WO2018107480A1

WO2018107480A1 - Service scheduling method and system

Info

Publication number: WO2018107480A1
Application number: PCT/CN2016/110443
Authority: WO
Inventors: 郑好棉
Original assignee: 华为技术有限公司
Priority date: 2016-12-16
Filing date: 2016-12-16
Publication date: 2018-06-21
Also published as: CN112398913A; CN112398913B; CN110063050B; CN110063050A

Abstract

The present application discloses a service scheduling method, comprising: receiving request information and obtaining a source client device identifier, a destination client device identifier, and a content tag from the request information; obtaining, according to the source client device identifier and the destination client device identifier, a network topology satisfying the request information; determining, according to the network topology and the content tag, whether there is a first connection in the network topology, wherein there is an overlap between the first connection and an existing connection in the network, and a service requested by the request information has the same content as that of a service transferred by the existing connection; if the first connection exists, establishing a second connection according to a segment in which the first connection does not overlap with the existing connection, and using the overlapped segment of the existing connection and the second connection as a connection satisfying the request information; and sending a message indicating that a connection satisfying the request information has been established successfully. The scheduling method disclosed in the present application can utilize an existing connection in the network, thereby improving utilization efficiency of network resources.

Description

Service scheduling method and system

Technical field

The present application relates to the field of communications technologies, and in particular, to a service scheduling method and system based on a software-defined network SDN.

Background technique

At this stage, the application of Software Defined Network (SDN) technology makes network control from distributed to centralized, the control plane of network equipment is simplified, and the control function rises to a centralized controller, which can be used for network services. The delivery and configuration of the network device. In this network deployment, there is one controller and multiple network devices, that is, multiple network elements (NEs). The NE and the controller are connected through a standard interface (commonly referred to as an SDN southbound interface) to implement control of the NE by the controller; and the other end of the controller is usually connected to the network user, that is, the client device. A typical SDN architecture is shown in Figure 1. The architecture consists of three parts, from top to bottom, the application layer controller (customer controller), the SDN controller, and the network equipment (NE).

The existing service scheduling method based on the SDN architecture adopts a non-aware mode, that is, if the application layer controller receives the request 1 and needs to establish a connection between NE1 and NE2, it requests to establish an SDN controller. Corresponding to the Label Switched Path (LSP) between the NEs. If the application layer controller receives the request 2 and needs to establish a connection between NE1 and NE3, it will request the SDN controller to establish another LSP between the corresponding NEs. The LSP can be established by some mature southbound technologies, such as the Path Computation Element Protocol (PCEP), for data transmission between NEs.

However, with the existing service scheduling method, the SDN controller cannot perceive the content that needs to be transmitted between the client devices. When there is a large amount of duplicate content in the network, the use efficiency of the network resources is greatly reduced.

Summary of the invention

The embodiment of the present invention provides a service scheduling method, which solves the problem that the use efficiency of network resources will be reduced when there is a large amount of duplicate content in the network by sensing the content that needs to be transmitted between the client devices.

The first aspect provides a service scheduling method, including: receiving request information, obtaining source client device identifier, sink client device identifier, and content label from the request information, wherein the request information is used to request the source client device Transmitting a service between the client device and the sink client device, the content tag is used to identify the content of the service requested by the request information; and obtaining, according to the source client device identifier and the sink client device identifier, the request information is satisfied. a network topology, determining, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the request information is The requested service is the same as the service content delivered by the existing connection; if the first connection exists, establishing a second connection according to a part of the first connection that does not coincide with the existing connection, Cooperating the overlapped portion of the existing connection with the second connection as a connection satisfying the request information; the request information will be satisfied Connection is established successfully the message sent.

The scheduling method provided by the embodiment of the present invention can efficiently and reasonably establish a network connection by sensing the service content that needs to be transmitted between the client devices, thereby improving the utilization efficiency of the network resources.

In conjunction with the first aspect, in a first possible implementation manner of the first aspect, the first connection is completely coincident with an existing connection in the network, and the existing connection is not connected according to the first connection. And a part of the overlap, the second connection is established, and the coincident part of the existing connection and the second connection are used as a connection that satisfies the request information, and the method includes: using the existing connection as the request information connection.

With reference to the first aspect or the first possible implementation manner of the first aspect, in a second possible implementation manner of the first aspect, after determining whether the first connection exists in the network topology, the method further includes And if the first connection does not exist, establishing the second connection, and using the second connection as a connection that satisfies the request information.

With reference to the first aspect, in a third possible implementation manner of the first aspect, if the first connection exists, establishing a second connection according to a part of the first connection that does not coincide with the existing connection, Specifically, if there are a plurality of the first connections, comparing the number of links included in a portion of the plurality of the first connections that does not coincide with the existing connection, selecting the non-coincident portion Establishing a second connection according to the non-coincident part of the selected connection, where the link is between different network elements or between the network element and the client device. Information transmission path.

With reference to the first aspect, or any one of the first to the third possible implementation manners of the first aspect, in a fourth possible implementation manner of the first aspect, the receiving request information, Obtaining the source client device identifier, the sink client device identifier, and the content label from the request information, specifically: receiving N request information at the same time, obtaining the source client device identifier, the sink client device identifier, and the content from each of the request information a label, N is a positive integer greater than 1; before the network topology that satisfies the request information is obtained according to the source client device identifier and the sink client device identifier, the method further includes: identifying the source client device And the request information that the sink client device identifier and the content label are the same are merged. The embodiment of the present application combines the same request information in advance, and does not need to compare each request information with an existing connection, which simplifies the operation flow.

The second aspect provides a software-defined network SDN controller, including: a receiving module, a processing module, and a sending module, where the receiving module is configured to receive request information, obtain a source client device identifier from the request information, and store the client And the device identifier and the content label, the network topology that satisfies the request information is obtained according to the source client device identifier and the sink client device identifier, and the content label and the network topology are sent to the processing module, where The request information is used to request delivery of a service between the source client device and the sink client device, the content tag is used to identify content of the service requested by the request information; and the processing module is configured to: Determining, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the service requested by the request information The same as the service content delivered by the existing connection; if the first connection exists, according to the first connection Having a portion of the connection coincidence, establishing a second connection, the coincident portion of the existing connection and the second connection being together as a connection satisfying the request information; the sending module, configured to satisfy the request information The connection was successfully sent and the message was sent out.

The SDN controller provided by the embodiment of the present application improves the utilization efficiency of network resources by sensing the content that needs to be transmitted between the client devices, and establishing the network connection efficiently and reasonably.

With reference to the second aspect, in a first possible implementation manner of the second aspect, the first connection is completely coincident with an existing connection in the network, and the processing module is further configured to satisfy the existing connection The connection of the request information.

With reference to the second aspect, or the first possible implementation manner of the second aspect, in a second possible implementation manner of the second aspect, the processing module is further configured to: if the first connection does not exist, establish a location Said second connection, said second connection being a connection that satisfies said request information.

With reference to the second aspect, in a third possible implementation manner of the second aspect, the processing module is further configured to: if there are multiple the first connections, compare the plurality of the first connections with the The number of links included in the portion where the connection overlaps is selected, and the connection having the least number of links in the non-coincident portion is selected, and the second connection is established according to the non-coincident portion of the selected connection, where The link is an information transmission path between different network elements or between the network element and the client device.

With reference to the second aspect, or any one of the first to the third possible implementation manners of the second aspect, in a fourth possible implementation manner of the second aspect, the receiving module is further And receiving, by each of the request information, a source client device identifier, a sink client device identifier, and a content label, where N is a positive integer greater than 1. The processing module is further configured to Determining, according to the source client device identifier and the sink client device identifier, the source client device identifier, the sink client device identifier, and the content label are the same before obtaining a network topology that satisfies the request information Request information to merge. The embodiment of the present application combines the same request information in advance, and does not need to compare each request information with an existing connection, which simplifies the operation flow.

A third aspect provides a service scheduling system, including: a plurality of client devices, a client controller, an SDN controller, and a plurality of network elements NE, wherein the client device is configured to generate request information, and add the request information. a content tag, the request information is sent to the client controller, wherein the request information is used to request delivery of a service between a source client device and a sink client device, and the content tag is used to identify the request information request The content of the service; the client controller is configured to send the request information to the SDN controller; the SDN controller is configured to obtain the source client device identifier from the request information, The sink client device identifier and the content tag are obtained according to the source client device identifier and the sink client device identifier. Determining, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the request information The requested service is the same as the service content delivered by the existing connection; if the first connection exists, establishing a second connection according to a part of the first connection that does not coincide with the existing connection And connecting the coincident portion of the existing connection and the second connection together as a connection satisfying the request information, and sending a control instruction to the NE through which the second connection passes, wherein the control instruction is used to indicate modification a connection relationship of the NE; a message that the connection that satisfies the request information is successfully sent to the client controller; and the NE that the second connection passes is used to establish the second according to the control instruction connection.

A fourth aspect provides a service scheduling system, including a plurality of client devices, configured to send and receive services, where the service scheduling system further includes: a client controller, an SDN controller, and a plurality of network elements NE, the client controller, And generating request information, adding a content tag to the request information, and sending the request information to the SDN subscriber controller, wherein the request information is used to request to be transmitted between the source client device and the sink client device The content label is used to identify the content of the service requested by the request information; the SDN controller is configured to obtain the source client device identifier from the request information, the sink client device identifier and And determining, by the content label, the network topology that satisfies the request information according to the source client device identifier and the sink client device identifier; determining, according to the network topology and the content label, whether the network topology exists a connection, the first connection has an overlap with an existing connection in the network, and the service requested by the request information and the existing connection The service content is the same; if the first connection exists, establishing a second connection according to a portion of the first connection that does not coincide with the existing connection, and the overlapping portion of the existing connection and the And the second connection is sent as a connection that satisfies the request information, and the control instruction is sent to the NE through which the first connection passes, where the control instruction is used to indicate that the connection relationship of the NE is modified; the request information is satisfied. The message that the connection is successfully established is sent to the client controller; the NE through which the second connection passes is used to establish the second connection according to the control instruction.

In conjunction with the third aspect or the fourth aspect, in the third aspect or the first possible implementation manner of the fourth aspect, the first connection is coincident with an existing connection in the network; the SDN controller is further used to The existing connection is used as a connection that satisfies the request information.

In combination with the third aspect or the first possible implementation of the third aspect or the fourth possible implementation of the fourth aspect or the fourth aspect, the second possible implementation of the third aspect or the fourth aspect The SDN controller is further configured to: if the first connection does not exist, establish the second connection, and use the second connection as a connection that satisfies the request information.

In combination with the third aspect or the fourth aspect, in the third aspect, or the third possible implementation manner of the fourth aspect, the SDN controller is further configured to compare multiple locations if there are multiple the first connections a number of links included in a portion of the first connection that does not coincide with the existing connection, and selecting one of the non-coincident portions with the least number of links, according to the non-coincident portion of the selected connection Establishing a second connection, where the link is an information transmission path between different network elements or between the network element and a client device.

Any one of the first to third possible implementations of the third aspect or the third aspect, or the first to third possible implementations of the fourth or fourth aspect In a third aspect, the fourth possible implementation manner of the fourth aspect, the SDN controller is further configured to receive N pieces of the request information at the same time, from each Obtaining a source client device identifier, a sink client device identifier, and a content label in the request information, and combining the source client device identifier, the sink client device identifier, and the request information that are the same as the content label, where N is A positive integer greater than one. The embodiment of the present application combines the same request information in advance, and does not need to compare each request information with an existing connection, which simplifies the operation flow.

In a fifth aspect, a computer readable storage medium is provided, where computer executed instructions are stored, and when the at least one processor of the device executes the computer to execute an instruction, the device performs the first aspect or the first aspect A service scheduling method provided by any of the possible implementations.

In a sixth aspect, a computer program product is provided, the computer program product comprising computer executable instructions stored in a computer readable storage medium; at least one processor of the device can read the computer from a computer readable storage medium Executing the instructions, the at least one processor executing the computer execution instructions causes the device to implement the service scheduling method provided by the first aspect or any of the possible implementations of the first aspect.

The scheduling method provided by the embodiment of the present application is to perceive the service that needs to be transmitted between the client devices. Content can establish network connections efficiently and reasonably, thereby improving the utilization efficiency of network resources.

DRAWINGS

Figure 1 is a diagram of a typical exemplary SDN architecture;

2 is a basic architecture diagram of a DCI network;

FIG. 3 is a flowchart of a service scheduling method according to an embodiment of the present application;

4 is a schematic diagram of a DCI network architecture adopted by another embodiment of the present application;

FIG. 5 is a schematic diagram of a DCI network architecture adopted by another embodiment of the present application; FIG.

6 is a schematic diagram of a DCI network architecture adopted by another embodiment of the present application;

FIG. 7 is an SDN controller according to another embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

As is known, a typical application scenario of SDN is Data Center Interconnection (DCI). A large number of enterprise or carrier-level applications need to implement data transmission between data centers (DCs) through the network. Each DC will access the DCI network through the NE connected to each other. The basic architecture of the DCI network is shown in Figure 2. The DC controller is used to collect the requirements of different DCs and send these requirements to the SDN controller. And the SDN controller establishes a connection between the NEs according to these requirements.

The embodiment of the present application provides a service scheduling method, as shown in FIG. 3, including:

301. Receive request information, obtain a source client device identifier, a sink client device identifier, and a content label from the request information.

The request information is used to request to transfer a service between the source client device and the sink client device; optionally, the service is a real-time service; the content tag is used to identify the content of the service requested by the request information; the method is applied to the DCI In the network, the client controller is the DC controller and the client device is the DC.

302. Obtain a network topology that satisfies the request information according to the source client device identifier and the sink client device identifier.

It should be noted that the SDN controller stores the network topology between any source client device and any sink client device in the network. Therefore, as long as it is determined which request information is requested to transfer services between two client devices, it can be known. A network topology between the two client devices, wherein the source client device identity and the sink client device identity indicate which two client devices are required to pass the service request information. The network topology includes nodes and links, the nodes refer to NEs, and the links refer to all connections connected to the NE, including one end where the client device is a NE at one end. In other words, as long as the network topology is known, the two are known. All possible connection relationships between client devices.

303. Determine, according to the network topology and the content label, whether the first connection exists in the network topology.

The first connection is overlapped with the existing connection in the network, that is, the first connection is a connection that partially overlaps or completely coincides with any existing connection in the network, and the service requested by the request information is in the network. The business content delivered by the existing connection is the same.

304. If there is a first connection, establish a second connection according to a part of the first connection that does not coincide with the existing connection, and the overlapping part of the existing connection and the second connection together serve as a connection that satisfies the request information.

Specifically, the first connection is overlapped with a part of an existing connection in the network, and the following description is performed. As shown in FIG. 2, it is assumed that there is a connection DC1-NE1-NE2-NE3-DC2 in the network that transmits the first service. , as existing connection 1; request information is required to transfer the first service between DC1 and DC3, then the network has a first connection; due to the connection in the network topology DC1-NE1-NE2-NE3-NE5-DC3 It overlaps with a part of the existing connection 1, and the transmitted service is also the same, so DC1-NE1-NE2-NE3-NE5-DC3 is the first connection. Sharing a coincident portion (DC1-NE1-NE2-NE3) of the existing connection 1 with the first connection, and establishing a second connection according to the non-coincident portion (NE3-NE5-DC3) of the existing connection 1 according to the first connection, The combination of the two can be used to transfer the first service between DC1 and DC3. The method utilizes existing connections in the network, eliminating the need to create a complete connection between DC1 and DC3, saving network resources.

305. Send a message that the connection that satisfies the request information is successfully established.

Optionally, if the first connection is completely coincident with the existing connection in the network, step 302 may be simplified as: determining whether the network topology exists in the network topology according to the network topology and the content label. A connection, if there is a first connection, an existing connection that coincides with the first connection is used as a connection that satisfies the request information.

Further, if there is no first connection, a second connection is established, and the second connection is used as a connection that satisfies the request information. Specifically, the second connection may be established according to the structure of the link with the least link in the network topology, where the link is an information transmission path between different network elements or between the network element and the client device.

Optionally, if there are multiple first connections, one of the first connections is selected according to the principle of highest network resource utilization, as follows: comparing the parts of the multiple first connections that do not coincide with the existing connection The number of links included, the one with the least number of links in the non-coincident part is selected, and the second connection is established according to the non-coincident part of the selected connection. The newly created connection required by this solution contains the fewest links and the least burden on the network.

Specifically, as shown in FIG. 4, it is assumed that there are two connections for transmitting the second service in the network, and DC1-NE1-NE2-NE3-DC4 and DC1-NE1-NE6-NE5-NE4-DC3 are respectively recorded as existing connections. 2 and existing connection 3; requesting information is to transfer the second service between DC1 and DC2, then there are two connections in the network topology satisfying the request information, wherein connection 1 is DC1-NE1-NE2- NE3-NE4-NE5-DC2, connection 2 is DC1-NE1-NE6-NE5-DC2. Since the existing connection 2 is the same as the part of the connection 1, the existing connection 3 is the same as the part of the connection 2, and the delivered service is the second service, so the two connections in the network topology are the first connection. The portions of the two first connections that do not coincide with the existing connection include three links (NE3-NE4, NE4-NE5, and NE5-DC2) and one link (NE5-DC2), that is, select connections. As the selected first connection, the existing connection 3 is shared, and only one link is needed to satisfy the request information. Therefore, the embodiment of the present application establishes a second connection according to the connection 2 in the network topology, and the burden on the network is Smaller, the utilization of network resources is higher.

It should be understood that, for different performance requirements and algorithm complexity requirements, there are many ways to select which ones to share, and the method provided by the present application may be adopted, or other methods such as random selection may be adopted. Not limited.

The service scheduling method provided by the present application can efficiently and reasonably establish a network connection by sensing content that needs to be transmitted between client devices, thereby improving the utilization efficiency of network resources.

Optionally, as another embodiment, N request information is received at the same time, from each request letter. The source client device identifier, the sink client device identifier, and the content label are obtained, and N is a positive integer greater than one; since more than one request information is received at the same time, the request information is satisfied according to the source client device identifier and the sink client device identifier. Before the network topology, the scheduling method further includes: combining the source client device identifier, the sink client device identifier, and the request information with the same content label. The solution provided by the present application merges the same request information in advance, and it is not necessary to have each request information perform steps 302-305, which simplifies the operation.

The solution of the present application will be described below in several specific embodiments.

Embodiment 1:

Taking a simplified DCI network as an example, its network structure is shown in Figure 5. The diagram contains three DCs and one network topology. The DC is maintained by the DC controller in the figure, and the network topology is represented by the SDN in the figure. The controller performs control and management, and DC1, DC2, and DC3 are connected to the network shown in FIG. 5 through NE1, NE3, and NE4, respectively.

Suppose the network has a connection DC1-NE1-NE2-NE3-DC2, and the content delivered is the real-time signal X. At this time, when the SDN controller receives another request message, since the prior art cannot support the expression of the content, the SDN controller needs to establish a new connection for the request regardless of whether there is duplicate content in the network. However, since the content tag is introduced in the application, the DC is allowed to add the requested content to the request information, so the SDN controller can extract the content tag of the request information, and can know the request in addition to the network topology that satisfies the request information. Based on this content, it is judged whether it is possible to utilize existing connections in the network to improve the utilization of network resources.

In this embodiment, it is assumed that the SDN controller receives another request information, and the DC2 requests to obtain a certain service from the DC1. By identifying the content label in the request information, the service can be known as the real-time signal X; the network already exists. An existing connection DC1-NE1-NE2-NE3-DC2 transmits the real-time signal X, and the network topology that satisfies the request information also includes the existing connection, that is, the existing network has The connection can be used for the transmission of the real-time signal X in response to the DC2 request, so this connection can be used directly in response to requests from DC2, saving network resources. Finally, after the connection is successfully established, the SDN controller feeds back to the DC controller that the service has been established successfully.

Similarly, when there are multiple connections in the network, the SDN controller needs to compare the new service request with each existing service connection to find the possibility of sharing the existing connection.

It should be noted that common content tag identification technologies include Content Centric Networking (CCN), Network of Information (NetInf), Data Oriented Network Architecture (DONA), etc. For the specific content tag identification technology and the naming method of the content tag, the application is not limited.

In addition, the present embodiment specifically indicates that the requested content is the real-time signal X because the real-time signal conforms to two characteristics: (1) Although the content tag specifies the uniqueness of the content, there is still a requirement for the synchronization mechanism. The real-time signal does not need to be synchronized, and it can be shared at any time. It is easy to share at any time. For example, when a certain A is watching a football match, a certain B can join for content sharing at any time. This is not related to whether the football match has just started or halfway. What a B needs is the latest game situation, not from the beginning. In a similar scenario, it is not appropriate to switch to a non-real-time signal. For example, watching a movie, a certain one has already seen half of it. If a B requests content sharing, it is necessary to start from the beginning, instead of looking at it from the middle. (2) The real-time signal is usually a kind of network hotspot, the demand is large, the dynamic of the request is very strong, and the trend is often erupted, which has an urgent need for efficient utilization of network resources. In addition to real-time signals, functions such as data backup and migration can also be implemented by the technical solution of the embodiment. For content that cannot be synchronized (like a movie, etc.), some synchronization mechanism needs to be introduced to ensure the integrity of the content. Not limited.

Embodiment 2:

The embodiment of the present application still takes the network structure shown in FIG. 5 as an example, and assumes that there is a connection DC1-NE1-NE2-NE3-DC2 in the network, and the real-time signal Y is transmitted. At this time, the SDN controller receives a request message from the DC3, and the DC3 requests to transmit a certain service from the DC1. Through the content tag identification technology, the SDN controller knows that the content of the service requested by the request information is the real-time signal Y, and The existing connections deliver the same services and can try to share the existing connections. However, the existing connections only partially overlap with one of the network topologies that meet the requirements of the request information. Therefore, DC1-NE1-NE2-NE4-DC3 in the network topology. That is, the first connection, it is obvious that the overlapping portion of the existing connection with the first connection is DC1-NE1-NE2, and the portion of the first connection that does not coincide with the existing connection is NE2-NE4-DC3. Therefore, the connection of the DC1-NE1-NE2 part of the existing connection is selected, and the connection is established at the NE2, and the connection of the NE2-NE4-DC3 is newly established to provide the requested service. Finally, after the connection is successfully established, the SDN controller feeds back to the DC controller that the service has been established successfully. Compared with the prior art, this embodiment does not need to newly establish a part of the connection of DC1-NE1-NE2, which saves network resources.

Embodiment 3:

Assume that a simplified DCI network is still taken as an example. The network structure is still as shown in FIG. 5. The SDN controller receives two request information at the same time, and the existing network structure already has a connection for transmitting certain services. At this point, there are two cases where the content tags of the two request messages are compared:

In the first case, the source client device identifier, the sink client device identifier, and the content label of the two request information are all consistent, and the SDN controller combines the two request information to obtain a network topology that satisfies the two request information, and further If the connection in the network topology is compared with the existing connection in the network, if there is a connection in the network topology that is the same as the connection in the network, and the connection is overlapped with the existing connection in the network, the workflow is as shown in the first embodiment; In the network topology, the connection is the same, and the connection is overlapped with a part of the existing connection in the network, and the workflow is as shown in the second embodiment.

In the second case, there are one or several items in the source client device identifier, the sink client device identifier, and the content label of the two request information, and the SDN controller needs to separately process the two request information, each request. The processing of the information is as shown in the first embodiment or the second embodiment, and details are not described herein again.

Embodiment 4:

The embodiment of the present application takes the network structure shown in FIG. 6 as an example, and the figure includes five DCs and one network topology, wherein the DC is maintained by the DC controller in the figure, and the network topology is determined by the SDN controller in the figure. For control and management, DC1 and DC2 access the DCI network through NE1 and NE2, respectively, and DC3, DC4, and DC5 access the DCI network through NE4, NE6, and NE7, respectively.

Assume that there are two connections DC1-NE1-NE3-NE7-DC5 and DC2-NE2-NE3-NE4-DC3, which are recorded as existing connection 1 and existing connection 2, respectively, and the real-time signals Z are transmitted. At this time, the SDN controller receives a request message from the DC4, and the DC4 requests to transmit a certain service from the DC2. Through the content tag identification technology, the SDN controller knows that the content of the service requested by the request information is also the real-time signal Y. The same as the traffic delivered by two existing connections, you can try to share the existing connection; there are two connection structures in the network topology that meet this requirement. Both of these connection structures overlap with the existing connection, so they can be regarded as First connection.

In this case, if only the coincident part of the existing connection 1 is shared, it is necessary to create four links of DC2-NE2, NE2-NE3, NE7-NE6, and NE6-DC4; if only the coincident part of the existing connection 2 is shared, New NE4-NE5, NE5-NE6, and NE6-DC4 links need to be created. Because the two existing connections are all real-time services Z, you can improve network resource utilization by sharing a part of each of the two existing connections. In this embodiment, DC2-NE2-NE3 in the existing connection 2 can be shared, and the NE3-NE7 of the existing connection 1 can be shared, so that only two links of the NE7-NE6 and the NE6-DC4 need to be newly created and shared separately. Compared to the case of an existing connection, the burden on network resources is smaller.

It should be noted that the foregoing embodiments can be used for real-time signal transmission, but for a signal that cannot be synchronized, such as a movie signal, the above implementation can be applied only when the request information is simultaneously received and the existing network connection is not shared. The technical solution provided by the example.

Another embodiment of the present application provides an SDN controller, as shown in FIG. 7, including: a receiving module 701, a processing module 702, and a sending module 703.

The receiving module 701 is configured to receive the request information, obtain the source client device identifier, the sink client device identifier, and the content label from the request information, and obtain a network topology that satisfies the request information according to the source client device identifier and the sink client device identifier, and The content tag and the network topology are sent to the processing module 702, wherein the request information is used to request delivery of a service between the source client device and the sink client device, the content tag being used to identify the content of the service requested by the request information.

The processing module 702 is configured to determine, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the service and network requested by the request information The service content delivered by the connection is the same; if there is a first connection, the second connection is established according to the part of the first connection that does not coincide with the existing connection, and the overlapping part of the existing connection is used together with the second connection A connection that satisfies the request information. Optionally, the service is a real-time service.

The sending module 703 is configured to send a message that the connection that satisfies the request information is successfully established.

Optionally, if the first connection completely coincides with the existing connection in the network, the processing module 702 is further configured to use the existing connection that coincides with the first connection as the connection that satisfies the request information.

Optionally, the processing module 702 is further configured to: if the first connection does not exist, establish a second connection Next, the second connection is used as a connection that satisfies the request information. Specifically, the second connection may be established according to the structure of the link with the least link in the network topology, where the link is an information transmission path between different network elements or between the network element and the client device.

The SDN controller provided by the present application senses the content that needs to be transmitted between the client devices by identifying the content tags in the request information, thereby avoiding waste of network resources and improving utilization of network resources.

Further, if there are multiple first connections, the processing module 702 is further configured to compare the number of links included in the part of the plurality of first connections that does not coincide with the existing connection, and select the number of links in the non-coincident part. a minimum of one connection, establishing a second connection according to the non-coincident part of the selected connection, and connecting the existing connection in the network with the coincident part of the first connection and the second connection as a connection satisfying the request information, wherein the link Refers to the information transmission path between different network elements or between network elements and client devices. The newly created connection required by this solution contains the fewest links and the least burden on the network.

Optionally, as another embodiment, the receiving module 701 is further configured to receive N request information at the same time, and obtain a source client device identifier, a sink client device identifier, and a content label from each request information, where N is greater than 1. The processing module 702 is further configured to merge the request information of the source client device identifier, the sink client device identifier, and the content label, before obtaining the network topology that satisfies the request information according to the source client device identifier and the sink client device identifier. . The SDN controller provided in this embodiment combines the same request information in advance, and does not need to compare each request information with an existing connection in the network, which simplifies the operation flow.

Another embodiment of the present application provides a service scheduling system, including: multiple client devices, a client controller, an SDN controller, and multiple NEs.

a client device, configured to generate request information, add a content tag to the request information, and send the request information to the client controller, where the request information is used to request to transfer the service between the source client device and the sink client device, the content The tag is used to identify the content of the service requesting the information request;

a client controller, configured to send the request information to the SDN controller;

The SDN controller is configured to obtain the source client device identifier, the sink client device identifier, and the content label from the request information, and obtain the content according to the source client device identifier and the sink client device identifier. Obtaining a network topology of the information; determining, according to the network topology and the content label, whether the first connection exists in the network topology, the first connection has an overlap with the existing connection in the network, and the service requested by the request information is The service content of the existing connection is the same; if there is a first connection, the second connection is established according to the part of the first connection that does not coincide with the existing connection, and the overlapping part of the existing connection and the second connection are satisfied together. The connection of the request information is sent to the NE through which the second connection passes, wherein the control instruction is used to indicate that the connection relationship of the NE is modified; and the message that the connection that satisfies the request information is successfully sent to the client controller;

The NE through which the second connection passes is used to establish a second connection according to the control instruction.

It should be noted that in addition to initiating a request by the client device, the request may be initiated by the client controller. At some point, the client controller decides whether to perform part of the data migration according to the content and status of each client device under the current jurisdiction. In this scenario, the request information is generated by the client controller, and the migrated original/sink client device and Content tags are also specified by the client controller.

Therefore, another embodiment of the present application provides a service scheduling system, including multiple client devices, for transmitting and receiving services; the service scheduling system further includes: a client controller, an SDN controller, and multiple NEs,

a client controller, configured to generate request information, add a content label to the request information, and send the request information to a SDN account controller, where the request information is used to request to transfer the service between the source client device and the sink client device The content tag is used to identify the content of the service requested by the request information;

An SDN controller, configured to obtain a source client device identifier, a sink client device identifier, and a content label from the request information, and obtain a network topology that satisfies the request information according to the source client device identifier and the sink client device identifier; according to the network topology and a content label, determining whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the service requested by the request information is the same as the service content delivered by the existing connection; a connection, according to a portion of the first connection that does not coincide with the existing connection, establishing a second connection, and the overlapping portion of the existing connection and the second connection together as a connection satisfying the request information, sending a control command to the first a second connected NE, wherein the control instruction is used to indicate that the connection relationship of the NE is modified; and the message that the connection that satisfies the request information is successfully established is sent to the client controller;

It should be understood that several embodiments of the SDN controller have been described in detail before, and the embodiments are not described herein again.

The service scheduling system provided in this embodiment achieves the purpose of perceiving the content that needs to be delivered between the client devices by adding the content tag in the request information, and improves the network by identifying the content to be delivered and making rational use of the existing connection. Resource utilization efficiency.

The embodiment of the present application further provides a computer readable storage medium. The computer readable storage medium stores computer execution instructions. When at least one processor of the device executes the computer execution instruction, the device executes the embodiment shown in FIG. 3 . The service scheduling method provided.

The embodiment of the present application further provides a computer program product, the computer program product comprising computer execution instructions stored in a computer readable storage medium; at least one processor of the device can read the computer readable storage medium The computer executes the instructions, and the at least one processor executes the computer to execute the instructions such that the device performs the service scheduling method provided by the embodiment shown in FIG. 3 above.

The foregoing is only a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto, and any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application. It should be covered by the scope of protection of this application. Therefore, the scope of protection of the present application should be determined by the scope of the claims.

Claims

A service scheduling method, comprising:

Receiving the request information, obtaining the source client device identifier, the sink client device identifier, and the content label from the request information, wherein the request information is used to request to transfer a service between the source client device and the sink client device, the content label Content for identifying the service of the request information request;

Obtaining, according to the source client device identifier and the sink client device identifier, a network topology that satisfies the request information;

Determining, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the service requested by the request information The same as the business content delivered by the existing connection;

If the first connection exists, establishing a second connection according to a portion of the first connection that does not coincide with the existing connection, and the overlapping portion of the existing connection and the second connection are used together as a satisfaction The connection of the request information;

A message that the connection that satisfies the request information is successfully established is sent out.
The method of claim 1 wherein said first connection is completely coincident with an existing connection in the network;

And establishing, according to a portion of the first connection that does not overlap with the existing connection, establishing a second connection, and the overlapping portion of the existing connection and the second connection together as a connection that satisfies the request information, Specifically, the existing connection is used as a connection that satisfies the request information.
The method according to claim 1 or 2, wherein after determining whether the first connection exists in the network topology, the method further comprises:

If the first connection does not exist, the second connection is established, and the second connection is used as a connection that satisfies the request information.
The method according to claim 1, wherein if the first connection is present, establishing a second connection according to a portion of the first connection that does not coincide with the existing connection, specifically:

If there are a plurality of the first connections, comparing the number of links included in a portion of the plurality of the first connections that does not coincide with the existing connection, selecting the number of links in the non-coincident portion A second connection is established according to the non-coincident part of the selected connection, wherein the link is an information transmission path between different network elements or between the network element and the client device.
Method according to claim 1 or 2, characterized in that

The receiving the request information, obtaining the source client device identifier, the sink client device identifier, and the content label from the request information, specifically: receiving N request information at the same time, and obtaining the source client device identifier from each of the request information, a client device identifier and a content tag, where N is a positive integer greater than one;

Before obtaining the network topology that satisfies the request information according to the source client device and the sink client device, the method further includes: identifying the source client device, the sink client device identifier, and the content label The request information that is the same is merged.
A software-defined network SDN controller, comprising: a receiving module, a processing module and a sending module,

The receiving module is configured to receive the request information, obtain the source client device identifier, the sink client device identifier, and the content label from the request information, and obtain the content according to the source client device identifier and the sink client device identifier. Requesting a network topology of the information, the content tag and the network topology are sent to the processing module, wherein the request information is used to request delivery of a service between a source client device and a sink client device, the content tag And identifying the content of the service requested by the request information;

The processing module is configured to determine, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the request The service requested by the information is the same as the service content delivered by the existing connection; if the first connection exists, establishing a second according to a portion of the first connection that does not coincide with the existing connection Connecting, the coincident portion of the existing connection and the second connection together as a connection satisfying the request information;

The sending module is configured to send a message that the connection that satisfies the request information is successfully established.
The SDN controller according to claim 6, wherein said first connection completely coincides with an existing connection in the network;

The processing module is further configured to use the existing connection as a connection that satisfies the request information.
The SDN controller according to claim 6 or 7, wherein the processing module is further configured to: if the first connection does not exist, establish the second connection, and use the second connection as a satisfaction The connection of the request information.
The SDN controller according to claim 6, wherein the processing module is further configured to compare, if there are a plurality of the first connections, a plurality of the first connections that are not coincident with the existing connection And the number of links included in the part, the one of the non-coincident parts having the least number of links is selected, and the second connection is established according to the non-coincident part of the selected connection, wherein the link is Information transmission path between different network elements or between the network element and the client device.
The SDN controller according to claim 6 or 7, wherein

The receiving module is further configured to receive N pieces of the request information at the same time, and obtain a source client device identifier, a sink client device identifier, and a content label from each of the request information, where N is a positive integer greater than 1.

The processing module is further configured to: after obtaining the network topology that meets the request information according to the source client device identifier and the sink client device identifier, identifying the source client device, the sink client device identifier, and The request information in which the content tags are the same is merged.
A service scheduling system, comprising: a plurality of client devices, a client controller, an SDN controller, and a plurality of network elements NE,

The client device is configured to generate request information, add a content tag to the request information, and send the request information to the client controller, where the request information is used to request the source client device and the sink client Transmitting a service between the devices, where the content tag is used to identify the content of the service requested by the request information;

The client controller is configured to send the request information to the SDN controller;

The SDN controller is configured to obtain, from the request information, a source client device identifier, a sink client device identifier, and the content label, and obtain the content request according to the source client device identifier and the sink client device identifier. a network topology of the information; determining, according to the network topology and the content label, whether there is a first connection in the network topology, where the first connection has an overlap with an existing connection in the network, and the request information is The requested service is the same as the service content delivered by the existing connection; if the first connection exists, according to the first connection And establishing, in the portion not coincident with the existing connection, establishing a second connection, and transmitting the coincidence portion of the existing connection together with the second connection as a connection satisfying the request information, and transmitting a control command to the first a second connected NE, wherein the control instruction is used to indicate that the connection relationship of the NE is modified; and a message that the connection that satisfies the request information is successfully established is sent to the client controller;

The NE through which the second connection passes is used to establish the second connection according to the control instruction.