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价值差。
更进一步地, 第二分配模块 130具体用于: 将各所述节点间待传输流量 的路径代价差值进行排序;按照路径代价差值的相反排序确定带宽调整顺序; 根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分配方 案, 形成第二带宽分配方案。
进一步地, 第一分配单元 112具体用于: 将各节点间待传输流量作为流 量需求映射至各所述最优路径中, 根据链路的流量需求之和计算网络拓扑中 的饱和链路; 按照预设权重将所述饱和链路的可用带宽分配给各节点间待传 输流量。
更进一步地, 所述计算模块 120还可以用于根据网络开销参数, 计算拓 扑结构中每条链路的代价值。
实施例七
图 13为本发明控制器实施例一的结构示意图, 如图 13所示, 本实施例 的控制器包括: 处理器 100和计算器 200。
其中, 处理器 100用于根据至少两个节点间的待传输流量, 以及拓扑结 构中各节点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流 量的传输路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案; 计算器 200, 用于针对每个所述节点间待传输流量, 计算两两传输路径之间 的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路的 代价值之和; 处理器 100还用于根据各所述节点间待传输流量的路径代价值 差, 调整各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
进一步地, 处理器 100可以具体用于: 对于每个节点间待传输流量按照 优先级排序的各传输路径, 将优先级高传输路径分配的带宽, 调整至分配优 先级低传输路径的带宽, 以形成第二带宽分配方案, 其中, 各节点间待传输 流量中传输路径间的带宽调整顺序, 与路径代价差值呈反向对应关系。
进一步地, 处理器 100还可以具体用于: 根据至少两个节点间的待传输 流量, 以及拓扑结构中各节点间链路的代价值, 获取每个所述节点间待传输 流量的最优路径; 基于第一设定规则, 将各所述节点间待传输流量, 在对应 的最优路径中进行带宽分配; 根据分配结果调整所述拓扑结构中各节点间链 路的可用带宽, 并调整各所述节点间待传输流量; 根据调整后的各所述节点 间待传输流量, 以及调整后的拓扑结构中各节点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流量的次优路径; 以及, 将调整后的各所述节 点间待传输流量, 在对应的次优路径中进行带宽分配, 所述最优路径和次优 路径的带宽分配方案作为第一带宽分配方案。
进一步地, 计算器 200可以具体用于: 针对每个所述节点间待传输流量,
计算最优路径和次优路径之间的代价值差。
更进一步地, 处理器 100还可以具体用于: 将各所述节点间待传输流量 的路径代价差值进行排序;按照路径代价差值的相反排序确定带宽调整顺序; 根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分配方 案, 形成第二带宽分配方案。
另外, 处理器 100可以具体用于:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路; 按照预设权重将所述饱和链 路的可用带宽分配给各节点间待传输流量。
更进一步地, 计算器 200还可以用于根据网络开销参数, 计算拓扑结构 中每条链路的代价值。
上述控制器可以执行前述方法实施例, 其实现原理类似, 在此不再赘述。 本领域普通技术人员可以理解: 实现上述各方法实施例的全部或部分步 骤可以通过程序指令相关的硬件来完成。 前述的程序可以存储于一计算机可 读取存储介质中。 该程序在执行时, 执行包括上述各方法实施例的步骤; 而 前述的存储介质包括: ROM、 RAM,磁碟或者光盘等各种可以存储程序代码 的介质。
最后应说明的是: 以上各实施例仅用以说明本发明的技术方案, 而非对 其限制; 尽管参照前述各实施例对本发明进行了详细的说明, 本领域的普通 技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改, 或者对其中部分或者全部技术特征进行等同替换; 而这些修改或者替换, 并 不使相应技术方案的本质脱离本发明各实施例技术方案的范围。
Claims
1、 一种路由流量调整方法, 其特征在于, 包括:
根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的可 用带宽和代价值, 分别获取每个所述节点间待传输流量的传输路径, 形成待 传输流量在各传输路径中分配的第一带宽分配方案;
针对每个所述节点间待传输流量, 计算两两传输路径之间的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路的代价值之和; 根据各所述节点间待传输流量的路径代价值差, 调整各节点间待传输流 量的第一带宽分配方案, 形成第二带宽分配方案。
2、 根据权利要求 1所述的方法, 其特征在于, 根据各所述节点间待传输 流量的路径代价值差, 调整各节点间待传输流量的第一带宽分配方案, 形成 第二带宽分配方案包括:
对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
3、 根据权利要求 1或 2所述的方法, 其特征在于, 根据至少两个节点间 的待传输流量, 以及拓扑结构中各节点间链路的可用带宽和代价值, 分别获 取每个所述节点间待传输流量的传输路径, 形成待传输流量在各传输路径中 分配的第一带宽分配方案包括:
根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的代 价值, 获取每个所述节点间待传输流量的最优路径;
基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中 进行带宽分配;
根据分配结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各 所述节点间待传输流量;
根据调整后的各所述节点间待传输流量, 以及调整后的拓扑结构中各节 点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流量的次优路 径;
将调整后的各所述节点间待传输流量, 在对应的次优路径中进行带宽分
配, 所述最优路径和次优路径的带宽分配方案作为第一带宽分配方案。
4、 根据权利要求 3所述的方法, 其特征在于, 针对每个所述节点间待传 输流量, 计算两两传输路径之间的代价值差包括:
针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价 值差。
5、 根据权利要求 4所述的方法, 其特征在于, 根据各所述节点间待传输 流量的路径代价值差, 调整各节点间待传输流量的第一带宽分配方案, 形成 第二带宽分配方案包括:
将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
6、 根据权利要求 3所述的方法, 其特征在于, 基于第一设定规则, 将各 所述节点间待传输流量, 在对应的最优路径中进行带宽分配包括:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。
7、 根据权利要求 1-6任一项所述的方法, 其特征在于, 根据至少两个节 点间的待传输流量, 以及拓扑结构中各节点间链路的可用带宽和代价值, 分 别获取每个所述节点间待传输流量的传输路径, 形成待传输流量在各传输路 径中分配的第一带宽分配方案之前, 还包括:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
8、 一种路由流量调整装置, 其特征在于, 包括:
第一分配模块, 用于根据至少两个节点间的待传输流量, 以及拓扑结构 中各节点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量 的传输路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案; 计算模块, 用于针对每个所述节点间待传输流量, 计算两两传输路径之 间的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路 的代价值之和;
第二分配模块, 用于根据各所述节点间待传输流量的路径代价值差, 调
整各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
9、 根据权利要求 8所述的装置, 其特征在于, 所述第二分配模块具体用 于:
对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
10、 根据权利要求 8或 9所述的装置, 其特征在于, 所述第一分配模块 包括:
第一获取单元, 用于根据至少两个节点间的待传输流量, 以及拓扑结构 中各节点间链路的代价值, 获取每个所述节点间待传输流量的最优路径; 第一分配单元, 用于基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中进行带宽分配;
调整单元, 用于根据分配结果调整所述拓扑结构中各节点间链路的可用 带宽, 并调整各所述节点间待传输流量;
第二获取单元, 用于根据调整后的各所述节点间待传输流量, 以及调整 后的拓扑结构中各节点间链路的可用带宽和代价值, 分别获取各所述节点间 待传输流量的次优路径;
第二分配单元, 用于将调整后的各所述节点间待传输流量, 在对应的次 优路径中进行带宽分配, 所述最优路径和次优路径的带宽分配方案作为第一 带宽分配方案。
11、根据权利要求 10所述的装置,其特征在于,所述计算模块具体用于: 针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价 值差。
12、 根据权利要求 11所述的装置, 其特征在于, 所述第二分配模块具体 用于:
将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
13、 根据权利要求 10所述的装置, 其特征在于, 所述第一分配单元具体 用于:
将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。
14、 根据权利要求 8-13任一项所述的装置, 其特征在于, 所述计算模块 还用于:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
15、 一种控制器, 其特征在于, 包括:
处理器, 用于根据至少两个节点间的待传输流量, 以及拓扑结构中各节 点间链路的可用带宽和代价值, 分别获取每个所述节点间待传输流量的传输 路径, 形成待传输流量在各传输路径中分配的第一带宽分配方案;
计算器, 用于针对每个所述节点间待传输流量, 计算两两传输路径之间 的代价值差, 其中每个传输路径的代价值等于传输路径中所有节点间链路的 代价值之和;
所述处理器还用于根据各所述节点间待传输流量的路径代价值差, 调整 各节点间待传输流量的第一带宽分配方案, 形成第二带宽分配方案。
16、根据权利要求 15所述的控制器,其特征在于,所述处理器具体用于: 对于每个节点间待传输流量按照优先级排序的各传输路径, 将优先级高 传输路径分配的带宽, 调整至分配优先级低传输路径的带宽, 以形成第二带 宽分配方案, 其中, 各节点间待传输流量中传输路径间的带宽调整顺序, 与 路径代价差值呈反向对应关系。
17、 根据权利要求 15或 16所述的控制器, 其特征在于, 所述处理器具 体用于:
根据至少两个节点间的待传输流量, 以及拓扑结构中各节点间链路的代 价值, 获取每个所述节点间待传输流量的最优路径;
基于第一设定规则, 将各所述节点间待传输流量, 在对应的最优路径中 进行带宽分配;
根据分配结果调整所述拓扑结构中各节点间链路的可用带宽, 并调整各 所述节点间待传输流量;
根据调整后的各所述节点间待传输流量, 以及调整后的拓扑结构中各节 点间链路的可用带宽和代价值, 分别获取各所述节点间待传输流量的次优路 径;
将调整后的各所述节点间待传输流量, 在对应的次优路径中进行带宽分 配, 所述最优路径和次优路径的带宽分配方案作为第一带宽分配方案。
18、根据权利要求 17所述的控制器,其特征在于,所述计算器具体用于: 针对每个所述节点间待传输流量, 计算最优路径和次优路径之间的代价 值差。
19、根据权利要求 18所述的控制器,其特征在于,所述处理器具体用于: 将各所述节点间待传输流量的路径代价差值进行排序;
按照路径代价差值的相反排序确定带宽调整顺序;
根据确定的带宽调整顺序, 分别调整各节点间待传输流量的第一带宽分 配方案, 形成第二带宽分配方案。
20、根据权利要求 17所述的控制器,其特征在于,所述处理器具体用于: 将各节点间待传输流量作为流量需求映射至各所述最优路径中, 根据链 路的流量需求之和计算网络拓扑中的饱和链路;
按照预设权重将所述饱和链路的可用带宽分配给各节点间待传输流量。
21、 根据权利要求 15-20任一项所述的控制器, 其特征在于, 所述计算 器还用于:
根据网络开销参数, 计算拓扑结构中每条链路的代价值。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2013/081459 WO2015021615A1 (zh) | 2013-08-14 | 2013-08-14 | 路由流量调整方法、装置及控制器 |
CN201380001093.3A CN103650435B (zh) | 2013-08-14 | 2013-08-14 | 路由流量调整方法、装置及控制器 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2013/081459 WO2015021615A1 (zh) | 2013-08-14 | 2013-08-14 | 路由流量调整方法、装置及控制器 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015021615A1 true WO2015021615A1 (zh) | 2015-02-19 |
Family
ID=50253424
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2013/081459 WO2015021615A1 (zh) | 2013-08-14 | 2013-08-14 | 路由流量调整方法、装置及控制器 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN103650435B (zh) |
WO (1) | WO2015021615A1 (zh) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111510383A (zh) * | 2019-01-31 | 2020-08-07 | 华为技术有限公司 | 一种路由计算方法以及相关设备 |
CN112583729A (zh) * | 2019-09-27 | 2021-03-30 | 华为技术有限公司 | 一种路径的流量分配方法、网络设备及网络系统 |
CN113098772A (zh) * | 2021-03-25 | 2021-07-09 | 中国联合网络通信集团有限公司 | 数据传输路径的确定方法及装置 |
CN113852570A (zh) * | 2021-09-23 | 2021-12-28 | 北京金山云网络技术有限公司 | 推荐节点带宽生成方法、装置、设备和计算机可读介质 |
CN114205283A (zh) * | 2021-12-16 | 2022-03-18 | 赫里奥(苏州)科技有限公司 | 物联网异构网络拓扑建立方法、网络及最优路径计算方法 |
Families Citing this family (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105897584B (zh) * | 2014-06-09 | 2018-11-30 | 华为技术有限公司 | 路径规划方法和控制器 |
CN104009915B (zh) * | 2014-06-09 | 2017-12-01 | 北京邮电大学 | 一种利用带宽分配简化网络的路由方法 |
WO2015196494A1 (zh) * | 2014-06-28 | 2015-12-30 | 华为技术有限公司 | 一种路径计算的方法和装置 |
CN104301256B (zh) * | 2014-10-31 | 2018-10-09 | 新华三技术有限公司 | 一种sdn网络动态预留带宽的方法及控制器 |
CN105656778B (zh) * | 2014-11-11 | 2019-11-19 | 中兴通讯股份有限公司 | 调用路由算法的方法及sdn控制器和sdn-oaf |
CN104378380A (zh) * | 2014-11-26 | 2015-02-25 | 南京晓庄学院 | 一种基于SDN架构的识别与防护DDoS攻击的系统及方法 |
US9866483B2 (en) * | 2015-07-20 | 2018-01-09 | Schweitzer Engineering Laboratories, Inc. | Routing of traffic in network through automatically generated and physically distinct communication paths |
CN105207908B (zh) * | 2015-09-30 | 2018-09-18 | 浪潮(北京)电子信息产业有限公司 | 一种报文处理方法及系统 |
US20180205660A1 (en) * | 2017-01-19 | 2018-07-19 | Futurewei Technologies, Inc. | Apparatus and method for controlling usage of a non-optimal path |
CN107135159B (zh) * | 2017-03-31 | 2019-11-22 | 武汉绿色网络信息服务有限责任公司 | 一种sdn网络中最优路径确定的方法和系统 |
US11190437B2 (en) * | 2017-12-21 | 2021-11-30 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods, apparatus and computer programs for allocating traffic in a telecommunications network |
US11258877B2 (en) | 2018-07-26 | 2022-02-22 | Netapp, Inc. | Methods for managing workloads in a storage system and devices thereof |
US10644957B1 (en) * | 2019-03-01 | 2020-05-05 | Juniper Networks, Inc. | Centralized controller-based dynamic network bandwidth allocation and management |
CN111694902B (zh) * | 2019-03-11 | 2023-04-07 | 阿里巴巴集团控股有限公司 | 差异路径识别方法、装置、电子设备及计算机存储介质 |
CN115567450A (zh) * | 2019-09-06 | 2023-01-03 | 华为技术有限公司 | 一种网络设备 |
CN111245720B (zh) * | 2020-01-03 | 2021-10-26 | 烽火通信科技股份有限公司 | 一种路径计算方法及系统 |
CN114071636B (zh) * | 2021-10-28 | 2024-07-09 | 浪潮通信信息系统有限公司 | 链路分配方法及装置 |
CN113890829B (zh) * | 2021-11-19 | 2024-06-11 | 中徽建技术有限公司 | 一种网络虚拟化资源分配方法及系统 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101399748A (zh) * | 2007-09-25 | 2009-04-01 | 华为技术有限公司 | 路由计算方法和路由器 |
CN101562556A (zh) * | 2008-04-15 | 2009-10-21 | 华为技术有限公司 | 一种降低网络编码代价的方法、装置及系统 |
CN101651600A (zh) * | 2008-08-14 | 2010-02-17 | 中国移动通信集团设计院有限公司 | 网格网络中更新链路代价的方法和装置 |
US20110134769A1 (en) * | 2009-12-08 | 2011-06-09 | Seungjoon Lee | Multi-path load balancing using route controller |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7027403B2 (en) * | 2001-05-22 | 2006-04-11 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for minimizing error in bandwidth allocation with an optimal number of renegotiations |
US7630401B2 (en) * | 2005-04-28 | 2009-12-08 | Sony Corporation | Bandwith management in a network |
CN101945434B (zh) * | 2009-07-03 | 2014-06-04 | 华为技术有限公司 | 实现负载均衡的方法、装置和系统 |
-
2013
- 2013-08-14 WO PCT/CN2013/081459 patent/WO2015021615A1/zh active Application Filing
- 2013-08-14 CN CN201380001093.3A patent/CN103650435B/zh active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101399748A (zh) * | 2007-09-25 | 2009-04-01 | 华为技术有限公司 | 路由计算方法和路由器 |
CN101562556A (zh) * | 2008-04-15 | 2009-10-21 | 华为技术有限公司 | 一种降低网络编码代价的方法、装置及系统 |
CN101651600A (zh) * | 2008-08-14 | 2010-02-17 | 中国移动通信集团设计院有限公司 | 网格网络中更新链路代价的方法和装置 |
US20110134769A1 (en) * | 2009-12-08 | 2011-06-09 | Seungjoon Lee | Multi-path load balancing using route controller |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111510383A (zh) * | 2019-01-31 | 2020-08-07 | 华为技术有限公司 | 一种路由计算方法以及相关设备 |
CN111510383B (zh) * | 2019-01-31 | 2023-03-24 | 华为技术有限公司 | 一种路由计算方法以及相关设备 |
CN112583729A (zh) * | 2019-09-27 | 2021-03-30 | 华为技术有限公司 | 一种路径的流量分配方法、网络设备及网络系统 |
CN112583729B (zh) * | 2019-09-27 | 2023-11-28 | 华为技术有限公司 | 一种路径的流量分配方法、网络设备及网络系统 |
CN113098772A (zh) * | 2021-03-25 | 2021-07-09 | 中国联合网络通信集团有限公司 | 数据传输路径的确定方法及装置 |
CN113098772B (zh) * | 2021-03-25 | 2022-11-22 | 中国联合网络通信集团有限公司 | 数据传输路径的确定方法及装置 |
CN113852570A (zh) * | 2021-09-23 | 2021-12-28 | 北京金山云网络技术有限公司 | 推荐节点带宽生成方法、装置、设备和计算机可读介质 |
CN114205283A (zh) * | 2021-12-16 | 2022-03-18 | 赫里奥(苏州)科技有限公司 | 物联网异构网络拓扑建立方法、网络及最优路径计算方法 |
CN114205283B (zh) * | 2021-12-16 | 2023-08-29 | 赫里奥(苏州)科技有限公司 | 物联网异构网络拓扑建立方法、网络及最优路径计算方法 |
Also Published As
Publication number | Publication date |
---|---|
CN103650435B (zh) | 2016-11-09 |
CN103650435A (zh) | 2014-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2015021615A1 (zh) | 路由流量调整方法、装置及控制器 | |
US9923798B1 (en) | Dynamic load balancing of network traffic on a multi-path label switched path using resource reservation protocol with traffic engineering | |
CN103746931B (zh) | 一种用于计算机网络的方法、网络设备及服务卡 | |
KR100411251B1 (ko) | 제한조건을 만족하는 다중 경로 배정방법 | |
US8493869B2 (en) | Distributed constraints-based inter-domain network traffic management | |
CN104994033A (zh) | 一种资源动态管理的SDN网络QoS保障方法 | |
CN103607358B (zh) | 基于链路利用率平均和的动态ecmp 方法及系统 | |
CN103685054A (zh) | 基于业务感知的多路径负载均衡方法 | |
CN106209669A (zh) | 面向sdn数据中心网络最大概率路径流调度方法及装置 | |
CN103346979B (zh) | 一种spbm网络中的流量分配方法及设备 | |
CN108833279A (zh) | 软件定义网络中基于业务分类的多约束QoS路由的方法 | |
Walkowiak et al. | Dynamic routing of anycast and unicast traffic in elastic optical networks | |
Tomovic et al. | Toward a scalable, robust, and QoS-aware virtual-link provisioning in SDN-based ISP networks | |
CN108768713A (zh) | SDN中的一种保障QoS动态路由算法 | |
Celenlioglu et al. | An SDN based intra-domain routing and resource management model | |
CN109672621A (zh) | 一种为vpn业务选择传输路径的方法和设备 | |
Ren et al. | A SDN-based dynamic traffic scheduling algorithm | |
Seliuchenko et al. | Enhanced multi-commodity flow model for QoS-aware routing in SDN | |
Bharanidharan et al. | An enhanced framework for traffic load balancing and QoS provisioning in SDN | |
Saad et al. | Optimal network rate allocation under end-to-end quality-of-service requirements | |
Cheng et al. | Application-aware routing scheme for SDN-based cloud datacenters | |
CN105207906B (zh) | 一种业务路径确定方法及装置 | |
CN112615750A (zh) | 一种基于sdn的骨干网流量粒度调整系统和方法 | |
CN108174446B (zh) | 一种资源占用度最小化的网络节点链路资源联合分配方法 | |
CN104917677A (zh) | 数据流转发的控制方法及系统 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13891427 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13891427 Country of ref document: EP Kind code of ref document: A1 |