CN115102831A - Method and system for deploying distributed BGP (Border gateway protocol) service - Google Patents
Method and system for deploying distributed BGP (Border gateway protocol) service Download PDFInfo
- Publication number
- CN115102831A CN115102831A CN202210895454.4A CN202210895454A CN115102831A CN 115102831 A CN115102831 A CN 115102831A CN 202210895454 A CN202210895454 A CN 202210895454A CN 115102831 A CN115102831 A CN 115102831A
- Authority
- CN
- China
- Prior art keywords
- bgp
- service
- resource management
- network
- services
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/04—Network management architectures or arrangements
- H04L41/042—Network management architectures or arrangements comprising distributed management centres cooperatively managing the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0893—Assignment of logical groups to network elements
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of communication, and provides a method and a system for deploying distributed BGP services. Wherein the method comprises: establishing a plurality of minimum resource management units according to the network resources and the network topology of the whole network; according to the service affinity between the minimum resource management units, network resource convergence is carried out on the minimum resource management units with high service affinity to obtain corresponding converged resource management units; and deploying the distributed BGP service according to the aggregation resource management unit. The invention deploys the BGP service according to the service affinity, thereby subordinately transmitting the equipment or resources with closer service to the nano-tubes of the same BGP service, only influencing the BGP service of the network area when the corresponding equipment or resources are in failure, and not influencing the normal transmission of the services of other areas, thereby realizing the resource isolation and the failure isolation.
Description
Technical Field
The present invention belongs to the field of communications technologies, and in particular, to a method and a system for deploying a distributed BGP service.
Background
As networks become larger, network architectures have gradually changed from a traditional control-by-control network architecture form to a distributed network architecture, in which a Border Gateway Protocol (BGP) is essential.
In a conventional distributed BGP service, the deployed service quantity and service resources are fixedly set at an initial stage of network construction, and are generally deployed according to a maximum specification preset by a network, and when the service quantity does not meet an expectation, the service resources are wasted. In addition, a specific rule does not exist in conventional distributed BGP service deployment, which causes resources of a whole network to be used by each BGP service in a crossed manner, and resource isolation and fault isolation of a network cannot be realized, under such a condition, once a network resource is adjusted, adjustment of multiple BGP services is required, or once a single network resource fails, multiple BGP services may be affected, in particular, in a cloud data center, a tenant is leased in a form of a virtual terminal, a virtual private network is usually formed under a single tenant, service interaction inside the virtual private network is far more frequent than external interaction, at this time, it is usually desired that adjustment inside the virtual BGP private network does not affect other virtual private networks, that is, resource isolation and fault isolation, and a conventional distributed BGP service deployment manner cannot meet dynamic deployment requirements of services of the cloud data center.
In view of the above, overcoming the drawbacks of the prior art is an urgent problem in the art.
Disclosure of Invention
The technical problem to be solved by the invention is that the existing BGP service deployment method can not realize resource isolation and fault isolation.
The invention adopts the following technical scheme:
in a first aspect, the present invention provides a method for deploying a distributed BGP service, including:
establishing a plurality of minimum resource management units according to the network resources and the network topology of the whole network;
according to the service affinity between the minimum resource management units, network resource convergence is carried out on the minimum resource management units with high service affinity to obtain corresponding converged resource management units;
deploying distributed BGP services according to the aggregation resource management unit; one BGP service corresponds to one converged resource management unit, and manages network resources under the corresponding converged resource management unit.
Preferably, the network resource aggregation is performed on the minimum resource management units with high affinity to each other according to the affinity between the minimum resource management units to obtain corresponding aggregated resource management units, and the method specifically includes:
taking the first resource management unit meeting the convergence condition as a second resource management unit, calculating the service affinity between any two second resource management units, and converging network resources of the two second resource management units with the highest service affinity to each other to obtain a third resource management unit;
replacing two first resource management units for network convergence by a third resource management unit obtained by network resource convergence for the last time, and iteratively converging network resources for the next time until the number of the second resource management units is less than two, or the total number of the first resource management units and the third resource management units is less than or equal to the preset number; the minimum resource management unit is used as a first resource management unit when network resources are converged for the first time;
and obtaining a first resource management unit and a third resource management unit after the iteration is finished, namely the corresponding converged resource management units.
Preferably, the calculating the service affinity between any two second resource management units specifically includes:
calculating the service affinity between the network resources of the same type in the two second resource management units;
and taking the weighted sum of the service affinities of all types of network resources in the two second resource management units as the service affinities of the two corresponding second resource management units.
Preferably, when a network resource addition occurs in the network, the method further includes:
dynamic capacity expansion is performed on BGP services, and, in particular,
judging whether the quantity of BGP services needs to be increased or not according to the load condition of each BGP service;
if the quantity of the BGP services does not need to be increased, selecting the corresponding BGP services from the deployed BGP services to manage the newly added network resources;
and if the quantity of the BGP services needs to be increased, redeploying the distributed BGP services according to the business affinity.
Preferably, the determining whether the number of the BGP services needs to be increased according to the load condition of each BGP service specifically includes:
and if the number proportion of the BGP services of which the corresponding loads exceed the first preset load threshold value exceeds the preset proportion and/or the load variance calculated by the loads of all the BGP services exceeds the preset variance threshold value in all the BGP services, increasing the number of the BGP services.
Preferably, the selecting a corresponding BGP service from the deployed BGP services to manage the newly added network resource specifically includes:
in the deployed first BGP service, taking the BGP service with the corresponding load lower than a second preset load threshold value as a second BGP service;
and calculating the service affinity of the newly added network resource and each second BGP service, and selecting the second BGP service with the highest service affinity to manage the newly added network resource.
Preferably, the redeploying the distributed BGP service according to the service affinity specifically includes:
for the newly added network resource, directly publishing a route corresponding to the newly added network resource when the distributed BGP service is redeployed;
for existing network resources in the network, a route deletion message is published by using the undeployed distributed BGP service, a new route is published by using the redeployed distributed BGP service, and route updating and route decision are processed in a delayed mode.
Preferably, when network resource pruning occurs in the network, the method further comprises:
dynamic profiling of BGP services is performed, specifically,
and if the load of the corresponding BGP service is lower than a third preset load threshold value, the network resources managed by the BGP service are managed by other BGP services, and the BGP service is deleted.
Preferably, the method further comprises:
judging whether the BGP service is abnormal or not according to the connection state and the health state of the BGP service;
and deleting the abnormal BGP service and releasing the corresponding network resources.
In a second aspect, the present invention further provides a deployment system of a distributed BGP service, including an acquisition module, a BGP service policy module, and a BGP service deployment module, where:
the acquisition module is used for acquiring the network resources and the network topology of the whole network;
the BGP service strategy module is used for calculating the quantity of BGP services and corresponding network resources;
and the BGP service deployment module is used for deploying the distributed BGP services according to the calculated quantity of the BGP services and the corresponding network resources.
In a third aspect, the present invention further provides a distributed BGP service deployment apparatus, configured to implement the distributed BGP service deployment method according to the first aspect, where the apparatus includes:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the processor to perform the method for deploying a distributed BGP service of the first aspect.
In a fourth aspect, the present invention further provides a non-transitory computer storage medium storing computer-executable instructions, which are executed by one or more processors, for implementing the method for deploying a distributed BGP service according to the first aspect.
The invention deploys the BGP service according to the service affinity, thereby subordinate the equipment or resources with closer service forwarding to the nano-tube of the same BGP service, only influencing the BGP service of the network area in which the equipment or resources are located when the corresponding equipment or resources are in failure, and not influencing the normal forwarding of the services of other areas, thereby realizing resource isolation and failure isolation.
Drawings
Fig. 1 is a schematic flowchart of a deployment method of a distributed BGP service according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a deployment method of a distributed BGP service according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a CLOS network according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for deploying a distributed BGP service according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating a method for deploying a distributed BGP service according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating attributes included in elements in a resource management unit set according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating a method for deploying a distributed BGP service according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a load indicator of a BGP service provided by an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a deployment system of a distributed BGP service according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of a deployment system of a distributed BGP service according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of a deployment apparatus of a distributed BGP service according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the respective embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1:
an embodiment of the present invention provides a method for deploying a distributed BGP service, where as shown in fig. 1, the method includes:
in step 201, a plurality of minimum resource management units are established according to the network resources and the network topology of the whole network.
The minimum resource management unit corresponds to the minimum BGP service management unit and network resources of the corresponding minimum BGP service management unit.
The minimum resource management unit is not an entity which actually acts, but is an alternative conceptual expression, and the minimum resource management unit is used for representing the corresponding minimum BGP service management unit and the network resource corresponding to the minimum BGP service management unit. The network resources and the minimum BGP service management element may be represented using respective attributes, which may be represented using respective sets of attributes. The minimum BGP service management unit is a minimum unit that can be managed by a single BGP service when constructing a distributed BGP service in a network, and is usually set by those skilled in the art according to analysis of the network size and BGP service management requirements. As in a cloud data center, the minimum BGP service management unit is at least one of a virtual private network, a virtual switch, or a virtual termination.
In step 202, according to the service affinity between the minimum resource management units, network resources are aggregated for the minimum resource management units with high service affinity to each other, so as to obtain corresponding aggregated resource management units.
For example, for a cloud data center, the cloud data center is generally divided into a plurality of virtual private networks, and a service forwarding frequency of a virtual terminal located in the same virtual private network is usually higher than that of a virtual terminal in a different virtual private network, that is, the service affinity is relatively close in the service forwarding process. For a large network, the service forwarding frequency between terminals in the same subnet or the same switch is usually higher than the service forwarding frequency between terminals in different subnets or different switches, i.e. it is relatively close in the service forwarding process. And the relative service affinity related to resource intersection in the service forwarding process is higher by analyzing the service forwarding level. For example, terminals located under the same switch all relate to resource usage of the same switch during service forwarding, that is, there is resource intersection during service forwarding, and it is also considered that the service affinity is higher. The service affinity may be used to represent a regional division of the network.
The service affinity is not separately for the minimum resource management unit and the minimum BGP service management unit, and there may be a service affinity between entities that contain or represent network resources or network devices. For example, for the minimum resource management unit, the service affinity is the service affinity calculated by the minimum BGP service management unit that it represents.
In step 203, deploying distributed BGP services according to the converged resource management unit; one BGP service corresponds to one converged resource management unit, and manages network resources under the corresponding converged resource management unit.
The step of network resource aggregation specifically refers to merging network resources in one or more minimum resource management units, where an aggregated resource management unit obtained after merging is used to represent one or more minimum BGP service management units and all network resources of the corresponding one or more minimum BGP service management units.
The network resources under the corresponding aggregated resource management unit of the nano-tube are specifically the minimum BGP service management unit managed by the corresponding BGP service and the network resources corresponding to the minimum BGP service management unit.
In this embodiment, the BGP service is deployed according to the service affinity, so that devices or resources with relatively close service forwarding belong to the same BGP service nanotube, and when a corresponding device or resource fails, only the BGP service in the network area is affected, without affecting normal forwarding of services in other areas, thereby implementing resource isolation and fault isolation.
In the foregoing embodiment, one of the most common implementation manners of performing network resource aggregation on the minimum resource management units with high service affinity according to the service affinity between the minimum resource management units is as follows: calculating the service affinity between any two minimum resource management units, converging the network resources of the two minimum resource management units with the highest service affinity, calculating the service affinity aiming at the minimum resource management units without network resource convergence, selecting two minimum resource management units for network resource convergence, and sequentially carrying out the service affinity until all the minimum resource management units carry out network resource convergence or only the rest minimum resource management units do not carry out network resource convergence. In this implementation, the number of BGP services must be the number of minimum resource management units divided by 2, or the number of minimum resource management units divided by 2 plus 1. This greatly limits the deployment flexibility of BGP services, and also represents an excessive waste of BGP services in the case of very small network resources corresponding to the minimum resource management unit. To solve this problem, in combination with the above embodiments, there is a preferred embodiment that, according to the affinity between the minimum resource management units, network resource aggregation is performed on the minimum resource management units with high affinity to each other, so as to obtain corresponding aggregated resource management units, as shown in fig. 2, specifically including:
in step 301, the first resource management unit that meets the convergence condition is used as a second resource management unit, the service affinity between any two second resource management units is calculated, and the two second resource management units with the highest service affinity therebetween are subjected to network resource convergence to obtain a third resource management unit.
In step 302, the third resource management unit obtained by aggregating the network resources at the previous time replaces two first resource management units for network aggregation, and the network resources are iteratively aggregated at the next time until the number of the second resource management units is less than two, or the total number of the first resource management units and the third resource management units is less than or equal to the preset number; the minimum resource management unit is used as a first resource management unit when network resources are converged for the first time.
In step 303, the first resource management unit and the third resource management unit obtained after the iteration is completed are the corresponding converged resource management units.
The replacement of the two first resource management units performing network convergence by the third resource management unit obtained by performing network resource convergence at the previous time specifically includes: and discarding the two first resource management units for network convergence, and taking the obtained third resource management unit as the first resource management unit to participate in the subsequent iterative process of network resource convergence.
The aggregation condition and the preset quantity are obtained by common analysis of technical personnel in the field according to BGP service management requirements and network resources, and the resource quantity managed by a single BGP service is limited by formulating the aggregation condition, so that the load of the BGP service is controlled. The distribution degree of BGP service is controlled by formulating a preset quantity.
The preset number can also be set by a user, and when the preset number is set by the user, the preset number is greater than or equal to a minimum preset number threshold set by a person skilled in the art, so as to ensure the minimum distribution degree of the BGP service.
The aggregation condition may be that the number of smallest BGP service management units represented in the first resource management unit does not exceed a corresponding number. A more precise implementation is that the aggregation condition is that the number of the network resources of the corresponding type in the first resource management unit is less than or equal to a preset resource number threshold; wherein, the preset resource quantity threshold is obtained by a person skilled in the art according to BGP service management requirements and network resource analysis. Multiple types of network resources may exist under one minimum resource management unit, and the judgment of the convergence condition for which type of network resources is specifically performed is also obtained by analyzing according to the BGP service management requirement by a person skilled in the art. The convergence condition judgment can be performed for one type of network resources, and also can be performed for multiple types of network resources.
To facilitate understandingIn the following, the iterative partial key process will be illustrated using corresponding sets and elements, and a set G is established using a minimum resource management unit as an element, where each element is G i Where i is the ordinal number of the corresponding element.
When the network convergence is carried out for the nth time, m elements exist in the set G, if G i1 And g i2 Meeting the convergence condition, and calculating to obtain the highest service affinity, and then g i1 And g i2 Network resource convergence is carried out to obtain g k G is mixing i1 And g i2 Deleting G from the set G k And inserting the elements into the set G, wherein the number of the elements in the set G is m-1 when the n +1 th network convergence is performed, performing network convergence by using the m-1 sets G, and judging whether the elements meet convergence conditions or not when network convergence is performed each time. When the first aggregation is carried out, the elements in the set G are all the minimum resource management units, and after the iteration is finished, each element in the set represents one aggregated resource management unit.
In the preferred embodiment, the third resource management unit obtained by aggregation is also involved in subsequent aggregation in a manner of performing network resource aggregation iteratively, and the two resource management units with the highest service affinity are aggregated each time, so that the service affinity between the minimum BGP service management units managed by a single BGP service nano-tube is ensured to be higher than the service affinity between the minimum BGP service management units managed by different BGP service nano-tubes. And the load of the BGP service and the quantity of the BGP service are controlled through the convergence condition and the preset quantity, so that the high isolation of resources and faults in the network is ensured on the basis that the distribution degree of the BGP service is adjustable.
In the above embodiment, one conceivable implementation manner of calculating the service affinity between any two second resource management units is as follows:
according to the network topology, dividing a multi-level network area set, setting a corresponding affinity value for each network area, and according to the network areas where any two minimum BGP service management units are located, determining the service affinity between the two minimum BGP service management units, namely the service affinity between the corresponding minimum resource management units.
If the affinity value is set to a for the virtual private network and b for the virtual private network, when the two minimum BGP service management units belong to the same virtual private network but do not belong to the same virtual private network, the service affinity between the two minimum BGP service management units is a, that is, the service affinity between the minimum resource management units representing the two minimum BGP service management units is a.
The foregoing implementation manner is simpler and more direct, but because it depends only on the relationship between network topologies, the case of resource intersection is not involved, and in view of this problem, in combination with the foregoing embodiment, there is also the following preferred embodiment, that is, the calculating the service affinity between any two second resource management units specifically includes:
calculating the service affinity between the network resources of the same type in the two second resource management units;
and taking the weighted sum of the service affinities between all types of network resources in the two second resource management units as the service affinities of the corresponding two second resource management units.
Each second resource management unit may include multiple types of network resources, for example, when the virtual switch is used as the minimum BGP service management unit in a cloud data center network scenario, the type of the corresponding network resource may be at least one of a virtual switch, an L0 switch connected to the virtual switch, an L1 switch connected to the L0 switch, an L2 switch connected to the L1 switch, a server to which the virtual switch belongs, a virtual terminal under the virtual switch, a subnet to which the virtual terminal belongs, and a virtual private network described by the virtual switch.
One calculation of the service affinity between the network resources of the same type is specifically as follows: and calculating the quantity ratio of the quantity of the resources which are intersected between the network resources of the same type in the two second resource management units in all the network resources of the same type in the two second resource management units. Because the service forwarding affinity degree is also related to resource cross, the service affinity between network resources of the same type can be obtained through resource cross calculation. And the weighted sum of the service affinities of all the network resources of the same type in the second resource management units can be used as the service affinities of the corresponding two second resource management units.
Wherein, the weight corresponding to each type of network resource is obtained by analyzing according to the corresponding network architecture or user requirement by the technicians in the field.
In the preferred embodiment, the service affinity of each of the same type of network resources in the two second resource management units is calculated, so that the service affinity of the two second resource management units is obtained comprehensively, and the resource cross relationship between the two second resource management units can be directly and accurately represented, thereby representing the service affinity.
In practical situations, network resources of a network are not constant, and how to enable a newly added network resource to be managed by a distributed BGP service when the network resource is newly added in the network, for this problem, there are the following preferred embodiments, that is, when the network resource is newly added in the network, the method further includes: carrying out capacity expansion on BGP service, specifically:
judging whether the quantity of BGP services needs to be increased or not according to the load condition of each BGP service;
if the quantity of the BGP services does not need to be increased, selecting the corresponding BGP services from the deployed BGP services to manage the newly added network resources;
and if the quantity of the BGP services needs to be increased, redeploying the distributed BGP services according to the business affinity.
Wherein the load condition comprises at least one of the memory use condition of BGP service, the CPU use condition, the number of managed virtual terminals and the number of managed subnets.
In the preferred embodiment, whether the load of the existing BGP service is too large due to newly adding the minimum BGP service is determined according to the load condition of the BGP service, so as to determine whether to newly add the corresponding BGP service, thereby ensuring that service forwarding is not affected due to the too large BGP service load. When the BGP service is newly added, the distributed BGP service is redeployed according to the service affinity, so that the resource isolation and the fault isolation are still realized after the minimum BGP service management unit is newly added.
In the foregoing embodiment, the most common implementation manner for determining whether to increase the number of BGP services according to the load condition of each BGP service is as follows: when the overall load of the distributed BGP service exceeds a preset ratio, the BGP service is increased. However, in an actual situation, not only the overall load of the distributed BGP service may affect the service forwarding efficiency, but also the service forwarding efficiency when there is an extremely high load of an extremely individual BGP service, for which, in combination with the above embodiment, there is the following preferred embodiment, specifically, the determining whether to increase the number of BGP services according to the load condition of each BGP service includes:
and if the number of the BGP services of which the corresponding loads exceed the first preset load threshold value exceeds a preset ratio in all the BGP services, and/or the load variance calculated by the loads of all the BGP services exceeds a preset variance threshold value, increasing the number of the BGP services.
The first preset load threshold, the preset duty ratio and the preset variance threshold are obtained by a person skilled in the art according to BGP service management requirements and network resource analysis.
And a plurality of load indexes can be formulated for the BGP service, and whether the load of the BGP service exceeds a first preset load threshold value is judged through one or more load indexes, wherein at the moment, the first preset load threshold value is obtained by the technical personnel in the field through comprehensive analysis according to the plurality of load indexes.
The preferred embodiment is not only used for judging whether new BGP services are added or not by calculating the load variance to represent the deviation degree between the load of the BGP services and the average load, thereby maintaining load balance among the BGP services and ensuring the efficiency of service forwarding.
In order to continuously ensure resource isolation and fault isolation without adding a new BGP service, in combination with the above embodiments, the following preferred embodiments are provided, that is, selecting a corresponding BGP service from deployed BGP services to manage a new network resource, specifically including:
and in the deployed first BGP service, taking the BGP service with the corresponding load lower than a second preset load threshold value as a second BGP service.
And calculating the service affinity of the newly added network resource and each second BGP service, and selecting the second BGP service with the highest service affinity to manage the newly added network resource.
Wherein, the second preset load threshold is obtained by a person skilled in the art according to the BGP service management requirement and the network resource analysis. The second predetermined load threshold is usually less than or equal to the first predetermined load threshold.
The preferred embodiment maintains the resource isolation and fault isolation of the network by selecting the corresponding BGP service hosting newly added minimum BGP service management unit through the service affinity.
When the distributed BGP service is redeployed, the method further involves route publishing and updating, and for this case, in combination with the above embodiment, provides the following preferred implementation manner, that is, the redeploying the distributed BGP service according to the service affinity specifically includes:
and for the newly added network resource, directly publishing the route corresponding to the minimum BGP service management unit when the distributed BGP service is redeployed.
For existing network resources in the network, a route deletion message is published by using the undeployed distributed BGP service, a new route is published by using the redeployed distributed BGP service, and route updating and route decision are processed in a delayed mode.
The delayed processing route updating and the route decision are specifically as follows: and if the newly added routing message of the same route is not received within a preset time period after the routing deletion message is received, the routing update and the routing decision are executed, otherwise, the routing update and the routing decision are not executed, namely the routing is reserved when the newly added routing message of the same route is received.
The preferred embodiment avoids that the same route of the local router is frequently deleted and newly added when the BGP service changes by delaying the route updating and the route decision, reduces the time consumed when the BGP service changes, and avoids the resource consumption caused by frequent route updating and route decision.
In an actual use situation, there is also a case that a BGP service in the network is abnormal, and at this time, if the abnormal BGP service is not processed, it may cause that network resources are continuously occupied by the abnormal BGP service and cannot be effectively utilized, and for this problem, in combination with the above embodiment, there is the following preferred implementation manner, that is, the method further includes:
and judging whether the BGP service is abnormal or not according to the connection state and the health state of the BGP service.
And deleting the abnormal BGP service and releasing the corresponding network resources.
The method further comprises the following steps: processing the BGP service appointed by the user to be scaled, specifically: and deleting the corresponding minimum resource management unit which is specified to be deleted by the user, and redeploying the BGP service.
The method further comprises the following steps: when network resource deletion occurs in the network, the BGP service is condensed, specifically,
and if the load of the corresponding BGP service is lower than a third preset load threshold value, the network resources managed by the BGP service are managed by other BGP services, and the BGP service is deleted.
The implementation of handing over network resources to other BGP services is consistent with the implementation idea of adding new network resources, specifically:
and in the deployed first BGP service, taking the BGP service with the corresponding load lower than a second preset load threshold value but not lower than a third preset load threshold value as a third BGP service.
And calculating the service affinity of the network resource and each third BGP service, and selecting the third BGP service with the highest service affinity to manage the network resource.
Or taking the number of the third BGP services as the number of the BGP services after the capacity reduction, and redeploying the BGP services.
In the present invention, expressions like "a and/or B" have a practical meaning that the implementation manner may be implemented by using a as an object, or B as an object, or an object in which a and B are combined, and a and B may also be replaced by specific subject name objects according to the requirements of the specific description scenario.
The terms "first," "second," and "third" in the present embodiment have no special limiting meanings, and are used for descriptive purposes only for convenience of describing different individuals among the objects, and should not be interpreted as having special limiting meanings in order or otherwise.
Example 2:
based on the method described in embodiment 1, the invention combines with a specific application scenario and uses technical expressions in a related scenario to describe an implementation process in a characteristic scenario.
In this embodiment, for example, a distributed BGP service is deployed in a cloud data center, where an underlying network of the cloud data center adopts a CLOS architecture for networking, and a network hierarchy architecture of the cloud data center is shown in fig. 3.
The corresponding deployment process of the distributed BGP service is shown in fig. 4, and specifically includes:
in step 401, traverse the switch ports and the port peers, calculate the link connections between the switches, and construct the physical network topology formed by the switches. According to the specification of a single virtual terminal in the cloud data center, the number of tenants in the cloud data center is estimated; each tenant represents a private virtual network in the network. Step 202 is entered.
In step 402, a virtual switch is used as a minimum BGP management unit to construct and initialize a resource management unit set G, where each element in the set G represents a minimum resource management unit to manage a minimum BGP management unit; step 403 is entered.
In step 403, element aggregation is performed on the elements in the resource management unit set G, where each element in the set G represents a converged resource management unit; step 404 is entered.
In step 404, the distributed BGP services are deployed according to the aggregated set G, where one BGP service is deployed corresponding to one element in the set G.
The following will perform detailed description on the above steps in combination with a specific scenario, where the constructing and initializing the resource management unit set G specifically includes:
constructing a corresponding element g by taking each virtual switch in the cloud data center as a minimum BGP service management unit i And i is the serial number of the corresponding virtual switch, and i is less than or equal to the number N of the virtual switches in the cloud data center.
Each element contains attributes of a corresponding type, each type of attribute representing a type of network resource.
The performing element aggregation specifically includes, as shown in fig. 5:
in step 501, each element G in the resource management unit set G is traversed i (ii) a Judgment element g i If the number of the corresponding attributes is larger than the number of the corresponding preset attributes, g is added i Move to the aggregation set, otherwise, g is still set i Remains in the set G and proceeds to step 502.
In step 502, judging whether the number of elements in the set G is greater than or equal to 2, if the number of elements is greater than 2, entering step 503; otherwise, step 507 is entered, and the convergence is ended.
In step 503, it is determined whether the total number of elements in the set G and the aggregation set is less than or equal to a preset number of elements; if the total number of the elements is less than or equal to the preset number of elements, step 507 is performed, otherwise, step 504 is performed.
In step 504, calculating the business affinity between any two elements in the set G; step 505 is entered.
In step 505, element aggregation is performed on two elements in the set G with the highest business affinity to each other, and the process proceeds to step 506.
In step 506, element aggregation is performed on the two elements with the highest service affinity between them in the set G, it is determined whether the number of corresponding attributes in the aggregated new elements is greater than the preset attribute number, if so, the new elements are moved to the aggregation set, otherwise, the new elements are still retained in the set G, and the process enters step 502 to determine whether to continue iterative element aggregation.
In step 507, all elements in the aggregation set are moved to a set G, where the set G is the aggregation management unit set. And ending the convergence.
Taking CLOS architecture networking as an example, a calculation process of business affinity between two elements is shown below, where two elements are respectively an element a and an element B, and the calculation process of the business affinity between the element a and the element B is: calculating the attribute of each same type in the element A and the element B, namely the service affinity between the network resources of the same type, and taking the weighted sum of the service affinity of the network resources as the service affinity of the two elements.
The present embodiment represents the service affinity between the network resources according to the resource intersection degree of the network resources. The calculation process of the business affinity of the corresponding element a and the element B is expressed in the form of a formula:
wherein J (A, B) represents the business affinity between element A and element B, K i Representing the weight corresponding to each type of network resource, i representing the serial number of the type of the network resource, NUM () representing the number of elements in the corresponding set, A i A collection representing a class of network resources in element A, i.e. a class of attributes under element A, B i Represents a collection of a class of network resources in element B, i.e., a class of attributes under element B. A. the i ∩B i Represents set A i And set B i Of intersection of, A i ∪B i Represents the set A i And set B i Is collected. From the intersection, A is obtained i And B i Network resources of intersection, by unionTo obtain A i And B i Obtaining the resource crossing degree of the corresponding type of network resources, namely the service affinity among the network resources, through the ratio of the number of the elements, and then passing K i And weighted summation is carried out to obtain the business affinity between the element A and the element B.
Weight K i Are analyzed by those skilled in the art according to the corresponding network architecture or user requirements. In the CLOS architecture networking, the network architecture of which is shown in fig. 3 and includes Tier3, Tier2 and Tier1, according to the network hierarchy, the attribute types included in each constructed element are shown in fig. 6 and include: the system comprises a corresponding virtual switch, an L0 switch linked up by the corresponding virtual switch, an L1 switch linked up by the corresponding L0 switch, an L2 switch linked up by the corresponding L1 switch, a server to which the virtual switch belongs, a virtual terminal subnet and a virtual private network, wherein each type of attribute exists in the form of a list, an ID used for representing the attribute is stored in the list so as to facilitate the aggregation of subsequent elements, and a sub element list is defined in the element and is used for storing sub elements forming the element in the aggregation process of the subsequent elements so as to facilitate the capacity expansion and capacity reduction of the BGP service in the later period.
And establishing a corresponding weight value range for each type of network resource according to the CLOS architecture networking, and enabling the selected weight to take values in the corresponding value range according to user requirements.
The above-mentioned element aggregation process of steps 501-507 will be explained in an exemplary manner, assuming that G exists in the constructed and initialized set G 1 、g 2 、g 3 、g 4 And g 5 The 5 elements are configured to set aggregation conditions that the number of virtual terminals in the corresponding elements is not more than 10000, the number of virtual private networks is not more than 100, and the preset number is set to 3, that is, aggregation is stopped when 3 elements are aggregated.
Suppose g 2 There are 101 virtual private networks in, then g 2 G is calculated without participating in subsequent element convergence 1 And g 3 Has a business affinity of 49 g between 1 And g 4 Has a business affinity of 49，g 1 And g 5 Has a traffic affinity of 55 g 3 And g 4 Has a traffic affinity of 32 g 4 And g 5 The business affinity between the g and the g is 27, the g with the highest business affinity between the g and the g is selected 1 And g 5 Carrying out element aggregation, wherein the aggregated elements are g (1，5) If the convergence condition is satisfied, the element participating in the convergence of the subsequent elements has g (1，5) 、g 3 And g 4 Calculating to obtain g (1，5) And g 3 Has a business affinity of 40 g between (1，5) And g 4 Has a traffic affinity of 44, then g (1，5) And g 4 Element gathering is carried out to obtain g (1，4，5) The element finally obtained is g 2 、g 3 And g (1，4，5) The number of elements has reached 3, so convergence stops.
The step 404 of deploying the distributed BGP service according to the aggregated set G specifically includes: and updating a configuration template for deploying BGP service according to the elements in the set G, deploying distributed BGP service according to the configuration template of the BGP service, and establishing BGP topology, wherein network resources and network parameters of the corresponding BGP service are set in the configuration template.
After the initial deployment of the distributed BGP service is completed, there is also a case where the minimum BGP service management unit in the network, that is, the number of virtual switches, changes.
When a virtual switch is newly added, the embodiment further includes the following steps:
in step 601, the load of each BGP service is collected, and it is determined whether a new BGP service is needed according to the load of the BGP service, if a new BGP service is needed, step 603 is performed, otherwise, step 602 is performed. The load of the BGP service is as shown in fig. 8, and includes multiple load indexes, that is, a BGP service memory usage rate, a BGP service CPU usage rate, a BGP service virtual terminal number, and a BGP service virtual private network number, and sets a corresponding threshold for each load index, and when one or more indexes of the BGP service exceed the corresponding thresholds, it is determined that the load of the BGP service exceeds the first load threshold. And if the number of the BGP services with the corresponding loads exceeding the first preset load threshold exceeds 20 percent, or calculating the variance of all the BGP services, and if the variance exceeds a preset variance threshold, determining that the BGP services need to be newly added.
In step 602, the newly added virtual switch is used as a minimum BGP management unit, a corresponding minimum resource management unit is established, the service affinity of the minimum resource management unit and each aggregation resource management unit in the set G is calculated, an element G with the highest service affinity is selected for element aggregation, the BGP service gateway corresponding to G is selected to manage the newly added virtual switch and the corresponding network resource, the routing update is performed, and the deployment is ended.
In step 603, the newly added virtual switch is used as a minimum BGP management unit to establish a corresponding minimum resource management unit, a BGP service with a corresponding load lower than 80% is selected as a second BGP service among all deployed BGP services, an aggregated resource management unit in a set G corresponding to the second BGP service is split into the minimum resource management units, and the split minimum resource management unit and the minimum resource management unit corresponding to the newly added virtual switch form a set G 2 . Step 604 is entered.
In step 604, for G 2 And carrying out element aggregation until the quantity of the BGP services obtained by aggregation is 1 added to the quantity of the original second BGP services. And redeploying the second BGP service according to the converged resource management unit, updating the route and making a route decision, and ending the deployment.
When reducing the virtual switch, there are two situations, one is to specify the capacity for the user and reduce the virtual switch, that is, specify the capacity, one is to perform dynamic capacity reduction according to the BGP load, and one is to perform service exception between the BGP service and the virtual switch, that is, actively reduce the capacity.
Specifically, for the specified capacity reduction, the minimum resource management unit of the corresponding virtual switch is deleted from the set G or the aggregation resource management unit of the set G, and the corresponding network resource under the corresponding BGP service is released to perform the route update and the route decision.
For dynamic capacity reduction, in particular to collect the load of each BGP service, the capacity is storedAnd when the load of the BGP service is lower than a third preset load threshold value, such as 10%, the network resources managed by the BGP service are managed by other BGP services, and the BGP service is deleted. Wherein, the network resource under the BGP service nano management is handed to other BGP services for nano management and is still carried out according to the affinity, specifically: selecting BGP services with corresponding load lower than 80% and not lower than 10% from all deployed BGP services as third BGP services, splitting the aggregation resource management units in the set G corresponding to all BGP services into minimum resource management units and forming a minimum resource management unit set G 3 . For G 3 And carrying out element aggregation according to the service affinity until the number of the BGP services obtained by aggregation is the number of the third BGP services. And redeploying the second BGP service according to the converged resource management unit, updating the route and making a route decision, and ending the deployment.
For active capacity reduction, specifically, to obtain a connection state and a health state of a BGP service, when a connection of a corresponding BGP service is interrupted or the health state of the BGP service is abnormal, the corresponding BGP service is deleted, and a route update and a route decision are performed. The BGP service connection interruption specifically refers to heartbeat message interruption between the BGP service management module and the BGP service module, and the BGP service health state anomaly includes that a neighbor cannot establish a state, internal data is abnormal, and the like.
The route updating and route decision specifically includes:
when receiving the routing message, judging whether the routing message is sent by a control surface of BGP service, if so, comparing whether a publisher deleting the route is the same as the publisher of the route stored in the local router, if not, immediately starting a route publishing and decision flow of the local router, deleting corresponding table entries in the local routing table and the forwarding table, and finishing route convergence.
If the publisher deleting the route is the same as the publisher of the route stored in the local router, the local router route publishing and decision flow is not started, whether a new route message consistent with the deleted route is received or not is judged in a preset time period, if the new route message consistent with the deleted route is received, the local router route publishing and decision flow is not executed, existing route information is delayed, and therefore the situation that the same route is repeatedly deleted and newly added in the BGP service capacity expansion or capacity reduction process is avoided. If the consistent newly added routing message is not received, starting a routing issuing and decision-making process of the local router after the preset time period is over, deleting corresponding entries in the local routing table and the forwarding table, and finishing routing convergence.
The preset time period is obtained by analyzing by a person skilled in the art according to the response rate of the network and the deployment requirement of the BGP service, and is implemented by a timer in this embodiment, that is, when a delete routing message sent by a control plane of the BGP service is received, the timer is started to perform delay, and in the delay process of the timer, the route publishing and decision flow of the local router is not performed.
The implementation method for judging whether the routing message is sent by the control plane of the BGP service comprises the following steps: newly adding a bgpclusterchangeextensedicommunity attribute in a BGP routing message, and defining that when the attribute value is 0, the routing message is not sent by a control plane of a BGP service, and when the attribute value is 1, the routing message is sent by the control plane of the BGP service.
Example 3:
fig. 9 is a schematic structural diagram of a distributed BGP service deployment system according to an embodiment of the present invention, where the system includes a resource collection module, a BGP service policy module, and a BGP service deployment module, where:
the acquisition module is used for acquiring the network resources and the network topology of the whole network; the BGP service strategy module is used for calculating the quantity of BGP services and corresponding network resources; and the BGP service deployment module is used for deploying the distributed BGP services according to the calculated quantity of the BGP services and the corresponding network resources. After the deployment is completed, the system also comprises a BGP service management module, wherein the BGP service management module manages all BGP services and manages the device routing in a centralized manner. Fig. 10 is a schematic diagram of the BGP service management module and the BGP service after deployment is completed, where each BGP service manages corresponding network resources and issues and receives routing messages.
The decision and deployment of the corresponding BGP service are based on the same concept as the deployment method of the distributed BGP service in embodiment 1, and specific contents may refer to the description in the embodiment of the method of the present invention, which is not described herein again.
Example 4:
fig. 11 is a schematic structural diagram of a deployment apparatus of a distributed BGP service according to an embodiment of the present invention. The deployment apparatus of the distributed BGP service of the present embodiment includes one or more processors 21 and a memory 22. In fig. 11, one processor 21 is taken as an example.
The processor 21 and the memory 22 may be connected by a bus or other means, and fig. 8 illustrates the connection by a bus as an example.
The memory 22 is a non-volatile computer-readable storage medium and can be used to store a non-volatile software program and a non-volatile computer-executable program, such as the deployment method of the distributed BGP service in embodiment 1. Processor 21 implements the distributed BGP service deployment method by executing non-volatile software programs and instructions stored in memory 22.
The memory 22 may include high speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, the memory 22 may optionally include memory located remotely from the processor 21, and these remote memories may be connected to the processor 21 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The program instructions/modules are stored in the memory 22, and when executed by the one or more processors 21, perform the deployment method of the distributed BGP service in embodiment 1, for example, perform the steps shown in fig. 1, fig. 2, fig. 4, fig. 5 and fig. 7 described above.
It should be noted that, for the information interaction, execution process and other contents between the modules and units in the apparatus and system, the specific contents may refer to the description in the embodiment of the method of the present invention because the same concept is used as the embodiment of the processing method of the present invention, and are not described herein again.
Those of ordinary skill in the art will appreciate that all or part of the steps of the various methods of the embodiments may be performed by associated hardware as instructed by a program, which may be stored on a computer-readable storage medium, which may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, and the like.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for deploying a distributed BGP service, comprising:
establishing a plurality of minimum resource management units according to the network resources and the network topology of the whole network;
according to the service affinity between the minimum resource management units, network resource convergence is carried out on the minimum resource management units with high service affinity to obtain corresponding converged resource management units;
deploying distributed BGP services according to the aggregation resource management unit; one BGP service corresponds to one converged resource management unit, and manages network resources under the corresponding converged resource management unit.
2. The method according to claim 1, wherein the method for deploying distributed BGP services according to the affinity between minimum resource management units performs network resource aggregation on minimum resource management units with high affinity to each other to obtain corresponding aggregated resource management units, specifically includes:
taking the first resource management unit meeting the convergence condition as a second resource management unit, calculating the service affinity between any two second resource management units, and converging network resources of the two second resource management units with the highest service affinity to each other to obtain a third resource management unit;
replacing two first resource management units for network convergence by a third resource management unit obtained by network resource convergence for the last time, and iteratively converging the network resources for the next time until the number of the second resource management units is less than two, or the total number of the first resource management units and the third resource management units is less than or equal to the preset number; the minimum resource management unit is used as a first resource management unit for carrying out first network resource aggregation;
and obtaining a first resource management unit and a third resource management unit after the iteration is finished, namely the corresponding converged resource management units.
3. The method for deploying a distributed BGP service according to claim 2, wherein the calculating the service affinity between any two second resource management units specifically includes:
calculating the service affinity between the network resources of the same type in the two second resource management units;
and taking the weighted sum of the service affinities of all types of network resources in the two second resource management units as the service affinities of the two corresponding second resource management units.
4. The method for deploying distributed BGP services according to claim 1, characterized in that when a network resource addition occurs in the network, the method further comprises:
dynamic capacity expansion is performed on BGP services, specifically,
judging whether the quantity of BGP services needs to be increased or not according to the load condition of each BGP service;
if the quantity of the BGP services does not need to be increased, selecting the corresponding BGP services from the deployed BGP services to manage the newly added network resources;
and if the quantity of the BGP services needs to be increased, redeploying the distributed BGP services according to the business affinity.
5. The method for deploying distributed BGP services according to claim 4, wherein the determining, according to the load condition of each BGP service, whether the number of BGP services needs to be increased specifically includes:
and if the number of the BGP services of which the corresponding loads exceed the first preset load threshold value exceeds a preset ratio in all the BGP services, and/or the load variance calculated by the loads of all the BGP services exceeds a preset variance threshold value, increasing the number of the BGP services.
6. The method according to claim 4, wherein the selecting a corresponding BGP service from the deployed BGP services to manage the newly added network resource specifically includes:
in the deployed first BGP service, taking the BGP service with the corresponding load lower than a second preset load threshold value as a second BGP service;
and calculating the service affinity of the newly added network resource and each second BGP service, and selecting the second BGP service with the highest service affinity to manage the newly added network resource.
7. The method for deploying distributed BGP services according to claim 4, wherein the relocating the distributed BGP service according to the service affinity specifically comprises:
for the newly added network resource, directly publishing a route corresponding to the newly added network resource when the distributed BGP service is redeployed;
for existing network resources in the network, a route deletion message is published by using the undeployed distributed BGP service, a new route is published by using the redeployed distributed BGP service, and route updating and route decision are processed in a delayed mode.
8. The method for deploying distributed BGP services according to claim 1, characterized in that when a network resource pruning occurs in the network, the method further comprises:
dynamic capacity reduction is performed on BGP services, specifically,
and if the load of the corresponding BGP service is lower than a third preset load threshold value, the network resources managed by the BGP service are managed by other BGP services, and the BGP service is deleted.
9. The method for deploying distributed BGP services according to any of claims 1-8, characterized in that the method further comprises:
judging whether the BGP service is abnormal or not according to the connection state and the health state of the BGP service;
and deleting abnormal BGP service and releasing corresponding network resources.
10. The distributed BGP service deployment system is characterized by comprising an acquisition module, a BGP service strategy module and a BGP service deployment module, wherein:
the acquisition module is used for acquiring the network resources and the network topology of the whole network;
the BGP service strategy module is used for calculating the quantity of BGP services and corresponding network resources;
and the BGP service deployment module is used for deploying the distributed BGP service according to the calculated quantity of the BGP service and the corresponding network resource.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210895454.4A CN115102831B (en) | 2022-07-26 | 2022-07-26 | Deployment method and system of distributed BGP service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210895454.4A CN115102831B (en) | 2022-07-26 | 2022-07-26 | Deployment method and system of distributed BGP service |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115102831A true CN115102831A (en) | 2022-09-23 |
| CN115102831B CN115102831B (en) | 2023-07-04 |
Family
ID=83300823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210895454.4A Active CN115102831B (en) | 2022-07-26 | 2022-07-26 | Deployment method and system of distributed BGP service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115102831B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117714453A (en) * | 2024-02-05 | 2024-03-15 | 济南千寻信息科技有限公司 | Intelligent device management method and system based on Internet of things card |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100291943A1 (en) * | 2008-01-23 | 2010-11-18 | Attila Mihaly | Method and Apparatus for Pooling Network Resources |
| GB201421184D0 (en) * | 2014-11-28 | 2015-01-14 | Aria Networks Ltd | Optimizing the topology of a network with variable traffic demands |
| CN108718244A (en) * | 2017-12-20 | 2018-10-30 | 北京时代民芯科技有限公司 | A kind of frame of reference and method for multi-service fusion |
| CN113381879A (en) * | 2021-05-17 | 2021-09-10 | 浪潮思科网络科技有限公司 | SDN-based network deployment method and device |
| CN113993214A (en) * | 2021-09-29 | 2022-01-28 | 西安电子科技大学 | Task-driven spatial information network resource management system and method |
-
2022
- 2022-07-26 CN CN202210895454.4A patent/CN115102831B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100291943A1 (en) * | 2008-01-23 | 2010-11-18 | Attila Mihaly | Method and Apparatus for Pooling Network Resources |
| GB201421184D0 (en) * | 2014-11-28 | 2015-01-14 | Aria Networks Ltd | Optimizing the topology of a network with variable traffic demands |
| CN108718244A (en) * | 2017-12-20 | 2018-10-30 | 北京时代民芯科技有限公司 | A kind of frame of reference and method for multi-service fusion |
| CN113381879A (en) * | 2021-05-17 | 2021-09-10 | 浪潮思科网络科技有限公司 | SDN-based network deployment method and device |
| CN113993214A (en) * | 2021-09-29 | 2022-01-28 | 西安电子科技大学 | Task-driven spatial information network resource management system and method |
Non-Patent Citations (2)
| Title |
|---|
| 季青;杨扬;孟坤;王强;张诗雅;: "基于云计算技术的一体化网络资源管理方法", 兵工自动化, no. 01 * |
| 朱海东;: "云网一体使能网络即服务", 中兴通讯技术, no. 02 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117714453A (en) * | 2024-02-05 | 2024-03-15 | 济南千寻信息科技有限公司 | Intelligent device management method and system based on Internet of things card |
| CN117714453B (en) * | 2024-02-05 | 2024-04-26 | 济南千寻信息科技有限公司 | Intelligent device management method and system based on Internet of things card |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115102831B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2515478B1 (en) | Method, apparatus and system for joint optimizations | |
| CN111654438B (en) | Method, controller and system for establishing forwarding path in network | |
| CN108540204B (en) | Satellite network topology generation method using fast convergence ant colony algorithm | |
| CN100488145C (en) | Distributed type clustering method in use for constructing cluster type peer-to-peer network | |
| CN105103492A (en) | Controlling a topology of a network | |
| CN105553749B (en) | A kind of ICN logical topology construction methods based on SDN | |
| CN114285758B (en) | Communication network optimization simulation system, method and device based on OPNET | |
| CN103475719A (en) | Content distribution method for minimizing cross-domain flows in CDN-P2P fusion network | |
| CN103618677A (en) | Network flow regulation method and system | |
| CN105357124B (en) | A kind of MapReduce bandwidth optimization methods | |
| CN105530312A (en) | Network service path selection system and selection method | |
| CN105681438A (en) | Centralized caching decision strategy in content-centric networking | |
| CN105472484A (en) | Wave channel balancing route wavelength allocation method of power backbone optical transport network | |
| CN115102831A (en) | Method and system for deploying distributed BGP (Border gateway protocol) service | |
| CN114513449A (en) | Method and system for optimizing routing in domain | |
| Patil | Load balancing approach for finding best path in SDN | |
| CN110535673B (en) | Virtual subnet construction method, equipment and storage medium | |
| CN104994019B (en) | A kind of horizontal direction interface system for SDN controllers | |
| CN107295103B (en) | Node management method based on centralized P2P system | |
| Tao et al. | A distributed heuristic multicast algorithm based on QoS implemented by SDN | |
| CN108174446B (en) | Network node link resource joint distribution method with minimized resource occupancy | |
| Hoang et al. | New distributed constraint satisfaction algorithms for load balancing in edge computing: A feasibility study | |
| CN104581965B (en) | Frequency spectrum distributing method based on user's distribution and time delay | |
| Parag et al. | Value-aware resource allocation for service guarantees in networks | |
| Pang et al. | Research on SDN-based data center network traffic management and optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230329 Address after: 430000 No. 6, High-tech Fourth Road, Donghu High-tech Development Zone, Wuhan City, Hubei Province Applicant after: FIBERHOME TELECOMMUNICATION TECHNOLOGIES Co.,Ltd. Address before: No.4, Guanshan 2nd Road, Donghu Development Zone, Wuhan City, Hubei Province 430205 Applicant before: WUHAN FIBERHOME TECHNICAL SERVICES Co.,Ltd. Applicant before: FIBERHOME TELECOMMUNICATION TECHNOLOGIES Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |