Attribute information subscription method and system, storage medium, and electronic device
Obtaining and subscribing to the configuration information of computing network services through middleware devices, solving the network burden problem caused by perception of computing power service providers in traditional technology, achieving efficient computing power information perception and routing decisions, and meeting high computing power sensitivity business needs.
Patent Information
- Application Number
- PCT/CN2023/143617
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-09
- Filing Date
- 2023-12-29
- Publication Date
- 2024-11-14
AI Technical Summary
The existing technology relies on traditional underlying network technology to realize the computing power information perception of computing power service providers, which in turn creates additional burden on traditional networks and cannot meet the perception needs of highly computing power-sensitive services.
The middleware device obtains the configuration information of the computing network service collection, determines the target computing power attribute set to be subscribed, and subscribes the target computing power attribute information to the computing power service provider to avoid using traditional underlying network technology for perception.
It reduces the impact and burden on traditional networks, meets the perception needs of highly computing power-sensitive services, and realizes efficient computing power information perception and routing decisions.
Smart Images

Figure CN2023143617_14112024_PF_FP_ABST
Abstract
Description
Attribute information subscription method and system, storage medium and electronic device
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This disclosure is based on and claims the priority of Chinese patent application No. 202310519088.7 filed on May 9, 2023, and all the disclosed contents are incorporated into this disclosure by reference. Technical Field
[0003] The embodiments of the present disclosure relate to the field of communications, and in particular, to a method and system for subscribing to attribute information, a storage medium, and an electronic device. Background Art
[0004] 5G has driven edge computing into a hot topic and accelerated the deployment of mobile edge computing (MEC). For emerging services like the future Industrial Internet and artificial intelligence, network-side edge computing, and even on-site edge computing, will provide users with flexible, local access and an exceptional user experience. Computing power is shifting from centralized to decentralized, with distributed resources, distributed computing power, and distributed services becoming the norm. Furthermore, with the development and prevalence of container technology and microservices architectures, applications are being decomposed into functions and services, requiring networks to shift from host-oriented addressing to service- and computing-oriented addressing. Consequently, the computing power network, a new technical form and operational model, has emerged. This new computing and network-integrated infrastructure provides common internet services to society at large, accelerating business innovation, reducing deployment costs, improving resource utilization, and promoting the development of the digital economy.
[0005] In the computing network technology, effectively perceiving and learning the dynamic status information of computing power and services is the premise and foundation for realizing computing network services from the perspective of computing network integration. However, the current computing power and service perception faces the following difficulties:
[0006] (1) The status and attribute information of computing power and services belongs to different operation and management domains than the network information in traditional networks. There is both information of the same dimension and information of different dimensions in the two. It is difficult for the network side to recognize and interpret the directly exposed computing power and service status metadata. The multi-dimensional computing power, service and network information cannot directly guide the computing power routing and forwarding process.
[0007] (2) Currently, the protocol extension based on the Interior Gateway Protocol (IGP) or the Border Gateway Protocol (BGP) to achieve the perception of computing power and service-side status information is a method that relies on traditional underlying network technology. It cannot meet the perception needs of high-computing-power-sensitive businesses and will also cause additional burden on traditional networks.
[0008] Regarding the problem in related technologies that relying on traditional underlying network technology to realize the computing power information perception of computing power service providers will cause additional burden on traditional networks, no effective solution has been proposed so far.
[0009] Summary of the Invention
[0010] The embodiments of the present disclosure provide a method and system for subscribing to attribute information, a storage medium, and an electronic device, so as to at least solve the problem in related technologies that relying on traditional underlying network technology to realize the perception of computing power information of computing power service providers will cause additional burden on traditional networks.
[0011] According to an embodiment of the present disclosure, a method for subscribing to attribute information is provided, which is applied to a middleware device, and includes: obtaining configuration information corresponding to a computing network service set, wherein the configuration information includes at least: computing power requirements of each group of computing network services in the computing network service set, each group of computing network services including one computing network service or multiple computing network services; determining a target computing power attribute set to be subscribed based on the configuration information; and subscribing to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider.
[0012] According to another embodiment of the present disclosure, a middleware device is also provided, including: an acquisition module, configured to obtain configuration information corresponding to a computing network service set, wherein the configuration information at least includes: computing power requirements of each group of computing network services in the computing network service set, each group of computing network services including one computing network service or multiple computing network services; a determination module, configured to determine a target computing power attribute set to be subscribed based on the configuration information; and a subscription module, configured to subscribe to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider.
[0013] According to another embodiment of the present disclosure, a subscription system for attribute information is also provided, including: a middleware device, used to obtain configuration information corresponding to a computing network service set, and determine a target computing power attribute set to be subscribed based on the configuration information, wherein the configuration information at least includes: the computing power requirements of each group of computing network services in the computing network service set, each group of computing network services including one computing network service or multiple computing network services; a computing power service provider, used to send attribute information of each computing power attribute in the target computing power attribute set to the middleware device.
[0014] According to another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.
[0015] According to another embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] FIG1 is a hardware structure block diagram of a mobile terminal for a method for subscribing to attribute information according to an embodiment of the present disclosure;
[0017] FIG2 is a flowchart of a method for subscribing to attribute information according to an embodiment of the present disclosure;
[0018] FIG3 is an overall flow chart of computing power perception and information usage based on a middleware device according to an embodiment of the present disclosure;
[0019] FIG4 is a flow chart of a middleware device performing service subscription according to an embodiment of the present disclosure;
[0020] FIG5 is a schematic diagram of a process of computing power perception performed by a middleware device according to an embodiment of the present disclosure;
[0021] FIG6 is an overall flow chart of information processing performed by a middleware device according to an embodiment of the present disclosure;
[0022] FIG7 is a schematic diagram of a computing power routing table according to an embodiment of the present disclosure;
[0023] FIG8 is a flow chart of a service traffic forwarding according to an embodiment of the present disclosure;
[0024] FIG9 is a schematic diagram of computing power routing forwarding and business traffic affinity according to an embodiment of the present disclosure;
[0025] FIG10 is a schematic diagram of computing power and service status perception and information modeling in an SFC scenario according to an embodiment of the present disclosure;
[0026] FIG11 is a schematic diagram of computing power perception and computing power routing calculation in a single service scenario according to an embodiment of the present disclosure;
[0027] FIG12 is a schematic diagram of a metric value conversion method in an SFC scenario according to an embodiment of the present disclosure;
[0028] FIG13 is a schematic diagram of computing power perception and SFP calculation in a multi-service scenario according to an embodiment of the present disclosure;
[0029] FIG14 is a structural block diagram of a middleware device according to an embodiment of the present disclosure;
[0030] FIG15 is a structural block diagram of a property information subscription system according to an embodiment of the present disclosure. DETAILED DESCRIPTION
[0031] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings and in conjunction with embodiments.
[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0033] The method embodiments provided in the embodiments of the present disclosure can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of a mobile terminal of a method for subscribing to attribute information in an embodiment of the present disclosure. As shown in Figure 1, the mobile terminal may include one or more (only one is shown in Figure 1) processors 102 (the processor 102 may include but is not limited to a microprocessor (Central Processing Unit, MCU) or a programmable logic device (Field Programmable Gate Array, FPGA) and a memory 104 for storing data, wherein the above-mentioned mobile terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that the structure shown in Figure 1 is only for illustration and does not limit the structure of the above-mentioned mobile terminal. For example, the mobile terminal may also include more or fewer components than those shown in Figure 1, or have a configuration different from that shown in Figure 1.
[0034] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the attribute information subscription method in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0035] The transmission device 106 is used to receive or send data via a network. A specific example of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0036] In this embodiment, a method for subscribing to attribute information running on a middleware device is provided. FIG2 is a flow chart of a method for subscribing to attribute information according to an embodiment of the present disclosure. As shown in FIG2 , the flow chart includes the following steps S202 to S206:
[0037] As an illustrative example, a middleware device is a device that has demand and resource awareness, routing control, and routing scheduling capabilities, and supports centralized or distributed deployment. Middleware devices can be mapped to different types of physical entities or combinations of these entities, such as a network controller, a computing network orchestrator, a "computing network brain," a database-based centralized controller, or a distributed control plane composed of network element devices.
[0038] It should be noted that the demand and resource perception functions include: supporting the perception of various business needs of users, supporting the perception of network information, and supporting the perception of newly added computing power information through extended channels or protocol extensions.
[0039] Routing control functions include: supporting the mapping and negotiation of business needs and resources, dispatching service applications to appropriate service nodes, and providing services to terminals; supporting the generation and update of routing table entries, and supporting the generation and update of a new computing power routing table to support forwarding business forwarding.
[0040] The routing scheduling function includes: supporting explicit specification of forwarding paths, specifying forwarding paths based on the generated "forwarding path + destination node"; supporting network path adjustment, supporting re-specifying the forwarding path when the original forwarding path is abnormal, and switching the forwarding path back to the original forwarding path after the fault is recovered.
[0041] In this embodiment, the middleware device has the function of perceiving various types of computing and network element information on the network and service side according to the computing service requirements proposed by the computing service users, and then performing filtering, classification, integration, modeling and calculation processing, and finally realizing computing power routing decisions to ensure various types of computing service requirements.
[0042] Step S202: Obtain configuration information corresponding to the computing network service set, wherein the configuration information at least includes: computing power requirements of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services;
[0043] As an illustrative example, the computing network service set S = {Service1, Service2, ...}, and the computing network service can be identified by the corresponding computing network service identifier, that is, the Service ID set SID corresponding to the computing network service set S = {Service ID1, Service ID2, ...}.
[0044] As an illustrative example, computing power requirements include requirements for different computing power attributes, including but not limited to: number of CPU cores, CPU utilization, memory, floating-point computing power, etc.
[0045] In an exemplary embodiment, when each group of computing network services includes multiple computing network services, each group of computing network services constitutes a service function chain SFC.
[0046] In an exemplary embodiment, obtaining configuration information corresponding to a computing network service set includes but is not limited to:
[0047] Method 1: Obtain the configuration information sent by the target management component;
[0048] As an illustrative example, the target management component includes but is not limited to: a service subscription management component and a service identification management component in the computing network system.
[0049] The computing network service uses the service subscription management component / service identification management component in the computing network system to subscribe to the computing network service. The corresponding component issues the computing network service identification Service ID. The computing network management / control plane then configures information on the middleware device based on the computing network SLA requirements of the computing network service represented by each Service ID.
[0050] Method 2: Obtain the configuration information configured by the target object through the middleware device;
[0051] That is, users can perform management and control configuration at the middleware device and determine the configuration information.
[0052] Mode three: reading the configuration information at a target path, wherein the middleware device is deployed at the target path.
[0053] That is, the middleware device can read local or distributed Profile configuration information.
[0054] In this embodiment, the above-mentioned method can realize diversified acquisition of configuration information.
[0055] Step S204: determining a target computing power attribute set to be subscribed based on the configuration information;
[0056] It should be noted that since the configuration information includes the requirements of each group of computing network services in the computing network service set for different computing power attributes, the target computing power attribute set to be subscribed can be determined based on the configuration information. In an exemplary embodiment, the above step S204 can be implemented by the following steps S11-S13:
[0057] Step S11: determining a computing network attribute set corresponding to a service level agreement SLA for each group of computing network services according to the configuration information;
[0058] As an illustrative example, the configuration information may be as shown in Table 1 below:
[0059] Table 1
[0060] Then, the network service set S = {Service1, Service2, ...} and the corresponding Service ID set SID = {Service ID1, Service ID2, ...} can be determined based on the configuration information. Each network service group includes one network service. For Service ID i ∈SID, and the computing attribute set ATTR involved in its computing SLA requirements i ={Net1, Net2, ..., Com1, Com2, ...}, where Net j For network attributes, Com j It is the computing power attribute.
[0061] Step S12: determining a computing power attribute set of each group of computing network services from the computing network attribute set corresponding to each group of computing network services;
[0062] As shown in the above example, the computing power attribute set COM = {Com1, Com2, ...} of each group of computing network services can be determined from the computing network attribute set ATTRi corresponding to each group of computing network services.
[0063] As an illustrative example, the configuration information may also be shown in Table 2 below. In this case, each group of computing network services in the computing network service set includes multiple computing network services (Service 1, Service 2, etc.):
[0064] Table 2
[0065] Step S13: Determine the union of the computing power attribute sets of multiple groups of computing network services in the computing network service set as the target computing power attribute set.
[0066] As shown in the above example, it is assumed that the computing network service set includes two groups of computing network service sets, each group of computing network service sets corresponds to the computing network service identified by Service ID1 and the computing network service identified by Service ID2. It is assumed that the computing power attribute set COM of the computing network service identified by Service ID1 is {Com1, Com2}, and the computing power attribute set COM of the computing network service identified by Service ID2 is {Com1, Com3}, then the target computing power attribute set is {Com1, Com2, Com3}.
[0067] In this embodiment, when each group of computing network services includes one computing network service, the middleware device needs to subscribe to the computing network service set S = {Service1, Service2, ...} and each element Service in the set S. i The computing network SLA attribute set ATTR i ={Net1, Net2, ..., Com1, Com2, ...}, and the computing power attribute set COM={Com1, Com2, ...} that needs to collect computing power and service status information is summarized.
[0068] Step S206: Subscribe to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider.
[0069] It should be noted that subscribing to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider includes: subscribing to the attribute information of each computing power attribute in the target computing power attribute set from multiple service providers that provide services for different computing network services in the computing network service set.
[0070] As an illustrative example, the middleware device may query or subscribe to the attribute information of each computing power attribute from the Service Agent of the computing power service provider, which is responsible for collecting computing power information and aggregating information within the site.
[0071] In an exemplary embodiment, the above step S206 includes steps S21-S23:
[0072] Step S21: determining one or more collection frequencies corresponding to each computing power attribute in the target computing power attribute set on different computing network services in the computing network service set;
[0073] Step S22: determining the highest acquisition frequency among the one or more acquisition frequencies as the target acquisition frequency for each computing power attribute;
[0074] Step S23: Subscribe to the attribute information of each computing power attribute from the computing power service provider through the target collection frequency.
[0075] It should be noted that due to the different sensitivity and tolerance of different computing network services to information changes on the computing power side (i.e., the computing power service provider mentioned above), as well as the differentiated priorities among various computing network services, the requirements of various computing network services for the collection and update frequency of computing power side information are different. i ∈SID identifies the computing network service for the computing power attribute Com j The collection frequency requirement is Frequency i,j , then, the middleware device and the corresponding Service Agent for the computing power attribute Com j The collection frequency should meet the Frequency j ≥max{Frequency 1,j , Frequency 2,j ,...}.
[0076] For a better understanding, let's take an example. Assume that the computing power attribute set COM to be collected by Computing Network Service 1 is COM = {Com1, Com2}, and the computing power attribute set COM to be collected by Computing Network Service 2 is COM = {Com1, Com3}. The middleware device summarizes and determines the target computing power attribute set as COM = {Com1, Com2, Com3}. If Computing Network Service 1 collects computing power attribute Com1 every 20 seconds, and Computing Network Service 2 collects computing power attribute Com1 every 5 seconds, then the middleware device should collect attribute information of computing power attribute Com1 at least every 5 seconds.
[0077] In this embodiment, through the above steps S21-S23, the perception requirements of high computing power sensitive businesses can be met.
[0078] Through the above steps, the target computing power attribute set to be subscribed is determined by the middleware device according to the configuration information corresponding to the computing network service set, and the attribute information of each computing power attribute in the target computing power attribute set is subscribed to the computing power service provider, thereby avoiding the use of traditional underlying network technology to realize the computing power information perception of the computing power service provider, thereby solving the problem that relying on traditional underlying network technology to realize the computing power information perception of the computing power service provider will cause additional burden on the traditional network, thereby reducing the impact and burden of the perceived computing power information on the network.
[0079] The execution subject of the above steps may be a middleware device, etc., but is not limited thereto.
[0080] As an exemplary embodiment, after obtaining the configuration information corresponding to the computing network service set, the following steps S11-S13 are further included:
[0081] Step S31: determining a target network attribute set according to the configuration information, wherein the configuration information further includes: network requirements of each group of computing network services in the computing network service set;
[0082] As an illustrative example, the network requirements include requirements for different network attributes, including but not limited to: transmission delay, bandwidth, etc.
[0083] As an illustrative example, the method of determining the target network attribute set based on the configuration information is similar to the type of the above-mentioned method of determining the target computing power attribute set based on the configuration information, and this disclosure will not elaborate on this.
[0084] Step S32: determining first attribute information of each network attribute in the target network attribute set based on the first network information reported by the network device, and determining second attribute information of each network attribute in the target network attribute set based on the second network information reported by the computing power service provider;
[0085] It should be noted that the second network information reported by the computing power service provider includes network information reported separately by multiple service providers providing services for different computing network services in the computing network service set.
[0086] Step S33: Determine the attribute information of each network attribute in the target network attribute set according to the first attribute information and the second attribute information of each network attribute.
[0087] As an illustrative example, for a service provider that needs to provide a certain type of computing network service, the middleware device can integrate the first network information reported by the network device and the same type of attribute information in the network information reported by the service provider.
[0088] For example: one-way service delay = transmission delay from the network side ingress gateway to the egress gateway + network transmission delay from the computing power side cloud gateway to the service instance (equivalent to the above-mentioned service provider) + time taken by the service instance to process and provide services; bottleneck bandwidth of computing network service = min{network bottleneck bandwidth on the network side, network bottleneck bandwidth on the computing power side}.
[0089] It should be noted that the attribute information of each network attribute includes attribute values corresponding to each network attribute of different groups of service providers.
[0090] In this embodiment, although the network information reported by the computing power service provider and the network information in the traditional network belong to different operation domains and management domains, through the above steps S31-S33, the middleware device can integrate the information of the same dimensions in the two to realize the integration of network information from different operation domains and management domains.
[0091] In an exemplary embodiment, when the attribute information of each computing power attribute in the target computing power attribute set and the attribute information of each network attribute in the target network attribute set are obtained, the following step S41 is further included:
[0092] Step S41: determining the target capability of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services according to the attribute information of each computing power attribute and the attribute information of each network attribute;
[0093] It should be noted that the target capability is the capability of each group of service providers to provide each group of computing network services to computing network service users through the corresponding network forwarding path. Each computing network service in each group of computing network services has a one-to-one correspondence with each service provider in each group of service providers. The attribute information of each computing power attribute includes the attribute values corresponding to each computing power attribute of different groups of service providers, and the attribute information of each network attribute includes the attribute values corresponding to each network attribute of different groups of service providers.
[0094] It should be noted that the number of computing network services in each group of computing network services is the same as the number of service providers in each group of service providers corresponding to each group of computing network services. That is, if a group of computing network services has two computing network services (computing network service 1 and computing network service 2), then the group of service providers corresponding to the group of computing network services includes: service provider 1 that provides services for computing network service 1, and service provider 2 that provides services for computing network service 2.
[0095] Assuming that each group of computing network services includes one computing network service, the target capability is the capability of the service provider providing the computing network service to provide the computing network service to the computing network service user by cooperating with the corresponding network forwarding path.
[0096] Assuming each computing network service group includes N computing network services, the target capacity is the ability of the N service providers that provide services for these N computing network services to provide these multiple computing network service service function chains (SFCs) to the computing network service users in coordination with the corresponding network forwarding paths. Where N is a positive integer greater than 1.
[0097] In an exemplary embodiment, the above step S41 can be implemented by the following steps S51-S53:
[0098] Step S51: Determine computing network attribute information corresponding to each group of service providers based on the attribute information of each computing power attribute and the attribute information of each network attribute, wherein the computing network attribute information includes the attribute value of each attribute in a computing network attribute set corresponding to the SLA of each group of computing network services, and the computing network attribute set includes computing power attributes and network attributes;
[0099] Step S52: determining a capability evaluation function corresponding to each group of computing network services according to the configuration information, and using the capability evaluation function to determine a target indicator value corresponding to each group of service providers according to the computing network attribute information corresponding to each group of service providers;
[0100] Step S53: determining the target capability of each group of service providers according to the target indicator value.
[0101] That is, in this embodiment, for a group of service providers that need to provide a group of computing network services, the middleware device filters out the attribute value of each attribute in the computing network attribute set required by the computing network service SLA from the integrated attribute information. If a group of computing network services is the computing network service identified by Service ID1 as shown in Table 1, then for each of the multiple service providers that provide services for the computing network service identified by Service ID1, it is necessary to determine the computing network attribute set ATTR from the integrated attribute information. i =The value of each element in {Net1, Net2, ..., Com1, Com2, ...}.
[0102] Then the middleware device calculates the network attribute set ATTR based on the element assignment i ={Net1, Net2, ..., Com1, Com2, ...}, call the capability evaluation function associated with the Service ID Function i (Net1, Net2, ..., Com1, Com2, ...), calculate and obtain the metric value (i.e., the target indicator value mentioned above). This metric value represents the service provider's ability to provide the computing network service identified by Service ID1 to the computing network service user by coordinating the corresponding network forwarding path.
[0103] In an exemplary embodiment, after the above step S41, the following steps S61-S62 are further performed:
[0104] Step S61: Generate a computing power routing table, wherein the computing power routing table is used to indicate the target capacity of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services;
[0105] As an illustrative example, assuming that each group of computing network services includes one computing network service, and its corresponding service providers are IP1, IP2, and IP3, the generated computing power routing table can be as shown in Figure 6.
[0106] Step S62: Send the computing power routing table to the network device, wherein the computing power routing table is used to guide the network device to forward computing network service traffic.
[0107] In an exemplary embodiment, after sending the computing power routing table to the network device, steps S71-S72 are further included:
[0108] Step S71: When the network device obtains first service traffic and the first service traffic requests a first group of computing network services, instruct the network device to determine a first group of service providers from multiple groups of service providers corresponding to the first group of computing network services according to the computing power routing table, wherein the first group of service providers has the strongest capability of providing the first group of computing network services to the computing network service user through the corresponding network forwarding path among the multiple groups of service providers;
[0109] Step S72: instruct the network device to direct the first service traffic to the first group of service providers.
[0110] In an exemplary embodiment, the above step S72 includes: directing the first service traffic to the first group of service providers through best effort forwarding (BE) or traffic engineering (TE).
[0111] For a better understanding, assume that the current computing network service user has subscribed to two types of computing network services identified by Service ID1 and Service ID2. For these two types of computing network services, Function 1 and Function 2 are used to calculate the metric values of the corresponding service providers through the above steps. Then, when the computing power network is processing multiple computing network service users requesting the corresponding computing network services using Service ID1 and Service ID2, if at time t1, user service flow 1 (i.e., the first service flow mentioned above) requests computing network service 1 using Service ID1, the network device determines the service provider IP1 with the strongest ability to provide computing network service 1 to the computing network service user through the corresponding network forwarding path based on the metric values of each service provider in the computing power routing table entry indexed by Service ID1 issued by the middleware device, and directs user service flow 1 to service provider IP1 in a BE or TE manner.
[0112] In an exemplary embodiment, after instructing the network device to direct the first service traffic to the first group of service providers, the method further includes steps S81-S82:
[0113] Step S81: When the network device obtains second service traffic and the second service traffic requests the first group of computing network services, instruct the network device to determine a second group of service providers from the multiple groups of service providers corresponding to the first group of computing network services according to the updated computing power routing table, wherein the second group of service providers has the strongest capability among the multiple groups of service providers to provide the first group of computing network services to the computing network service user through the corresponding network forwarding path;
[0114] Step S82: If the second group of service providers is different from the first group of service providers, instruct the network device to direct the second service traffic to the second group of service providers and continue to direct the first service traffic to the first group of service providers.
[0115] It should be noted that for subsequent packets following the first packet of the same service flow, traffic affinity is a common basic service requirement, meaning that subsequent service packets must be sent to the same service provider for processing. Therefore, in this embodiment, service packet processing logic requires a distinction between the first packet and subsequent packets, corresponding to two forwarding actions: computing power routing forwarding and traffic affinity forwarding. As in the example above, if at time t2, user service flow 2, as a different service flow requesting the same computing network service, also requests computing network service 1 with Service ID 1, the network device will, based on the metric values of each service provider in the computing power routing table entry indexed by Service ID 1, newly determine from among the various service providers the service provider with the strongest capability to provide computing network service 1 to the computing network service user via the corresponding network forwarding path, and then redirect user service flow 2 to service provider IP 2 via BE or TE. Due to the traffic affinity requirements of computing network service 1, the original user service flow 1 will still be redirected to service provider IP 1.
[0116] It should be noted that if at time t3, user service flow 3, as a different service flow requesting a different type of computing network service, requests computing network service 2 with Service ID 2, the network device, based on the metric values of each service provider in the computing power routing table entry indexed by Service ID 2 and issued by the middleware device, determines the service provider IP 2 with the strongest capability to provide computing network service 2 to the computing network service user through the corresponding network forwarding path, and then directs user service flow 3 to service provider IP 2 in BE or TE mode. The original user service flows 1 and 2 are still directed to service provider IP 1 and service provider IP 2, respectively.
[0117] From the above steps, it can be seen that the present disclosure proposes a method for computing power and service status perception and information usage based on middleware equipment, including collecting multi-dimensional attribute information of computing power and service side with adaptive frequency based on different computing network business needs, and performing pre-processing work such as information integration, filtering, modeling, etc. through middleware facilities. Then, according to the diversified computing network business needs, the multi-dimensional computing and network attribute information is converted into a metric value that can reflect the service capability of the service instance for a certain computing network business, and finally a computing power routing table entry is generated and sent to the network side device to guide business forwarding.
[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory (ROM / RAM), a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present disclosure.
[0119] In this embodiment, a middleware device is also provided, which is used to implement the above-mentioned embodiments and exemplary implementations. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the middleware devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.
[0120] FIG14 is a structural block diagram of a middleware device according to an embodiment of the present disclosure. As shown in FIG14 , the middleware device includes
[0121] An acquisition module 142 is configured to acquire configuration information corresponding to a computing network service set, wherein the configuration information includes at least: computing power requirements of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services;
[0122] A determination module 144 is configured to determine a target computing power attribute set to be subscribed based on the configuration information;
[0123] The subscription module 146 is configured to subscribe to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider.
[0124] In the present disclosure, the middleware device determines the target computing power attribute set to be subscribed based on the configuration information corresponding to the computing network service set, and subscribes to the attribute information of each computing power attribute in the target computing power attribute set to the computing power service provider, thereby avoiding the use of traditional underlying network technology to realize the computing power information perception of the computing power service provider, thereby solving the problem that relying on traditional underlying network technology to realize the computing power information perception of the computing power service provider will cause additional burden on the traditional network, thereby achieving the effect of reducing the impact and burden of the perceived computing power information on the network.
[0125] In an exemplary embodiment, the determination module 144 is further configured to determine the computing network attribute set corresponding to the service level agreement SLA of each group of computing network services based on the configuration information; determine the computing power attribute set of each group of computing network services from the computing network attribute set corresponding to each group of computing network services; and determine the union of the computing power attribute sets of all groups of computing network services in the computing network service set as the target computing power attribute set.
[0126] In an exemplary embodiment, the subscription module 146 is further configured to determine one or more acquisition frequencies corresponding to each computing power attribute in the target computing power attribute set on different computing network services in the computing network service set; determine the highest acquisition frequency among the one or more acquisition frequencies as the target acquisition frequency for each computing power attribute; and subscribe to the attribute information of each computing power attribute to the computing power service provider through the target acquisition frequency.
[0127] In an exemplary embodiment, the determination module 144 is further configured to obtain the configuration information corresponding to the computing network service set, and then determine the target network attribute set based on the configuration information, wherein the configuration information also includes: the network requirements of each group of computing network services in the computing network service set; determining the first attribute information of each network attribute in the target network attribute set based on the first network information reported by the network device, and determining the second attribute information of each network attribute in the target network attribute set based on the second network information reported by the computing power service provider; determining the attribute information of each network attribute in the target network attribute set based on the first attribute information and the second attribute information of each network attribute.
[0128] In an exemplary embodiment, the determination module 144 is further configured to determine the target capability of each group of service providers in the multiple groups of service providers corresponding to each group of computing network services based on the attribute information of each computing power attribute and the attribute information of each network attribute in the target network attribute set, upon obtaining the attribute information of each computing power attribute in the target computing power attribute set and the attribute information of each network attribute in the target network attribute set; wherein the target capability is the capability of each group of service providers to provide each group of computing network services to computing network service users through the corresponding network forwarding path, each computing network service in each group of computing network services has a one-to-one correspondence with each service provider in each group of service providers, the attribute information of each computing power attribute includes the attribute values of different groups of service providers corresponding to each computing power attribute, and the attribute information of each network attribute includes the attribute values of different groups of service providers corresponding to each network attribute.
[0129] In an exemplary embodiment, the determination module 144 is further configured to determine the computing network attribute information corresponding to each group of service providers based on the attribute information of each computing power attribute and the attribute information of each network attribute, wherein the computing network attribute information includes the attribute value of each attribute in the computing network attribute set corresponding to the SLA of each group of computing network services, and the computing network attribute set includes computing power attributes and network attributes; determine the capability evaluation function corresponding to each group of computing network services based on the configuration information, and use the capability evaluation function to determine the target indicator value corresponding to each group of service providers based on the computing network attribute information corresponding to each group of service providers; and determine the target capability of each group of service providers based on the target indicator value.
[0130] In an exemplary embodiment, the above-mentioned middleware device also includes: a processing module, which is configured to determine the target capability of each group of service providers in the multiple groups of service providers corresponding to each group of computing network services based on the attribute information of each computing power attribute and the attribute information of each network attribute, and then generate a computing power routing table, wherein the computing power routing table is used to indicate the target capability of each group of service providers in the multiple groups of service providers corresponding to each group of computing network services; and send the computing power routing table to the network device, wherein the computing power routing table is used to guide the network device to forward computing network service traffic.
[0131] In an exemplary embodiment, the processing module is further configured to, when the network device obtains the first business traffic and the first business traffic requests the first group of computing network services, instruct the network device to determine the first group of service providers from the multiple groups of service providers corresponding to the first group of computing network services according to the computing power routing table, wherein the first group of service providers has the strongest ability to provide the first group of computing network services to the computing network service user through the corresponding network forwarding path among the multiple groups of service providers; and instruct the network device to divert the first business traffic to the first group of service providers.
[0132] In an exemplary embodiment, the processing module is further configured to direct the first service traffic to the first group of service providers through best effort forwarding (BE) or traffic engineering (TE).
[0133] In an exemplary embodiment, the processing module is further configured to instruct the network device to direct the first business traffic to the first group of service providers. When the network device obtains the second business traffic and the second business traffic requests the first group of computing network services, instruct the network device to determine the second group of service providers from the multiple groups of service providers corresponding to the first group of computing network services according to the updated computing power routing table, wherein the second group of service providers has the strongest ability to provide the first group of computing network services to the computing network service users through the corresponding network forwarding path among the multiple groups of service providers; when the second group of service providers is different from the first group of service providers, instruct the network device to direct the second business traffic to the second group of service providers, and continue to direct the first business traffic to the first group of service providers.
[0134] In an exemplary embodiment, the acquisition module 142 is further configured to acquire the configuration information sent by the target management component; or acquire the configuration information configured by the target object through the middleware device; or read the configuration information at the target path, wherein the middleware device is deployed at the target path.
[0135] In an exemplary embodiment, when each group of computing network services includes multiple computing network services, each group of computing network services constitutes a service function chain SFC.
[0136] The embodiment of the present disclosure further provides a subscription system for attribute information. FIG15 is a structural block diagram of the subscription system for attribute information according to the embodiment of the present disclosure. As shown in FIG15 , the system includes:
[0137] The middleware device 152 is configured to obtain configuration information corresponding to a computing network service set and determine a target computing power attribute set to be subscribed based on the configuration information, wherein the configuration information includes at least: computing power requirements of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services;
[0138] The computing power service provider 154 is configured to send attribute information of each computing power attribute in the target computing power attribute set to the middleware device.
[0139] In the present disclosure, the middleware device determines the target computing power attribute set to be subscribed based on the configuration information corresponding to the computing network service set, and subscribes to the attribute information of each computing power attribute in the target computing power attribute set to the computing power service provider, thereby avoiding the use of traditional underlying network technology to realize the computing power information perception of the computing power service provider, thereby solving the problem that relying on traditional underlying network technology to realize the computing power information perception of the computing power service provider will cause additional burden on the traditional network, thereby achieving the effect of reducing the impact and burden of the perceived computing power information on the network.
[0140] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
[0141] Obviously, the embodiments described above are only part of the embodiments of the present disclosure, rather than all the embodiments. In order to better understand the above method, the above process is described below in conjunction with the embodiments, but it is not intended to limit the technical solutions of the embodiments of the present disclosure. Specifically:
[0142] As an illustrative example, a method for sensing computing power and service status and using information based on a middleware facility is proposed, as shown in FIG3 , including the following steps 1 to 4:
[0143] Step 1: The subscription management component in the computing network operation or management architecture receives computing network service subscriptions from users or businesses, and notifies the middleware device of the subscribed service information. Then, the user forms a variable and controllable computing and network information modeling method corresponding to various subscribed computing network services on the middleware device through the management and control interface configuration or Profile configuration, thereby realizing the perception of subscription service needs.
[0144] Step 2: The computing power side (equivalent to the computing power service provider in the above embodiment) perceives the relevant computing power and service status information of the subscribed service, combines the network information on the network side and the cloud side, and reports them to the middleware device together to realize the perception of computing and network information.
[0145] Step 3: The middleware device integrates similar items of the collected computing and network information, and then filters and calculates the computing and network attribute information based on the computing and network information modeling method of various computing and network services subscribed to with the computing and network service identifier as the index, and obtains the service instance (equivalent to the service provider in the above embodiment) to cooperate with the corresponding network forwarding path to provide computing and network services. The ability to provide computing and network services is represented by the metric value obtained by calculation.
[0146] Step 4: Based on the computing network scheduling strategy, the middleware device generates a computing power routing table entry indexed by the computing network service identifier and sends it to the network to guide service forwarding.
[0147] To better understand the above steps, the following are detailed instructions:
[0148] (1) Network service subscription and service modeling configuration (equivalent to obtaining configuration information in the above embodiment)
[0149] As shown in Figure 4, the computing network service user subscribes to the computing network service with the service subscription management component / service identification management component in the computing network system, and the corresponding component issues the computing network service identification Service ID. The computing network management / control plane then configures and generates the information modeling method of the subscribed computing network service at the middleware device based on the computing network SLA requirements of the computing network service represented by each Service ID, that is, realizing service demand perception at the middleware device. The configuration generation method of the modeling method includes but is not limited to: (1) control configuration at the middleware facility; (2) reading the local or issued Profile configuration file at the middleware facility; (3) notification to the middleware facility by the service subscription management component / service identification management component.
[0150] Assume that the subscribed computing network service set S = {Service1, Service2, ...}, and the corresponding Service ID set SID = {Service ID1, Service ID2, ...}.i ∈SID, the computing network attribute set ATTR involved in its computing network SLA requirements i ={Net1, Net2, ..., Com1, Com2, ...}, where Net j For network attributes, such as transmission delay, bandwidth, etc., Com j For computing power attributes, such as the number of CPU cores, CPU utilization, memory, floating-point computing power, etc., a typical computing and network information modeling configuration is shown in Table 1 above.
[0151] (2) Computing power and service status information perception (equivalent to determining the attribute information of each attribute in the target computing power attribute set in the above embodiment)
[0152] As shown in FIG5, according to the subscribed computing network service set S = {Service1, Service2, ...} and each element Service in the set S i The computing network SLA attribute set ATTR i ={Net1, Net2, ..., Com1, Com2, ...}, the middleware device (Middle Ware in Figure 5) summarizes the attribute set COM={Com1, Com2, ...} that needs to be collected for computing power and service status information, and then queries or subscribes to the Service Agent on the computing power side that is responsible for collecting computing power metadata and aggregating information within the site.
[0153] It should be noted that, since different computing network services (Instances in Figure 5) identified by each Service ID have different sensitivities and tolerances to changes in computing power side information, and there are differentiated priorities among various computing network services, the requirements of various computing network services for the collection and update frequency of computing power side information are different. Assuming that Service ID i ∈SID identifies the computing network service for the computing power attribute Com j The collection frequency requirement is Frequency i,j , then, the middleware facilities and the corresponding Service Agent for the computing power attribute Com j The collection frequency should meet the Frequency j ≥max{Frequency 1,j , Frequency 2,j , ...}. It should be noted that the Interval in Figure 5 is the collection frequency.
[0154] (3) Calculation, network element information processing and calculation
[0155] As shown in Figure 6, the middleware device processes the computing and network information as follows:
[0156] S602: Sense the network and computing power information of the computing and network sides;
[0157] The middleware device obtains network information reported by the network controllers on the network side and the cloud side or obtained through measurement and OAM means, and collects the computing power and service status metadata on the computing power side according to the method described in (2) above.
[0158] S604: Integrate similar information from the computing and network sides;
[0159] For service instances that need to provide a certain type of computing network service, the middleware device integrates similar attribute information in the computing and network information, such as: one-way service delay = transmission delay from the network side ingress gateway to the egress gateway + network transmission delay from the computing power side cloud gateway to the service instance + time taken by the service instance to process and provide services; bottleneck bandwidth of computing network service = min{network bottleneck bandwidth on the network side, network bottleneck bandwidth on the computing power side}.
[0160] S606: Filter to obtain attributes involved in a type of computing network service SLA requirement;
[0161] For a service instance that needs to provide a certain type of computing network service, the middleware facility filters out the computing network attributes required by the SLA of the computing network service from the integrated attribute information, that is, the computing network attributes associated with the Service ID as shown in Table 1 above, and obtains the computing network attribute set ATTR i =The value of each element in {Net1, Net2, ..., Com1, Com2, ...}.
[0162] S608: Calculate and obtain the capability of the service instance to provide the computing network service to the computing network service user, and express it in a metric value.
[0163] The middleware device calculates the network attribute set ATTR based on the element assignment i ={Net1, Net2, ..., Com1, Com2, ...}, call the function associated with the Service ID Function i (Net1, Net2, ..., Com1, Com2, ...), calculate and get the metric value. This metric value can be used to represent the service instance and provide the service ID of this type to the computing network service user in conjunction with the corresponding network forwarding path. i The capabilities of the identified computing network service.
[0164] (4) Generation of computing power routing table entries
[0165] According to the above (1), (2), and (3), the middleware device calculates the metric values of several service instances that provide a certain type of computing network service, which is used to evaluate the ability of each service instance to cooperate with the corresponding network forwarding path to provide different computing network services, and then generates the computing power routing table shown in Figure 7, and sends the computing power routing table to the network to guide the forwarding of computing network business traffic.
[0166] It should be noted that for subsequent packets after the first packet of the same service flow, traffic affinity is a common basic service requirement, that is, subsequent service packets need to be sent to the same service instance for processing. Therefore, the service packet processing logic needs to distinguish between the first packet and subsequent packets, corresponding to the two forwarding actions of computing power routing forwarding and traffic affinity forwarding. Specifically, as shown in Figure 8:
[0167] S802: Determine whether the service flow is the first packet. If yes, execute step S804; otherwise, execute step S806.
[0168] S804: Forwarding based on computing power routing;
[0169] S806: Forwarding based on the service traffic affinity principle.
[0170] For a better understanding, the above steps S802-S806 are described in detail below:
[0171] As shown in Figure 9, assume that the current computing network service user has subscribed to two types of computing network services identified by Service ID1 and Service ID2. For these two types of computing network services, Function1 and Function2 are used to calculate the metric values of the corresponding service instances. Then, when the computing power network processes multiple computing network service users requesting the corresponding computing network services using Service ID1 and Service ID2:
[0172] (1) At time t1, user service flow 1 requests computing network service 1 with Service ID 1. The network device directs user service flow 1 to the service instance of Service IP 1 in BE or TE mode based on the metric value of each service instance in the computing power routing table entry indexed by Service ID 1 issued by the middleware device.
[0173] (2) At time t2, user service flow 2, as a different service flow requesting the same type of computing network service, also requests computing network service 1 with Service ID 1. The network device directs user service flow 2 to the service instance of Service IP 2 in BE or TE mode based on the metric values of each service instance in the computing power routing table entry indexed by Service ID 1, which is recently issued by the middleware device. Due to the traffic affinity requirements of computing network service 1, the original user service flow 1 is still directed to the service instance of Service IP 1.
[0174] (3) At time t3, user service flow 3, as a different service flow requesting a different type of computing network service, requests computing network service 2 with Service ID 2. The network device directs user service flow 3 to the service instance of Service IP 2 in BE or TE mode based on the metric values of each service instance in the computing power routing table entry indexed by Service ID 2 issued by the middleware facility. The original user service flows 1 and 2 are still directed to the service instances of Service IP 1 and Service IP 2, respectively.
[0175] (V) Information processing and computing in the context of multiple computing network services
[0176] During end-to-end traffic transmission, various service functions (SFs) are typically provided. These include traditional network SFs, such as firewalls and NAT, as well as application-specific SFs, such as HTTP header modifications. These SFs form a service function chain (SFC).
[0177] With the deep integration of cloud and network and the continued development of computing networks, the combination of multiple computing network services, followed by serial orchestration and use, to form a computing network service chain has become a possible form of computing network development. In this scenario, how to simultaneously instantiate multiple service instances and orchestrate an SFP that meets the SLA requirements of a computing network service chain composed of multiple computing network services will also become a pressing issue. As shown in Figure 10, a computing network service SFC consists of three computing network services: Service A, Service B, and Service C, in sequence. Each of these computing network services is provided by multiple distributed service instances. Similar to Table 1, a typical computing and network information modeling approach for a computing network service SFC containing multiple computing network services is shown in Table 2 above.
[0178] Similar to Figure 6, the middleware device processes the computing and network information as follows:
[0179] Step 1: The middleware device obtains network information reported by the network controllers on the network side and the cloud side or obtained through measurement and OAM means, and collects computing power and service status information on the computing power side according to the above (2).
[0180] Step 2: For a group of service instances that need to provide a certain type of computing network service SFC, the middleware device integrates similar attribute information in the computing and network information, such as: SFC service latency = network transmission latency connecting each edge cloud + network transmission latency from the cloud gateway in each edge cloud to the service instance + the time taken by each service instance to process and provide services.
[0181] Step 3: For a group of service instances that need to provide a certain type of computing network service SFC, the middleware device filters out the computing network attributes associated with the SFC as shown in Table 2 required by the SLA of the computing network service SFC from the integrated attribute information, and obtains the values of each element in the computing network attribute set.
[0182] Step 4: The middleware device calls the function associated with the network service SFC based on the network attribute set after element assignment. i (Net1, Net2, ..., Com1, Com2, ...), calculate and obtain the metric value. The metric value can be used to represent the ability of the group of service instances to provide the computing network service SFC to the computing network service user in conjunction with the corresponding network forwarding path.
[0183] In other words, the present disclosure uniformly implements service information perception and service demand perception based on middleware devices, combining the two to achieve computing network service assurance. Specifically, a computing power and service status perception method based on middleware devices is proposed. This method decouples computing power and service status perception and notification from the underlying network technology, adapting to the high-frequency computing power perception needs of high-computing power-sensitive services, optimizing the user experience of computing network services, and reducing the impact and burden of dynamic computing power changes on the network. A method for using computing power and service status information based on middleware devices is also proposed. The functions of the middleware devices include: integration of similar computing and network information, filtering of SLA requirement attribute information, integrated secondary modeling of computing network information, and metric value calculation. This method is also applicable to scenarios where SFCs are composed of multiple types of computing network services. In the computing power network ecosystem, middleware devices improve the evaluation capabilities of end-to-end computing network services. Combined with the increased ability to perceive service demands, they supplement the personalized evaluation capabilities of different computing network services, thereby enhancing the computing power network's refined computing network scheduling capabilities.
[0184] Furthermore, this disclosure improves the integration and integrated modeling and processing capabilities of computing and network information through middleware devices. It provides computing power perception at a service granularity and evaluation capabilities for the integrated computing and network services. This is a key technology for computing power networks to achieve refined service routing and computing power scheduling. This disclosure decouples computing power and service status perception from the underlying network technology, making it more adaptable to the high-frequency computing power perception needs of future high-computing power-sensitive businesses, while also reducing the impact and burden of high dynamic changes in computing power on the network.
[0185] To facilitate understanding of the technical solutions provided by the present disclosure, embodiments of specific scenarios will be described in detail below.
[0186] Specific Example 1: Computing Power Perception and Computing Power Routing Calculation in a Single Service Scenario
[0187] Assume that a type of computing network service identified by Service ID1 is sensitive to service delay and the memory attributes of the service instance. The corresponding metric value of this type of computing network service is calculated as Metric(Service ID1) = Function(delay, memory) = 0.6×Grade_delay(delay) + 0.4×Grade_memory(memory), where Grade_delay() and Grade_memory() take membership functions as an example, and their definitions are shown in Figure 11.
[0188] It should be noted that the service instances and network paths capable of providing the computing network service identified by Service ID 1 are shown in Figure 11. The middleware device collects network path capabilities for Path 1, Path 2, and Path 3, as well as computing power information for Instance 1 and Instance 2, from both the network and computing power sides. This information is then combined to determine the total latency under different combinations and calculate the corresponding metric values. Under the exemplary minimum metric value strategy, it can be determined that at this point, service instance Instance 2, combined with network forwarding path Path 3, is the most suitable provider of the computing network service identified by Service ID 1.
[0189] Specific Example 2: Computing Power Perception and SFP Calculation in Multi-Service Scenarios
[0190] Assume that an SFC consists of three types of computing network services identified by Service ID 1, Service ID 2, and Service ID 3. These three types of computing network services are sensitive to memory attributes, load conditions, and the number of CPU cores, respectively. The computing network SFC is sensitive to overall latency attributes. This type of SFC has the following constraints:
[0191] (1) The overall SFC delay should not exceed 120ms;
[0192] (2) The memory of the service instance providing the computing network service Service A should be no less than 15G;
[0193] (3) The load of the service instance providing the computing network service Service B should not exceed 80%;
[0194] (4) The number of CPU cores of the service instance providing the computing network service Service C should be no less than 3.
[0195] The metric value calculation method of the SFC is shown in Figure 12. The service instance and network path conditions of the three types of computing network services identified by Service ID1, Service ID2 and Service ID3 that each edge cloud can provide are shown in Figure 13. The middleware device collects the relevant computing power information of each service instance and the network path capability information connecting these service instances, and calculates the corresponding metric value. Among them, the service function path (SFP) service function path SFP1, SFP2 and SFP5 all have the largest metric value because the total delay of SFC is greater than 120ms, and they are SFPs that do not meet the constraints. Among the remaining SFPs, SFP4 has the smallest metric value and can be selected as the SFP that provides SFC.
[0196] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.
[0197] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.
[0198] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.
[0199] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0200] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.
[0201] Obviously, those skilled in the art should understand that the modules or steps of the present disclosure described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present disclosure is not limited to any particular combination of hardware and software.
[0202] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will readily appreciate that the present disclosure is susceptible to various modifications and variations. Any modifications, equivalent substitutions, improvements, and the like made within the principles of the present disclosure shall be included within the scope of protection of the present disclosure.
Claims
1. A method for subscribing to attribute information, applied to a middleware device, comprising: Obtain configuration information corresponding to the computing network service set, wherein the configuration information at least includes: computing power requirements of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services; Determine a target computing power attribute set to be subscribed according to the configuration information; Subscribe to the computing power service provider for the attribute information of each computing power attribute in the target computing power attribute set.
2. The method according to claim 1, wherein: Determining a target computing power attribute set to be subscribed according to the configuration information includes: Determine a set of computing network attributes corresponding to a service level agreement SLA for each group of computing network services according to the configuration information; Determine a computing power attribute set of each group of computing network services from the computing network attribute set corresponding to each group of computing network services; The union of computing power attribute sets of multiple groups of computing network services in the computing network service set is determined as the target computing power attribute set.
3. The method according to claim 1, wherein: Subscribe to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider, including: Determine one or more collection frequencies corresponding to each computing power attribute in the target computing power attribute set on different computing network services in the computing network service set; Determine the highest acquisition frequency among the one or more acquisition frequencies as the target acquisition frequency for each computing power attribute; Subscribe to the attribute information of each computing power attribute from the computing power service provider through the target collection frequency.
4. The method according to claim 1, wherein: After obtaining the configuration information corresponding to the computing network service set, the method further includes: Determine a target network attribute set according to the configuration information, wherein the configuration information further includes: network requirements of each group of computing network services in the computing network service set; Determine the first attribute information of each network attribute in the target network attribute set according to the first network information reported by the network device, and determine the second attribute information of each network attribute in the target network attribute set according to the second network information reported by the computing power service provider; The attribute information of each network attribute in the target network attribute set is determined according to the first attribute information and the second attribute information of each network attribute.
5. The method according to claim 4, wherein: In the case where the attribute information of each computing power attribute in the target computing power attribute set and the attribute information of each network attribute in the target network attribute set are obtained, the method further includes: Determining the target capacity of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services according to the attribute information of each computing power attribute and the attribute information of each network attribute; Among them, the target capability is the capability of each group of service providers to provide each group of computing network services to the computing network service users through the corresponding network forwarding path, each computing network service in each group of computing network services has a one-to-one correspondence with each service provider in each group of service providers, the attribute information of each computing power attribute includes the attribute values corresponding to each computing power attribute of different groups of service providers, and the attribute information of each network attribute includes the attribute values corresponding to each network attribute of different groups of service providers.
6. The method according to claim 5, wherein: Determining the target capability of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services according to the attribute information of each computing power attribute and the attribute information of each network attribute includes: Determine computing network attribute information corresponding to each group of service providers according to the attribute information of each computing power attribute and the attribute information of each network attribute, wherein the computing network attribute information includes the attribute value of each attribute in the computing network attribute set corresponding to the SLA of each group of computing network services, and the computing network attribute set includes computing power attributes and network attributes; Determine a capability evaluation function corresponding to each group of computing network services according to the configuration information, and use the capability evaluation function to determine a target indicator value corresponding to each group of service providers according to the computing network attribute information corresponding to each group of service providers; The target capability of each group of service providers is determined according to the target indicator value.
7. The method according to claim 5, wherein: After determining the target capability of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services according to the attribute information of each computing power attribute and the attribute information of each network attribute, the method further includes: Generate a computing power routing table, wherein the computing power routing table is used to indicate the target capacity of each group of service providers in the plurality of groups of service providers corresponding to each group of computing network services; The computing power routing table is sent to the network device, wherein the computing power routing table is used to guide the network device to forward computing network service traffic.
8. The method according to claim 7, wherein: The method further comprises: In the case where the network device obtains the first service flow and the first service flow requests the first group of computing network services, instructing the network device to determine a first group of service providers from multiple groups of service providers corresponding to the first group of computing network services according to the computing power routing table, wherein the first group of service providers has the strongest ability to provide the first group of computing network services to the computing network service user through the corresponding network forwarding path among the multiple groups of service providers; Instruct the network device to direct the first service traffic to the first group of service providers.
9. The method according to claim 8, wherein: Directing the first service traffic to the first group of service providers includes: The first service traffic is directed to the first group of service providers through best effort forwarding BE or traffic engineering TE.
10. The method according to claim 8, wherein: After instructing the network device to direct the first service traffic to the first group of service providers, the method further includes: The network device obtains the second service flow, and the second service flow requests the first group of computing network services. In this case, instruct the network device to determine a second group of service providers from the multiple groups of service providers corresponding to the first group of computing network services according to the updated computing power routing table, wherein the second group of service providers has the strongest ability to provide the first group of computing network services to the computing network service user through the corresponding network forwarding path among the multiple groups of service providers; In case the second group of service providers is different from the first group of service providers, the network device is instructed to direct the second service traffic to the second group of service providers and continue to direct the first service traffic to the first group of service providers.
11. The method according to claim 1, wherein: Get the configuration information corresponding to the computing network service set, including: Obtain the configuration information sent by the target management component; or Obtaining the configuration information configured by the target object through the middleware device; or The configuration information is read at a target path, wherein the middleware device is deployed at the target path.
12. The method according to claim 1, wherein: In the case where each group of computing network services includes multiple computing network services, each group of computing network services constitutes a service function chain SFC.
13. A middleware device, comprising: An acquisition module is configured to acquire configuration information corresponding to a computing network service set, wherein the configuration information at least includes: a computing power requirement of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services; A determination module, configured to determine a target computing power attribute set to be subscribed according to the configuration information; The subscription module is configured to subscribe to the attribute information of each computing power attribute in the target computing power attribute set from the computing power service provider.
14. A subscription system for attribute information, comprising: A middleware device, used to obtain configuration information corresponding to a computing network service set, and determine a target computing power attribute set to be subscribed according to the configuration information, wherein the configuration information at least includes: computing power requirements of each group of computing network services in the computing network service set, wherein each group of computing network services includes one computing network service or multiple computing network services; The computing power service provider is used to send the attribute information of each computing power attribute in the target computing power attribute set to the middleware device.
15. A computer-readable storage medium having a computer program stored therein, wherein: When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 12 are implemented.
16. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 12 are implemented.
Citation Information
Patent Citations
Data acquisition method, service providing end, service using end and network function entity
CN110166502A
Service-oriented computing power network system, working method and storage medium
CN113079218A
Resource request method and device, computing power network element node and computing power application equipment
CN114095577A
Computing power sensing network, use method thereof and storage medium
CN115002681A
Subscription for Communication Attributes
US20170295209A1
