WO2020253328A1 - 资源分配方法以及装置 - Google Patents

资源分配方法以及装置 Download PDF

Info

Publication number
WO2020253328A1
WO2020253328A1 PCT/CN2020/083211 CN2020083211W WO2020253328A1 WO 2020253328 A1 WO2020253328 A1 WO 2020253328A1 CN 2020083211 W CN2020083211 W CN 2020083211W WO 2020253328 A1 WO2020253328 A1 WO 2020253328A1
Authority
WO
WIPO (PCT)
Prior art keywords
resource
server
node
slice
combination
Prior art date
Application number
PCT/CN2020/083211
Other languages
English (en)
French (fr)
Inventor
李飞
唐朋成
里卡德 维拉塔
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2020253328A1 publication Critical patent/WO2020253328A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W16/00Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/02Resource partitioning among network components, e.g. reuse partitioning
    • H04W16/04Traffic adaptive resource partitioning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements

Definitions

  • This application relates to communication technology, and in particular to a method and device for resource allocation.
  • the network is abstracted as a "network slice".
  • a network slice meets the communication service requirements of a certain type or use case.
  • the entire 5G network consists of a large number of different capabilities. Network slice composition.
  • VNF virtualisation network function
  • the NSSI allocation process does not involve the concept of a data center (DC) in the physical network, for example, the performance of the server in the DC of the physical network to which the virtual network is mapped. Whether the requirements of the network slicing are met, the corresponding DC cannot be allocated to the NSSI according to the resource requirements of the network slicing, and the needs of users cannot be met, resulting in poor user experience.
  • DC data center
  • the embodiments of the present application provide a resource allocation method and device, which are used to allocate a corresponding DC to the NSSI according to the resource demand of the actual user to meet the demand of the user.
  • the first aspect of the embodiments of the present application provides a resource allocation method, including:
  • the NSSI resource request which carries the first resource requirement of the first slicing node, the second resource requirement of the second slicing node, and the relationship between the first slicing node and the second slicing node included in the NSSI to be created
  • the first server in the first DC combination successfully maps the second slicing node to the second server in the first DC combination according to the second resource requirement, and successfully the first slicing node according to the third resource requirement
  • the virtual link between the second slicing node is mapped to the first physical link between the first server and the second server, it can be determined that the first DC combination is the target DC combination, and the NSSI slice node’s The mapping result and the mapping result of the virtual link.
  • the corresponding DC is selected to provide resources for the network slice according to the resource demand of the slice node and the resource demand of the virtual link, so that the NSSI can be allocated according to the resource demand of the actual user Corresponding DC to meet user needs.
  • all DCs in the DC set are sorted according to the available resource evaluation value of the DC, or all DCs in the DC set are sorted according to the available resource evaluation value of the DC from small to large Sort.
  • the method before determining the DC set, further includes: collecting statistics on the available resource quantity of the server included in each DC in the DC set to obtain the available resource evaluation value of each DC.
  • the DC set includes a first DC
  • the first DC includes a third server and a fourth server
  • the number of available resources of the servers included in each DC in the DC set is counted
  • Obtaining the available resource evaluation value of each DC includes: when the available network bandwidth provided by the third server and the available network bandwidth provided by the fourth server are both greater than a first preset threshold, determining the first available resource of the third server The resource quantity and the fourth available resource quantity of the fourth server are added, and the first available resource quantity is added to the second available resource quantity to obtain the available resource evaluation value of the first DC.
  • a specific method for determining the available resource evaluation value of the DC is provided.
  • each DC combination in the DC combination set includes the available resource evaluation value of each DC combination.
  • each DC combination in the DC combination set further includes at least one of a DC performance weight and a DC preference value of each DC combination, and the DC performance weight indicates the service of the server included in the DC combination Processing performance, DC preference value is calculated according to NSSI's deployment requirements for DC location and each DC combination.
  • the first DC combination is a DC combination with the largest available resource evaluation value, DC performance weight, and DC preference value among the DC combinations currently included in the DC combination set.
  • the method before determining the DC combination set, further includes: first, determining a second DC combination, the second DC combination includes the second DC and the third DC, and the second DC combination includes the first DC combination.
  • the fifth server and the sixth server when the available network bandwidth provided by the fifth server and the available network bandwidth provided by the sixth server are both greater than the second preset threshold, determine the third available resource quantity of the fifth server and the sixth server The fourth number of available resources; then, it is determined that the delay of the second physical link between the second DC and the third DC is less than or equal to the third preset threshold; then it is determined that the third number of available resources plus the fourth available Whether the resource quantity is greater than or equal to the total resource demand quantity of the slice nodes included in the NSSI, if so, it is determined that the available resource evaluation value of the second DC combination is the third available resource quantity plus the fourth available resource quantity.
  • the first slicing node is mapped to the first server in the first DC combination in the DC combination set according to the first resource requirement
  • the second slicing node is mapped according to the second resource requirement
  • the second server mapped to the first DC combination includes: firstly, determining the first DC combination from the DC combination set, the first DC combination including the first server and the second server; then, determining the number of available resources of the first server Whether it is greater than the resource demand of the first slicing node and judging whether the available resource quantity of the second server is greater than the resource demand of the second slicing node, if so, map the first slicing node to the first server, and The second slice node is mapped to the second server.
  • the virtual link between the first slice node and the second slice node is mapped to the first physical link between the first server and the second server according to the third resource requirement Including: First, determine whether the available network bandwidth of the first physical link between the DC where the first server is located and the DC where the second server is located is greater than that of the virtual link between the first slice node and the second slice node Bandwidth requirement, if yes, judge whether the delay between the first physical link is the delay requirement of the virtual link, if yes, then change the virtual link between the first slicing node to the second slicing node The way is mapped to the first physical link.
  • the method before obtaining the NSSI request, further includes: first, determining that the first network slice and the second network slice share the NSSI; then, determining the first resource requirement of the first slice node And the second resource demand of the second slice node, the first resource demand includes the resource demand of the first network slice for the first slice node and the resource demand of the second network slice for the first slice node, the first 2.
  • the resource requirement includes the resource requirement of the first network slice for the second slice node and the resource requirement of the second network slice for the second slice node; then, the virtual link between the first slice node and the second slice node is determined
  • the third resource demand includes the resource demand of the first network slice for the virtual link and the resource demand of the second network slice for the virtual link.
  • determining the third resource requirement of the virtual link between the first slicing node and the second slicing node includes: first, determining the first network slice of the virtual link for the first network slice. The bandwidth demand and the second bandwidth demand of the second network slice for the virtual link; then, the first bandwidth demand plus the second bandwidth demand are used as the total bandwidth demand of the virtual link; and it is determined that the first network slice has a virtual link The first delay demand of the link and the second delay demand of the second network slice for the virtual link.
  • the first delay demand is regarded as the The total delay demand of the virtual link; if the first delay demand is greater than the second delay demand, the second delay demand is taken as the total delay demand of the virtual link.
  • the resource request carries a request for cross-DC deployment;
  • the first DC combination includes a fourth DC and a fifth DC, and the fourth DC and the fifth DC are two deployed in different regions.
  • the fourth DC includes the seventh server, and the fifth DC includes the eighth server;
  • the method further includes: first, dividing the NSSI into a first NSSI and a second NSSI according to the cross-DC deployment request; then, determining The slice nodes across the DC in the first NSSI and the second NSSI are the third slice node, the fourth slice node, and the virtual link between the third slice node and the fourth slice node; when the number of available resources of the seventh server When the resource requirements of the third slicing node are met and the number of available resources of the eighth server meets the resource requirements of the fourth slicing node, determine the third physical link between the DC where the seventh server is located and the DC where the eighth server is located Whether the available network bandwidth of the path is greater than the bandwidth requirement of the virtual link between the third slice node and the fourth slice node, if so, determine whether the delay between the third physical link is lower than the time of the virtual link If so, the virtual link is mapped to the third physical link, and the third slice node and the
  • a second aspect of the embodiments of the present application provides a resource allocation device, and the resource allocation device has a function of implementing the foregoing first aspect and any possible implementation manner of the first aspect.
  • This function can be realized by hardware, or by hardware executing corresponding software, or by combining software and hardware.
  • the hardware and/or software includes one or more modules corresponding to the above-mentioned functions.
  • a third aspect of the embodiments of the present application provides a resource allocation device.
  • the resource allocation device includes a memory, a transceiver, and at least one processor.
  • the memory stores instructions; the memory, the transceiver, and the At least one processor is connected by a wire; the at least one processor invokes the instruction to execute the data processing or control operation performed on the resource allocation device in the first aspect.
  • a fourth aspect of the present application provides a chip system, which includes at least one processor, a transceiver, and a memory, the memory having instructions stored in the memory, and the at least one processor and the transceiver are interconnected through a wire,
  • the at least one processor is configured to perform operations in any implementation manner of the first aspect of the present application.
  • the fifth aspect of the embodiments of the present application provides a computer program product including instructions, which is characterized in that when it runs on a computer, the computer is caused to execute any implementation manner in the first aspect.
  • a sixth aspect of the embodiments of the present application provides a computer-readable storage medium, which is characterized by including instructions, which when run on a computer, cause the computer to execute any implementation manner as in the first aspect.
  • the resource request of the NSSI is obtained, and the resource request carries the first resource demand of the first slice node, the second resource demand of the second slice node, and the first slice node to the NSSI to be created.
  • the third resource requirement of the virtual link between the second slice nodes determine the DC set, and determine the DC combination set from the DC set; when the first slice node is successfully mapped to The first server in the first DC combination in the DC combination set successfully maps the second slice node to the second server in the first DC combination according to the second resource requirement, and successfully transfers
  • the virtual link between the first slicing node and the second slicing node is mapped to the first physical link between the first server and the second server, it can be determined that the first DC combination is the target DC combination, and Output the mapping result of the NSSI slice node and the mapping result of the virtual link.
  • the corresponding DC is selected according to the resource requirements of the slice node and the resource requirements of the virtual link to provide resources for the network slice, so that the resource requirements of the actual users can be NSSI allocates the corresponding DC to meet the needs of users.
  • Figure 1 is a schematic diagram of a system framework according to an embodiment of the application.
  • FIG. 2 is a schematic diagram of an embodiment of a resource allocation method according to an embodiment of the application.
  • FIG. 3 is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 4 is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 5 is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 6 is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 7A is a schematic diagram of a scenario of a resource allocation method according to an embodiment of this application.
  • FIG. 7B is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 8A is a schematic diagram of another scenario of a resource allocation method according to an embodiment of this application.
  • 8B is a schematic diagram of another embodiment of a resource allocation method according to an embodiment of this application.
  • FIG. 9 is a schematic structural diagram of a resource allocation device according to an embodiment of the application.
  • FIG. 10 is another schematic structural diagram of a resource allocation device according to an embodiment of the application.
  • the embodiments of the present application provide a resource allocation method and device, which are used to allocate a corresponding DC to the NSSI according to the resource demand of the actual user to meet the demand of the user.
  • Figure 1 is a system framework diagram of an embodiment of this application.
  • the resource allocation method of this embodiment of the application can be applied to the 3GPP of network functions virtualisation management and orchestration (NFV-MANO) Communication system
  • the system framework includes network slice subnet management functions (NSSMF) and NFV-MANO.
  • NSSMF network slice subnet management functions
  • NSSMF is used to manage and orchestrate NSSI, providing sliced component package management, life cycle management, and operation and maintenance capabilities.
  • NFV MANO is used to manage and coordinate the virtualisation network function (VNF) and the framework of supporting software components, and supports deployment and connection on virtual machines.
  • VNF virtualisation network function
  • NFV-MANO can be installed on the management server or in computer equipment, which is not specifically limited by this application.
  • the NFV-MANO includes network functions virtualization orchestrator (NFVO), virtualized network function manager (VNFM) and virtualized infrastructure management (VIM) ,
  • NFVO network functions virtualization orchestrator
  • VNFM virtualized network function manager
  • VIM virtualized infrastructure management
  • the slice designer can be deployed in NFV-MANO, or it can be a separate functional module, which is not limited in this application.
  • the slice designer can be integrated into NFVO.
  • Figure 1 only shows the slice designer integrated in NFVO as an example for illustration.
  • a VNF is a virtualized network functional unit. Multiple VNFs form an NSSI, which can be understood as a VNF corresponding to a slice node in the NSSI. As shown in Figure 1, the requested NSSI includes 4 slice nodes, corresponding to VNF1 to VNF4, and in the physical network, VNF1 is mapped to DC1, VNF2 is mapped to DC2, VNF3 is mapped to DC4, and VNF4 is mapped to DC3.
  • NFVO is used to deploy, operate, manage and coordinate VNF and its corresponding NFVI, and realize the orchestration and management of the entire NFV infrastructure, software resources and network services.
  • VNFM is used for the life management of VNF instances, such as instantiation, expansion and contraction, query, update, and planting.
  • a VNFM can be associated with a single VNF instance, or it can be associated with multiple VNF instances of the same type or different types.
  • VIM is used to control and manage the computing of the network function virtualization infrastructure, and to store the function modules of the network resources.
  • VIM can be the network function virtualization infrastructure.
  • FIG. 1 shows an application system of the resource allocation method of the embodiment of the present application. It should be noted that the resource allocation method of the embodiment of the present application is also applicable to other systems, and the details are not limited here. Secondly, the slice designer in the embodiment of the present application may be integrated in the management server, or may be integrated in the computer device. In the subsequent embodiments, only the integration of the management server in the management server is taken as an example for description.
  • mapping of network slices on the core network side and also suitable for the mapping of network slices on the access network side, for example, the mapping of network slices in the cloud part of the access network.
  • This application is not limited.
  • FIG. 2 is a schematic diagram of an embodiment of a resource allocation method in an embodiment of the application. The method includes:
  • the resource request carries the resource demand of the slice node included in the NSSI to be created and the resource demand of the virtual link between the slice nodes. For example, if the NSSI includes the first slice node and the second slice node, the resource request includes the first resource demand of the first slice node, the second resource demand of the second slice node, and the first slice node to the second slice. The third resource requirement of the virtual link connected between nodes.
  • the resource requirements of the slicing node may include the performance requirements of the CPU, memory, and hard disk storage of the server on the DC, and the resource requirements of the virtual link between the slicing nodes may include the corresponding virtual link.
  • the resource request may be sent by the NFVO to the slice designer, that is, after the NFVO receives the NSSI resource request, it reports the NSSI resource request to the slice designer.
  • the management server can obtain the DC information list available in the current system and the resource information of the physical links between the servers included in these DCs; then, the management server can sort these DCs and determine the DC set.
  • the available DC information list and the resource information of the physical links between the servers included in these DCs can be sent by the NFVO to the slice designer.
  • all DCs in the DC set are sorted according to the available resource evaluation value of the DCs, or all DCs in the DC set are sorted according to the available resource evaluation value of the DCs from small to large.
  • the available resource evaluation value is obtained by the management server by counting the available resources of the server included in each DC in the DC set.
  • the specific statistical process for the available resource evaluation value of each DC is shown in Figure 3. For illustration, here is an example of counting the number of available resources of the first DC. Please refer to Figure 3. This process includes:
  • the management server determines the first DC.
  • the management server determines the first DC from the available DC information, and determines the number of available resources of each server included in the first DC. For example, if the first DC includes a first server and a second server, the management server can determine the number of available resources of the first server and the number of available resources of the second server.
  • the management server counts the total number of available resources of servers in the first DC whose available network bandwidth is greater than a first preset threshold, and obtains an estimated value of available resources of the first DC.
  • the management server can determine whether the available network bandwidth provided by each server included in the first DC is greater than a first preset threshold; then, the management server counts the number of servers in the first DC whose available network bandwidth is greater than the first preset threshold. The total amount of available resources is used to obtain the evaluation value of the available resources of the first DC.
  • the first preset threshold is determined by the management server according to the virtual link of the maximum bandwidth requirement included in the NSSI, and the available network bandwidth refers to the network bandwidth that the server can provide except for the used network bandwidth Network bandwidth.
  • the management server may determine the DC combination from the DC set, each DC combination includes at least one DC, and the number of DCs in each DC combination is not greater than the number of DCs included in the DC set. For example, if the DC set includes m in total, r DCs are selected as the DC combination. It can be seen that there are many combinations of DCs, and m is an integer greater than or equal to 1.
  • the DC combination set includes the available resource evaluation value of each DC combination.
  • the DC combination further includes the DC performance weight and DC preference value of each DC combination.
  • the DC performance weight indicates the service processing performance of the servers included in the DC combination
  • the DC preference value is calculated based on the NSSI's deployment requirements for DC location and each DC combination. For example, the user wants to slice the user plane of the same network The part of the control plane and the control plane should be deployed in a DC that is closer to the geographical location or the same as possible to make the communication delay between the user plane and the control plane more secure. Therefore, the management server can be based on this demand and each DC Combine and calculate the corresponding DC preference value.
  • the calculation process of the available resource evaluation value of the DC combination is described in detail through the embodiment shown in FIG. 4.
  • the available resource evaluation value of the second DC combination is taken as an example. Please refer to FIG. 4.
  • the process includes:
  • the management server determines a second DC combination.
  • the management server determines the second DC combination from the DC set.
  • the second DC combination includes a second DC and a third DC
  • the second DC combination includes a fifth server and a sixth server.
  • the management server counts the total number of available resources of servers in the second DC combination whose available network bandwidth is greater than a first preset threshold.
  • the management server may determine whether the available network bandwidth provided by each server included in the second DC combination is greater than the first preset threshold, and then the management server counts according to the determination result that the available network bandwidth in the second DC combination is greater than the first The total number of available resources of the server with a preset threshold. For example, when the management server determines that the available network bandwidth provided by the fifth server and the available network bandwidth provided by the sixth server are both greater than the first preset threshold, the management server may determine the total amount of available resources of the second DC combination Is the number of available resources of the fifth server plus the number of available resources of the sixth server.
  • the first preset threshold is the virtual link required by the management server according to the maximum bandwidth included in the NSSI
  • the available network bandwidth refers to the network bandwidth that the server can provide except for the used network bandwidth .
  • the management server determines whether the delay of the physical link between the DC and the DC included in the second DC combination is less than or equal to a second preset threshold, and if so, execute step 404; if not, execute step 407.
  • the second preset threshold is determined by the management server according to the resource request of the NSSI to determine the virtual link with the minimum delay requirement included in the NSSI.
  • the physical link between DC and DC may be the shortest path between DC and DC, and the physical link is the path with the smallest delay among all the calculated shortest paths.
  • the management server can calculate the physical link in multiple ways, as illustrated below:
  • the management server can randomly select a server 1 from the second DC and a server 2 from the second DC, and then calculate the shortest path between the server 1 and server 2 according to the shortest path algorithm; the second DC and the first The shortest paths between the servers included in the three DCs are all calculated, and then the path with the smallest distance and the smallest delay is determined from these shortest paths.
  • the management server determines the edge server for communication between the second DC and the third DC, and then calculates the shortest path between the edge servers according to the shortest path algorithm, and selects the path with the smallest distance and the smallest delay from these shortest paths.
  • the management server judges whether the total number of available resources is greater than or equal to the total resource demand number of the slice nodes included in the NSSI, if yes, execute step 405; if not, execute step 406.
  • the management server may determine whether the total number of available resources in the second DC combination is greater than or equal to The total resource requirements of the slice nodes included in the NSSI. For example, if the NSSI includes a first slicing node and a second slicing node, the management server can determine whether the total number of available resources of the second DC combination is greater than or equal to the resource demand number of the first slicing node and the second slicing node. The sum of the number of resource requirements.
  • the management server uses the total amount of available resources as the available resource evaluation value of the second DC combination.
  • the management server determines that the physical link between the DC and the DC of the second DC combination meets the delay requirements of the virtual link of the NSSI, and the total number of available resources of the second DC combination meets the slice nodes included in the NSSI When the total number of available resources is determined, the management server can use the total number of available resources as the available resource evaluation value of the second DC combination, so that the subsequent management server selects the DC combination from the DC combination set to provide resources for the NSSI.
  • the management server sets the available resource evaluation value of the second DC combination to 0.
  • the management server sets the available resource evaluation value of the second DC combination to 0 to indicate the second DC The combination cannot meet the needs of the NSSI.
  • the management server sets the available resource evaluation value of the second DC combination to 0.
  • the management server sets the available resource evaluation value of the second DC combination to 0 to indicate the The second DC combination cannot meet the needs of the NSSI.
  • the management server selects the first DC combination from the DC combination set.
  • the first DC combination may be that the available resource evaluation value, DC performance weight, and DC preference value in the DC combination set are all the largest DC combination in the current DC combination set.
  • the management server maps the slice nodes included in the NSSI one by one to the corresponding servers in the first DC combination. If the mapping is successful, the management server may determine that the first DC combination is the target DC combination. It should be noted that when the resource request carries the DC performance requirement or DC preference, the management server can select the corresponding DC combination according to these requirements.
  • the following illustrates the specific process of the management server mapping the slice nodes to the servers in the first DC combination through FIG. 5, and the process includes:
  • the management server determines the first DC combination.
  • the management server selects the first DC combination from the DC combination set.
  • the first DC combination may be the DC combination with the largest available resource evaluation value in the DC combination set.
  • the first DC combination includes a first server and a second server, and the first DC combination includes a first DC and a second DC.
  • the management server selects a slice node from the NSSI.
  • the management server selects a slice node from the NSSI.
  • the NSSI includes four slice nodes, namely VNF1 to VNF4, and this VNF1 is selected here.
  • the management server selects a server from the first DC combination.
  • the management server selects a server from the first DC combination. For example, the management server selects the first server in the first DC combination.
  • the management server judges whether the number of available resources of the server meets the resource requirement of the slicing node, if yes, execute step 505; if not, return to execute step 503 again.
  • the management server judges whether the number of available resources of the first server meets the resource requirement of VNF1, if yes, then execute step 505, if not, then return to step 503 again, that is, select a server from the first DC combination again.
  • the management server maps the slice node to the server, and records the mapping result.
  • the management server maps the VNF1 to the first server, and records the mapping result.
  • the management server determines whether the mapping of each slice node included in the NSSI is completed, if yes, execute step 507, and if not, execute step 502.
  • the management server judges whether VNF1 to VNF4 are mapped to the corresponding server in the first DC combination, if yes, execute step 507, if not, return to execute step 502.
  • the management server can determine that the first DC combination does not meet the requirements of the NSSI, and can reselect a DC combination from the DC combination set.
  • the management server determines that the slice node included in the NSSI is successfully mapped.
  • the management server maps the virtual link between the first slice node to the second slice node to the physical link between the servers corresponding to the slice node.
  • the management server determines the server to which each slice node included in the NSSI is mapped
  • the management server maps the virtual links between the slice nodes.
  • the specific mapping process is described in detail in FIG. 6 , Please refer to Figure 6, the process includes:
  • the management server selects a virtual link from the NSSI.
  • the NSSI includes four slice nodes, VNF1 to VNF4, then the virtual links of the NSSI include VNF1 to VNF2, VNF2 to VNF3, and VNF3 to VNF4, and the management server can select one of the virtual links.
  • the management server determines all the shortest physical links between the slice nodes in the virtual link.
  • the management server may calculate all the shortest physical links between the slice nodes in the virtual link according to the shortest path algorithm.
  • the management server selects a target physical link from all the shortest physical links.
  • the management server After the management server determines multiple shortest physical links, it can select a target physical link from them.
  • the target physical link may be the physical link with the smallest delay among all the shortest physical links.
  • the management server selects the physical link corresponding to the virtual link, it can select the shortest physical link, or it can select any physical link corresponding to the virtual link, which is not specifically limited in this application.
  • the shortest physical link is selected as an example for description.
  • the management server determines whether the available network bandwidth of the target physical link is greater than the bandwidth requirement of the virtual link, if yes, execute step 605, and if not, return to step 603.
  • the available network bandwidth of the target physical link refers to the bandwidth of the edge with the smallest bandwidth among the edges included in the target network link.
  • the target physical link includes n edges, and each edge of the target physical link
  • bw i refers to the bandwidth of the i-th side of the target physical link
  • the bandwidth of the target physical link is min(bw 1 , bw 2 ... bw n ), where the function min(x) is the minimum value of x.
  • the management server determines that the available network bandwidth of the target physical link is less than or equal to the bandwidth requirement of the virtual link, it can return to step 603, reselect a physical link, and then map the NSSI.
  • the management server judges whether the delay of the target physical link is lower than the delay requirement of the virtual link, if yes, execute step 606, and if not, execute step 603.
  • the delay of the target physical link includes the service processing delay of the slice node in the NSSI (for example, queue delay, processing delay, sending delay, etc.) and the transmission delay of the infrastructure in the physical link.
  • the service processing delay can be estimated according to service characteristics; the transmission delay of the infrastructure in the physical link can be calculated according to a preset algorithm or according to the speed of the signal in the transmission medium, which is not specifically limited in this application.
  • step 603 select a physical link again, and then map the NSSI.
  • the management server selects a corresponding target physical link for the virtual link according to the delay requirement and bandwidth requirement of the virtual link, which guarantees the end-to-end delay of NSSI and the bandwidth requirement of NSSI. .
  • the management server maps the virtual link to the target physical link, and makes a record.
  • the management server judges whether the mapping of all virtual links of the NSSI is completed, if yes, execute step 601, and if not, execute step 608.
  • the management server determines that the virtual link mapping of the NSSI is successful, and outputs the virtual link mapping result.
  • the management server determines that the first DC combination is the target DC combination, and outputs the mapping result of the slice node included in the NSSI and the relationship between the slice node The mapping result of the virtual link.
  • the management server can select another in the DC combination again A DC combination is then mapped to the NSSI.
  • a resource request from an NSSI is received, and the resource request carries the first resource requirement of the first slice node, the second resource requirement of the second slice node, and the first slice node to the NSSI to be created.
  • the third resource requirement of the virtual link between the second slice nodes then, determine the DC set, and determine the DC combination set from the DC set; when the first slice node is successfully mapped to The first server in the first DC combination in the DC combination set successfully maps the second slice node to the second server in the first DC combination according to the second resource requirement, and successfully transfers
  • the virtual link between the first slicing node and the second slicing node is mapped to the first physical link between the first server and the second server, it can be determined that the first DC combination is the target DC combination, and Output the mapping result of the NSSI slice node and the mapping result of the virtual link.
  • the corresponding DC is selected to provide resources for the network slice, so that the resource requirements of the actual users NSSI allocates the corresponding DC to meet the needs of users.
  • different network slices can share the same NSSI.
  • the network slice instance NSIX is composed of NSSI A and NSSI C
  • NSI Y is composed of NSSI A and NSSI B. Since NSSI A is shared by NSI X and NSI Y, it is called shared NSSI. Part of the topology of this NSSI A in NSI X and NSI Y is the same, that is, the topology of NSSI A_X and NSSI A_Y are the same.
  • NSSI A_X and NSSI A_Y may have different resource requirements for each slice node sharing NSSI and the bandwidth requirements and delays of each virtual link. Therefore, NSSI A The resource requirements of NSSI A_X and NSSI A_Y are combined.
  • the process includes:
  • the management server determines to share the NSSI.
  • the management server can determine the NSSI.
  • the management server selects a slice node from the shared NSSI.
  • the management server can select the slice node VNF1 in NSSI A, and then merge resources on this VNF1.
  • the management server counts the resource requirements of different network slices for the slice nodes included in the shared NSSI, and obtains the total resource demand of the slice nodes.
  • the management server determines the resource requirements of NSI X and NSI Y for the VNF1, then the resource requirements of NSI X and NSI Y for the VNF1 are added to the resource requirements of NSI Y for the VNF1 to obtain the The total resource demand of VNF1.
  • the management server judges whether each slice node included in the shared NSSI has completed resource merging, if yes, execute step 705; if not, return to execute step 702.
  • step 705 is executed. If the management server does not merge the resources of the four slice nodes one by one, it returns to step 702 to continue selecting the corresponding Slice the node, and merge the resources of the slice node.
  • the management server selects a virtual link from the shared NSSI.
  • NSS A includes four virtual links, VNF1 to VNF2, VNF2 to VNF3, and VNF3 to VNF4.
  • the management server can select a virtual link from it, and then merge the resources of the virtual link.
  • the management server counts the bandwidth requirements of the virtual link included in the shared NSSI by different network slices, and obtains the total bandwidth demand of the virtual link.
  • the management server determines the first bandwidth requirement of NSI X for the virtual link between VNF1 to VNF2 and the second bandwidth requirement of NSI Y for the virtual link between VNF1 to VNF2, and then sets the first bandwidth The requirement plus the second bandwidth requirement obtains the total bandwidth requirement of the virtual link.
  • the management server determines the delay requirements of different network slices for the virtual link sharing the NSSI.
  • the management server determines that NSI X requires 10 ms for the virtual link between VNF1 and VNF2, and determines that NSI Y requires 20 ms for the virtual link between VNF1 and VNF2.
  • the management server uses the delay value that requires the minimum delay of the virtual link in different network slices as the delay demand of the virtual link.
  • the management server may set the delay requirement of the virtual link to 10 ms.
  • the management server judges whether each virtual link included in the shared NSSI has completed resource consolidation, if yes, execute step 710; if not, execute step 705.
  • step 710 is performed. If the management server performs resource integration on the four virtual links one by one To merge, return to step 705 to continue selecting the corresponding virtual link, and perform resource merge on the virtual link.
  • the management server maps the shared NSSI.
  • the specific mapping process of the shared NSSI by the management server is similar to the foregoing mapping process shown in FIG. 2. For details, please refer to the foregoing embodiment shown in FIG. 2 and will not be repeated here.
  • a method for deploying a shared NSSI is provided.
  • the overall resource requirements of the NSSI are obtained by combining the resource requirements of the shared NSSI from different network slices and the resource requirements of the virtual link.
  • the method shown in 2 implements the deployment of the shared NSSI. In practical applications, it has greater practicability and can meet the requirements of different network slices for the shared NSSI.
  • the resource request of the NSSI may also carry requirements for DC deployment, for example, requirements for the region to which the DC belongs.
  • the network slicing subnet NSS requires a part of NSSI to be deployed in Shanghai and another part of NSSI in Beijing.
  • VNF1 to VNF4 of NSS A are deployed in DC1
  • VNF5 to VNF7 of NSS B are deployed in DC2.
  • the DC required by the NSSI is cross-regional, the communication delay requirements between the slice nodes that communicate between two cross-regional DCs are relatively high, so the guarantee of the delay between the DCs is extremely important.
  • FIG. 8B is used to introduce the process in which the management server performs the mapping of the slice nodes communicating between two DCs across regions for this problem. Please refer to FIG. 8B.
  • the process includes:
  • the management server divides the NSSI into a first NSSI and a second NSSI according to a resource request.
  • the resource request carries a cross-DC deployment request
  • the management server determines to divide the NSSI into a first NSSI and a second NSSI according to the cross-DC deployment request.
  • the request for cross-DC deployment includes deploying VNF1 to VNF4 in a DC in Shanghai, and VNF5 to VNF7 in a DC in Shenzhen, then the management server divides the NSS into NSS A and NSS B.
  • the management server determines that the slice nodes across the DC in the first NSSI and the second NSSI are the third slice node and the fourth slice node, and a virtual link between the third slice node and the fourth slice node, respectively.
  • VNF4 in NSSA communicates with VNF5 in NSSB, that is, VNF4 and VNF5 are cross-DC slice nodes, and the management server can also determine the virtual link from VNF4 to VNF5.
  • the management server determines that the number of available resources of the fifth server in the first DC meets the resource requirements of the third slicing node and the number of available resources of the sixth server in the second DC meets the resource requirements of the fourth slicing node.
  • the management server can select the fifth server in the first DC that meets the regional requirements from the first DC combination, and then the management server determines whether the number of available resources of the fifth server meets the resource requirements of the third slicing node, and if so, it can Map the third slice node to the fifth server. The same is true for the fourth slice node, and the fourth slice node can be mapped to the sixth server.
  • the management server determines all the shortest physical links corresponding to the virtual links between the third slice node and the fourth slice node.
  • the management server selects a target physical link from the shortest physical links.
  • the management server judges whether the available network bandwidth of the target physical link is greater than the bandwidth requirement of the virtual link, if yes, execute step 807; if not, return to execute step 805.
  • the management server judges whether the delay of the target physical link is lower than the delay requirement of the virtual link, if yes, execute step 808; if not, return to execute step 805.
  • the management server maps the virtual link to the target physical link, and outputs a mapping result of the virtual link and marks the third slice node and the fourth slice node as mapped slice nodes.
  • Step 804 to step 808 are similar to step 602 to step 606 shown in FIG. 6. For details, please refer to the related description of FIG.
  • the management server maps the remaining slice nodes of the NSSI and the virtual links between the slice nodes.
  • the management server After the management server completes the mapping of the third slice node and the fourth slice node, it also maps the virtual links between the other slice nodes of the NSSI and the slice nodes. For example, as shown in Figure 8A, the management server maps VNF1 to VNF3 and VNF6 and VNF7.
  • the specific mapping process is similar to the process shown in Figure 2 above, and there is no need to perform mapping again for the mapped slice nodes. Refer to the related description of the aforementioned FIG. 2, which will not be repeated here.
  • NSSI cross-DC deployment when the network slicing distinguishes the user plane and the control plane, and the NSSI for the user plane or the control plane has a requirement for cross-DC deployment, it is applicable as shown in Figure 8B
  • the embodiment of NSSI is deployed across DCs to ensure the delay requirements of NSSI; and when the network slicing does not distinguish between the user plane and the control plane, and the NSSI has a requirement for cross-DC deployment, the embodiment shown in FIG. 8B is directly used to The NSSI is deployed across DCs.
  • a method is provided to ensure the communication delay between the servers of the DC mapped by the slice node when the NSSI is deployed across DCs.
  • the delay requirements of the NSSI for requesting cross-regional DCs are guaranteed. , Improve the practicality of the application scheme.
  • the resource allocation device 900 is used to perform FIG. 2, FIG. 3, and FIG.
  • the resource allocation device 900 includes a transceiver module 901 and a processing module 902.
  • the transceiver module 901 is configured to obtain a resource request of the NSSI, the resource request carrying the first resource requirement of the first slice node, the second resource requirement of the second slice node and the first slice included in the NSSI to be created The third resource requirement of the virtual link between the node and the second slice node;
  • the processing module 902 is configured to determine a data center DC set, where the DC set includes at least one DC that can be used to provide resources for the NSSI;
  • the processing module 902 is further configured to determine a DC combination set from the DC set, where the DC combination set includes at least one DC combination that can be used to provide resources for the NSSI; and map the first slice node according to the first resource requirement To the first server in the first DC combination in the DC combination set and map the second slicing node to the second server in the first DC combination according to the second resource requirement; according to the third resource requirement
  • the virtual link between the first slicing node and the second slicing node is mapped to the first physical link between the first server and the second server; when the first slicing node is successfully mapped to the first
  • the second slice node is successfully mapped to the second server, and the virtual link is successfully mapped to the first physical link
  • the first DC combination is determined to be the target DC combination
  • the slice nodes included in the NSSI are output The mapping result of and the mapping result of the virtual link.
  • all DCs in the DC set are sorted according to the available resource evaluation value of the DC, or all DCs in the DC set are sorted according to the available resource evaluation value of the DC from small to large Sort.
  • the processing module 902 is further configured to: perform statistics on the number of available resources of the servers included in each DC in the DC set to obtain an evaluation value of the available resources of each DC.
  • the DC set includes a first DC
  • the first DC includes a third server and a fourth server
  • the processing module 902 is specifically configured to: when the available network bandwidth provided by the third server and The available network bandwidth provided by the fourth server is greater than the first preset threshold, the first available resource quantity of the third server and the fourth available resource quantity of the fourth server are determined, and the first available resource quantity is added
  • the second available resource quantity obtains the available resource evaluation value of the first DC.
  • each DC combination in the DC combination set includes the available resource evaluation value of each DC combination.
  • each DC combination in the DC combination set further includes at least one of a DC performance weight and a DC preference value of each DC combination, and the DC performance weight indicates the service of the server included in the DC combination Processing performance, DC preference value is calculated according to NSSI's deployment requirements for DC location and each DC combination.
  • the first DC combination is a DC combination with the largest available resource evaluation value, DC performance weight, and DC preference value among the DC combinations currently included in the DC combination set.
  • processing module 902 is further configured to:
  • the second DC combination includes a second DC and a third DC
  • the second DC combination includes a fifth server and a sixth server
  • the available resource evaluation value of the second DC combination is the third available resource quantity plus the fourth available resource quantity.
  • processing module 902 is specifically configured to:
  • processing module 902 is specifically configured to:
  • the virtual link between the first slice node and the second slice node is mapped to the first physical link.
  • processing module 902 is further configured to:
  • the first resource demand includes the resource demand of the first network slice for the first slice node and the second network slice pair
  • the resource demand of the first slice node, the second resource demand includes the resource demand of the first network slice on the second slice node and the resource demand of the second network slice on the second slice node;
  • processing module 902 is specifically configured to:
  • the first delay demand is less than or equal to the second delay demand, then the first delay demand is used as the total delay demand of the virtual link;
  • the second delay demand is taken as the total delay demand of the virtual link.
  • the resource request carries a request for cross-DC deployment;
  • the first DC combination includes a fourth DC and a fifth DC, and the fourth DC and the fifth DC are two deployed in different regions.
  • the fourth DC includes a seventh server, and the fifth DC includes an eighth server;
  • the processing module 902 is further configured to:
  • the slice nodes across the DC in the first NSSI and the second NSSI are the third slice node, the fourth slice node, and the virtual link between the third slice node and the fourth slice node, respectively;
  • the transceiver module 901 obtains the resource request of the NSSI.
  • the resource request carries the first resource requirement of the first slicing node, the second resource requirement of the second slicing node, and the first resource included in the NSSI to be created.
  • the corresponding DC is selected according to the resource requirements of the slice node and the resource requirements of the virtual link to provide resources for the network slice, so that the resource requirements of the actual users can be NSSI allocates the corresponding DC to meet the needs of users.
  • an embodiment of the present application also provides another resource allocation device.
  • the resource allocation device 1000 includes a processor 1001, a transceiver 1002, and a memory 1003.
  • the processor 1001 is connected to the transceiver 1002 and the memory 1003 through wires.
  • the memory 1003 may include a read-only memory and/or a random access memory, and provides operation instructions and data to the processor 1002.
  • the transceiver 1003 may be used to perform the operations performed by the transceiver module 901 in FIG. 9 described above, and/or the transceiver 1003 may also be used to perform other processing steps of the resource allocation device in the embodiment of the present application.
  • the processor 1001 may be used to perform the operations of the processing module 902 in FIG. 9 described above, and/or the processor 1001 may also be used to perform other processing steps of the resource allocation apparatus in the embodiment of the present application.
  • the resource allocation device when the resource allocation device is a chip, the chip includes at least one processor, a transceiver, and a memory, the memory stores instructions, and the transceiver and the at least one processor are interconnected through a wire;
  • the processor is used to perform the operations of the processing module 902 in FIG. 9, and/or the processor is also used to perform other processing steps of the resource allocation device in the embodiment of the present application;
  • the transceiver is used to perform the operations of the transceiver module 901 in FIG. 9, And/or the transceiver is also used to perform other processing steps of the resource allocation device in the embodiment of the present application.
  • a computer-readable storage medium is provided, and an instruction is stored thereon.
  • the instruction is executed, the method for managing the server in the foregoing method embodiment is executed.
  • a computer program product containing instructions is provided, and when the instructions are executed, the method for managing the server in the foregoing method embodiment is executed.
  • processors mentioned in the embodiments of this application may be a central processing unit (Central Processing Unit, CPU), or other general-purpose processors, digital signal processors (Digital Signal Processors, DSPs), and application-specific integrated circuits ( Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory mentioned in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), and electrically available Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • the volatile memory may be a random access memory (Random Access Memory, RAM), which is used as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • DDR SDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synchlink DRAM, SLDRAM synchronous connection dynamic random access memory
  • DR RAM Direct Rambus RAM
  • the processor is a general-purpose processor, DSP, ASIC, FPGA or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component
  • the memory storage module
  • the disclosed system, device, and method may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , Including several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

本申请实施例公开了一种资源分配方法以及装置。本申请实施例方法包括:获取网络切片子网实例NSSI的资源请求,该资源请求携带待创建的所述NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至第二切片节点之间的虚拟链路的第三资源需求;确定DC集合,DC集合包括至少一个可用于为NSSI提供资源的DC;从DC集合中确定DC组合集合,DC组合集合包括至少一个可用于为NSSI提供资源的DC组合;当第一切片节点成功映射至第一服务器、第二切片节点成功映射至第二服务器和虚拟链路成功映射至第一物理链路时,确定第一DC组合为目标DC组合,并输出NSSI所包括的切片节点的映射结果以及虚拟链路的映射结果。

Description

资源分配方法以及装置
本申请要求于2019年6月21日提交中国专利局、申请号为201910551895.0、发明名称为“资源分配方法以及装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术,尤其涉及一种资源分配方法以及装置。
背景技术
随着移动通信的高速发展,数字化转型几乎涉及了所有传统行业。但是,传统蜂窝网络架构只能提供统一网络服务,难以满足数字化转型浪潮带来的差异性极大的通信需求,包括功能性差异和性能差异等。在第五代(fifth-generation,简称5G)无线通信系统中,网络被抽象为“网络切片”,一个网络切片满足某一类或者一个用例的通信服务需求,整个5G网络由满足不同能力的大量网络切片组成。通过5G网络切片技术,运营商将能够最大化提升网络对外部环境、客户需求、新业务场景的适应能力,提高网络资源的使用效率,构建灵活、敏捷的移动通信网络。
目前,针对网络切片子网实例(network slice subnet instance,NSSI)的资源请求,需要把所请求的网络切片所需的虚拟化网络功能(virtualisation network function,VNF)放在底层物理网络上并互连,目前主要是采用对该网络切片所对应的虚拟网络进行统一分配处理的架构,在进行虚拟网络与物理网络映射的运算方面多采用启发时算法进行求解以使得将该虚拟网络映射至物理网络。
由上述方案可知,在NSSI的分配过程中,并未涉及物理网络中的数据中心(data center,DC)的概念,例如,虚拟网络所映射至的物理网络的DC中的服务器的性能等相关参数是否满足该网络切片的需求,无法根据网络切片对资源的需求为NSSI分配对应的DC,无法满足用户的需求,导致用户体验较差。
发明内容
本申请实施例提供了一种资源分配方法以及装置,用于根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
本申请实施例第一方面提供了一种资源分配方法,包括:
获取NSSI的资源请求,该资源请求携带待创建的NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至该第二切片节点之间的虚拟链路的第三资源需求;然后,确定DC集合,并从DC集合中确定DC组合集合;当根据该第一资源需求成功将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器,根据该第二资源需求成功将第二切片节点映射至该第一DC组合中的第二服务器,且根据该第三资源需求成功将该第一切片节点至第二切片节点之间的虚拟链路映射至该第一服务器至第二服务器之间的第一物理链路时,可以确定该第一DC组合为目标DC组合,并 输出NSSI的切片节点的映射结果和虚拟链路的映射结果。因此,本实施例中,在对NSSI的分配过程中,根据切片节点的资源需求和虚拟链路的资源需求选择对应的DC为该网络切片提供资源,这样可以根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
一种可能的实现方式中,该DC集合中的所有DC按照DC的可用资源评估值由大到小进行排序,或者,该DC集合中的所有DC按照DC的可用资源评估值由小到大进行排序。
另一种可能的实现方式中,在确定DC集合之前,该方法还包括:对该DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值。
另一种可能的实现方式中,该DC集合包括第一DC,该第一DC包括第三服务器和第四服务器;对该DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值包括:当该第三服务器所提供的可用网络带宽和该第四服务器所提供的可用网络带宽均大于第一预设阈值,确定该第三服务器的第一可用资源数量和第四服务器的第四可用资源数量,并将该第一可用资源数量加上该第二可用资源数量,得到该第一DC的可用资源评估值。在该可能的实现方式中,提供了一种具体的DC的可用资源评估值的确定方式。
另一种可能的实现方式中,该DC组合集合中的每个DC组合包括每个DC组合的可用资源评估值。
另一种可能的实现方式中,该DC组合集合中的每个DC组合还包括每个DC组合的DC性能权重和DC偏好值中的至少一个,DC性能权重指示DC组合所包括的服务器的业务处理性能,DC偏好值是根据NSSI在部署上对DC位置需求和每个DC组合计算得到的。
另一种可能的实现方式中,第一DC组合为当前该DC组合集合所包括的DC组合中可用资源评估值、DC性能权重和DC偏好值都为最大的DC组合。
另一种可能的实现方式中,在确定DC组合集合之前,该方法还包括:首先,确定第二DC组合,该第二DC组合包括第二DC和第三DC,该第二DC组合包括第五服务器和第六服务器;当第五服务器所提供的可用网络带宽和第六服务器所提供的可用网络带宽均大于第二预设阈值,确定第五服务器的第三可用资源数量和第六服务器的第四可用资源数量;然后,再确定第二DC至第三DC之间的第二物理链路的时延小于或者等于第三预设阈值;再判断该第三可用资源数量加上第四可用资源数量是否大于等于该NSSI所包括的切片节点的总资源需求数量,如果是,则确定该第二DC组合的可用资源评估值为该第三可用资源数量加上第四可用资源数量。
另一种可能的实现方式中,该根据第一资源需求将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器和根据第二资源需求将第二切片节点映射至第一DC组合中的第二服务器包括:首先,从DC组合集合中确定第一DC组合,该第一DC组合包括第一服务器和第二服务器;然后,判断第一服务器的可用资源数量是否大于第一切片节点的资源需求量和判断该第二服务器的可用资源数量是否大于第二切片节点的资源需求量,如果是,则将第一切片节点映射至第一服务器,和将第二切片节点映射至第二服务器。
另一种可能的实现方式中,在根据该第三资源需求将第一切片节点至第二切片节点之 间的虚拟链路映射至第一服务器至第二服务器之间的第一物理链路包括:首先,判断第一服务器所在的DC至该第二服务器所在的DC之间的第一物理链路的可用网络带宽是否大于第一切片节点至第二切片节点之间的虚拟链路的带宽需求,如果是,则判断该第一物理链路之间的时延是否地域该虚拟链路的时延需求,如果是,则将第一切片节点至第二切片节点之间的虚拟链路映射至第一物理链路。
另一种可能的实现方式中,在获取NSSI请求之前,该方法还包括:首先,确定第一网络切片和第二网络切片共享该NSSI;然后,确定该第一切片节点的第一资源需求和第二切片节点的第二资源需求,该第一资源需求包括该第一网络切片对该第一切片节点的资源需求和第二网络切片对该第一切片节点的资源需求,该第二资源需求包括第一网络切片对该第二切片节点的资源需求和第二网络切片对第二切片节点的资源需求;然后,确定第一切片节点至第二切片节点之间的虚拟链路的第三资源需求,该第三资源需求包括第一网络切片对该虚拟链路的资源需求和第二网络切片对该虚拟链路的资源需求。
另一种可能的实现方式中,确定该第一切片节点至第二切片节点之间的虚拟链路的第三资源需求包括:首先,确定该第一网络切片对该虚拟链路的第一带宽需求和第二网络切片对该虚拟链路的第二带宽需求;然后,将第一带宽需求加上第二带宽需求作为该虚拟链路的带宽总需求;并确定该第一网络切片对虚拟链路的第一时延需求和第二网络切片对该虚拟链路的第二时延需求,如果第一时延需求小于等于该第二时延需求,则将该第一时延需求作为该虚拟链路的时延总需求;如果第一时延需求大于第二时延需求,则将第二时延需求作为该虚拟链路的时延总需求。
另一种可能的实现方式中,该资源请求携带跨DC部署的请求;该第一DC组合包括第四DC和第五DC,且该第四DC和第五DC为部署在不同地域的两个DC;该第四DC包括第七服务器,第五DC包括第八服务器;在根据第一资源需求将第一切片节点映射至DC组合集合中的第一DC组合中的第一服务器和根据第二资源需求将第二切片节点映射至第一DC组合中的第二服务器之前,该方法还包括:首先,根据该跨DC部署的请求将NSSI划分为第一NSSI和第二NSSI;然后,确定该第一NSSI与第二NSSI中跨DC的切片节点分别为第三切片节点和第四切片节点以及第三切片节点至第四切片节点之间的虚拟链路;当第七服务器的可用资源数量满足该第三切片节点的资源需求且第八服务器的可用资源数量满足该第四切片节点的资源需求时,判断该第七服务器所在的DC至第八服务器所在的DC之间的第三物理链路的可用网络带宽是否大于第三切片节点至第四切片节点之间的虚拟链路的带宽需求,如果是,则判断第三物理链路之间的时延是否低于该虚拟链路的时延需求,如果是,则将虚拟链路映射至该第三物理链路,并将该第三切片节点和第四切片节点标记为已映射成功的切片节点。
本申请实施例第二方面提供一种资源分配装置,所述资源分配装置具有实现上述第一方面以及第一方面的任一可能实现方式的功能。该功能可以通过硬件实现,也可以通过硬件执行相应的软件实现,还可以采用软件与硬件结合的形式实现。该硬件和/或软件包括一个或多个与上述功能相对应的模块。
本申请实施例第三方面提供一种资源分配装置,所述资源分配装置包括:存储器、收 发器和至少一个处理器,所述存储器中存储有指令;所述存储器、所述收发器和所述至少一个处理器通过线路连接;所述至少一个处理器调用所述指令,执行第一方面在所述资源分配装置进行的数据处理或者控制操作。
本申请第四方面提供一种芯片系统,该芯片系统包括至少一个处理器、收发器和存储器,所述存储器,所述存储器中存储有指令,该至少一个处理器与该收发器通过线路互联,所述至少一个处理器用于执行如本申请第一方面任一种实现方式中的操作。
本申请实施例第五方面提供了一种包括指令的计算机程序产品,其特征在于,当其在计算机上运行时,使得该计算机执行如第一方面中任一种的实现方式。
本申请实施例第六方面提供了一种计算机可读存储介质,其特征在于,包括指令,当该指令在计算机上运行时,使得计算机执行如第一方面中任一种实现方式。
从以上技术方案可以看出,本申请实施例具有以下优点:
经由上述技术方案可知,获取NSSI的资源请求,该资源请求携带待创建的NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至该第二切片节点之间的虚拟链路的第三资源需求;然后,确定DC集合,并从DC集合中确定DC组合集合;当根据该第一资源需求成功将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器,根据该第二资源需求成功将第二切片节点映射至该第一DC组合中的第二服务器,且根据该第三资源需求成功将该第一切片节点至第二切片节点之间的虚拟链路映射至该第一服务器至第二服务器之间的第一物理链路时,可以确定该第一DC组合为目标DC组合,并输出NSSI的切片节点的映射结果和虚拟链路的映射结果。因此,通过本申请的技术方案,在对NSSI的分配过程中,根据切片节点的资源需求和虚拟链路的资源需求选择对应的DC为该网络切片提供资源,这样可以根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
附图说明
图1为本申请实施例的一个系统框架示意图;
图2为本申请实施例资源分配方法的一个实施例示意图;
图3为本申请实施例资源分配方法的另一个实施例示意图;
图4为本申请实施例资源分配方法的另一个实施例示意图;
图5为本申请实施例资源分配方法的另一个实施例示意图;
图6为本申请实施例资源分配方法的另一个实施例示意图;
图7A为本申请实施例资源分配方法的一个场景示意图;
图7B为本申请实施例资源分配方法的另一个实施例示意图;
图8A为本申请实施例资源分配方法的另一个场景示意图;
图8B为本申请实施例资源分配方法的另一个实施例示意图;
图9为本申请实施例资源分配装置的一个结构示意图;
图10为本申请实施例资源分配装置的另一个结构示意图。
具体实施方式
本申请实施例提供了一种资源分配方法以及装置,用于根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
请参阅图1,图1为本申请实施例的一个系统框架图,本申请实施例的资源分配方法可以应用于网络功能虚拟化管理和编排(network functions virtualisation management and orchestration,NFV-MANO)的3GPP通信系统,该系统框架包括网络切片子网管理功能(network slice subnet management functions,NSSMF)和NFV-MANO。其中,NSSMF用于对NSSI的管理和编排,提供切片的组件包管理、生命周期管理和运维能力。
NFV MANO用于管理和协调虚拟化网络功能(virtualisation network function,VNF)和支撑软件组件的架构框架,支持在虚拟机上部署与连接。
其中,NFV-MANO可以是安装在管理服务器上,也可以安装计算机设备中,具体本申请不做限定。而该NFV-MANO包括网络功能虚拟化编排器(network functions virtualization orchestrator,NFVO)、虚拟化的网络功能模块管理器(virtualised network function Manager,VNFM)和虚拟基础设施管理器(virtualized infrastructure management,VIM),而切片设计器可以是部署在NFV-MANO中,也可以是一个单独的功能模块,具体本申请不做限定。其次,当该切片设计器部署在NFV-MANO中时,该切片设计器可以集成NFVO中。图1仅仅示出切片设计器集成在NFVO中为例进行说明。
VNF是虚拟化的网络功能单元,多个VNF组成NSSI,可以理解为一个VNF对应NSSI中的一个切片节点。如图1所示,请求的NSSI中包括4个切片节点,分别对应于VNF1至VNF4,而在物理网络中VNF1映射至DC1,VNF2映射至DC2,VNF3映射至DC4以及VNF4映射至DC3。
NFVO用于对VNF及其对应的NFVI进行部署、操作、管理以及协调,实现整个NFV基础架构、软件资源和网络服务的编排和管理。
VNFM用于对VNF实例的生命管理,如实例化、扩缩容、查询、更新以及种植等。一个VNFM可以关联到单个VNF实例,也可以关联到多个同类型或者不同类型的VNF实例。
VIM用于控制和管理网络功能虚拟化基础设施的计算,存储网络资源的功能模块,例如,VIM可以为网络功能虚拟化基础设施。
上述通过图1示出了本申请实施例资源分配方法的一个应用系统,需要说明的是,本申请实施例的资源分配方法同样适用于其他系统,具体此处不做限定。其次,本申请实施例中切片设计器可以集成在管理服务器中,也可以是集成在计算机设备中,在后续的实施例中,仅以管理服务器集成在管理服务器为例进行说明。
本申请实施例中,针对NSSI的部署,适用于对核心网侧网络切片的映射,也适用于对接入网侧网络切片的映射,例如接入网的云化部分的网络切片的映射,具体本申请不做限定。
请参阅图2,图2为本申请实施例中资源分配方法的一个实施例示意图,该方法包括:
201、获取NSSI的资源请求。
其中,该资源请求携带待创建的NSSI所包括的切片节点的资源需求和切片节点之间的虚拟链路的资源需求。例如,NSSI包括第一切片节点和第二切片节点,则该资源请求包括第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至第二切片节点之间连接的虚拟链路的第三资源需求。
本申请实施例中,切片节点的资源需求可以包括对DC上的服务器的CPU、内存和硬盘存储等性能的需求,切片节点之间的虚拟链路的资源需求可以包括该虚拟链路所对应的物理链路的可用网络带宽和时延等的需求。
结合图1所示的系统框架,该资源请求可以是NFVO向切片设计器发送的,即NFVO接收到NSSI的资源请求之后,向切片设计器上报该NSSI的资源请求。
202、确定DC集合。
管理服务器可以获取当前系统中可用的DC信息列表以及这些DC所包括的服务器之间的物理链路的资源信息;然后,管理服务器可以对这些DC进行整理,确定DC集合。结合上述图1,可用的DC信息列表以及这些DC所包括的服务器之间的物理链路的资源信息可以由NFVO向切片设计器发送。
可选的,该DC集合中的所有DC按照DC的可用资源评估值由大到小进行排序,或者该DC集合中的所有DC按照DC的可用资源评估值由小到大进行排序。其中,可用资源评估值是由管理服务器通过对DC集合中的每个DC所包括的服务器的可用资源数量进行统计得到的,针对每个DC的可用资源评估值的具体统计过程通过图3所示的实施例进行说明,这里以对第一DC的可用资源数量进行统计为例进行说明,请参阅图3,该过程包括:
301、管理服务器确定第一DC。
管理服务器从可用的DC信息中确定该第一DC,并确定该第一DC中所包括的每个服务器的可用资源数量。例如,该第一DC包括第一服务器和第二服务器,那么,该管理服务器可以确定该第一服务器的可用资源数量和第二服务器的可用资源数量。
302、管理服务器统计该第一DC中可用网络带宽大于第一预设阈值的服务器的可用资源总数量,得到该第一DC的可用资源评估值。
管理服务器可以判断第一DC所包括的每个服务器所提供的可用网络带宽是否,大于第一预设阈值;然后,管理服务器统计该第一DC中可用网络带宽大于第一预设阈值的服务器的可用资源总数量,得到该第一DC的可用资源评估值。其中,该第一预设阈值为管理服务器根据该NSSI所包括的最大带宽需求的虚拟链路确定的,可用网络带宽是指服务器所能提供的网络带宽中除已被使用的网络带宽之外的网络带宽。
203、从DC集合中确定DC组合。
在步骤202中确定DC集合之后,管理服务器可以从DC集合中确定DC组合,每个DC组合包括至少一个DC,且每个DC组合的DC数量不大于DC集合中包括的DC数量。例如,DC集合总共包括m个,则选择r个DC作为DC组合,可知DC的组合方式有多种,m为大于等于1的整数。
该DC组合集合包括每个DC组合的可用资源评估值。可选的,该DC组合还包括每个DC组合的DC性能权重和DC偏好值。其中,DC性能权重指示DC组合所包括的服务器的业 务处理性能,DC偏好值是根据NSSI在部署上对DC位置需求和每个DC组合计算得到的,例如,用户希望将同一网络切片的用户面和控制面部分尽量部署在地理位置更为接近或者相同的DC中,以使得用户面与控制面之间的通信的时延等更有保障,所以,管理服务器可以根据该需求以及该每个DC组合计算对应的DC偏好值。
其中,DC组合的可用资源评估值的计算过程通过图4所示的实施例进行详细介绍,这里以第二DC组合的可用资源评估值为例,请参阅图4,该过程包括:
401、管理服务器确定第二DC组合。
管理服务器从DC集合确定该第二DC组合。例如,该第二DC组合包括第二DC和第三DC,该第二DC组合包括第五服务器和第六服务器。
402、管理服务器统计第二DC组合中可用网络带宽大于第一预设阈值的服务器的可用资源总数量。
管理服务器可以判断该第二DC组合中所包括的每个服务器所提供的可用网络带宽是否大于第一预设阈值,然后,管理服务器根据判断结果统计该第二DC组合中可用网络带宽大于第一预设阈值的服务器的可用资源总数量。例如,当管理服务器确定该第五服务器所提供的可用网络带宽和该第六服务器所提供的可用网络带宽均大于第一预设阈值,那么管理服务器可以确定该第二DC组合的可用资源总数量为该第五服务器的可用资源数量加上该第六服务器的可用资源数量。其中,该第一预设阈值为管理服务器根据该NSSI所包括的最大带宽需求的虚拟链路,可用网络带宽是指服务器所能提供的网络带宽中除已被使用的网络带宽之外的网络带宽。
403、管理服务器判断第二DC组合所包括的DC与DC之间的物理链路的时延是否小于等于第二预设阈值,若是,则执行步骤404;若否,则执行步骤407。
其中,该第二预设阈值为管理服务器根据NSSI的资源请求确定该NSSI所包括的时延要求最小虚拟链路确定的。
可选的,DC与DC之间的物理链路可以为DC与DC之间的最短路径,且该物理链路是所计算得到的所有最短路径中时延最小的路径。具体的,管理服务器计算该物理链路的方式可以有多种,下面举例说明:
1、管理服务器可以随机从第二DC选择一个服务器1和从第二DC中选择一个服务器2,然后根据最短路径算法计算该服务器1至服务器2之间的最短路径;依次将第二DC和第三DC所包括的服务器之间的最短路径都计算出来,然后再从这些最短路径确定距离最小且时延最小的路径。
2、管理服务器确定第二DC与第三DC之间进行通信的边缘服务器,然后根据最短路径算法计算边缘服务器之间的最短路径,并从这些最短路径中选择距离最小且时延最小的路径。
404、管理服务器判断该可用资源总数量是否大于或者等于该NSSI所包括的切片节点的总资源需求数量,若是,则执行步骤405;若否,则执行步骤406。
当确定该第二DC组合所包括的DC与DC之间的物理链路的时延小于等于第二预设阈值时,管理服务器可以判断该第二DC组合中的可用资源总数量是否大于或者等于该NSSI所 包括的切片节点的总资源需求数量。例如,该NSSI包括第一切片节点和第二切片节点,那么管理服务器可以判断该第二DC组合的可用资源总数量是否大于等于该第一切片节点的资源需求数量与第二切片节点的资源需求数量之和。
405、管理服务器将该可用资源总数量作为该第二DC组合的可用资源评估值。
当管理服务器确定该第二DC组合的DC与DC之间的物理链路满足该NSSI的虚拟链路的时延需求,且该第二DC组合的可用资源总数量满足该NSSI所包括的切片节点的可用资源总数量时,那么管理服务器可以将该可用资源总数量作为该第二DC组合的可用资源评估值,以便于后续管理服务器从DC组合集合中选择DC组合为NSSI提供资源。
406、管理服务器将该第二DC组合的可用资源评估值设置为0。
而当该第二DC组合的可用资源总数量小于该NSSI所包括的切片节点的可用资源总数量时,管理服务器将该第二DC组合的可用资源评估值设置为0,以表示该第二DC组合无法满足该NSSI的需求。
407、管理服务器将该第二DC组合的可用资源评估值设置为0。
当该第二DC组合中所包括的DC与DC之间的物理链路的时延大于第二预设阈值时,管理服务器将该第二DC组合的可用资源评估值设置为0,以表示该第二DC组合无法满足该NSSI的需求。
204、根据第一资源需求将第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器和根据第二资源需求将第二切片节点映射至该第一DC组合中的第二服务器。
管理服务器从DC组合集合中选择第一DC组合。可选的,该第一DC组合可以为DC组合集合中可用资源评估值、DC性能权重和DC偏好值都为当前DC组合集合中最大的DC组合。然后,管理服务器将NSSI所包括切片节点一一映射至该第一DC组合中的对应服务器。若映射成功,则管理服务器可以确定该第一DC组合为目标DC组合。需要说明的是,当该资源请求携带该对DC性能的要求或者对DC的偏好时,则管理服务器可以根据这些要求选择对应的DC组合。
下面通过图5来说明该管理服务器将切片节点映射至第一DC组合中的服务器的具体过程,该过程包括:
501、管理服务器确定第一DC组合。
管理服务器从DC组合集合中选择该第一DC组合,可选的,该第一DC组合可以为该DC组合集合中可用资源评估值最大的DC组合。例如,该第一DC组合包括第一服务器和第二服务器,第一DC组合包括第一DC和第二DC。
502、管理服务器从NSSI中选择切片节点。
管理服务器从该NSSI中选择一个切片节点。例如,如图1所示,NSSI包括四个切片节点,分别为VNF1至VNF4,这里选择该VNF1。
503、管理服务器从第一DC组合中选择服务器。
管理服务器从第一DC组合选择服务器。例如,管理服务器选择该第一DC组合中第一服务器。
504、管理服务器判断该服务器的可用资源数量是否满足该切片节点的资源需求,若 是,则执行步骤505;若否,则返回重新执行步骤503。
例如,该管理服务器判断该第一服务器的可用资源数量是否满足VNF1的资源需求,如果是,那么执行步骤505,如果不是,那么重新返回步骤503,即重新从第一DC组合中选择一个服务器。
505、管理服务器将该切片节点映射至该服务器,并记录该映射结果。
例如,当该服务器的可用资源数量满足VNF1的资源需求时,管理服务器将该VNF1映射至第一服务器,并记录该映射结果。
506、管理服务器判断该NSSI所包括的每个切片节点是否映射完成,若是,则执行步骤507,若否,则执行步骤502。
例如,管理服务器判断VNF1至VNF4是否完成映射至该第一DC组合中对应的服务器,如果是,则执行步骤507,如果不是,则返回执行步骤502。
需要说明的是,如果存在未完成映射的切片节点,可以返回步骤502继续执行,但是当管理服务器确定该第一DC组合中所有的服务器都无法满足该NSSI所包括的某个或者某些切片节点的资源需求时,则管理服务器可以确定该第一DC组合不满足该NSSI的需求,可以重新在DC组合集合中重新选择一个DC组合。
507、管理服务器确定该NSSI所包括的切片节点映射成功。
205、根据第三资源需求将第一切片节点至第二切片节点之间的虚拟链路映射至第一服务器至第二服务器之间的第一物理链路。
管理服务器将该第一切片节点至第二切片节点之间的虚拟链路映射至该切片节点所对应的服务器之间的物理链路。
本申请实施例中,管理服务器确定了该NSSI所包括的每个切片节点所映射至的服务器之后,管理服务器将切片节点之间的虚拟链路进行映射,具体的映射过程通过图6进行详细说明,请参阅图6,该过程包括:
601、管理服务器从NSSI中选择虚拟链路。
例如,结合图1所示,NSSI包括四个切片节点,VNF1至VNF4,那么该NSSI的虚拟链路包括VNF1至VNF2,VNF2至VNF3和VNF3至VNF4,管理服务器可以选择其中一条虚拟链路。
602、管理服务器确定该虚拟链路中的切片节点之间的所有最短物理链路。
具体的,管理服务器可以根据最短路径算法计算该虚拟链路中的切片节点之间的所有最短物理链路。
603、管理服务器从该所有最短物理链路中选择一个目标物理链路。
管理服务器确定了多个最短物理链路之后,可以从中选择一个目标物理链路。可选的,该目标物理链路可以为该所有最短物理链路中时延最小的物理链路。
需要说明的是,管理服务器在选择虚拟链路所对应的物理链路时,可以选择最短物理链路,也可以是选择任意一条该虚拟链路所对应的物理链路,具体本申请不做限定,本实施例以选择最短物理链路为例进行说明。
604、管理服务器判断该目标物理链路的可用网络带宽是否大于该虚拟链路的带宽需 求,若是,则执行步骤605,若否,则返回执行步骤603。
其中,该目标物理链路的可用网络带宽是指目标网络链路所包括的边中带宽最小的边的带宽,例如,该目标物理链路包括n条边,该目标物理链路的各条边带宽为path=(bw 1,bw 2……bw n),bw i是指该目标物理链路的第i条边的带宽,而目标物理链路的带宽为min(bw 1,bw 2……bw n),其中,函数min(x)为求x中的最小值。
需要说明的是,当管理服务器确定该目标物理链路的可用网络带宽小于或者等于该虚拟链路的带宽需求时,可以返回步骤603,重新选择一条物理链路,然后对NSSI进行映射。
605、管理服务器判断该目标物理链路的时延是否低于该虚拟链路的时延需求,若是,则执行步骤606,若否,则执行步骤603。
其中,该目标物理链路的时延包括该NSSI中的切片节点的业务处理时延(例如,队列时延、处理时延和发送时延等)以及物理链路中基础设施的传输时延。而业务处理时延可以根据业务特性进行估算得到;对于物理链路中基础设施的传输时延可以根据预设的算法或者根据信号在传输介质中的速度计算得到,具体本申请不做限定。
需要说明的是,该目标物理链路的时延大于该虚拟链路的时延时,可以返回步骤603,重新选择一条物理链路,然后对NSSI进行映射。
由此可知,本实施例中,管理服务器根据虚拟链路的时延需求和带宽需求为该虚拟链路选择一条对应的目标物理链路,保障了NSSI的端到端的时延和NSSI的带宽需求。
606、管理服务器将该虚拟链路映射至该目标物理链路,并做记录。
607、管理服务器判断该NSSI的所有虚拟链路是否映射完成,若是,则执行步骤601,若否,则执行步骤608。
608、管理服务器确定该NSSI的虚拟链路映射成功,并输出虚拟链路的映射结果。
206、确定第一DC组合为目标DC组合,并输出该NSSI所包括的切片节点的映射结果和切片节点之间的虚拟链路的映射结果。
若确定每个切片节点映射成功,且每条虚拟链路都映射成功,则管理服务器确定该第一DC组合为目标DC组合,并输出该NSSI所包括的切片节点的映射结果和切片节点之间的虚拟链路的映射结果。
需要说明的是,如果管理服务器通过第一DC组合对该NSSI的切片节点进行映射出现映射失败,或者切片节点之间的虚拟链路的映射出现失败,则管理服务器可以重新在DC组合中选择另外一个DC组合,再对该NSSI进行映射。
本申请实施例中,接收NSSI的资源请求,该资源请求携带待创建的NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至该第二切片节点之间的虚拟链路的第三资源需求;然后,确定DC集合,并从DC集合中确定DC组合集合;当根据该第一资源需求成功将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器,根据该第二资源需求成功将第二切片节点映射至该第一DC组合中的第二服务器,且根据该第三资源需求成功将该第一切片节点至第二切片节点之间的虚拟链路映射至该第一服务器至第二服务器之间的第一物理链路时,可以确定该第一DC组合为 目标DC组合,并输出NSSI的切片节点的映射结果和虚拟链路的映射结果。因此,通过本申请的技术方案,在对NSSI的分配过程中,根据切片节点和虚拟链路的资源需求结合DC来选择对应的DC为该网络切片提供资源,这样可以根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
本申请实施例中,不同的网络切片可以共享同一个NSSI,如图7A所示,网络切片实例NSIX由NSSI A和NSSI C构成,而NSI Y由NSSI A和NSSI B构成。由于NSSI A是NSI X和NSI Y共享的,因此称之为共享NSSI。该NSSI A在NSI X和NSI Y中的部分拓扑是相同的,即NSSI A_X和NSSI A_Y的拓扑结构是相同的。而由于NSI X与NSI Y所服务的用户规模不同,NSSI A_X和NSSI A_Y对共享NSSI的各个切片节点的资源以及对每个虚拟链路的带宽需求和时延可能都不相同,因此,NSSI A的资源需求是将NSSI A_X和NSSI A_Y的资源需求的合并。下面通过图7B所示的实施例来介绍本申请实施例中针对共享NSSI的资源合并过程,请参阅图7B,该过程包括:
701、管理服务器确定共享NSSI。
如图7A所示,当存在两个或者两个以上的网络切片同时共享一个NSSI时,则管理服务器可以确定该NSSI。
702、管理服务器从共享NSSI选择切片节点。
例如,结合图7A所示,管理服务器可以选择NSSI A中的切片节点VNF1,然后对该VNF1进行资源合并。
703、管理服务器统计不同网络切片对该共享NSSI所包括的切片节点的资源需求,得到该切片节点的资源总需求。
例如,如图7A所示,针对VNF1,管理服务器确定NSI X和NSI Y对该VNF1的资源需求,那么将该NSI X对该VNF1的资源需求加上NSI Y对该VNF1的资源需求,得到该VNF1的资源总需求。
704、管理服务器判断该共享NSSI所包括的每个切片节点是否完成资源合并,若是,则执行步骤705;若否,则返回执行步骤702。
如图7A所示,如果管理服务器对该VNF1至VNF4分别进行资源合并完成后,则执行步骤705,如果管理服务器未对这四个切片节点一一进行资源合并,则返回步骤702继续选择相应的切片节点,并对该切片节点进行资源合并。
705、管理服务器从共享NSSI选择虚拟链路。
如图7A所示,NSS A包括四条虚拟链路,分别为VNF1至VNF2,VNF2至VNF3以及VNF3至VNF4。管理服务器可以从中选择一条虚拟链路,然后对虚拟链路进行资源合并。
706、管理服务器统计不同网络切片对该共享NSSI所包括的该虚拟链路的带宽需求,得到该虚拟链路的带宽总需求。
如图7A所示,管理服务器确定NSI X对VNF1至VNF2之间的虚拟链路的第一带宽需求和NSI Y对VNF1至VNF2之间的虚拟链路的第二带宽需求,然后将第一带宽需求加上第二带宽需求,得到该虚拟链路的带宽总需求。
707、管理服务器确定不同网络切片对该共享NSSI的该虚拟链路的时延要求。
如图7A所示,管理服务器确定NSI X对VNF1至VNF2之间的虚拟链路的时延要求为10ms,和确定NSI Y对VNF1至VNF2之间的虚拟链路的时延要求为20ms。
708、管理服务器将不同网络切片中对虚拟链路的时延要求最小的时延值作为该虚拟链路的时延需求。
例如,步骤707中可知,管理服务器可以将该虚拟链路的时延需求设置为10ms。
709、管理服务器判断该共享NSSI所包括的每条虚拟链路是否完成资源合并,若是,则执行步骤710;若否,则返回执行步骤705。
如图7A所示,如果管理服务器对VNF1至VNF2,VNF2至VNF3以及VNF3至VNF4这四条虚拟链路分别进行资源合并完成后,则执行步骤710,如果管理服务器这四条虚拟链路一一进行资源合并,则返回步骤705继续选择相应的虚拟链路,并对该虚拟链路进行资源合并。
710、管理服务器对该共享NSSI进行映射。
具体管理服务器对共享NSSI的映射过程与前述图2所示的映射过程类似,详细请参阅前述图2所示的实施例,这里不再赘述。
本申请实施例中,提供了一种部署共享NSSI的方法,通过把不同网络切片对共享NSSI的资源需求的合并以及虚拟链路的资源需求的合并得到该NSSI的总体资源需求,再通过前述图2所示的方法实现该共享NSSI的部署,在实际应用中,其实用性较大,能够满足不同网络切片对该共享NSSI的需求。
本申请实施例中,NSSI的资源请求还可以携带对DC部署的要求,例如,对DC所属地域的要求。如图8A所示,网络切片子网NSS要求部署一部分NSSI在上海,另一部分NSSI部署在北京,如将NSS A的VNF1至VNF4部署在DC1中,将NSS B的VNF5至VNF7部署在DC2中。而由于该NSSI所需求的DC是跨地域的,对于跨地域的两个DC之间进行通信的切片节点之间的通信时延要求比较高,这样DC之间的时延的保障就异常重要。下面通过图8B所示的实施例来介绍管理服务器针对该问题进行跨地域的两个DC之间进行通信的切片节点进行映射的过程,请参阅图8B,该过程包括:
801、管理服务器根据资源请求将该NSSI划分为第一NSSI和第二NSSI。
其中,资源请求携带跨DC部署的请求,管理服务器根据该跨DC部署的请求确定将该NSSI划分为第一NSSI和第二NSSI。例如,如图8A所示,跨DC部署的请求包括将VNF1至VNF4部署在上海的DC,而VNF5至VNF7部署在深圳的DC,那么管理服务器将该NSS划分为NSS A和NSS B。
802、管理服务器确定该第一NSSI与该第二NSSI中跨DC的切片节点分别为第三切片节点和第四切片节点以及第三切片节点至第四切片节点之间的虚拟链路。
如图8A可知,NSS A中的VNF4与NSS B中的VNF5进行通信,即VNF4和VNF5为跨DC的切片节点,那么管理服务器也可以确定VNF4至VNF5的虚拟链路。
803、管理服务器确定该第一DC中的第五服务器的可用资源数量满足该第三切片节点的资源需求和第二DC中的第六服务器的可用资源数量满足该第四切片节点的资源需求。
管理服务器可以从第一DC组合中选择满足地域要求的第一DC中的第五服务器,然后 管理服务器判断该第五服务器的可用资源数量是否满足该第三切片节点的资源需求,若是,则可以将该第三切片节点映射至该第五服务器。对于第四切片节点也同理,可以将该第四切片节点映射至第六服务器。
804、管理服务器确定第三切片节点至第四切片节点之间的虚拟链路对应的所有最短物理链路。
805、管理服务器从该所有最短物理链路选择一条目标物理链路。
806、管理服务器判断该目标物理链路的可用网络带宽是否大于该虚拟链路的带宽需求,若是,则执行步骤807,;若否,则返回执行步骤805。
807、管理服务器判断该目标物理链路的时延是否低于该虚拟链路的时延需求,若是,则执行步骤808;若否,则返回执行步骤805。
808、管理服务器将该虚拟链路映射至该目标物理链路,并输出该虚拟链路的映射结果和将该第三切片节点和第四切片节点标记为已映射的切片节点。
步骤804至步骤808与前述图6所示的步骤602至步骤606类似,详细请参阅前述图6的相关说明,这里不再赘述。
809、管理服务器对该NSSI剩余的切片节点和切片节点之间的虚拟链路进行映射。
管理服务器将第三切片节点和第四切片节点进行映射完成后,对该NSSI的其他切片节点和切片节点之间的虚拟链路也进行映射。例如,图8A所示,管理服务器对VNF1至VNF3以及VNF6和VNF7进行映射,具体的映射过程与前述图2所示的过程类似,并且针对已映射的切片节点则无需再次进行映射额,详细请参阅前述图2的相关说明,这里不再赘述。
需要说明的是,上述针对NSSI跨DC部署的实施例中,当网络切片区分用户面和控制面,且针对用户面或者控制面的NSSI有跨DC部署的需求时,都适用通过图8B所示的实施例进行跨DC部署,以保证NSSI的时延需求;而当网络切片不区分用户面和控制面,且该NSSI存在跨DC部署的需求时,则直接通过图8B所示的实施例对该NSSI进行跨DC部署。
本申请实施例中,提供了一种保障NSSI跨DC部署时,切片节点所映射的DC的服务器之间的通信时延,在实际应用中,保障了请求跨地域的DC的NSSI的时延需求,提高了本申请方案的实用性。
下面对本申请实施例中提供的一种资源分配装置进行描述,请参阅图9,本申请实施例中资源分配装置的一个实施例,该资源分配装置900用于执行图2、图3、图4、图5、图6、图7B和图8B所示实施例中接收端设备执行的步骤,可以参考上述实施例中的相关描述。
该资源分配装置900包括收发模块901和处理模块902。
收发模块901,用于获NSSI的资源请求,该资源请求携带待创建的该NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及该第一切片节点至该第二切片节点之间的虚拟链路的第三资源需求;
处理模块902,用于确定数据中心DC集合,该DC集合包括至少一个可用于为该NSSI提供资源的DC;
该处理模块902,还用于从该DC集合中确定DC组合集合,该DC组合集合包括至少一个可用于为该NSSI提供资源的DC组合;根据该第一资源需求将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器和根据该第二资源需求将该第二切片节点映射至该第一DC组合中的第二服务器;根据该第三资源需求将该第一切片节点至该第二切片节点之间的虚拟链路映射至该第一服务器至该第二服务器之间的第一物理链路;当该第一切片节点成功映射至该第一服务器、该第二切片节点成功映射至该第二服务器和该虚拟链路成功映射至该第一物理链路时,确定该第一DC组合为目标DC组合,并输出该NSSI所包括的切片节点的映射结果以及该虚拟链路的映射结果。
一种可能的实现方式中,该DC集合中的所有DC按照DC的可用资源评估值由大到小进行排序,或者,该DC集合中的所有DC按照DC的可用资源评估值由小到大进行排序。
另一种可能的实现方式中,该处理模块902还用于:对该DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值。
另一种可能的实现方式中,该DC集合包括第一DC,该第一DC包括第三服务器和第四服务器;该处理模块902具体用于:当该第三服务器所提供的可用网络带宽和该第四服务器所提供的可用网络带宽均大于第一预设阈值,确定该第三服务器的第一可用资源数量和第四服务器的第四可用资源数量,并将该第一可用资源数量加上该第二可用资源数量,得到该第一DC的可用资源评估值。
另一种可能的实现方式中,该DC组合集合中的每个DC组合包括每个DC组合的可用资源评估值。
另一种可能的实现方式中,该DC组合集合中的每个DC组合还包括每个DC组合的DC性能权重和DC偏好值中的至少一个,DC性能权重指示DC组合所包括的服务器的业务处理性能,DC偏好值是根据NSSI在部署上对DC位置需求和每个DC组合计算得到的。
另一种可能的实现方式中,第一DC组合为当前该DC组合集合所包括的DC组合中可用资源评估值、DC性能权重和DC偏好值都为最大的DC组合。
另一种可能的实现方式中,该处理模块902还用于:
确定第二DC组合,该第二DC组合包括第二DC和第三DC,该第二DC组合包括第五服务器和第六服务器;
当第五服务器所提供的可用网络带宽和第六服务器所提供的可用网络带宽均大于第二预设阈值,确定第五服务器的第三可用资源数量和第六服务器的第四可用资源数量;
确定第二DC至第三DC之间的第二物理链路的时延小于或者等于第三预设阈值;
判断该第三可用资源数量加上第四可用资源数量是否大于等于该NSSI所包括的切片节点的总资源需求数量;
若是,则确定该第二DC组合的可用资源评估值为该第三可用资源数量加上第四可用资源数量。
另一种可能的实现方式中,该处理模块902具体用于:
从DC组合集合中确定第一DC组合,该第一DC组合包括第一服务器和第二服务器;
判断第一服务器的可用资源数量是否大于第一切片节点的资源需求量和判断该第二服 务器的可用资源数量是否大于第二切片节点的资源需求量;
若是,则将第一切片节点映射至第一服务器,和将第二切片节点映射至第二服务器。
另一种可能的实现方式中,该处理模块902具体用于:
判断第一服务器所在的DC至该第二服务器所在的DC之间的第一物理链路的可用网络带宽是否大于第一切片节点至第二切片节点之间的虚拟链路的带宽需求;
若是,则判断该第一物理链路之间的时延是否地域该虚拟链路的时延需求;
若是,则将第一切片节点至第二切片节点之间的虚拟链路映射至第一物理链路。
另一种可能的实现方式中,该处理模块902还用于:
确定第一网络切片和第二网络切片共享该NSSI;
确定该第一切片节点的第一资源需求和第二切片节点的第二资源需求,该第一资源需求包括该第一网络切片对该第一切片节点的资源需求和第二网络切片对该第一切片节点的资源需求,该第二资源需求包括第一网络切片对该第二切片节点的资源需求和第二网络切片对第二切片节点的资源需求;
确定第一切片节点至第二切片节点之间的虚拟链路的第三资源需求,该第三资源需求包括第一网络切片对该虚拟链路的资源需求和第二网络切片对该虚拟链路的资源需求。
另一种可能的实现方式中,该处理模块902具体用于:
确定该第一网络切片对该虚拟链路的第一带宽需求和第二网络切片对该虚拟链路的第二带宽需求;
将第一带宽需求加上第二带宽需求作为该虚拟链路的带宽总需求;并确定该第一网络切片对虚拟链路的第一时延需求和第二网络切片对该虚拟链路的第二时延需求;
如果第一时延需求小于等于该第二时延需求,则将该第一时延需求作为该虚拟链路的时延总需求;
如果第一时延需求大于第二时延需求,则将第二时延需求作为该虚拟链路的时延总需求。
另一种可能的实现方式中,该资源请求携带跨DC部署的请求;该第一DC组合包括第四DC和第五DC,且该第四DC和第五DC为部署在不同地域的两个DC;该第四DC包括第七服务器,第五DC包括第八服务器;该处理模块902还用于:
根据该跨DC部署的请求将NSSI划分为第一NSSI和第二NSSI;
确定该第一NSSI与第二NSSI中跨DC的切片节点分别为第三切片节点和第四切片节点以及第三切片节点至第四切片节点之间的虚拟链路;
当第七服务器的可用资源数量满足该第三切片节点的资源需求且第八服务器的可用资源数量满足该第四切片节点的资源需求时,判断该第七服务器所在的DC至第八服务器所在的DC之间的第三物理链路的可用网络带宽是否大于第三切片节点至第四切片节点之间的虚拟链路的带宽需求;
如果是,则判断第三物理链路之间的时延是否低于该虚拟链路的时延需求;
如果是,则将虚拟链路映射至该第三物理链路,并将该第三切片节点和第四切片节点标记为已映射成功的切片节点。
本申请实施例中,收发模块901获取NSSI的资源请求,该资源请求携带待创建的NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及第一切片节点至该第二切片节点之间的虚拟链路的第三资源需求;然后,处理模块902确定DC集合,并从DC集合中确定DC组合集合;当根据该第一资源需求成功将该第一切片节点映射至该DC组合集合中的第一DC组合中的第一服务器,根据该第二资源需求成功将第二切片节点映射至该第一DC组合中的第二服务器,且根据该第三资源需求成功将该第一切片节点至第二切片节点之间的虚拟链路映射至该第一服务器至第二服务器之间的第一物理链路时,处理模块902可以确定该第一DC组合为目标DC组合,并输出NSSI的切片节点的映射结果和虚拟链路的映射结果。因此,通过本申请的技术方案,在对NSSI的分配过程中,根据切片节点的资源需求和虚拟链路的资源需求选择对应的DC为该网络切片提供资源,这样可以根据实际用户的资源需求为NSSI分配对应的DC,以满足用户的需求。
在另一种可能的设计中,本申请实施例还提供另一种资源分配装置,请参阅图10,该资源分配装置1000包括处理器1001、收发器1002和存储器1003。该处理器1001与该收发器1002以及存储器1003通过线路连接,该存储器1003可以包括只读存储器和/或随机存储器,并向处理器1002提供操作指令和数据。本实施例中,收发器1003可以用于执行前述图9中收发模块901执行的操作,和/或收发器1003还用于执行本申请实施例中资源分配装置的其他处理步骤。处理器1001可以用于执行前述图9中处理模块902的操作,和/或处理器1001还用于执行本申请实施例中资源分配装置的其他处理步骤。
在另一种可能的设计中,当该资源分配装置为芯片时,该芯片至少包括一个处理器、收发器和存储器,存储器中存储有指令,该收发器与该至少一个处理器通过线路互联;该处理器用于执行图9中处理模块902的操作,和/或处理器还用于执行本申请实施例中资源分配装置的其他处理步骤;该收发器用于执行图9中收发模块901的操作,和/或收发器还用于执行本申请实施例中资源分配装置的其他处理步骤。
作为本实施例的另一种形式,提供一种计算机可读存储介质,其上存储有指令,该指令被执行时执行上述方法实施例中管理服务器的方法。
作为本实施例的另一种形式,提供一种包含指令的计算机程序产品,该指令被执行时执行上述方法实施例中管理服务器的方法。
应理解,本申请实施例中提及的处理器可以是中央处理单元(Central Processing Unit,CPU),还可以是其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现成可编程门阵列(Field Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
还应理解,本申请实施例中提及的存储器可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(Read-Only Memory,ROM)、可编程只读存储器(Programmable ROM,PROM)、可擦除可编程只读存储器(Erasable PROM,EPROM)、电可擦除可编程只读存储器(Electrically  EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(Static RAM,SRAM)、动态随机存取存储器(Dynamic RAM,DRAM)、同步动态随机存取存储器(Synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DR RAM)。
需要说明的是,当处理器为通用处理器、DSP、ASIC、FPGA或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件时,存储器(存储模块)集成在处理器中。
应注意,本文描述的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (28)

  1. 一种资源分配方法,其特征在于,所述方法包括:
    获取网络切片子网实例NSSI的资源请求,所述资源请求携带待创建的所述NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及所述第一切片节点至所述第二切片节点之间的虚拟链路的第三资源需求;
    确定数据中心DC集合,所述DC集合包括至少一个可用于为所述NSSI提供资源的DC;
    从所述DC集合中确定DC组合集合,所述DC组合集合包括至少一个可用于为所述NSSI提供资源的DC组合;
    根据所述第一资源需求将所述第一切片节点映射至所述DC组合集合中的第一DC组合中的第一服务器和根据所述第二资源需求将所述第二切片节点映射至所述第一DC组合中的第二服务器;
    根据所述第三资源需求将所述第一切片节点至所述第二切片节点之间的虚拟链路映射至所述第一服务器至所述第二服务器之间的第一物理链路;
    当所述第一切片节点成功映射至所述第一服务器、所述第二切片节点成功映射至所述第二服务器和所述虚拟链路成功映射至所述第一物理链路时,确定所述第一DC组合为目标DC组合,并输出所述NSSI所包括的切片节点的映射结果以及所述虚拟链路的映射结果。
  2. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    所述DC集合中的所有DC按照DC的可用资源评估值由大到小进行排序,或者所述DC集合中的所有DC按照DC的可用资源评估值由小到大进行排序。
  3. 根据权利要求2所述的方法,其特征在于,所述确定DC集合之前,所述方法还包括:
    对所述DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值。
  4. 根据权利要求3所述的方法,其特征在于,所述DC集合包括第一DC,所述第一DC包括第三服务器和第四服务器;所述对所述DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值包括:
    当所述第三服务器所提供的可用网络带宽和所述第四服务器所提供的可用网络带宽均大于第一预设阈值,确定所述第三服务器的第一可用资源数量和所述第四服务器的第二可用资源数量;
    将所述第一可用资源数量加上所述第二可用资源数量,得到所述第一DC的可用资源评估值。
  5. 根据权利要求1至4中的任一项所述的方法,其特征在于,所述DC组合集合中的每个DC组合包括每个DC组合的可用资源评估值。
  6. 根据权利要求5所述的方法,其特征在于,所述DC组合集合中的每个DC组合还包括所述每个DC组合的DC性能权重和DC偏好值中的至少一个,所述每个DC组合的DC性能权重指示所述每个DC组合所包括的服务器的业务处理性能,所述DC偏好值是根据所述NSSI在部署上对DC的位置需求和所述每个DC组合计算得到的。
  7. 根据权利要求5或6所述的方法,其特征在于,所述第一DC组合为当前所述DC组合集合所包括的DC组合中可用资源评估值、DC性能权重和DC偏好值都为最大的DC组合。
  8. 根据权利要求5至7中的任一项所述的方法,其特征在于,所述确定DC组合集合之前,所述方法还包括:
    确定第二DC组合,所述第二DC组合包括第二DC和第三DC,所述第二DC组合包括第五服务器和第六服务器;
    当所述第五服务器所提供的可用网络带宽和所述第六服务器所提供的可用网络带宽均大于第二预设阈值,确定第五服务器的第三可用资源数量和所述第六服务器的第四可用资源数量;
    确定所述第二DC至所述第三DC之间的第二物理链路的时延小于或者等于第三预设阈值;
    判断所述第三可用资源数量加上所述第四可用资源数量是否大于等于所述NSSI所包括的切片节点的总资源需求数量;
    若是,则确定所述第二DC组合的可用资源评估值为所述第三可用资源数量加上所述第四可用资源数量。
  9. 根据权利要求1至8中的任一项所述的方法,其特征在于,所述根据所述第一资源需求将所述第一切片节点映射至所述DC组合集合中的第一DC组合中的第一服务器和根据所述第二资源需求将所述第二切片节点映射至所述第一DC组合中的第二服务器包括:
    从所述DC组合集合中确定第一DC组合,所述第一DC组合包括所述第一服务器和所述第二服务器;
    判断所述第一服务器的可用资源数量是否大于所述第一切片节点的资源需求量和判断所述第二服务器的可用资源数量是否大于所述第二切片节点的资源需求量;
    若是,则将所述第一切片节点映射至所述第一服务器,和将所述第二切片节点映射至所述第二服务器。
  10. 根据权利要求1至9中的任一项所述的方法,其特征在于,所述根据所述第三资源需求将所述第一切片节点至所述第二切片节点之间的虚拟链路映射至所述第一服务器至所述第二服务器之间的第一物理链路包括:
    判断所述第一服务器所在的DC至所述第二服务器所在的DC之间的所述第一物理链路的可用网络带宽是否大于所述第一切片节点至所述第二切片节点之间的虚拟链路的带宽需求;
    若是,则判断所述第一物理链路之间的时延是否低于所述虚拟链路的时延需求;
    若是,则将所述第一切片节点至所述第二切片节点之间的虚拟链路映射至所述第一物理链路。
  11. 根据权利要求1至10中的任一项所述的方法,其特征在于,所述获取NSSI请求之前,所述方法还包括:
    确定第一网络切片和第二网络切片共享所述NSSI;
    确定所述第一切片节点的第一资源需求和所述第二切片节点的第二资源需求,所述 第一资源需求包括所述第一网络切片对所述第一切片节点的资源需求和所述第二网络切片对所述第一切片节点的资源需求,所述第二资源需求包括所述第一网络切片对所述第二切片节点的资源需求和所述第二网络切片对所述第二切片节点的资源需求;
    确定所述第一切片节点至所述第二切片节点之间的虚拟链路的第三资源需求,所述第三资源需求包括所述第一网络切片对所述虚拟链路的资源需求和所述第二网络切片对所述虚拟链路的资源需求。
  12. 根据权利要求11所述的方法,其特征在于,所述确定所述第一切片节点至所述第二切片节点之间的虚拟链路的第三资源需求包括:
    确定所述第一网络切片对所述虚拟链路的第一带宽需求和所述第二网络切片对所述虚拟链路的第二带宽需求;
    将所述第一带宽需求加上所述第二带宽需求作为所述虚拟链路的带宽总需求;
    确定所述第一网络切片对所述虚拟链路的第一时延需求和所述第二网络切片对所述虚拟链路的第二时延需求;
    若所述第一时延需求小于等于所述第二时延需求,则将所述第一时延需求作为所述虚拟链路的时延总需求;
    若所述第一时延需求大于所述第二时延需求,则将所述第二时延需求作为所述虚拟链路的时延总需求。
  13. 根据权利要求1至10中的任一项所述的方法,其特征在于,所述资源请求携带跨DC部署的请求;所述第一DC组合包括第四DC和第五DC,且所述第四DC和所述第五DC为部署在不同地域的两个DC;所述第四DC包括第七服务器,所述第五DC包括第八服务器;所述根据所述第一资源需求将所述第一切片节点映射至所述DC组合集合中的第一DC组合中的第一服务器和根据所述第二资源需求将所述第二切片节点映射至所述第一DC组合中的第二服务器之前,所述方法还包括:
    根据所述跨DC部署的请求将所述NSSI划分为第一NSSI和第二NSSI;
    确定所述第一NSSI与所述第二NSSI中跨DC的切片节点分别为第三切片节点和第四切片节点以及所述第三切片节点至所述第四切片节点之间的虚拟链路;
    当所述第七服务器的可用资源数量满足所述第三切片节点的资源需求且所述第八服务器的可用资源数量满足所述第四切片节点的资源需求时,判断所述第七服务器所在的DC至所述第八服务器所在的DC之间的第三物理链路的可用网络带宽是否大于所述第三切片节点至所述第四切片节点之间的虚拟链路的带宽需求;
    若是,则判断所述第三物理链路之间的时延是否低于所述虚拟链路的时延需求;
    若是,则将所述虚拟链路映射至所述第三物理链路,并将所述第三切片节点和第四切片节点标记为已映射成功的切片节点。
  14. 一种资源分配装置,其特征在于,所述资源分配装置包括:
    收发模块,用于获取网络切片子网实例NSSI的资源请求,所述资源请求携带待创建的所述NSSI所包括的第一切片节点的第一资源需求、第二切片节点的第二资源需求以及所述第一切片节点至所述第二切片节点之间的虚拟链路的第三资源需求;
    处理模块,用于确定数据中心DC集合,所述DC集合包括至少一个可用于为所述NSSI提供资源的DC;
    所述处理模块,还用于从所述DC集合中确定DC组合集合,所述DC组合集合包括至少一个可用于为所述NSSI提供资源的DC组合;根据所述第一资源需求将所述第一切片节点映射至所述DC组合集合中的第一DC组合中的第一服务器和根据所述第二资源需求将所述第二切片节点映射至所述第一DC组合中的第二服务器;根据所述第三资源需求将所述第一切片节点至所述第二切片节点之间的虚拟链路映射至所述第一服务器至所述第二服务器之间的第一物理链路;当所述第一切片节点成功映射至所述第一服务器、所述第二切片节点成功映射至所述第二服务器和所述虚拟链路成功映射至所述第一物理链路时,确定所述第一DC组合为目标DC组合,并输出所述NSSI所包括的切片节点的映射结果以及所述虚拟链路的映射结果。
  15. 根据权利要求14所述的资源分配装置,其特征在于,所述DC集合中的所有DC按照DC的可用资源评估值由大到小进行排序,或者所述DC集合中的所有DC按照DC的可用资源评估值由小到大进行排序。
  16. 根据权利要求15所述的资源分配装置,其特征在于,所述处理模块还用于:
    对所述DC集合中的每个DC所包括的服务器的可用资源数量进行统计,得到每个DC的可用资源评估值。
  17. 根据权利要求16所述的资源分配装置,其特征在于,所述DC集合包括第一DC,所述第一DC包括第三服务器和第四服务;所述处理模块具体用于:
    当所述第三服务器所提供的可用网络带宽和所述第四服务器所提供的可用网络带宽均大于第一预设阈值,确定所述第三服务器的第一可用资源数量和所述第四服务器的第二可用资源数量;
    将所述第一可用资源数量加上所述第二可用资源数量,得到所述第一DC的可用资源评估值。
  18. 根据权利要求14至17中的任一项所述的资源分配装置,其特征在于,所述DC组合集合中的每个DC组合包括每个DC组合的可用资源评估值。
  19. 根据权利要求18所述的资源分配装置,其特征在于,所述DC组合集合中的每个DC组合还包括所述每个DC组合的DC性能权重和DC偏好值中的至少一个,所述每个DC组合的DC性能权重指示所述每个DC组合所包括的服务器的业务处理性能,所述DC偏好值是根据所述NSSI在部署上对DC的位置需求和所述每个DC组合计算得到的。
  20. 根据权利要求18或19所述的资源分配装置,其特征在于,所述第一DC组合为当前所述DC组合集合中各项值最大的DC组合。
  21. 根据权利要求18至20中的任一项所述的资源分配装置,其特征在于,所述处理模块还用于:
    确定第二DC组合,所述第二DC组合包括第二DC和第三DC,所述第二DC组合包括第五服务器和第六服务器;
    当所述第五服务器所提供的可用网络带宽和所述第六服务器所提供的可用网络带宽均 大于第二预设阈值,确定第五服务器的第三可用资源数量和所述第六服务器的第四可用资源数量;
    确定所述第二DC至所述第三DC之间的第二物理链路的时延小于或者等于第三预设阈值;
    判断所述第三可用资源数量加上所述第四可用资源数量是否大于等于所述NSSI所包括的切片节点的总资源需求数量;
    若是,则确定所述第二DC组合的可用资源评估值为所述第三可用资源数量加上所述第四可用资源数量。
  22. 根据权利要求14至21中的任一项所述的资源分配装置,其特征在于,所述处理模块具体用于:
    从所述DC组合集合中确定第一DC组合,所述第一DC组合包括所述第一服务器和所述第二服务器;
    判断所述第一服务器的可用资源数量是否大于所述第一切片节点的资源需求量和判断所述第二服务器的可用资源数量是否大于所述第二切片节点的资源需求量;
    若是,则将所述第一切片节点映射至所述第一服务器,和将所述第二切片节点映射至所述第二服务器。
  23. 根据权利要求14至22中的任一项所述的资源分配装置,其特征在于,所述处理模块具体用于:
    判断所述第一服务器所在的DC至所述第二服务器所在的DC之间的所述第一物理链路的可用网络带宽是否大于所述第一切片节点至所述第二切片节点之间的虚拟链路的带宽需求;
    若是,则判断所述第一物理链路之间的时延是否低于所述虚拟链路的时延需求;
    若是,则将所述第一切片节点至所述第二切片节点之间的虚拟链路映射至所述第一物理链路。
  24. 根据权利要求14至23中的任一项所述的资源分配装置,其特征在于,所述处理模块还用于:
    确定第一网络切片和第二网络切片共享所述NSSI;
    确定所述第一切片节点的第一资源需求和所述第二切片节点的第二资源需求,所述第一资源需求包括所述第一网络切片对所述第一切片节点的资源需求和所述第二网络切片对所述第一切片节点的资源需求,所述第二资源需求包括所述第一网络切片对所述第二切片节点的资源需求和所述第二网络切片对所述第二切片节点的资源需求;
    确定所述第一切片节点至所述第二切片节点之间的虚拟链路的第三资源需求,所述第三资源需求包括所述第一网络切片对所述虚拟链路的资源需求和所述第二网络切片对所述虚拟链路的资源需求。
  25. 根据权利要求24所述的资源分配装置,其特征在于,所述处理模块具体用于:
    确定所述第一网络切片对所述虚拟链路的第一带宽需求和所述第二网络切片对所述虚拟链路的第二带宽需求;
    将所述第一带宽需求加上所述第二带宽需求作为所述虚拟链路的带宽总需求;
    确定所述第一网络切片对所述虚拟链路的第一时延需求和所述第二网络切片对所述虚拟链路的第二时延需求;
    若所述第一时延需求小于等于所述第二时延需求,则将所述第一时延需求作为所述虚拟链路的时延总需求;
    若所述第一时延需求大于所述第二时延需求,则将所述第二时延需求作为所述虚拟链路的时延总需求。
  26. 根据权利要求14至23中的任一项所述的资源分配装置,其特征在于,所述资源请求携带跨DC部署的请求;所述第一DC组合包括第四DC和第五DC,且所述第四DC和所述第五DC为部署在不同地域的两个DC;所述第四DC包括第七服务器,所述第五DC包括第八服务器;所述处理模块还用于:
    根据所述跨DC部署的请求将所述NSSI划分为第一NSSI和第二NSSI;
    确定所述第一NSSI与所述第二NSSI中跨DC的切片节点分别为第三切片节点和第四切片节点以及所述第三切片节点至所述第四切片节点之间的虚拟链路;
    当所述第七服务器的可用资源数量满足所述第三切片节点的资源需求且所述第八服务器的可用资源数量满足所述第四切片节点的资源需求时,判断所述第七服务器所在的DC至所述第八服务器所在的DC之间的第三物理链路的可用网络带宽是否大于所述第三切片节点至所述第四切片节点之间的虚拟链路的带宽需求;
    若是,则判断所述第三物理链路之间的时延是否低于所述虚拟链路的时延需求;
    若是,则将所述虚拟链路映射至所述第三物理链路,并将所述第三切片节点和第四切片节点标记为已映射成功的切片节点。
  27. 一种包含指令的计算机程序产品,其特征在于,当其在计算机上运行时,使得所述计算机执行如权利要求1至13中任一项所述的方法。
  28. 一种计算机可读存储介质,其特征在于,包括指令,当所述指令在计算机上运行时,使得计算机执行如权利要求1至13中任一项所述的方法。
PCT/CN2020/083211 2019-06-21 2020-04-03 资源分配方法以及装置 WO2020253328A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910551895.0A CN112118579B (zh) 2019-06-21 2019-06-21 资源分配方法以及装置
CN201910551895.0 2019-06-21

Publications (1)

Publication Number Publication Date
WO2020253328A1 true WO2020253328A1 (zh) 2020-12-24

Family

ID=73795688

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/083211 WO2020253328A1 (zh) 2019-06-21 2020-04-03 资源分配方法以及装置

Country Status (2)

Country Link
CN (1) CN112118579B (zh)
WO (1) WO2020253328A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108132827A (zh) * 2016-11-30 2018-06-08 华为技术有限公司 一种网络切片资源映射方法、相关设备及系统
WO2018134911A1 (en) * 2017-01-18 2018-07-26 Nec Corporation Resource allocation system, method, and program
CN108400998A (zh) * 2017-02-07 2018-08-14 华为技术有限公司 一种部署vnf的方法和系统
CN109600246A (zh) * 2017-09-30 2019-04-09 华为技术有限公司 网络切片管理方法及其装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107659426B (zh) * 2016-07-26 2021-02-12 华为技术有限公司 分配物理资源的方法和网络侧设备
CN108023761B (zh) * 2016-11-04 2020-04-21 华为技术有限公司 分配资源的方法和设备
US20180317134A1 (en) * 2017-04-28 2018-11-01 Huawei Technologies Co., Ltd. Nssmf nsmf interaction connecting virtual 5g networks and subnets
CN109587024B (zh) * 2017-09-29 2020-12-22 华为技术有限公司 一种资源处理的方法以及相关装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108132827A (zh) * 2016-11-30 2018-06-08 华为技术有限公司 一种网络切片资源映射方法、相关设备及系统
WO2018134911A1 (en) * 2017-01-18 2018-07-26 Nec Corporation Resource allocation system, method, and program
CN108400998A (zh) * 2017-02-07 2018-08-14 华为技术有限公司 一种部署vnf的方法和系统
CN109600246A (zh) * 2017-09-30 2019-04-09 华为技术有限公司 网络切片管理方法及其装置

Also Published As

Publication number Publication date
CN112118579A (zh) 2020-12-22
CN112118579B (zh) 2024-03-26

Similar Documents

Publication Publication Date Title
WO2020258920A1 (zh) 一种网络切片资源管理方法及设备
US20190123963A1 (en) Method and apparatus for managing resources of network slice
EP3028406B1 (en) Profile-based sla guarantees under workload migration in a distributed cloud
US11831509B2 (en) Network service management method, device, and system
US10764132B2 (en) Scale-out association method and apparatus, and system
US10924966B2 (en) Management method, management unit, and system
Baumgartner et al. Combined virtual mobile core network function placement and topology optimization with latency bounds
WO2018188619A1 (en) Networking service level agreements for computer datacenters
Alkmim et al. Mapping virtual networks onto substrate networks
US10666570B2 (en) Computing infrastructure resource-workload management methods and apparatuses
CN108462592A (zh) 基于sla的资源分配方法和nfvo
CN108132827B (zh) 一种网络切片资源映射方法、相关设备及系统
WO2019179301A1 (zh) 一种管理虚拟资源的方法及装置
WO2016183799A1 (zh) 一种硬件加速方法以及相关设备
CN112583615B (zh) Vnf实例化方法、nfvo、vim、vnfm及系统
Gonçalves et al. Dynamic network slicing in fog computing for mobile users in mobfogsim
Javadpour et al. Mapping and embedding infrastructure resource management in software defined networks
Casetti et al. Arbitration among vertical services
WO2020253328A1 (zh) 资源分配方法以及装置
WO2018170732A1 (zh) 一种边缘云架构下服务部署的方法和装置
WO2017070963A1 (zh) 一种虚拟资源的部署方法、装置及系统
EP3096227A1 (en) Resource allocation method in distributed clouds
Caixinha et al. ViTeNA: an SDN-based virtual network embedding algorithm for multi-tenant data centers
Lim et al. FARCREST: Euclidean Steiner tree-based cloud service latency prediction system
Esteves et al. Evaluating allocation paradigms for multi-objective adaptive provisioning in virtualized networks

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20825464

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20825464

Country of ref document: EP

Kind code of ref document: A1