CN111385198A

CN111385198A - Path determining method, device and communication system

Info

Publication number: CN111385198A
Application number: CN201811645971.6A
Authority: CN
Inventors: 尹龙; 秦国华; 赵敏
Original assignee: Huawei Technologies Co Ltd
Current assignee: Huawei Technologies Co Ltd
Priority date: 2018-12-29
Filing date: 2018-12-29
Publication date: 2020-07-07
Anticipated expiration: 2038-12-29
Also published as: CN111385198B

Abstract

The application discloses a path determining method, a path determining device and a communication system, and belongs to the technical field of communication. The method comprises the following steps: receiving a path calculation request; when a source region to which a source node belongs and a destination region to which a destination node belongs are different regions, sequentially performing a link determination process on each region from the source region along a direction far away from the source region to obtain a target sub-link with the smallest link cost from an inlet node to each outlet node in each region; and determining the link with the minimum link cost in a plurality of feasible links from the source node to the destination node as the target link based on the target sub-link with the minimum link cost from the inlet node to each outlet node in each area. The method and the device solve the problems that the path calculation unit is high in operation cost and low in operation efficiency. The method and the device are used for determining the paths between the nodes.

Description

Path determining method, device and communication system

Technical Field

The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, and a communication system for determining a path.

Background

With the development of communication technology, more and more nodes (also referred to as network elements or communication devices) are deployed in a network, and thus a network topology structure formed by connecting nodes in the network to each other becomes more and more complex.

In the related art, a Path Computation Element (PCE) and a Path Computation Client (PCC) may also be deployed in the network. The PCC may send a path computation request to the PCE to request the PCE to compute a target path with a minimum link cost between a source node to a destination node (also referred to as a sink node) in the network. After receiving the path computation request, the PCE sequentially traverses all nodes located between the source node and the destination node in the network from the source node in a direction away from the source node, computes all feasible paths between the source node and the destination node, that is, determines a data transmission combination mode of all nodes between the source node and the destination node, and finally determines a target path among all feasible paths.

However, as the number of nodes in the network increases, the PCE needs to sequentially traverse other nodes between the source node and the destination node to determine all feasible paths, and the PCE has high computation cost and low computation efficiency.

Disclosure of Invention

The application provides a path determination method, a path determination device and a communication system, which can solve the problems that the path calculation unit has high operation cost and low operation efficiency.

In a first aspect, a path determining method is provided, which is used for a path calculating unit in a communication system, where the communication system includes a plurality of regions that are connected to each other and do not overlap with each other, and each region includes a plurality of nodes, and the method includes: receiving a path calculation request, wherein the path calculation request is used for requesting to calculate a target link with the minimum link cost from a source node to a destination node; when a source region to which a source node belongs and a destination region to which a destination node belongs are different regions, sequentially performing a link determination process on each region from the source region along a direction far away from the source region to obtain a target sub-link with the smallest link cost from an inlet node to each outlet node in each region; determining a link with the minimum link cost in a plurality of feasible links from a source node to a destination node as a target link based on a target sub-link with the minimum link cost from an inlet node to each outlet node in each area;

the entry node in the source region is a source node, the entry nodes in the regions except for the source region in the plurality of regions are nodes connected with the exit node of the previous region, the exit nodes in the regions except for the destination region in the plurality of regions are nodes connected with the next region, and the exit node of the destination region is a destination node.

According to the method and the device, the path calculation is carried out in the divided areas, only the combination mode of the target sublinks of each area needs to be determined, and the data transmission combination mode of all nodes between the source node and the destination node does not need to be determined, so that the calculation cost of the path calculation unit is reduced, and the calculation efficiency is improved.

In one possible implementation, for each region, the link determination process includes: determining feasible sublinks from an ingress node to each egress node; calculating the link cost of the feasible sub-links from the entrance node to each exit node based on the initial link cost of the entrance node; based on the calculated link cost, determining a feasible sublink with the minimum link cost from the entry node to each exit node as a target sublink, and recording the link cost of the target sublink, wherein the initial link cost of the entry node in the source area is 0, and the initial link cost of the entry node in an area except the source area in the plurality of areas is: the link cost of a target sublink to which an exit node of a previous area connected by an entry node belongs;

determining a link with the minimum link cost in a plurality of feasible links from a source node to a destination node as a target link based on the target sub-link with the minimum link cost from the inlet node to each outlet node in each area, wherein the target link comprises: and determining a feasible link to which the target sub-link in the target area belongs as a target link.

In another possible implementation, for each region, the link determination process includes: determining feasible sublinks from an ingress node to each egress node; calculating the link cost of the feasible sublinks from the inlet node to each outlet node based on the initial link cost of the inlet node, wherein the initial link cost of the inlet node is 0; determining a feasible sub-link with the minimum link cost from the inlet node to each outlet node as a target sub-link based on the calculated link cost, and recording the link cost of the target sub-link;

determining a link with the minimum link cost in a plurality of feasible links from a source node to a destination node as a target link based on the target sub-link with the minimum link cost from the inlet node to each outlet node in each area, wherein the target link comprises: and determining the target link based on the link cost of the target sublink of each area and the link costs of every two adjacent areas.

In another possible implementation, calculating link costs of the feasible sub-links from the ingress node to each egress node based on the initial link costs of the ingress node includes: and calculating the link cost of the feasible sub-link from the inlet node to each outlet node based on the initial link cost of the inlet node according to a single-source shortest path algorithm.

In another possible implementation, when the plurality of zones is at least three zones, the link determination process of at least two zones of the plurality of zones is performed in parallel starting from the source zone and along a direction away from the source zone. Since the link determination processes of the plurality of areas are performed in parallel, the rate at which the path calculation unit determines the target sub-links of the plurality of areas in the communication system can be increased.

In another possible implementation, before receiving the path computation request, the method further includes: dividing a plurality of nodes in a communication system to obtain a plurality of areas; alternatively, area division information for indicating information of nodes included in a plurality of areas in the communication system is received.

In another possible implementation manner, dividing a plurality of nodes in a communication system into a plurality of areas includes: acquiring resource information of a communication system, wherein the resource information comprises a connection relation among a plurality of nodes in the communication system; and dividing a plurality of nodes in the communication system according to the resource information and the division rule to obtain a plurality of areas.

The sizes of the areas obtained by dividing according to the dividing rule are balanced, and the connection number of each area and other areas is small, so that the time difference of the path calculation unit for executing the link determination process on each area is small, the parallel execution of the link determination process of each area is facilitated, and the speed of calculating the target link by the path calculation unit can be high. And the computing resources consumed by the virtual machines to compute the links in the corresponding areas are approximately the same, so that the virtual machines with the same performance can be used for computing the links in each area, the virtual machines with different performances do not need to be distributed to different areas, and the link determining efficiency can be further improved. And when the number of nodes deployed in the communication system is increased, so that the number of areas in the communication system is increased, only virtual machines with the same performance need to be added in the path computing unit, and the path computing unit has better adaptability and higher universality. Further, by setting a plurality of virtual machines to execute the link determination process, parallel calculation of the link determination process can be realized.

In another possible implementation manner, dividing a plurality of nodes in a communication system into a plurality of regions according to resource information and a division rule includes: determining a plurality of nodes to be divided in a plurality of nodes in a communication system, wherein the number of the nodes connected with the nodes to be divided is larger than a second connection number threshold value, or the nodes to be divided are nodes of an appointed type, or the nodes to be divided are non-bottom nodes in the communication system; dividing the nodes to be divided according to resource information and a division rule to obtain a plurality of transition areas; and dividing the rest nodes except the nodes to be divided in the communication system into transition areas to which the nodes connected with the rest nodes belong to obtain a plurality of areas.

In another possible implementation manner, dividing the plurality of nodes to be divided according to the resource information and a division rule to obtain a plurality of transition regions includes: preliminarily dividing a plurality of nodes to be divided according to the data transmission control type adopted by the nodes to be divided to obtain a plurality of initial areas; and dividing the plurality of initial regions according to the resource information and a division rule to obtain a plurality of transition regions.

In another possible implementation manner, dividing the plurality of initial regions according to the resource information and a division rule to obtain a plurality of transition regions includes: and based on a community discovery algorithm, dividing the plurality of initial regions according to resource information and a division rule to obtain a plurality of transition regions.

In another possible implementation manner, the partitioning rule includes: and the difference of the number of the nodes of each area is smaller than the difference number threshold, and the number of the areas connected with each area is smaller than at least one item in the first connection number threshold.

In another possible implementation manner, the path calculation unit includes a plurality of virtual machines in one-to-one correspondence with a plurality of areas, and the target child chain in each area routes the corresponding virtual machine computer.

In a second aspect, the present application provides a path determination apparatus including means for performing the path determination method in the first aspect or any one of the possible implementations of the first aspect.

In a third aspect, the present application provides a communication system comprising a plurality of nodes, a path calculation unit and a path calculation client, the plurality of nodes, the path calculation unit and the path calculation client being interconnected, the path calculation unit comprising the path determination apparatus of the second aspect.

In a fourth aspect, the present application provides a path computation unit, comprising: at least one processor, at least one interface, a memory, and at least one communication bus, the processor being configured to perform the method for path determination in the first aspect or any one of the possible implementations of the first aspect.

In a fifth aspect, the present application provides a computer-readable storage medium having stored therein instructions, which, when executed on a computer, cause the computer to perform the method of the above aspects.

In a sixth aspect, the present application provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of the above aspects.

The present application can further combine to provide more implementations on the basis of the implementations provided by the above aspects.

Drawings

Fig. 1 is a schematic structural diagram of a communication system according to an embodiment of the present application;

fig. 2 is a flowchart of a path calculation method provided in an embodiment of the present application;

fig. 3 is a flowchart of a method for dividing a plurality of areas according to an embodiment of the present application;

fig. 4 is a schematic diagram of a partial area in a communication system according to an embodiment of the present application;

fig. 5 is a flowchart of a link determination process provided in an embodiment of the present application;

fig. 6 is a flowchart of another link determination process provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of a path computation unit according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of an area in a communication system according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a path determination apparatus according to an embodiment of the present application;

fig. 10 is a schematic structural diagram of a sub-link determining module according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of another sub-link determining module provided in an embodiment of the present application;

fig. 12 is a schematic structural diagram of another path determination device provided in an embodiment of the present application;

fig. 13 is a schematic structural diagram of another path determining apparatus provided in an embodiment of the present application;

fig. 14 is a schematic structural diagram of a partitioning module according to an embodiment of the present application;

fig. 15 is a schematic structural diagram of a path computation unit according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

Fig. 1 is a schematic structural diagram of a communication system according to an embodiment of the present application. As shown in fig. 1, the communication system 10 includes a plurality of areas Q, a path calculation unit, and a path calculation client, which are connected to each other and do not overlap. The communication system 10 may also be referred to as a communication network, such as an optical transport network, and each area Q in the communication system 10 may include a plurality of nodes (also referred to as network elements or communication devices) 101, and the plurality of areas Q may establish communication connections (such as wire connections or wireless connections) among each other through the nodes 101.

For example, the path computation unit may be a stand-alone device, or may be integrated inside the server 102 (fig. 1 illustrates that the path computation unit is integrated inside the server), or may be integrated in one server cluster or cloud computing center. The path calculation client may be installed on a User Equipment (UE) 103, and when the User is a personal User or an enterprise User, the User Equipment 103 may be a terminal such as a mobile phone or a computer; when the user is an enterprise user, the user device 103 may also be a server. A plurality of nodes 101 in the communication system 10 are respectively connected with the user equipment 103 and the server 102 in a communication manner, and the plurality of nodes 101 are also connected in a communication manner to form a network topology. The path calculation unit may acquire all node information and link information of the communication system 10. The node information is information for characterizing attributes or characteristics of the node, and includes at least one of an identifier of the node (such as a number or a name of the node), a location of the node, a device type, and the like. The device type of the node may be characterized by a network type to which the node can access, for example, if the communication system is an optical transport network, the device type of the node may be a multi-service optical transport network (MSOTN) type or an Automatic Switched Optical Network (ASON) type. If the communication system is an optical transport network, the node information may further include an optical wavelength required for the node to transmit data. The link information is information for characterizing attributes or characteristics of the link, and includes at least one of a connection relationship between the nodes, a time delay of data transmission by a cable connecting the nodes, and a data transmission channel remaining in the cable. It should be noted that each cable may have at least one data transmission channel, and usually has a plurality of data transmission channels, different data transmission channels may be used to transmit different data, and the remaining data transmission channels in the cable are also idle channels that are not used to transmit data in the cable. When the communication system is an optical transport network, the link information may further include the wavelength of light that the cable is capable of transmitting. The connection relationship between the nodes and the number of nodes in the region in fig. 1 are merely examples, and the connection relationship between the nodes and the number of nodes in the region Q are not limited in the embodiments of the present application.

The path computation client may be authorized to obtain node information of the source node and the destination node in the communication system 10, and the path computation client may send a path computation request to the path computation unit under the trigger of the user to request the path computation unit to compute a target link between the source node and the destination node. Illustratively, the path computation request may carry an identifier of the active node and an identifier of the destination node, and the target link may be a link with the smallest link cost. The link cost represents the cost consumed by traffic traversing the link. A link between any two nodes may pass through a plurality of cables and a plurality of nodes, and the link cost of the link may be characterized by the time delay of data transmission of the link and/or the number of nodes through which the link passes, wherein the time delay of data transmission of the link is positively correlated with the link cost, that is, the smaller the time delay of data transmission of the link is, the less the link cost is; the number of nodes passed by the link is positively correlated with the link cost, and the less the number of nodes passed by the link is, the less the link cost is.

Fig. 2 is a flowchart of a path determining method according to an embodiment of the present application. The method may be used in a path computation element in the communication system 10 shown in fig. 1, and as shown in fig. 2, the method may include:

step 201, a plurality of nodes in the communication system are divided into a plurality of areas.

In the communication system, each node and at least one node establish communication connection, and the connection relationship between each node and other nodes reflects the data interaction between the node and other nodes, that is, if a certain node is connected with only one node, the frequency of data interaction between the certain node and other nodes is low, and if a certain node is connected with a plurality of nodes, the frequency of data interaction between the certain node and other nodes is high. The path calculation unit may divide a plurality of nodes in the communication system into a plurality of regions according to a connection relationship between each node and other nodes, divide a node with a higher data interaction frequency into the same region, and divide a node with a lower data interaction frequency into different regions.

For example, referring to fig. 3, step 201 may include:

step 2011, resource information of the communication system is obtained.

The resource information of the communication system may include a connection relationship between nodes in the communication system, where the connection relationship includes at least one of an identifier of a node to which each node is connected, a number of connected nodes, and the like. Optionally, the connection relationship may further include at least one of the number of nodes in the communication system, the location of the node (for example, the location coordinates of the node in the communication system), information of cables connected between the nodes, and the like. Wherein, the information of the cable may include: at least one of link cost of the cable (such as time delay of data transmission of the cable), the number of data transmission channels of the cable, the type of data that can be transmitted by the cable, and the like.

Step 2012, according to the resource information and the division rule, the plurality of nodes in the communication system are divided to obtain a plurality of areas.

Illustratively, the partitioning rule includes: and the difference of the number of the nodes of each area is smaller than the difference number threshold, and the number of the areas connected with each area is smaller than at least one item in the first connection number threshold. Illustratively, the difference number threshold is 50, and the first connection number threshold is 20. In the embodiment of the present application, there may be multiple region division manners, which is not limited in the present application, as long as it is ensured that the multiple regions obtained by final division meet the division rule.

According to the foregoing region division principle, to divide the nodes with low data interaction frequency into different regions, the data interaction frequency between the divided regions needs to be low. The data interaction frequency of a certain region and other regions can be reflected by the number of other regions connected with the region, for example, the number of regions connected with a certain region is positively correlated with the data interaction frequency of the region and other regions, so that the number of regions connected with each region obtained by division can be small. The node number difference of each region is smaller than the difference number threshold, that is, the scale of each region obtained by dividing is more balanced, so that the efficiency of region division is improved.

In an alternative implementation, the path calculation unit may divide the plurality of regions directly based on the division rule. The division of the plurality of regions is performed, for example, using a pre-established regular division model.

In another alternative implementation, since there are more nodes in the communication system connected to only a small number (e.g., 1 or 2) of other nodes, in order to improve the efficiency of region division, the path computation unit may perform multiple division based on the division rule to obtain multiple regions. For example, a small number of primary nodes may be divided to obtain a transition region, and then a large number of secondary nodes may be divided to obtain a plurality of final regions, where the number of nodes connected to the primary nodes is greater than the number of nodes connected to the secondary nodes. That is, the nodes with a large number of nodes connected in the communication system may be divided first, and then the remaining nodes in the communication system may be divided into the areas to which the nodes connected thereto belong. Then step 2012 may include the steps of:

step X1, determining a plurality of nodes to be divided among a plurality of nodes in the communication system.

As described above, the path calculation unit may determine a node with a larger number of nodes connected in the communication system, determine the node as a node to be divided, that is, the aforementioned main node, and then divide the node to be divided. The node number (also referred to as the ingress and egress degree of the node) of the node to be divided may be greater than the second connection number threshold, that is, the path calculating unit may determine the node whose node number is greater than the second connection number threshold in the communication system as the node to be divided. The second connection number threshold may be 2, and optionally, the second connection number threshold may also be 3 or 4, which is not limited in this embodiment of the application.

Optionally, the path calculation unit may also determine the node to be partitioned in the communication system according to the device type of each node in the communication system, where the device type may be used to reflect the maximum number of connectable nodes of the node. For example, the path calculation unit may determine a node whose device type is a first specified type as the node to be divided, where the maximum number of connectable nodes reflected by the first specified type is greater than or equal to the second connection number threshold, or the path calculation unit may determine a node other than the node whose device type is a second specified type as the node to be divided, where the maximum number of connectable nodes reflected by the second specified type is less than or equal to the second connection number threshold. For example, the communication system is an optical transport network, the second specified device type is an Optical Switch Network (OSN) 1800I/II device type, the second connection number threshold is 3, and the maximum number of connectable nodes reflected by the OSN1800I/II device type is 2, and the maximum number of connectable nodes is smaller than the second connection number threshold, so that the node may be determined to be the remaining node except the node to be partitioned in the communication system. The "1800I/II" is a type of multi-service transport platform (MSTP), which refers to a node that simultaneously implements access, processing, and transmission of services such as Time Division Multiplexing (TDM), Asynchronous Transfer Mode (ATM), and ethernet, etc. of a data transmission channel, and is used to provide a unified network manager.

In addition, the various nodes in a communication system are typically connected in a hierarchy, with the communication system including multiple levels of networks, with a high level network managing multiple lower levels of networks. If the communication system is an optical transmission network, the communication system comprises a backbone network, a plurality of provincial networks, a plurality of metropolitan area networks and a plurality of access ring networks, wherein the backbone network can be an upper-level network, each provincial network can be a lower-level network of the backbone network, each metropolitan area network can be a lower-level network of the corresponding provincial backbone network, and each access ring network is a lower-level network of the corresponding metropolitan area network. The backbone network can manage each provincial network, each provincial network can manage each metropolitan area network in the provincial domain range, and each metropolitan area network can manage the access looped network in the city range. The networks of multiple levels may be divided according to geographical location, or according to the logical principle of network deployment. The lower network can acquire the node information in the current network and send the information to the upper network managing the lower network, so that the upper network manages the lower network.

Illustratively, the communications system backbone network comprises a plurality of third nodes, each backbone network comprising a plurality of second nodes, and each metro network comprising a plurality of first nodes. The first node in each metropolitan area network may be connected to a second node that manages or provides data access or forwarding services for the group of first nodes, which may be referred to as an aggregation node (e.g., a network management device or a wireless network access point) of the first nodes. The second nodes in each backbone network may in turn each be connected to a third node, which is configured to manage the group of second nodes, or provide data access or forwarding services for the group of second nodes, and may be referred to as an aggregation node (e.g., a network management device or a wireless network access point) of the second nodes.

For example, a region may be provided with a base station, and communication devices (such as mobile phones) in the region are connected to the base station and transmit data through the base station. The communication devices in the area may each be a node in the communication system, and the base station may be a sink node of the communication devices in the area.

Optionally, since the nodes with a high hierarchy may be aggregation nodes of the nodes with a low hierarchy, and the number of nodes connected by the aggregation nodes is large, the nodes to be divided in the embodiment of the present application may also be non-bottom nodes in the communication system. For example, assuming that the first node is a bottom node, the nodes to be divided in the embodiment of the present application are a second node and a third node.

And step X2, dividing the nodes to be divided according to the resource information and the dividing rule to obtain a plurality of transition areas.

In an optional implementation manner, the path calculation unit may directly divide the plurality of nodes to be divided based on the division rule to obtain the transition region. The partitioning of the plurality of transition regions is performed, for example, using a pre-established regular partitioning model.

In another optional implementation manner, since the data transmission control types of the nodes to be divided in the communication system may be different, in order to improve the efficiency of area division, the path calculation unit may perform coarse division first based on the data transmission control types of the nodes to be divided. And then thinning and dividing the transition region based on a dividing rule to obtain the transition region. The step X2 may include the steps of:

and step X21, preliminarily dividing the plurality of nodes to be divided according to the data transmission control types adopted by the nodes to be divided to obtain a plurality of initial areas.

The communication system may include a control plane for controlling a plurality of nodes of the transport plane to transmit data and a transport plane, which may include a two-layer network of an optical layer and an electrical layer. The data transmission control type refers to a network type on which the control plane controls each node to perform data transmission. In the communication system, the nodes adopting the same data transmission control type are connected with each other more likely, and the frequency of data interaction of the nodes is higher. Therefore, the nodes to be divided in the communication system can be divided primarily according to the data transmission control types adopted by the nodes, and the nodes to be divided adopting the same data transmission control types in the communication system are divided into the same initial area.

For example, the data transmission control types may include: an Automatic Switching Optical Network (ASON) control type and an all static control type. The ASON control type refers to a network type in which a process of transmitting data by a plurality of nodes is controlled by a control plane, and the all-static control type refers to a network type in which a process of transmitting data by a plurality of nodes is not controlled by the control plane. In addition, the control plane based on the ASON control type can automatically calculate a new link and control two nodes to transmit data through the new link when an original link between any two nodes fails. In the network of the all-static control type, two links for data transmission are allocated to any two nodes in advance, namely a main link and a standby link, and in the two links between the two nodes, if the main link for transmitting data fails, the standby link is started to transmit data.

Alternatively, the ASON control type may be subdivided into: an electrical layer ASON control type, an optical layer ASON control type, and an electro-optical ASON control type. The electrical layer ASON control type is a network type in which each node is controlled to transmit data only through an electrical layer in a control plane, the optical layer ASON control type is a network type in which each node is controlled to transmit data only through an optical layer in a control plane, and the photoelectric ASON control type is a network type in which each node is controlled to transmit data through an optical layer and an electrical layer in a control plane at the same time.

And step X22, dividing the plurality of initial areas according to the resource information and the dividing rule to obtain a plurality of transition areas.

For example, the nodes to be divided of each initial region in the plurality of initial regions may be divided based on a community discovery algorithm, so as to obtain a plurality of transition regions. The community discovery algorithm may be a GN algorithm (that is, a Newman and girvan algorithm), or may also be other algorithms, such as a Label Propagation Algorithm (LPA), and the like, which is not limited in this embodiment of the present application.

When the GN algorithm is used to divide the initial region, the optical fiber cables connecting any two nodes to be divided in the initial region may be marked as edges, and then the betweenness of each edge is determined. The betweenness is also the number of the target links to which each edge belongs, and the target link is the link with the minimum link cost between two nodes in the communication system. The side with the largest intermediary number in the communication system is deleted, and the intermediary numbers of the remaining sides in the communication system are recalculated. Repeating the process of deleting edges and recalculating medians until the nodes to be divided in the communication system are divided into a plurality of independent transition areas, the nodes to be divided in each transition area are connected through the edges which are not deleted, and the difference of the number of the nodes to be divided in each transition area is less than the difference number threshold.

And step X3, dividing the remaining nodes in the communication system except the nodes to be divided into transition areas to which the nodes connected with the remaining nodes belong to obtain the areas.

The number of nodes connected by the remaining nodes is less than or equal to a second connection number threshold, and the second connection number threshold is usually smaller (for example, 2 or 3). If the remaining nodes are connected with only one node, the remaining nodes can be directly divided into transition areas to which the connected nodes belong; if the remaining node is connected to a plurality of nodes, the remaining node may be divided into transition regions to which any one of the connected nodes belongs, and one remaining node may be divided into only one transition region.

It should be noted that the setting of the threshold in the partition rule in step 2012 may vary according to the actual application scenario, for example, in two optional implementations of step 2012, the difference number thresholds in the partition rule may be the same or different, and the first connection number thresholds may be the same or different.

The embodiment of the present application only takes the example that the path calculation unit divides a plurality of nodes in the communication system to obtain a plurality of areas. Alternatively, if the path calculating unit is installed on the server, when the server is started, the path calculating unit may execute step 201, that is, divide a plurality of nodes in the communication system into a plurality of areas. Alternatively, the plurality of areas may be divided by other nodes in the communication system to obtain area division information and stored in the other nodes, or divided by staff in advance to obtain area division information and stored in the storage device, where the area division information is used to indicate information of nodes included in the plurality of areas in the communication system. In this case, the path calculation unit only needs to receive the area division information transmitted by the other node or the storage device, and determine information of nodes included in the plurality of areas in the current communication system based on the area division information, without performing step 201 described above.

Step 202, receiving a path computation request.

Illustratively, the optical fiber cables connecting the nodes in the communication system are pre-arranged, and an enterprise user may request the path computation unit to allocate a dedicated data transmission link to the enterprise through the path computation client, where the data transmission link is a target link to be determined by the path computation unit. Or, when the user needs to transmit data between the source node and the destination node, the user may request the path computation unit to determine a target link for transmitting the data through the path computation client.

The path computation request may carry an identifier of the active node and an identifier of the destination node, and the target link may be a link with the smallest link cost from the source node to the destination node. It should be noted that when the demands of the users are different, the link cost can be characterized by different parameters. For example, the link cost may be represented by a time delay of data transmitted by a link, or the link cost may also be represented by the number of nodes passed by the link, which is not limited in the embodiment of the present application. Optionally, the path computation request may also carry a parameter for characterizing the link cost.

And 203, when the source area and the destination area are different areas, sequentially performing a link determination process on each area from the source area along a direction far away from the source area to obtain a target sub-link with the smallest link cost from the entry node to each exit node in each area.

The source area is an area to which a source node belongs in a plurality of areas in the communication system, and the destination area is an area to which a destination node belongs in the plurality of areas. An entry node in the source region is a source node, an entry node of a region other than the source region among the plurality of regions is a node connected to an exit node of a previous region, an exit node of a region other than the destination region among the plurality of regions is a node connected to a subsequent region in the region, and an exit node of the destination region is a destination node.

Taking two regions in a communication system as an example, assuming that the two regions are a first region and a second region respectively, the first region is directly connected with the source region, and the second region is connected with the source region through the first region, it can be determined that the first region is a previous region of the second region, and the second region is a next region of the first region. The direction away from the source region is the direction from the first region to the second region.

Illustratively, fig. 4 shows a schematic diagram of a portion of a region in a communication system. Assuming that the path calculation unit in the communication system receives the path calculation request, and the path calculation request calculates the target path between the source node 101a and the destination node 101h, the path calculation unit may determine that the area Q0 where the node 101a is located is the source area and the area Q2 where the node 101h is located is the destination area in the communication system shown in fig. 4. As shown in FIG. 4, the source domain Q0 includes a source node 101a, a node 101b, and a node 101c, the first domain Q1 includes a node 101d, a node 101e, and a node 101f, and the destination domain Q2 includes a destination node 101h, a node 101m, and a node 101 n. Node 101c in source region Q0 is connected to node 101d in region Q1, and node 101e in region Q1 is connected to node 101m in destination region Q2. In the communication system of the type shown in fig. 4, the source node 101a in the source area Q0 is an ingress node, and the node 101c is an egress node; the node 101d in the first region Q1 is an ingress node, and the node 101e is an egress node; the node 101m in the destination area Q2 is an ingress node, and the destination node 101h is an egress node. It should be noted that each area shown in fig. 4 is only used to explain an entry node and an exit node of each area, and the number of nodes and the connection relationship of each area in the embodiment of the present application are not limited.

Alternatively, when the plurality of zones is at least three zones, the link determination process for at least two of the plurality of zones may be performed in parallel starting from the source zone in a direction away from the source zone. If the communication system shown in fig. 4 further includes a third area (not shown in fig. 4) through which the source area and the destination area may be further connected, after the link determination process is performed on the source area, the link determination process on the first area and the link determination process on the third area may be performed in parallel. In addition, after the link execution process of any one of the first area and the third area is completed, the link determination process may be started for the destination area. If the link determination process for the third area is not completed, the link determination process for the third area and the link determination process for the destination area may be executed in parallel.

It should be noted that, because the sizes of the plurality of areas obtained by dividing in step 201 are relatively balanced, and the number of connections between each area and other areas is relatively small, the time difference of the path calculation unit executing the link determination process on each area is relatively small, which is beneficial to parallel execution of the link determination processes of each area, and the rate of calculating the target link by the path calculation unit can be relatively high.

The link determining process in the embodiment of the present application may have various implementation manners, and the embodiment of the present application takes the following two implementation manners as examples for explanation.

In a first implementation manner, referring to fig. 5, the link determining process may include:

step 501, determining feasible sublinks from an ingress node to each egress node.

Illustratively, for region Q0 in the communication system shown in fig. 4, the feasible sublinks of ingress node 101a to egress node 101c include: two possible sublinks, "101 a → 101 c" and "101 a → 101b → 101 c". Where "A → B" represents the link of node A directly to node B, and node A is directly connected with node B. Illustratively, "101 a → 101 c" represents a sublink from the ingress node 101a directly to the egress node 101c, and "101 a → 101b → 101 c" represents a sublink from the ingress node 101a through node 101b to the egress node 101 c.

Step 502, calculating link costs of the feasible sublinks from the ingress node to each egress node based on the initial link costs of the ingress node, where the initial link cost of the ingress node in the source region is 0, and the initial link costs of the ingress nodes in regions other than the source region in the plurality of regions are: a link cost of a target sublink to which an egress node of a previous area to which the ingress node is connected belongs.

Illustratively, taking the source area Q0 in fig. 4 as an example, assuming that the link cost is characterized by the delay of data transmission through the link, and the initial link cost of the ingress node 101a is t0, the link cost of the node 101a directly to the node 101b is t1, the link cost of the node 101b directly to the node 101c is t2, and the link cost of the node 101a directly to the node 101c is t 3; in this case, the link cost of the feasible sublink "101 a → 101b → 101 c" is t0+ t1+ t2, and the link cost of the feasible sublink "101 a → 101 c" is t0+ t 3.

Alternatively, the path computation unit may compute the link cost of the feasible sub-links from the ingress node to each egress node based on the initial link cost of the ingress node according to a single-source shortest path algorithm. The single source shortest path algorithm includes: at least one of Dijkstra (DJ) Algorithm and Shortest Path Fast Algorithm (SPFA) Algorithm, also known as a queue optimization version of bellman-ford Algorithm.

Step 503, based on the calculated link cost, determining the feasible sub-link with the minimum link cost from the ingress node to each egress node as the target sub-link, and recording the link cost of the target sub-link.

For example, for each area in the communication system, the path computation unit may compare the link costs of a plurality of feasible sublinks from each ingress node to each egress node in the area, and determine the feasible sublink with the smallest link cost from each ingress node to each egress node as a target sublink of the area. And the path computation element may record the link cost of each target sublink.

In a second implementation manner, referring to fig. 6, the link determining process may include:

step 601, determining feasible sublinks from the entrance node to each exit node.

Step 501 may be referred to in step 601, and details thereof are not described herein again in this embodiment.

Step 602, calculating the link cost of the feasible sublinks from the ingress node to each egress node based on the initial link cost of the ingress node, where the initial link cost of the ingress node is 0.

Wherein, the link cost of the feasible sublinks from the ingress node to the egress node may be: the sum of the link costs between each two adjacent nodes in the feasible sublink. Illustratively, taking the source region Q0 in fig. 4 as an example, assuming that the link cost is characterized by the delay of data transmission through the link, and the initial link cost of the ingress node 101a is 0, the link cost of the node 101a directly to the node 101b is t1, the link cost of the node 101b directly to the node 101c is t2, and the link cost of the node 101a directly to the node 101c is t 3; in this case, the link cost of the feasible sublink "101 a → 101b → 101 c" is t1+ t2, and the link cost of the feasible sublink "101 a → 101 c" is t 3.

Step 502 may be referred to as another process in step 602, which is not described in detail herein.

Step 603, based on the calculated link cost, determining the feasible sublink with the minimum link cost from the entry node to each exit node as the target sublink, and recording the link cost of the target sublink.

Step 603 may refer to step 503, which is not described herein again. Alternatively, the path calculation unit may record and store a correspondence between each target sublink and the link cost of the target sublink.

It should be noted that the link cost of the target sub-link may be represented by different parameters, and when the parameters for representing the link cost of the target sub-link are different, the initial link cost of the ingress node in the area to which the target sub-link belongs may be different, and the link cost of the target sub-link may also be different.

In the first implementation manner, the link cost of the target sub-link is characterized by the minimum link cost from the source node to the egress node of the target sub-link, and the link cost of the target sub-link is related to the link cost of the link before the target sub-link. At this time, if the area to which the target sub-link belongs is the source area to which the source node belongs (the entry node of the area is the source node), the initial link cost of the entry node is 0. If the area to which the target sub-link belongs is an area other than the source area in the plurality of areas in the communication system, the initial link cost of the ingress node is: a link cost of a target sublink to which an egress node of a previous area to which the ingress node is connected belongs. For example, for the communication system shown in fig. 4, assuming that the link cost is the time delay of the link transmitting data, the destination sublink from the source node 101a to the node 101c in the source area Q0 is "101 a → 101 c", and the link cost of the destination sublink is 100 ms, then the initial link cost of the ingress node 101d of the first area Q1 is 100 ms. If the time delay for transmitting data of the target sub-link "101 d → 101f → 101 e" in the first region Q1 is 50 ms, the link cost of the target sub-link "101 d → 101f → 101 e" is 150 ms from 100 ms +50 ms.

In the second implementation manner, the link cost of the target sub-link may be represented by only the link cost of the target sub-link itself, and the link cost of the target sub-link is unrelated to the link cost of the link before the target sub-link. At this time, the initial link costs of the entry nodes in the area to which the target sub-link belongs are all 0. If the link cost is characterized by the delay of the link transmitting data, and the delay of the target sublink "101 d → 101f → 101 e" in the first region Q1 is 50 ms, the link cost of the target sublink "101 d → 101f → 101 e" is 50 ms.

And step 204, determining the link with the minimum link cost in a plurality of feasible links from the source node to the destination node as the target link based on the target sub-link with the minimum link cost from the entry node to each exit node in each area.

In a first aspect, corresponding to the first implementation manner in step 203, in step 204, the path calculation unit may directly determine a feasible link to which the target sub-link in the destination area belongs as the target link. As described above, a plurality of feasible links exist between the source node and the destination node, the path calculation unit records and stores a correspondence between the link cost of each target sub-link and the traversed link to which the target sub-link belongs, and after the target sub-link in the destination area is determined, the traversed link to which the target sub-link belongs is the feasible link to which the target sub-link belongs, and the feasible link is determined as the target link.

For example, for the communication system shown in fig. 4, if the path calculation unit determines that the target sub-link in the destination area is "101 m → 101 h", and the traversed link to which the target sub-link belongs is the feasible link "101 a → 101c → 101d → 101f → 101e → 101m → 101 h" in the correspondence relationship recorded by the path calculation unit, the feasible link may be directly determined as the target link with the smallest link cost from the source node to the destination node.

Optionally, in the process of executing the first implementation manner of step 203, after determining each target sublink, the path computation unit needs to mark a node on the target sublink, so as to determine a target link based on the target sublink in step 204.

In a first optional implementation manner, during the process of executing the first implementation manner of step 203, the path calculation unit marks a node located on the target sublink in each area, and after step 203 is executed, based on a result of the marking and a recorded link cost, sequentially obtains an optimal forward target sublink corresponding to each area from the target area in a reverse direction (i.e., a direction from the target node to the source node) until the target sublink in the source area is obtained, and determines a link obtained by connecting the obtained target sublinks as a feasible link to which the target sublink in the target area belongs, where the feasible link is the target link. The optimal forward target sublink of any region is the sublink with the minimum link cost in the target sublink connected with the target sublink in the region.

In a second optional implementation manner, in the process of executing the first implementation manner of step 203, the path computation unit instructs each node to record the optimal forward node of each node, so as to mark the optimal forward node of each node, where the optimal forward node of any node is a node directly connected to any node in a link with the smallest link cost between the any node and the source node. After the path calculation unit determines the target sub-link in the destination area, the optimal forward node corresponding to each node may be sequentially obtained in a reverse direction (i.e., a direction from the destination node to the source node) from the destination node until the source node is obtained. And connecting the acquired nodes according to the acquisition sequence to obtain a link, wherein the link is a feasible link to which the target sub-link in the target area belongs, and determining the feasible link as the target link. In this case, only the information of one node needs to be stored in each node, and the path calculation unit can obtain the target link by sequentially acquiring the optimal forward node of each node when determining the target link, so that the resource occupation of each node and the path calculation unit is small.

Of course, in the process of executing the first implementation manner of step 203, the path computation unit may further record the correspondence between all determined target sub-links and link costs thereof, determine, based on the correspondence, a feasible link to which the target sub-link in the target area belongs, and determine, as the target link, a feasible link to which the target sub-link in the target area belongs.

In a second aspect, corresponding to the second implementation manner in step 203, in step 204, the path computation unit may determine the target link based on the link cost of the target sublink of each zone and the link costs of each two adjacent zones.

It should be noted that, in the process of executing the second implementation manner of step 203, the initial link cost of each ingress node is 0, which actually means that if another area is connected before the area to which the ingress node belongs, the path calculation unit assumes that the link cost of the ingress node and the egress node of the previous area connected thereto is 0, so that the influence of the previous area is not considered when calculating the target sublink of the current area. In the actual calculation process, the path calculation unit may record a link cost between every two adjacent regions, that is, a link cost between an entry node of a subsequent region and an exit node of a previous region, so as to determine the target link. For example, in fig. 4, the link costs of the region Q0 and the region Q1 are the link costs between the node 101c and the node 101 d.

In an alternative example, the determined plurality of target sub-links are combined starting from the source area and moving away from the source area to obtain a plurality of feasible links from the source node to the destination node. Then, the sum of the link costs of the target sub-links constituting each feasible link is determined as the link cost of each feasible link, and the link with the smallest link cost among the feasible links is determined as the target link. As described above, the path calculation unit may record and store the correspondence between each target sub-link and the link cost of the target sub-link. The path calculation unit may query the correspondence to obtain the plurality of target sub-links, and combine the obtained plurality of target sub-links.

For example, for the communication system shown in fig. 4, it is assumed that the link cost of the target sublink adopts the second link cost characterization manner, and the target sublink in the source area Q0 includes "101 a → 101 c", the target sublink in the first area Q1 includes "101 d → 101f → 101 e", and the target sublink in the destination area Q2 includes "101 m → 101n → 101 h", the path calculating unit may combine the target sublinks in the three areas to obtain the first feasible link "101 a → 101c → 101d → 101f → 101e → 101m → 101 h". If the source area, the first area and the destination area do not include other destination sublinks, the path calculation unit determines the first feasible link as a destination link from the source node to the destination node. If the source area, the first area, and the destination area further include other target sublinks, the path calculation unit may determine, as the link cost of the first feasible link, the sum of the link costs of the target sublinks "101 a → 101 c", "101 d → 101f → 101 e", and "101 m → 101 h", and the link costs of each two areas (i.e., the link cost between "101 c → 101 d" and the link cost between "101 e → 101 m"). Then, the path calculation unit combines the target sub-links in each area to obtain other feasible links, and determines a feasible link with a lower link cost between the first feasible link and the other feasible links as a target link from the source node to the destination node.

In another optional example, the path computation unit may also use the method for determining the target link in the foregoing first aspect, and in the process of performing the second implementation manner of step 203, after determining each target sublink, mark a node on the target sublink, and then determine the target link using the two optional implementation manners of the foregoing first aspect.

Optionally, after the path computation unit determines the target link with the minimum link cost from the source node to the destination node, the information of the target link may be sent to the path computation client, so as to notify the user of the information of the target link. The information of the target link may include: link cost of the target link, and nodes and fiber cables through which the target link passes. The user can know the information of the target link, so that the maintenance of the target link or the data transmission based on the target link can be facilitated.

The path calculation unit may include a plurality of Virtual Machines (VMs), where the plurality of VMs correspond to the plurality of areas one by one, and the target child chain in each area is calculated by the corresponding VM, that is, each VM is configured to perform the link determination process, i.e., perform the steps 501 to 503, or perform the steps 601 to 603. The plurality of virtual machines may be deployed in one or more devices. Each virtual machine may include one or more compute instances. As mentioned above, the number of nodes in each of the plurality of regions in the communication system may be substantially the same, for example, the number of nodes in each region may range from 350 to 450. In this way, the calculation resources consumed by the virtual machines to calculate the links in the corresponding areas are approximately the same, so that the virtual machines with the same performance can be used to calculate the links in each area, virtual machines with different performances do not need to be allocated to different areas, and the link determination efficiency can be improved. When the number of nodes deployed in the communication system increases so that the number of areas in the communication system increases (the newly added nodes can be divided into one area individually, or the step 201 is executed again on the nodes of the whole communication system to obtain new areas by division), only virtual machines with the same performance need to be added in the path calculation unit, and the path calculation unit has better adaptability and higher universality. Further, by setting a plurality of virtual machines to execute the link determination process, parallel calculation of the link determination process can be realized.

Referring to fig. 7, fig. 7 is a schematic structural diagram of a path calculating unit 70 according to an embodiment of the present disclosure, where the path calculating unit 70 includes a dividing module 701, a path calculation control module 702, and a plurality of virtual machines 703 in one-to-one correspondence with a plurality of areas, where the dividing module 701 is configured to execute the step 201, each virtual machine 703 is configured to execute the link determining process, and the path calculation control module 702 is configured to execute the processes executed by the virtual machines 703 in the step 202 and the step 203, and the step 204.

As shown in fig. 8, assuming that a region includes 6 nodes, a conventional path determining method is adopted, a path calculating unit needs to traverse each node in the region, and the calculation complexity is high, but in the present application, corresponding to the first implementation manner in step 203, the path calculation control module 702 does not need to participate in the calculation process of the virtual machine, and only needs to determine the target link based on the link cost output by the virtual machine corresponding to the target region; corresponding to the second implementation manner in step 203, the path computation control module 702 does not need to participate in the computation process of the virtual machines, and only needs to determine the target link based on the sum of the link costs output by each virtual machine, so that the overall computation complexity of the path computation unit is low by reasonably dividing each functional unit in the path computation unit. Fig. 8 illustrates the first implementation manner in step 203, where the initial link cost of the area corresponding to the virtual machine in fig. 8 is 100, the target sublinks are 3, and the link costs are 111, 105, and 103, respectively.

It should be noted that, with the development of communication technology, the number of nodes in a communication system is increasing. Today, communication systems have covered more than three hundred and a million cities, and there are already over a hundred thousand nodes in the network. The number of network elements in a network will reach thirty-thousand nodes quickly, and the time for calculating a single target link by a path calculation unit in the prior art is about 10 seconds, so that the requirement on the calculation efficiency of the path calculation unit is difficult to meet. In the path determining method provided by the embodiment of the application, the path calculation is performed in regions, and the link determining process of each region can be executed in parallel, so that even if the number of nodes in the network reaches thirty thousand, the path calculating unit can determine a single target link within 200 milliseconds, and the requirement on the calculating efficiency of the path calculating unit can be met.

To sum up, in the path determining method provided in the embodiment of the present application, the target sub-link with the smallest link cost from the ingress node to each egress node in each area is determined, and the target link is determined based on the target sub-link with the smallest link cost from the ingress node to each egress node in each area. Therefore, the path calculation is carried out by partitioning the regions, and only the combination mode of the target sublinks of each region is needed to be determined, but the data transmission combination mode of all nodes between the source node and the destination node is not needed to be determined, so that the calculation cost of the path calculation unit is reduced, and the calculation efficiency is improved. In addition, the link determination processes of a plurality of areas can be executed in parallel, and the operation efficiency of the path calculation unit is further improved.

Fig. 9 is a schematic structural diagram of a path determination device according to an embodiment of the present application. The path determination apparatus may be used for a path calculation unit in the communication system 10 shown in fig. 1, where the communication system 10 includes a plurality of areas that are connected to each other and do not overlap with each other, and each area includes a plurality of nodes. As shown in fig. 9, the path calculation means 90 may include:

a first receiving module 901, configured to receive a path computation request, where the path computation request is used to request to compute a target link with a minimum link cost from a source node to a destination node.

A sub-link determining module 902, configured to, when a source area to which a source node belongs and a destination area to which a destination node belongs are different areas, sequentially perform a link determining process on each area from the source area in a direction away from the source area, and obtain a target sub-link with a smallest link cost from an ingress node to each egress node in each area.

A link determining module 903, configured to determine, as a target link, a link with the smallest link cost in multiple feasible links between a source node and a destination node, based on the target sub-link with the smallest link cost from an ingress node to each egress node in each area;

To sum up, in the path determining apparatus provided in the embodiment of the present application, the sub-link determining module determines the target sub-link with the smallest link cost from the ingress node to each egress node in each area, and the link determining module determines the target link based on the target sub-link with the smallest link cost from the ingress node to each egress node in each area. Therefore, the path calculation is carried out by partitioning the regions, and only the combination mode of the target sublinks of each region is needed to be determined, but the data transmission combination mode of all nodes between the source node and the destination node is not needed to be determined, so that the operation cost of the path determination device is reduced, and the operation efficiency is improved.

Optionally, as shown in fig. 10, the sub-link determining module 902 may include:

a first determining submodule 9021 is configured to determine, in each area, a feasible sub-link from an ingress node to each egress node.

A first calculating submodule 9022, configured to calculate, based on the initial link cost of the ingress node, link costs of the feasible sub-links from the ingress node to each egress node.

A second determining sub-module 9023, configured to determine, based on the calculated link cost, a feasible sub-link with a smallest link cost from the ingress node to each egress node as a target sub-link, and record a link cost of the target sub-link, where an initial link cost of the ingress node in the source area is 0, and an initial link cost of an ingress node in an area other than the source area in the multiple areas is: a link cost of a target sublink to which an egress node of a previous area to which the ingress node is connected belongs.

A link determining module 903, configured to determine a feasible link to which the target sub-link in the destination area belongs as the target link.

Optionally, as shown in fig. 11, the sub-link determining module 902 may include:

a third determining submodule 9024 is configured to determine a feasible sub-link from the ingress node to each egress node in each area.

And the second calculating submodule 9025 is configured to calculate, based on the initial link cost of the ingress node, a link cost of a feasible sub-link from the ingress node to each egress node, where the initial link cost of the ingress node is 0.

And the fourth determining submodule 9026 is configured to determine, based on the calculated link cost, a feasible sub-link with the smallest link cost from the ingress node to each egress node as a target sub-link, and record the link cost of the target sub-link.

The link determination module 903 is configured to: and determining the target link based on the link cost of the target sublink of each area and the link costs of every two adjacent areas.

Optionally, the sub-link determining module 902 is configured to: and calculating the link cost of the feasible sub-link from the inlet node to each outlet node based on the initial link cost of the inlet node according to a single-source shortest path algorithm.

Optionally, the sub-link determining module 902 is configured to: when the plurality of zones is at least three zones, the link determination process of at least two zones of the plurality of zones is executed in parallel starting from the source zone in a direction away from the source zone.

Optionally, as shown in fig. 12, on the basis of fig. 9, the path determining apparatus 90 further includes:

a dividing module 904, configured to divide a plurality of nodes in the communication system into a plurality of areas before receiving the path calculation request;

alternatively, as shown in fig. 13, the path determination device 90 further includes, in addition to fig. 9:

a second receiving module 905, configured to receive area division information before receiving the path calculation request, where the area division information is used to indicate information of nodes included in a plurality of areas in the communication system.

Optionally, as shown in fig. 14, the dividing module 904 includes:

the obtaining sub-module 9041 is configured to obtain resource information of the communication system, where the resource information includes a connection relationship between multiple nodes in the communication system.

The partitioning submodule 9042 is configured to partition, according to the resource information and according to a partitioning rule, a plurality of nodes in the communication system into a plurality of regions.

Optionally, the partitioning sub-module 9042 is configured to:

determining a plurality of nodes to be divided in a plurality of nodes in the communication system, wherein the number of the nodes connected with the nodes to be divided is larger than a second connection number threshold value, or the nodes to be divided are nodes of an appointed type, or the nodes to be divided are non-bottom nodes in the communication system; dividing a plurality of nodes to be divided according to resource information and a division rule to obtain a plurality of transition areas; and dividing the rest nodes except the nodes to be divided in the communication system into transition areas to which the nodes connected with the rest nodes belong to obtain a plurality of areas.

Optionally, the partitioning sub-module 9042 is configured to:

preliminarily dividing a plurality of nodes to be divided according to the data transmission control type adopted by the nodes to be divided to obtain a plurality of initial areas; and dividing the plurality of initial regions according to the resource information and a division rule to obtain a plurality of transition regions.

Optionally, the partitioning sub-module 9042 is configured to: and based on a community discovery algorithm, dividing the plurality of initial regions according to resource information and a division rule to obtain a plurality of transition regions.

Optionally, the partitioning rule includes: and the difference of the number of the nodes of each area is smaller than the difference number threshold, and the number of the areas connected with each area is smaller than at least one item in the first connection number threshold.

Optionally, the path calculation unit includes a plurality of virtual machines in one-to-one correspondence with the plurality of areas, and the target child chain in each area routes the corresponding virtual machine calculation.

Fig. 15 is a schematic structural diagram of a path computation unit according to an embodiment of the present application. As shown in fig. 15, the path calculation unit 150 may include: at least one processor 1501 (e.g., a central processing unit), at least one network interface 1502, memory 1503, and at least one bus 1504 to enable communications among the processor, network interface, and memory; the memory 1503 and the network interface 1502 are connected to the processor 1501 via the bus 1504, respectively. The processor 1501 is used to execute executable modules, such as computer programs, stored in the memory 1503. The Memory 1503 may be implemented by any type of volatile or non-volatile storage device or combination thereof, and the Memory 1503 may include a Random Access Memory (RAM) and may further include a non-volatile Memory (non-volatile) such as at least one disk Memory. The communication connection between the apparatus and at least one other apparatus is realized through at least one network interface 1502 (wired or wireless). In some embodiments, the memory 1503 stores programs and modules that can be executed by the processor 1501 to implement the path determination methods provided by the embodiments of the present application. As shown in fig. 15, the memory 1503 may store therein a partitioning module 1503a, a path calculation control module 1503b, and a virtual machine 1503c, as well as at least one application program required for other functions. The processor 1501 may execute the partitioning module 1503a in the memory 1503 to implement the above step 201, the processor 1501 may execute the virtual machine 1503c to implement the link determination process in the above step 203, and the processor 1501 may execute the path calculation control module 1503b to implement the processes performed by the dividing module 1503c in the above step 202, step 203, and step 204. The function of the dividing module 1503a may refer to the function of the dividing module 701 in fig. 7, the function of the path calculation control module 1503b may refer to the function of the path calculation control module 702 in fig. 7, and the function of the virtual machine 1503c may refer to the function of the virtual machine 703 in fig. 7, which is not described herein in detail in this embodiment of the present application.

The above communication connections may be connected through a wired network or a wireless network, wherein the wired network may include, but is not limited to: computer networks connected using fiber optics, Universal Serial Bus (USB), coaxial cable, twisted pair, or the like, wireless networks may include, but are not limited to: wireless fidelity (WIFI), bluetooth, infrared, Zigbee (Zigbee), data network, and the like.

The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded or executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more collections of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a Solid State Drive (SSD).

It should be noted that: the path determining apparatus provided in the foregoing embodiment is only illustrated by dividing the functional modules when determining the target link, and in practical applications, the function distribution may be completed by different functional modules according to needs, that is, the internal structure of the path calculating unit is divided into different functional modules to complete all or part of the functions described above. In addition, the path determining apparatus and the path determining method provided in the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments and are not described herein again.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments. The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A path determination method used in a path computation unit in a communication system including a plurality of areas connected to each other and not overlapping with each other, each of the areas including a plurality of nodes, the method comprising:

receiving a path calculation request, wherein the path calculation request is used for requesting to calculate a target link with the minimum link cost from a source node to a destination node;

when the source region to which the source node belongs and the destination region to which the destination node belongs are different regions, sequentially performing a link determination process on each region from the source region along a direction far away from the source region to obtain a target sub-link with the smallest link cost from an inlet node to each outlet node in each region;

determining a link with the smallest link cost in a plurality of feasible links from the source node to the destination node as a target link based on the target sub-link with the smallest link cost from the inlet node to each outlet node in each area;

wherein an entry node in the source region is the source node, an entry node of a region other than the source region in the plurality of regions is a node connected to an exit node of a previous region, an exit node of a region other than the destination region in the plurality of regions is a node connected to a next region, and an exit node of the destination region is the destination node.

2. The method of claim 1, wherein for each of the regions, the link determination procedure comprises:

determining feasible sublinks from an ingress node to each egress node;

calculating link costs of the feasible sub-links from the ingress node to each egress node based on the initial link costs of the ingress node;

determining a feasible sublink with the minimum link cost from the inlet node to each outlet node as the target sublink based on the calculated link cost, and recording the link cost of the target sublink, wherein the initial link cost of the inlet node in the source area is 0, and the initial link cost of the inlet node in an area except the source area in the plurality of areas is: link costs of a target sub-link to which an exit node of a previous area to which the entry node is connected belongs;

the determining, as a target link, a link with the smallest link cost among a plurality of feasible links from the source node to the destination node based on the target sub-link with the smallest link cost from the ingress node to each egress node in each of the regions, includes:

and determining a feasible link to which the target sub-link in the target area belongs as the target link.

3. The method of claim 1, wherein for each of the regions, the link determination procedure comprises:

determining feasible sublinks from an ingress node to each egress node;

calculating link costs of the feasible sub-links from the ingress node to each egress node based on the initial link costs of the ingress node, wherein the initial link costs of the ingress node are 0;

determining a feasible sublink with the minimum link cost from the inlet node to each outlet node as the target sublink based on the calculated link cost, and recording the link cost of the target sublink;

and determining the target link based on the link cost of the target sublink of each area and the link costs of every two adjacent areas.

4. The method of claim 2 or 3, wherein said calculating link costs of feasible sublinks from the ingress node to each egress node based on an initial link cost of the ingress node comprises:

and calculating the link cost of the feasible sub-link from the inlet node to each outlet node based on the initial link cost of the inlet node according to a single-source shortest path algorithm.

5. The method as claimed in any one of claims 1 to 4, wherein when the plurality of zones is at least three zones, the link determination process for at least two of the plurality of zones is performed in parallel starting from the source zone in a direction away from the source zone.

6. The method of any of claims 1 to 5, wherein prior to said receiving a path computation request, the method further comprises:

dividing a plurality of nodes in the communication system to obtain a plurality of areas;

or receiving area division information indicating information of nodes included in the plurality of areas in the communication system.

7. The method of claim 6, wherein the dividing the plurality of nodes in the communication system into the plurality of regions comprises:

acquiring resource information of a communication system, wherein the resource information comprises connection relations among a plurality of nodes in the communication system;

and dividing a plurality of nodes in the communication system according to the resource information and a division rule to obtain a plurality of areas.

8. The method of claim 7, wherein the dividing the plurality of nodes in the communication system into the plurality of regions according to the resource information and a division rule comprises:

determining a plurality of nodes to be divided in a plurality of nodes in the communication system, wherein the number of the nodes connected with the nodes to be divided is greater than a second connection number threshold, or the nodes to be divided are nodes of a specified type, or the nodes to be divided are non-bottom nodes in the communication system;

dividing the nodes to be divided according to the resource information and a dividing rule to obtain a plurality of transition areas;

and dividing the rest nodes except the nodes to be divided in the communication system into transition areas to which the nodes connected with the rest nodes belong to obtain the plurality of areas.

9. The method according to claim 8, wherein the dividing the plurality of nodes to be divided into a plurality of transition regions according to the resource information and a division rule comprises:

preliminarily dividing the nodes to be divided according to the data transmission control type adopted by the nodes to be divided to obtain a plurality of initial areas;

and dividing the plurality of initial regions according to the resource information and a dividing rule to obtain the plurality of transition regions.

10. The method of claim 9, wherein the dividing the plurality of initial regions into the plurality of transition regions according to the resource information and a division rule comprises:

and based on a community discovery algorithm, dividing the plurality of initial regions according to the resource information and a division rule to obtain the plurality of transition regions.

11. The method of claim 7,

the partitioning rule includes: and the difference of the number of the nodes of each region is smaller than a difference number threshold value, and the number of the regions connected with each region is smaller than at least one of a first connection number threshold value.

12. The method of any of claims 1 to 11, wherein the path computation unit comprises a plurality of virtual machines in one-to-one correspondence with the plurality of zones, and wherein the target child chain in each zone is routed to the corresponding virtual machine computer.

13. A path determination device used in a path calculation unit in a communication system including a plurality of areas connected to each other and not overlapping with each other, each of the areas including a plurality of nodes, the path determination device comprising:

a receiving module, configured to receive a path computation request, where the path computation request is used to request computation of a target link with a minimum link cost from a source node to a destination node;

a sub-link determining module, configured to, when a source region to which the source node belongs and a destination region to which the destination node belongs are different regions, sequentially perform a link determining process on each of the regions from the source region in a direction away from the source region, and obtain a target sub-link with a minimum link cost from an ingress node to each egress node in each of the regions;

a link determining module, configured to determine, based on a target sub-link with a smallest link cost from an ingress node to each egress node in each of the regions, a link with a smallest link cost from a plurality of feasible links between the source node and the destination node as the target link;

14. The path determination device of claim 13, wherein the sub-link determination module comprises:

a first determining submodule for determining feasible sub-links from an ingress node to each egress node in each of said regions;

a first calculating submodule, configured to calculate, based on an initial link cost of the ingress node, link costs of feasible sub-links from the ingress node to each egress node;

a second determining sub-module, configured to determine, based on the calculated link cost, a feasible sub-link with a smallest link cost from the ingress node to each egress node as the target sub-link, and record a link cost of the target sub-link, where an initial link cost of an ingress node in the source area is 0, and initial link costs of ingress nodes in areas other than the source area in the plurality of areas are: link costs of a target sub-link to which an exit node of a previous area to which the entry node is connected belongs;

the link determination module is to:

15. The path determination device of claim 13, wherein the sub-link determination module comprises:

a third determining submodule, configured to determine a feasible sub-link from an ingress node to each egress node in each of the areas;

a second calculating submodule, configured to calculate, based on an initial link cost of the ingress node, link costs of feasible sub-links from the ingress node to each egress node, where the initial link cost of the ingress node is 0;

a fourth determining submodule, configured to determine, based on the calculated link cost, a feasible sub-link with a smallest link cost from the ingress node to each egress node as the target sub-link, and record the link cost of the target sub-link;

the link determination module is to:

16. The path determination device according to claim 14 or 15, wherein the sub-link determination module is configured to:

17. The path determination device according to any one of claims 13 to 16, wherein the sub-link determination module is configured to:

when the plurality of regions are at least three regions, the link determination process of at least two regions of the plurality of regions is performed in parallel starting from the source region in a direction away from the source region.

18. The path determination apparatus according to any one of claims 13 to 17, characterized by further comprising:

a dividing module, configured to divide a plurality of nodes in the communication system to obtain the plurality of areas before receiving the path computation request;

or, the second receiving module is configured to receive, before receiving the path calculation request, area division information, where the area division information is used to indicate information of nodes included in the plurality of areas in the communication system.

19. The path determination device of claim 18, wherein the partitioning module comprises:

the acquisition submodule is used for acquiring resource information of a communication system, wherein the resource information comprises a connection relation among a plurality of nodes in the communication system;

and the division submodule is used for dividing the plurality of nodes in the communication system according to the resource information and the division rule to obtain the plurality of areas.

20. The path determination device of claim 19, wherein the partitioning sub-module is configured to:

21. The path determination device of claim 20, wherein the partitioning sub-module is configured to:

22. The path determination device of claim 21, wherein the partitioning sub-module is configured to:

23. The path determination device of claim 19,

24. The apparatus according to any one of claims 13 to 23, wherein the path calculation unit includes a plurality of virtual machines in one-to-one correspondence with the plurality of zones, and the target child link in each zone is routed by the corresponding virtual machine.

25. A communication system, the communication system comprising: a plurality of nodes, a path computation element and a path computation client, the plurality of nodes, the path computation element and the path computation client being interconnected, the path computation element comprising the path determination apparatus according to any one of claims 13 to 24.

26. A path determination device, characterized in that the path determination device comprises: at least one processor for performing the path determination method of any of claims 1 to 12, at least one interface, a memory and at least one communication bus.

27. A computer-readable storage medium having stored therein instructions which, when run on a computer, cause the computer to perform the path determination method according to any one of claims 1 to 12.