Energy consumption and carbon emissions calculation method and device for intelligent computing services in data centers

Abstract

One or more embodiments of the present specification provide a method and device for calculating energy consumption and carbon emissions of intelligent computing services in a data center, wherein the method includes: determining service equipment related to a target intelligent computing service in a cloud service system, wherein the service equipment includes: non-virtualized physical hardware equipment and virtualized equipment; wherein the virtualized equipment is a virtual equipment obtained by virtualizing a physical hardware equipment based on virtualization technology; obtaining a first energy consumption of the non-virtualized physical hardware equipment, and a second energy consumption of a physical hardware equipment that serves as a host device of the virtualized equipment; calculating a third energy consumption of the first energy consumption used for the target intelligent computing service, and a fourth energy consumption of the second energy consumption used for the target intelligent computing service; and calculating the carbon emissions of the target intelligent computing service based on the third energy consumption and the fourth energy consumption.

Description

Technical Field

[0001] One or more embodiments of the present specification relate to the field of resource management technology, and in particular, to a method and device for calculating energy consumption and carbon emissions of intelligent computing services in a data center. Background Art

[0002] Cloud service systems used to support intelligent computing services have become an important part of the "new infrastructure". For example, intelligent computing services can be provided to enterprises and organizations by building Internet Data Centers (IDCs). As the demand for intelligent computing services, such as artificial intelligence (AI) and big data, continues to grow, the energy consumption and carbon emissions of cloud computing systems are also increasing.

[0003] In order to better manage the carbon emissions generated by cloud service systems, participate in carbon market transactions, and develop related carbon products, relevant technologies have proposed some methods for calculating the carbon emissions of cloud service systems. However, these methods are all for the overall energy consumption and overall carbon emissions of the entire cloud service system (such as IDC), and do not support the calculation of the carbon emissions that need to be shared by the single intelligent computing service it provides. Summary of the invention

[0004] In view of this, one or more embodiments of this specification provide the following technical solutions:

[0005] According to a first aspect of one or more embodiments of this specification, a method for calculating energy consumption and carbon emissions of an intelligent computing service of a data center is proposed, which is applied to a server corresponding to a cloud service system that provides intelligent computing services. The method includes:

[0006] Determine a service device related to the target intelligent computing service in the cloud service system, wherein the service device includes: a non-virtualized physical hardware device and a virtualized device; wherein the virtualized device is a virtual device obtained by virtualizing the physical hardware device based on virtualization technology;

[0007] Acquire a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of a physical hardware device that is a host device of the virtualized device;

[0008] Calculate and obtain a third energy consumption used for the target intelligent computing service in the first energy consumption, and a fourth energy consumption used for the target intelligent computing service in the second energy consumption;

[0009] Based on the third energy consumption and the fourth energy consumption, the carbon emissions of the target intelligent computing service are calculated.

[0010] According to a second aspect of one or more embodiments of this specification, a carbon emissions accounting device is provided, comprising:

[0011] A device determination module is used to determine a service device related to a target intelligent computing service in a cloud service system, wherein the service device includes: a non-virtualized physical hardware device and a virtualized device; wherein the virtualized device is a virtual device obtained by virtualizing a physical hardware device based on virtualization technology;

[0012] An energy consumption collection module, used to obtain a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of a physical hardware device that is a host device of the virtualized device;

[0013] an energy consumption calculation module, configured to calculate a third energy consumption used for the target intelligent computing service in the first energy consumption, and a fourth energy consumption used for the target intelligent computing service in the second energy consumption;

[0014] The carbon emission accounting module is used to calculate the carbon emissions of the target intelligent computing service based on the third energy consumption and the fourth energy consumption.

[0015] According to a third aspect of one or more embodiments of this specification, an electronic device is proposed, comprising: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in the first aspect by running the executable instructions.

[0016] According to a fourth aspect of one or more embodiments of the present specification, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0017] According to a fifth aspect of one or more embodiments of this specification, a computer program product is proposed, comprising a computer program / instruction, which implements the steps of the method described in the first aspect when executed by a processor.

[0018] It can be seen from the above embodiments that this specification obtains the energy consumption of non-virtualized physical hardware devices and virtualized devices related to intelligent computing services respectively, and combines the characteristics of these two types of devices to calculate their actual energy consumption in intelligent computing services, so as to accurately evaluate the energy consumption of a single intelligent computing service and calculate the corresponding carbon emissions. In this way, not only can we have an in-depth understanding of the carbon emissions generated by the cloud service system, but also strengthen the effective management of carbon emissions. At the same time, it can also provide users with carbon emission bills related to the intelligent computing services they use, which is helpful for participating in carbon market transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1It is a schematic diagram of the architecture of a carbon emission accounting service system provided by an exemplary embodiment.

[0020] Figure 2 It is a flowchart of a method for calculating energy consumption and carbon emissions of intelligent computing services in a data center provided by an exemplary embodiment.

[0021] Figure 3 It is a schematic diagram of the composition of carbon emissions provided by an exemplary embodiment.

[0022] Figure 4 It is a structural schematic diagram of a device provided by an exemplary embodiment.

[0023] Figure 5 It is a block diagram of an energy consumption and carbon emission accounting device for intelligent computing services in a data center provided by an exemplary embodiment. DETAILED DESCRIPTION

[0024] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this manual are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0025] The cloud service system used to support intelligent computing services has become an important part of the "new infrastructure". For example, intelligent computing services can be provided to enterprises and organizations by building IDCs. As the demand for intelligent computing services, such as AI and big data, continues to grow, the energy consumption and carbon emissions of cloud computing systems are also increasing.

[0026] In order to better manage the carbon emissions generated by cloud service systems, participate in carbon market transactions, and develop related carbon products, relevant technologies have proposed some methods for calculating the carbon emissions of cloud service systems. However, these accounting methods are all for the overall energy consumption and overall carbon emissions of the entire cloud service system (such as IDC). For example, by dividing the entire life cycle of IDC into multiple stages, the energy consumption and corresponding carbon emissions of different stages are obtained; or an energy consumption and carbon emissions accounting system including energy consumption monitoring and carbon emissions accounting modules is constructed, etc. It can be seen that the same technology does not support the calculation of the carbon emissions that need to be shared by a single intelligent computing service, and cannot support cloud service operators to provide users with corresponding carbon emissions bills.

[0027] In view of this, this specification proposes a method for calculating the energy consumption and carbon emissions of intelligent computing services in a data center. Based on the characteristics of intelligent computing services, the service equipment related to the intelligent computing service is divided into non-virtualized physical hardware equipment and virtualized equipment, and the corresponding energy consumption is obtained respectively, and the energy consumption used for the intelligent computing service is calculated in the obtained energy consumption, and then the carbon emissions of the intelligent computing service are calculated based on the calculated energy consumption.

[0028] During implementation, the service equipment related to the intelligent computing service in the cloud service system can be determined first, and the service equipment can include: non-virtualized physical hardware equipment and virtualized equipment; obtain the first energy consumption of the non-virtualized physical hardware equipment, and the second energy consumption of the physical hardware device that serves as the host device of the virtualized device; then, calculate the third energy consumption and the fourth energy consumption for the target intelligent computing service from the obtained first energy consumption and the second energy consumption respectively; and then, the carbon emissions of the target intelligent computing service can be calculated based on the third energy consumption and the fourth energy consumption.

[0029] In the above technical solution, by obtaining the energy consumption of non-virtualized physical hardware devices and virtualized devices related to intelligent computing services respectively, and combining the characteristics of these two types of devices, the energy consumption they actually consume in intelligent computing services is calculated, so that the energy consumption of a single intelligent computing service can be accurately evaluated and the corresponding carbon emissions can be calculated. In this way, not only can we have an in-depth understanding of the carbon emissions generated by the cloud service system, but we can also strengthen the effective management of carbon emissions. At the same time, it can also provide users with carbon emission bills related to the intelligent computing services they use, which is helpful for participating in carbon market transactions.

[0030] Figure 1 FIG. 1 is a schematic diagram of the architecture of an energy consumption and carbon emission accounting service system for a data center intelligent computing service provided by an exemplary embodiment. Figure 1 As shown, the system may include a server 11, a network 12, and several electronic devices, such as a PC (Personal Computer) 13, a mobile phone 14, and the like.

[0031] The server 11 may be a physical server including an independent host, or the server 11 may be a virtual server carried by a host cluster. During operation, the server 11 may run a server-side program of a certain application to implement the relevant functions of the application. For example, when the server 11 runs a program of a carbon emission accounting service, it may be implemented as a corresponding carbon emission accounting server or cloud service platform.

[0032] PC13 and mobile phone 14 are only some types of electronic devices that users can use. In fact, users can obviously also use electronic devices such as the following types: tablet devices, laptops, PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), etc., and one or more embodiments of this specification do not limit this. During operation, the electronic device can run a program on the client side of a certain application to implement the relevant functions of the application. For example, when the electronic device runs a program for a carbon emissions accounting service, it can be implemented as a client of the carbon emissions accounting service. Among them, the client application of the above-mentioned carbon emissions accounting service can be started and run on the electronic device. The program on the client side can be a native application installed on the electronic device, or the program on the client side can be a small program, a quick application or other similar forms. Of course, when using web page technologies such as HTML5 or similar, the relevant functions can be implemented through the page displayed by the browser. The browser here can be an independent browser application or a browser module embedded in certain applications.

[0033] As for the network 12 for interaction between electronic devices such as PC 13 and mobile phone 14 and server 11, it is possible to select a wired or wireless network to achieve communication based on the communication mode supported by the corresponding electronic device, and this specification does not limit this. For example, PC 13 can support both wired and wireless communication, so it can use a wired or wireless network to achieve communication as needed, while mobile phone 14 usually only supports wireless communication, so it can use a wireless network to achieve communication.

[0034] In order to enable those skilled in the art to better understand the technical solutions in the present application, the technical solutions in this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0035] See also Figure 2 , Figure 2 An exemplary embodiment provides a method for calculating energy consumption and carbon emissions of intelligent computing services in a data center. The method can be applied to a cloud service platform corresponding to a cloud service system that provides intelligent computing services, or can also be applied to a terminal or server that executes the method.

[0036] The cloud service system may refer to a collection of various computing resources and services provided through the Internet. The cloud service system may provide intelligent computing services to users, including providing various physical infrastructure equipment, hosting services, data management, etc. required for intelligent computing services. In one embodiment, the cloud service system may include an Internet data center IDC, which may provide the necessary physical environment and resources for intelligent computing services.

[0037] The intelligent computing services provided by the cloud service system may include a variety of service forms including infrastructure, platform, software, and various professional computing services. For example, in one embodiment, the intelligent computing services may include intelligent computing services. Intelligent computing services may use technologies such as AI and machine learning (ML) to help users handle complex data analysis tasks, automated processes, and intelligent decision-making. For example, they may include the following types: machine learning services, natural language processing, computer vision, predictive analysis, intelligent automation, and so on.

[0038] For the sake of simplicity, in the following embodiments, IDC may be used as a cloud service system and the intelligent computing service may be used as an example for illustration.

[0039] The carbon emission accounting method provided in the present application may be a carbon emission accounting method for the intelligent computing service provided by the cloud service system. The method may include the following steps.

[0040] S201. Determine service equipment related to the target intelligent computing service in the cloud service system, where the service equipment includes: non-virtualized physical hardware equipment and virtualized equipment.

[0041] In one embodiment, service devices related to the target intelligent computing service are determined from the service devices of the cloud service system. Among them, the service devices related to the target intelligent computing service may refer to devices that directly or indirectly support the target intelligent computing service (cloud computing service), and can provide basic functions such as computing, storage, and networking, or carry virtualized resources, management tools, etc. For example, they may include information technology (IT) equipment, etc. According to the characteristics of the equipment, the service devices related to the target intelligent computing service can be divided into non-virtualized devices and virtualized devices, among which non-virtualized devices are non-virtualized physical hardware devices that can be directly used to run operating systems and applications without any abstraction layer or virtualization technology, for example, they can be an independent computer or server; virtualized devices are virtual devices obtained by virtualizing physical hardware devices based on virtualization technology, and can be logical or software model environments created based on virtualization technology.

[0042] S202: Obtain a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of a physical hardware device that is a host device of the virtualized device.

[0043] After determining the service equipment related to the target intelligent computing service, the first energy consumption of the non-virtualized device and the second energy consumption of the virtualized device can be obtained respectively; wherein, the first energy consumption of the non-virtualized device can be the first energy consumption of the non-virtualized physical hardware device, for example, it can include the first energy consumption of physical hardware devices such as non-virtualized processors, network devices, storage devices, etc.; the second energy consumption of the virtualized device can be the second energy consumption of the physical hardware device of the host device of the virtualized device, for example, it can include the second energy consumption corresponding to the processor, network device, storage device, etc. of the host device.

[0044] It should be noted that the energy consumption mentioned in this specification may include power consumption.

[0045] S203: Calculate and obtain a third energy consumption used for a target intelligent computing service in the first energy consumption, and a fourth energy consumption used for the target intelligent computing service in the second energy consumption.

[0046] Since other intelligent computing services besides the target intelligent computing service may be deployed on the non-virtualized physical hardware devices and virtualized host devices related to the target intelligent computing service, it is necessary to judge the deployment of these service devices and calculate the energy consumption that needs to be borne by the target intelligent computing service.

[0047] For non-virtualized physical hardware devices, you can first determine whether other intelligent computing services are deployed on the non-virtualized physical hardware devices; if so, you need to calculate the portion used for the target intelligent computing service from the first energy consumption, that is, the third energy consumption; if not, you can regard the first energy consumption as the third energy consumption of the target intelligent computing service. For example, if a physical server processes computing tasks of multiple intelligent computing services (including the target intelligent computing service) at the same time, the first energy consumption of the physical server needs to be allocated according to the actual operating conditions, and the portion borne by the target intelligent computing service, that is, the third energy consumption, is calculated from it.

[0048] For the host device of the virtualized device, you can first determine whether other intelligent computing services are deployed on the host device; if so, you need to calculate the part used for the target intelligent computing service from the second energy consumption, that is, the fourth energy consumption; if not, the second energy consumption can be regarded as the fourth energy consumption of the target intelligent computing service. For example, a host device runs multiple virtual machines, each of which is assigned to a different intelligent computing service (including the target intelligent computing service). The second energy consumption of the host device needs to be allocated according to the actual operation of the virtual machine, and the part that needs to be borne by the virtual machine of the target intelligent computing service, that is, the fourth energy consumption, is calculated.

[0049] S204. Based on the third energy consumption and the fourth energy consumption, calculate the carbon emissions of the target intelligent computing service.

[0050] After obtaining the third energy consumption and the fourth energy consumption corresponding to the target intelligent computing service, the energy consumption of the service equipment required for the target intelligent computing service during its operation can be calculated based on the third energy consumption and the fourth energy consumption, and then the carbon emissions of the target intelligent computing service can be calculated.

[0051] For example, it is determined that the service devices related to the target intelligent computing service s include: non-virtualized physical hardware devices NV1 and NV2, and virtualized devices deployed on the host device V1, wherein the physical hardware devices of the host device V1 include: VH1 and VH2; obtain the first energy consumptions P1 and P2 corresponding to NV1 and NV2, and the second energy consumptions P3 and P4 corresponding to VH1 and VH2; it is determined that only the target intelligent computing service is deployed on NV1, and multiple intelligent computing services are deployed on NV2, then the third energy consumption for the target intelligent computing service s in P2 can be calculated as E 1-2 , the total third energy consumption of the target intelligent computing service s is E1= P1+ E 1-2 ; Determine that in addition to the target intelligent computing service, two intelligent computing services are deployed on the host device V1. Then, the fourth energy consumption for the target intelligent computing service s in P3 and P4 can be calculated as E 2-3 and E 2-4 , the total fourth energy consumption of the target intelligent computing service s is E2 = E 2-3 + E 2-4 ; Based on E1 and E2, the total energy consumption required for the intelligent computing service can be further calculated, and the carbon emissions of the target intelligent computing service can be calculated.

[0052] In the above technical solution, by obtaining the energy consumption of non-virtualized physical hardware devices and virtualized devices related to intelligent computing services respectively, and combining the characteristics of these two types of devices, the energy consumption they actually consume in intelligent computing services is calculated, so that the energy consumption of a single intelligent computing service can be accurately evaluated and the corresponding carbon emissions can be calculated. In this way, not only can we have an in-depth understanding of the carbon emissions generated by the cloud service system, but we can also strengthen the effective management of carbon emissions. At the same time, it can also provide users with carbon emission bills related to the intelligent computing services they use, which is helpful for participating in carbon market transactions.

[0053] In some embodiments, the energy consumption of physical hardware devices can be divided into static components and dynamic components. The static component represents the basic energy consumed by the corresponding physical hardware device during operation. This part of the energy consumption can be considered as the minimum energy consumption of the physical hardware device in standby or idle state, and is mainly used to maintain the basic branches of the physical hardware device and support the functions of its internal components; the dynamic component represents the computing energy consumed by the corresponding physical hardware device when responding to intelligent computing services. This part of the energy consumption can be considered to be directly related to the actual workload of the physical hardware device, and increases with the complexity and load of the computing task, including the energy consumption required for operations such as data processing, storage access, and network communication.

[0054] When calculating the energy consumption used for the target intelligent computing service in the energy consumption of the hardware physical device, different calculation methods can be used for the static component and the dynamic component to respectively calculate the static component of the energy consumption used for the target intelligent computing service in the static component of the energy consumption of the hardware physical device and the dynamic component of the energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the hardware physical device, and then combine them to obtain the energy consumption used for the target intelligent computing service.

[0055] For non-virtualized physical hardware devices related to the target intelligent computing service, if the non-virtualized physical hardware devices are deployed with multiple intelligent computing services, the static component of the third energy consumption used for the target intelligent computing service in the static component of the first energy consumption and the dynamic component of the third energy consumption used for the target intelligent computing service in the dynamic component of the first energy consumption can be calculated separately, and then the static component and dynamic component of the third energy consumption are merged to obtain the third energy consumption used for the target intelligent computing service.

[0056] For virtualization devices related to the target intelligent computing service, if multiple intelligent computing services are deployed on the host device of the virtualization device, the static component of the fourth energy consumption used for the target intelligent computing service in the static component of the second energy consumption and the dynamic component of the fourth energy consumption used for the target intelligent computing service in the dynamic component of the second energy consumption can be calculated separately, and then the static component and dynamic component of the fourth energy consumption are merged to obtain the fourth energy consumption used for the target intelligent computing service.

[0057] Among them, the main allocation principles for static components and dynamic components can include: all intelligent computing services deployed on physical hardware devices share the static component of the energy consumption of the physical hardware devices; all intelligent computing services that are responding to user requests share the dynamic component of the energy consumption of the physical hardware devices. The allocation standard can be the size of the allocated resources and the size of the actually used resources. For example, for a processor, the allocated and actually used resources can be the computing power consumption; for a network device, the allocated and actually used resources can be the bandwidth; for a storage device, the allocated and actually used resources are the storage space.

[0058] In practical applications, the amount of computing power consumption can be measured by some metrics related to computing power. For example, in one example, the amount of computing power consumption can be expressed by the number of CPU milli-cores consumed. In another example, the amount of computing power consumption can also be expressed by the amount of GPU memory occupied.

[0059] In the above embodiment, the static component and dynamic component of the energy consumption of the physical hardware device can be determined by using targeted calculation methods to calculate the static component and dynamic component of the energy consumption used for the target intelligent computing service, and then merge them into the energy consumption of the target intelligent computing service, so that the energy consumption of the target intelligent computing service can be calculated more accurately, and the calculated carbon emissions of the target intelligent computing service can be made more accurate.

[0060] In some embodiments, the types of physical hardware devices (such as IT equipment) may be various, for example, they may include processors, network devices, storage devices, etc. Among them, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a tensor processing unit (TPU), a neural network processing unit (NPU), etc.; the network device may include a router, a switch, etc.; the storage device may include a hard disk drive, a solid state drive, etc.

[0061] Accordingly, the energy consumption of the physical hardware device may include: processor energy consumption corresponding to the processor, network device energy consumption corresponding to the network device, and storage device energy consumption corresponding to the storage device.

[0062] In one embodiment, non-virtualized physical hardware devices may include: processors, network devices, storage devices, etc.; their corresponding first energy consumption may include the first processor energy consumption corresponding to the processor, the first network device energy consumption corresponding to the network device, and the first storage device energy consumption corresponding to the storage device.

[0063] Correspondingly, for different device types:

[0064] If the non-virtualized physical hardware device includes a processor, the energy consumption of a third processor used for the target intelligent computing service in the energy consumption of the first processor can be calculated;

[0065] If the non-virtualized physical hardware device includes a network device, the energy consumption of a third network device used for the target intelligent computing service in the energy consumption of the first network device can be calculated;

[0066] If the non-virtualized physical hardware device includes a storage device, the energy consumption of the third storage device used for the target intelligent computing service in the energy consumption of the first storage device can be calculated.

[0067] Before performing the above calculations, you can first determine whether the non-virtualized physical hardware device is deployed with other intelligent computing services; if not, the first processor energy consumption can be used as the third processor energy consumption, the first network device energy consumption can be used as the third network device energy consumption, and the first storage device energy consumption can be used as the third storage device energy consumption.

[0068] In one embodiment, the physical hardware devices of the host device of the virtualized device may include: a processor, a network device, a storage device, etc.; the corresponding second energy consumption may include a second processor energy consumption corresponding to the processor, a second network device energy consumption corresponding to the network device, and a second storage device energy consumption corresponding to the storage device.

[0069] Correspondingly, for different device types:

[0070] If the host device includes a processor, the second processor energy consumption and the fourth processor energy consumption used for the target intelligent computing service in the second processor energy consumption can be calculated;

[0071] If the host device includes a network device, the second processor energy consumption, the fourth processor energy consumption, and the fourth network device energy consumption used for the target intelligent computing service in the second network device energy consumption can be calculated;

[0072] The host device includes a processor, and the second processor energy consumption and the fourth storage device energy consumption used for the target intelligent computing service in the second processor energy consumption can be calculated.

[0073] The method for calculating the energy consumption for the target intelligent computing service from the energy consumption of the physical hardware device can be set according to the actual situation. Different calculation methods can be used for different device types, energy consumption categories, etc. Different calculation methods can also be used based on whether it is used to deploy virtualized devices. For example, the corresponding calculation method can be determined based on one or more combinations of the deployment time, resource usage ratio, and response time ratio of multiple intelligent computing services deployed on the physical hardware device.

[0074] In one implementation, for a processor, the energy consumption used for the target intelligent computing service in the processor energy consumption may be calculated based on the computing power consumption used by the target intelligent computing service.

[0075] Among them, for the static component of processor energy consumption, the static component of processor energy consumption used for the target intelligent computing service in the static component of processing energy consumption can be calculated based on the ratio of the computing power consumption used by the target intelligent computing service to the total computing power consumption of the processor;

[0076] For the dynamic component of processor energy consumption, the dynamic component of processor energy consumption used for the target intelligent computing server can be calculated based on the ratio of the computing power consumption used by the target intelligent computing service to the sum of the computing power consumption used by all intelligent computing services deployed on the processor.

[0077] In one implementation, for a network device, the energy consumption for the target intelligent computing service in the energy consumption of the network device may be calculated based on the bandwidth allocated for the target intelligent computing service and the actually used bandwidth.

[0078] Among them, for the static component of network device energy consumption, the static component of network device energy consumption used for the target intelligent computing service in the static component of network device energy consumption can be calculated based on the ratio of the maximum bandwidth provided by the network device to the target intelligent computing service and the total bandwidth of the network device;

[0079] For the dynamic component of network device energy consumption, the dynamic component of network device energy consumption used for the target intelligent computing service can be calculated by the ratio of the bandwidth used by the target intelligent computing service and the sum of the bandwidth used by all intelligent computing services deployed on the network device.

[0080] In one implementation, for a storage device, the energy consumption for the target intelligent computing service in the energy consumption of the storage device may be calculated based on the storage space allocated for the target intelligent computing service and the storage space actually used.

[0081] Among them, for the static component of the energy consumption of the storage device, the static component of the energy consumption of the storage device used for the target intelligent computing service in the static component of the energy consumption of the storage device can be calculated based on the ratio of the maximum storage space provided by the storage device to the target intelligent computing service and the total storage space of the storage device;

[0082] For the dynamic component of storage device energy consumption, the dynamic component of storage device energy consumption used for the target intelligent computing service can be calculated based on the ratio of the storage space used by the target intelligent computing service and the sum of the storage space used by all intelligent computing services deployed on the storage device.

[0083] In some embodiments, if the non-virtualized physical hardware device includes a processor, the first energy consumption may include the first processor energy consumption of the processor, and the third energy consumption may include the third processor energy consumption; when it is determined that the processor is deployed with other intelligent computing services in addition to the target intelligent computing service, the following calculation process may be performed for the static component and the dynamic component of the first processor energy consumption respectively:

[0084] Based on the ratio of the computing power consumption used by the target intelligent computing service to the total computing power consumption of the processor in the processor, calculate the static component of the energy consumption of the third processor used for the target intelligent computing service in the static component of the energy consumption of the first processor;

[0085] Based on the ratio of the computing power consumption used by the target intelligent computing service to the sum of the computing power consumption used by all intelligent computing services deployed on the processor, the dynamic component of the energy consumption of the third processor for the target intelligent computing service in the dynamic component of the energy consumption of the first processor is calculated;

[0086] By adding the static component and the dynamic component of the third processor energy consumption, the third processor energy consumption of the target intelligent computing service can be obtained.

[0087] In some embodiments, if the non-virtualized physical hardware device includes a network device, the first energy consumption may include the first network device energy consumption of the network device, and the third energy consumption includes the third network device energy consumption; when it is determined that the network device is deployed with other intelligent computing services in addition to the target intelligent computing service, the following calculation process may be performed for the static component and the dynamic component of the energy consumption of the first network device respectively:

[0088] Based on the ratio of the maximum bandwidth provided to the target intelligent computing service in the network device and the total bandwidth of the network device, calculate the static component of the energy consumption of the third network device used for the target intelligent computing service in the static component of the energy consumption of the first network device;

[0089] Based on the ratio of the bandwidth used by the target intelligent computing service and the sum of the bandwidths used by all intelligent computing services deployed on the network device, calculate the dynamic component of the energy consumption of the third network device used for the target intelligent computing service in the dynamic component of the energy consumption of the first network device;

[0090] By adding the static component and the dynamic component of the energy consumption of the third network device, the energy consumption of the third network device for the target intelligent computing service can be obtained.

[0091] In some embodiments, if the non-virtualized physical hardware device includes a storage device, the first energy consumption includes the first storage device energy consumption of the storage device, and the third energy consumption includes the third storage device energy consumption; when it is determined that the storage device is deployed with other intelligent computing services in addition to the target intelligent computing service, the following calculation process can be performed for the static component and the dynamic component of the energy consumption of the first storage device respectively:

[0092] Based on the ratio of the maximum storage space provided to the target intelligent computing service and the total storage space of the storage device in the storage device, calculate the static component of the energy consumption of the third storage device used for the target intelligent computing service in the static component of the energy consumption of the first storage device;

[0093] Based on the ratio of the storage space used by the target intelligent computing service and the sum of the storage spaces used by all intelligent computing services deployed on the storage device, calculate the dynamic component of the energy consumption of the third storage device used for the target intelligent computing service in the dynamic component of the energy consumption of the first storage device;

[0094] By adding the static component and the dynamic component of the energy consumption of the third storage device, the energy consumption of the third storage device of the target intelligent computing service can be obtained.

[0095] In some embodiments, when the physical hardware devices of the non-virtualized device of the target intelligent computing service include a processor, a network device, and a storage device, the energy consumption of the third processor can be calculated by the above calculation method. 3. Energy consumption of network equipment and the third storage device energy consumption ; Based on the third processor energy consumption 3. Energy consumption of network equipment and the third storage device energy consumption The third energy consumption of the target intelligent computing service is calculated .

[0096] In some embodiments, if the host device includes a processor, the second energy consumption may include the second processor energy consumption of the processor, and the fourth energy consumption may include the fourth processor energy consumption; when it is determined that the host device is deployed with other intelligent computing services in addition to the target intelligent computing service, the following calculation process may be performed for the static component and the dynamic component of the second processor energy consumption respectively:

[0097] Based on the ratio of the computing power consumption used by the target intelligent computing service to the total computing power consumption of the processor in the processor, the static component of the fourth processor energy consumption used for the target intelligent computing service in the static component of the second processor energy consumption is calculated; wherein the computing power consumption used by the intelligent computing service may refer to the computing power consumption used by the virtualization device of the intelligent computing service;

[0098] Based on the ratio of the computing power consumption used by the target intelligent computing service to the sum of the computing power consumption used by all intelligent computing services deployed on the processor, the dynamic component of the fourth processor energy consumption used for the target intelligent computing service in the dynamic component of the second processor energy consumption is calculated;

[0099] By adding the static component and the dynamic component of the fourth processor energy consumption, the fourth processor energy consumption of the target intelligent computing service can be obtained.

[0100] In one implementation, the calculation formula for the energy consumption of the fourth processor can be expressed as follows:

[0101]

[0102] in, represents the energy consumption of the fourth processor; g represents the device number of the processor, and j represents the service number of the intelligent computing service; represents the set of intelligent computing services j deployed on processor g; Indicates the computing power consumption used by the target intelligent computing service s in processor g, Indicates the total amount of computing power consumed by processing device g, Indicates the computing power consumption of intelligent computing service j in processor g; represents the second processor energy consumption of processor g, represents the static component of the second processor's energy consumption, Represents the dynamic component of the energy consumption of the second processor.

[0103] In one implementation, if the host device includes a network device, the second energy consumption may include the second network device energy consumption of the network device, and the fourth energy consumption may include the fourth network device energy consumption; when it is determined that the host device is deployed with other intelligent computing services other than the target intelligent computing service, the following calculation process may be performed for the static component and the dynamic component of the second network device energy consumption respectively:

[0104] Based on the ratio of the maximum bandwidth provided to the target intelligent computing service and the total bandwidth of the network device in the network device, the static component of the energy consumption of the third network device used for the target intelligent computing service in the static component of the energy consumption of the first network device is calculated; wherein the maximum bandwidth provided to the intelligent computing service may be the maximum bandwidth of the virtualized device provided to the intelligent computing service;

[0105] Based on the ratio of the bandwidth used by the target intelligent computing service and the sum of the bandwidths used by all intelligent computing services deployed on the network device, the dynamic component of the energy consumption of the fourth network device used for the target intelligent computing service in the dynamic component of the energy consumption of the second network device is calculated; wherein the bandwidth used by the intelligent computing service may refer to the bandwidth used by the virtualized device of the intelligent computing service;

[0106] By adding the static component and the dynamic component of the energy consumption of the fourth network device, the energy consumption of the fourth network device for the target intelligent computing service can be obtained.

[0107] In one implementation, the calculation formula for the energy consumption of the fourth network device can be expressed as follows:

[0108]

[0109] in, represents the energy consumption of the fourth network device; n represents the device number of the network device, and j represents the service number of the intelligent computing service; represents the set of intelligent computing services j deployed on network device n; Indicates the maximum bandwidth provided by network device n to the target intelligent computing service s, Indicates the total bandwidth of network device n; Indicates the bandwidth used by the target intelligent computing service s in the network device n. Indicates the bandwidth used by intelligent computing service j in network device n; represents the energy consumption of the second network device of network device n, represents the static component of the energy consumption of the second network device, The dynamic component representing the energy consumption of the second network device.

[0110] In one implementation, if the host device includes a storage device, the second energy consumption includes the second storage device energy consumption of the storage device, and the fourth energy consumption includes the fourth storage device energy consumption; when it is determined that the host device is deployed with other intelligent computing services in addition to the target intelligent computing service, the following calculation process may be performed for the static component and the dynamic component of the second storage device energy consumption respectively:

[0111] Based on the ratio of the maximum storage space provided to the target intelligent computing service and the total storage space of the storage device in the storage device, the static component of the energy consumption of the fourth storage device used for the target intelligent computing service in the static component of the energy consumption of the second storage device is calculated; wherein the maximum storage space provided to the target intelligent computing service may refer to the maximum storage space of the virtualized device provided to the intelligent computing service;

[0112] Based on the ratio of the storage space used by the target intelligent computing service and the sum of the storage spaces used by all intelligent computing services deployed on the storage device, the dynamic component of the energy consumption of the fourth storage device used for the target intelligent computing service in the dynamic component of the energy consumption of the second storage device is calculated; wherein the storage space used by the intelligent computing service may refer to the storage space used by the virtualized device of the intelligent computing service;

[0113] By adding the static component and the dynamic component of the energy consumption of the fourth storage device, the energy consumption of the fourth storage device of the target intelligent computing service can be obtained.

[0114] In one implementation, the calculation formula for the energy consumption of the fourth storage device can be expressed as follows:

[0115]

[0116] in, represents the energy consumption of the fourth storage device; d represents the device number of the storage device, and j represents the service number of the intelligent computing service; represents the set of intelligent computing services j deployed on storage device d; Indicates the maximum storage space provided by storage device d to the target intelligent computing service s. Represents the total storage space of storage device n; Indicates the storage space used by the target intelligent computing service s in the storage device d. Indicates the storage space used by intelligent computing service j in storage device d; represents the second storage device energy consumption of storage device d, represents the static component of the energy consumption of the second storage device, Represents the dynamic component of energy consumption of the second storage device.

[0117] In one embodiment, when the host device of the virtualization device of the target intelligent computing service includes a processor, a network device, and a storage device, the fourth processor energy consumption can be calculated by the above calculation method. 4. Network equipment energy consumption and the fourth storage device energy consumption ; Based on the fourth processor energy consumption 4. Network equipment energy consumption and the fourth storage device energy consumption The fourth energy consumption of the target intelligent computing service is calculated .

[0118] In the above embodiment, corresponding calculation methods are designed for different device types and energy consumption types to accurately calculate the energy consumption of physical hardware devices in the target intelligent computing service, so that the obtained calculation results can better reflect the actual use of the equipment, thereby improving the accuracy of the energy consumption calculation results, and helping to improve the accuracy of energy consumption and carbon emissions accounting.

[0119] In some embodiments, the carbon emissions of the target intelligent computing service, in addition to being related to the energy consumption of the service equipment used by the target intelligent computing service during operation, may also be related to the carbon emissions generated by the basic operating equipment of the cloud service system and the carbon emissions generated by the operation and maintenance personnel. Among them, the basic operating equipment can be equipment unrelated to computing services, such as refrigeration equipment, power generation equipment, and other non-IT equipment, etc. The carbon emissions generated by the operation and maintenance personnel may include the carbon emissions generated by the commuting facilities and maintenance equipment used by the operation and maintenance personnel during their commuting and equipment maintenance.

[0120] Based on different equipment types, commuting facilities, etc., the carbon emissions statistical method corresponding to the equipment type can be pre-set.

[0121] In some embodiments, if the basic operating equipment includes refrigeration equipment, its carbon emissions can be counted based on the dissipation of the refrigerant. Carbon emission factors corresponding to different refrigerant types can be set to calculate the carbon emissions of the refrigeration equipment based on the dissipation of the refrigerant. The specific formula can be expressed as follows:

[0122]

[0123] in, represents the carbon emissions of the refrigeration equipment, r represents the type number of the refrigerant type, represents the carbon emission factor corresponding to the refrigerant type r, Indicates the amount of refrigerant of refrigerant type r that escapes.

[0124] In some embodiments, if the basic operating equipment includes power generation equipment, its carbon emissions can be counted based on the energy consumption of the power generation equipment. Carbon emission factors corresponding to different energy types can be set to calculate the carbon emissions of the power generation equipment based on the amount of energy consumed or the energy generated. The specific formula can be expressed as follows:

[0125]

[0126] in, represents the carbon emissions of power generation equipment, d represents the type number of power generation equipment, Indicates the carbon emission factor corresponding to the energy generated by type d power generation equipment (for example, the carbon emission corresponding to the unit of electricity, the unit can be expressed as kgCO2 / kWh), Indicates the energy generated by type d power generation equipment.

[0127] In some embodiments, if the basic operating equipment includes other non-IT equipment, the carbon emissions of the non-IT equipment can be calculated based on the energy consumption of the non-IT equipment based on a preset carbon emission factor corresponding to the energy consumption; the specific formula can be expressed as follows:

[0128]

[0129] in, represents the carbon emissions of non-IT equipment, f represents the carbon emission factor corresponding to energy consumption, Indicates the energy consumption used by non-IT equipment.

[0130] The carbon emissions of basic operating equipment can be calculated by adding the carbon emissions of refrigeration equipment, power generation equipment, and non-IT equipment. The specific formula can be expressed as follows:

[0131]

[0132] After calculating the carbon emissions of the basic operating equipment, the carbon emissions of the basic operating equipment can be further calculated based on the first allocation coefficient k1. The first carbon emission that needs to be shared by the target intelligent computing service ; Wherein, the calculation method of the first allocation coefficient k1 can be set according to actual needs, for example, it can be calculated based on one or more of the deployment time of the target intelligent computing service, the actual operation time, the number of resources used, and the energy consumption used. In one embodiment, the first allocation coefficient can represent the ratio of the service equipment energy consumption of the target intelligent computing service to the total energy consumption of the service equipment of the data center; wherein, the total energy consumption of the service equipment can refer to the total energy consumption of all service equipment in the cloud service system, or it can be the sum of the energy consumption used by all intelligent computing services provided by the cloud service system, and so on.

[0133] In some embodiments, the carbon emissions generated by the operation and maintenance personnel can be calculated by counting the commuting methods and distances of each operation and maintenance personnel, and a pre-set carbon emission factor corresponding to the commuting method; the specific formula can be expressed as follows:

[0134]

[0135] in, represents the carbon emissions generated by the operation and maintenance personnel, t represents the commuting mode, represents the carbon emission factor corresponding to commuting mode t, Represents the total distance corresponding to commuting mode t.

[0136] After calculating the carbon emissions generated by the operation and maintenance personnel, the carbon emissions of the operation and maintenance personnel can be further calculated based on the second allocation coefficient k2. The second carbon emission amount that needs to be shared by the target intelligent computing service s ; The calculation method of the second apportionment coefficient k2 can be set according to actual needs. For example, it can be calculated based on one or more of the deployment time, actual operation time, number of resources used, and energy consumption of the target intelligent computing service. In one embodiment, the second apportionment coefficient represents the ratio of the number of working hours of the operation and maintenance personnel for the target intelligent computing service to the total number of working hours of the operation and maintenance personnel.

[0137] After calculating the third energy consumption and the fourth energy consumption of the target intelligent computing service, the service equipment energy consumption of the target intelligent computing service can be calculated based on the sum of the third energy consumption and the fourth energy consumption, and further based on the carbon emission factor corresponding to the energy consumption, the third carbon emission corresponding to the service equipment energy consumption can be calculated. .

[0138] Then, based on the calculated first carbon emissions , Second carbon emissions and the third carbon emission corresponding to the energy consumption of the service equipment The total carbon emissions of the target intelligent computing service are calculated by summing .

[0139] In the above embodiment, through analysis, it can be determined that the target intelligent computing service also needs to consider the carbon emissions of basic operating equipment and operation and maintenance personnel. To this end, it is necessary to calculate the first carbon emissions of the carbon emissions of the basic operating equipment that are shared by the target intelligent computing service and the second carbon emissions of the carbon emissions of the operation and maintenance personnel that are shared by the target intelligent computing service, and then combine them with the third carbon emissions corresponding to the energy consumption of the service equipment of the target intelligent computing service. By combining these factors, the calculated total carbon emissions of the target intelligent computing service can be more accurate.

[0140] In some embodiments, the entire life cycle of the entire cloud service system can be divided into a construction phase, an operation phase, and a retirement phase.

[0141] During the construction phase, since the purpose of building a cloud service system is to provide infrastructure for intelligent computing services, the carbon emissions generated during the construction phase need to be recorded in the carbon emissions of the target intelligent computing service according to a certain proportion; similarly, the carbon emissions generated during the scrapping phase also need to be recorded in the carbon emissions of the target intelligent computing service according to a certain proportion.

[0142] The carbon emissions of the cloud service system during the construction phase and the carbon emissions of the cloud service system during the scrapping phase can be obtained separately.

[0143] Among them, the carbon emissions of the cloud service system during the construction phase can come from the carbon emissions generated by the production, manufacturing, transportation and installation of raw materials during the construction process. For example, in one embodiment, the carbon emissions of all current equipment in the service system over the entire life cycle can be analyzed, and the carbon emissions generated by the cloud service system during the construction phase can be calculated based on the equipment type, the number of equipment, the expected service life of the equipment, and the preset carbon emission coefficient corresponding to the equipment type, and the proportional coefficient corresponding to the equipment type during the construction phase.

[0144] After obtaining the carbon emissions of the cloud service system during the construction phase, the fourth carbon emissions allocated by the target intelligent computing service in the carbon emissions during the construction phase can be further calculated based on the fourth allocation coefficient k4. ; The calculation method of the fourth allocation coefficient k4 can be set according to actual needs. For example, it can be calculated based on one or more of the deployment time, actual operation time, number of resources used, and energy consumption of the target intelligent computing service. In one embodiment, the fourth allocation coefficient can represent the ratio of the service equipment energy consumption of the target intelligent computing service to the total service equipment energy consumption of the data center.

[0145] The carbon emissions of the cloud service system at the scrapping stage can come from the carbon emissions of the transportation, destruction and reuse of scrapped equipment. For example, in one embodiment, the carbon emissions of all the current equipment in the service system over the entire life cycle can be analyzed, and the carbon emissions generated by the cloud service system at the scrapping stage can be calculated based on the equipment type, the number of equipment, the expected service life of the equipment, and the preset carbon emission coefficient corresponding to the equipment type, and the proportional coefficient corresponding to the equipment type at the scrapping stage.

[0146] After obtaining the carbon emissions of the cloud service system at the scrapping stage, the fifth carbon emissions allocated by the target intelligent computing service in the carbon emissions at the scrapping stage can be further calculated based on the fifth allocation coefficient k5. ; The calculation method of the fifth allocation coefficient k5 can be set according to actual needs. For example, it can be calculated based on one or more of the deployment time, actual operation time, number of resources used, and energy consumption of the target intelligent computing service. In one embodiment, the fifth allocation coefficient can represent the ratio of the service equipment energy consumption of the target intelligent computing service to the total service equipment energy consumption of the data center.

[0147] For the operation phase, the first carbon emission, the second carbon emission and the third carbon emission of the target intelligent computing service can be calculated based on the calculation method in the above embodiment. Based on the sum of the first carbon emission, the second carbon emission and the third carbon emission, the sixth carbon emission that needs to be allocated to the target intelligent computing service during the operation phase can be calculated. .

[0148] Based on the sum of the fourth carbon emissions, the fifth carbon emissions and the sixth carbon emissions that need to be allocated to the target intelligent computing service during the construction stage, the operation stage and the scrapping stage, the total carbon emissions of the target intelligent computing service can be calculated.

[0149] It should be noted that, in the process of calculating the above-mentioned carbon emissions, the calculation process and sequence of each carbon emission can be designed according to actual needs, and no specific limitation is made here. For example, when calculating the third carbon emissions, the carbon emissions of each service equipment can be calculated first, and then the third carbon emissions that need to be shared by the target intelligent computing service can be obtained.

[0150] For example, in one implementation, the cloud service system is an IDC, the intelligent computing service is an intelligent computing service, and the method for calculating the carbon emissions of the intelligent computing service is as follows:

[0151] The carbon emission process of the target intelligent computing service is divided into three stages, such as Figure 3As shown in the figure, they are the construction phase, operation phase and scrapping phase respectively; the operation phase can include the development and actual operation of the target intelligent computing service, and can include the carbon emissions of the related basic operating equipment, the carbon emissions of the operation and maintenance personnel and the carbon emissions of IT equipment. Therefore, the total carbon emissions of the target intelligent computing service over its entire life cycle can be expressed by the following formula:

[0152]

[0153] in, Represents the total carbon emissions of the target intelligent computing service s throughout its life cycle; It represents the carbon emissions during the IDC construction phase; Indicates the carbon emissions of the target intelligent computing service s throughout its life cycle during the operation phase (equivalent to the sixth carbon emissions); represents the carbon emissions at the end-of-life stage of the IDC; k4 represents the fourth allocation coefficient as described above; k5 represents the fifth allocation coefficient as described above; Indicates the carbon emissions that need to be shared by the target intelligent computing service s during the construction phase (equivalent to the fourth carbon emissions); It indicates the carbon emissions that the target intelligent computing service s needs to share during the scrapping stage (equivalent to the fifth carbon emissions).

[0154] Considering that annual or monthly bills are often required when generating the carbon bill of the target intelligent computing service s, taking the annual bill as an example, the total carbon emissions of the entire life cycle of the above target intelligent computing service can be converted into the annual carbon emissions calculation formula as shown below:

[0155]

[0156] in, Represents the annual carbon emissions of the target intelligent computing service s; Represents the annual carbon emissions during the IDC construction phase; Indicates the annual carbon emissions of the target intelligent computing service s during the operation phase (equivalent to the sixth carbon emissions); It represents the annual carbon emissions during the IDC scrapping phase; Indicates the annual carbon emissions that need to be allocated to the target intelligent computing service s during the construction phase (equivalent to the fourth carbon emissions); It represents the annual carbon emissions that the target intelligent computing service s needs to share during the scrapping stage (equivalent to the fifth carbon emissions).

[0157] Annual carbon emissions during the IDC construction phase :

[0158] By analyzing the carbon emissions of all current devices in the IDC over their entire life cycle, the calculation formula for the annual carbon emissions of the cloud service system during the construction phase can be expressed as follows:

[0159]

[0160] Among them, e represents the equipment (or raw material) type number, and E represents the equipment (or raw material) type set; Indicates the quantity of equipment (or raw materials) of type e; Indicates the expected useful life of type e equipment (or raw materials); Indicates the carbon emissions of a single device (or raw material) of type e during its entire life cycle; It represents the proportion of carbon emissions during the entire life cycle of type e equipment (or raw materials) that needs to be borne during the construction phase.

[0161] Annual carbon emissions at the end-of-life stage of IDC ,Through the analysis of the carbon emissions of all current devices in the IDC over their entire life cycle, the calculation formula for the annual carbon emissions of the cloud service system at the scrapping stage can be expressed as follows:

[0162]

[0163] in, It represents the proportion coefficient of carbon emissions of type e equipment (or raw materials) during its entire life cycle that needs to be borne at the scrapping stage.

[0164] For the annual carbon emissions of the target intelligent computing service s during the operation phase :

[0165] It mainly comes from the following three parts: basic operation equipment, operation and maintenance personnel and service equipment (IT equipment). The calculation formula can be expressed as follows:

[0166]

[0167] in, Represents the annual carbon emissions of basic operating equipment; represents the annual carbon emissions of operation and maintenance personnel; represents the annual carbon emissions of the service equipment of the target intelligent computing service s (equivalent to the third carbon emissions); k1 represents the first allocation coefficient as described above; k2 represents the second allocation coefficient as described above; Indicates the annual carbon emissions that the target intelligent computing service s needs to share in the annual carbon emissions of the basic operating equipment (equivalent to the first carbon emissions); It represents the annual carbon emissions that the target intelligent computing service needs to share in the annual carbon emissions of the operation and maintenance personnel (equivalent to the second carbon emissions).

[0168] Annual carbon emissions from infrastructure operations :

[0169] It can be considered that the main sources are the following three parts: refrigeration equipment, power generation equipment and other non-IT equipment; the calculation formula can be expressed as follows:

[0170]

[0171] in, represents the annual carbon emissions of refrigeration equipment; Represents the annual carbon emissions of power generation equipment; Represents the annual carbon emissions of other non-IT equipment. The calculation formula for the annual carbon emissions of each part can be expressed as follows:

[0172]

[0173]

[0174]

[0175] Where r represents the type number of the refrigerant type, represents the carbon emission factor corresponding to the refrigerant type r, represents the amount of refrigerant dissipated by refrigerant type r; d represents the type number of power generation, represents the carbon emission factor corresponding to the energy produced by type d power generation equipment, represents the energy generated by the power generation equipment of type d; f represents the carbon emission factor corresponding to the energy consumption, Indicates the energy consumption used by non-IT equipment.

[0176] Annual carbon emissions for operation and maintenance personnel :

[0177] It can be considered that it mainly comes from the commuting mode of operation and maintenance personnel, and the calculation formula can be expressed as follows:

[0178]

[0179] Where t represents the commuting mode, represents the carbon emission factor corresponding to commuting mode t, Represents the total distance corresponding to commuting mode t.

[0180] Annual carbon emissions of service equipment for target intelligent computing services :

[0181] like Figure 3 As shown, the IT equipment involved may include processors, network equipment, and storage equipment, and the calculation formula can be expressed as follows:

[0182]

[0183] in, represents the annual service equipment energy consumption of the target intelligent computing service s, f represents the carbon emission factor corresponding to the energy consumption, represents the annual processor carbon emissions of the target intelligent computing service s, represents the annual network equipment carbon emissions of the target intelligent computing service s, Indicates the annual storage device carbon emissions of the target intelligent computing service s.

[0184] Since a large number of virtualized devices (such as virtual machines, containers, etc.) are required to support intelligent computing services, the above three types of IT equipment can be divided into two categories, non-virtualized devices and virtualized devices, and the following calculation formula can be obtained:

[0185]

[0186]

[0187]

[0188]

[0189] in, , , They are used to represent the annual non-virtualized processor energy consumption (equivalent to the third processor energy consumption), annual non-virtualized network device energy consumption (equivalent to the third network device energy consumption), and annual non-virtualized storage device energy consumption (equivalent to the third storage device energy consumption) of the target intelligent computing service s. , , They are used to represent the carbon emissions obtained by multiplying the energy consumption of the corresponding non-virtualized equipment by the carbon emission factor f corresponding to the energy consumption in the region where the IDC is located: annual non-virtualized processor carbon emissions, annual non-virtualized network equipment carbon emissions, and annual non-virtualized storage equipment carbon emissions; , , They are used to represent the annual virtualized processor energy consumption (equivalent to the fourth processor energy consumption), the annual virtualized network device energy consumption (equivalent to the fourth network device energy consumption), and the annual virtualized storage device energy consumption (equivalent to the fourth storage device energy consumption) of the target intelligent computing service s respectively; , , They are used to represent the carbon emissions obtained by multiplying the energy consumption of the corresponding virtualization equipment by the carbon emission factor f corresponding to the energy consumption in the area where the IDC is located: annual virtualization processor carbon emissions, annual virtualization network equipment carbon emissions, and annual virtualization storage equipment carbon emissions.

[0190] Among them, since non-virtualized devices are often only used for target intelligent computing services, their energy consumption can be directly collected through electricity metering equipment; while the host devices of virtualized devices are often deployed with multiple virtualized devices serving multiple intelligent computing services, their energy consumption needs to be separated from the power consumption of the IT equipment of the corresponding host device.

[0191] The energy consumption of IT equipment can include static components and dynamic components. The calculation formula is as follows:

[0192]

[0193] Among them, P represents the energy consumption of IT equipment, which can be collected through electricity metering equipment. Represents the static component of IT equipment energy consumption, Represents the dynamic component of IT equipment energy consumption.

[0194] The following principle is adopted for the splitting process of the virtualized device energy consumption that the target intelligent computing service needs to share in the IT equipment energy consumption: all intelligent computing services deployed on the IT equipment share the static component of the IT equipment energy consumption; all intelligent computing services that are responding to user requests share the dynamic component of the IT equipment energy consumption. The sharing standard is the upper limit of the allocated resources and the actual amount of resources used.

[0195] It should be noted that discrete sampling is used in the following calculation formulas. The energy consumption is obtained by integrating the time. The sampled energy consumption is regarded as the average energy consumption in the sampling period. The energy consumption in the sampling period is multiplied by the length of the sampling period. The energy consumption in each sampling period is then summed to obtain the total energy consumption.

[0196] For virtualized processors:

[0197] Taking GPU as an example, the allocation standards of static and dynamic components of processor energy consumption can be based on the amount of video memory used by the intelligent computing service. The calculation formula is as follows:

[0198]

[0199] Where g is the GPU device number, t is the time period number, and j is the intelligent computing service number. represents the set of GPUs deployed with the target intelligent computing service s, T represents the time period set (for an annual bill, the sum of the time periods included should be 1 year), represents the set of intelligent computing services j deployed on the GPU g; represents the amount of video memory used by the target intelligent computing service s in GPU g during time period t, represents the amount of video memory used by intelligent computing service j in GPU g during time period t, Indicates the total amount of video memory of GPU g, Indicates whether the GPU g is used for intelligent computing service j in time period t; represents the sampled GPU g energy consumption (equivalent to the second processor energy consumption), represents the static component of GPU g’s energy consumption, Represents the dynamic component of GPU g’s energy consumption; Indicates the sampling period of GPU energy consumption.

[0200] For virtualized network devices:

[0201] The allocation standard of the static component of network equipment energy consumption can be based on the maximum bandwidth provided to the intelligent computing service, and the allocation standard of the dynamic component can be based on the actual network traffic used by the intelligent computing service (equivalent to the bandwidth used);

[0202]

[0203] Where n represents the device number of the network device, and t represents the time period number; represents a set of network devices where the target intelligent computing service s is deployed, and T represents a time period set; represents the maximum bandwidth provided by network device n to the target intelligent computing service s in time period t, Indicates the total bandwidth of network device n; It represents the bandwidth used by the target intelligent computing service s in the network device n in the time period t. It represents the total bandwidth used by network device n in time period t; Indicates the energy consumption of the network device obtained by sampling (equivalent to the energy consumption of the second network device), Represents the static component of network equipment energy consumption, Represents the dynamic component of energy consumption of network devices; Indicates the sampling period of network device energy consumption.

[0204] For virtualized storage devices:

[0205] The allocation standard of the static component of the storage device energy consumption can be based on the maximum storage space provided to the intelligent computing service, and the allocation standard of the dynamic component can be based on the actual read and write volume of the intelligent computing service (equivalent to the actual storage space used)

[0206]

[0207] Where d represents the device number of the storage device, and t represents the time period number; represents the set of storage devices where the target intelligent computing service s is deployed, and T represents the time period set; It represents the maximum storage space provided by storage device d to target intelligent computing service s in time period t. Indicates the total storage space of storage device d; Indicates the actual read and write volume of the target intelligent computing service s in the storage device d during the time period t. Represents the total read and write volume of storage device d in time period t; Indicates the sampled storage device energy consumption (equivalent to the second storage device energy consumption), represents the static component of the energy consumption of the storage device, Represents the dynamic component of storage device energy consumption; Indicates the sampling period of the energy consumption of the storage device.

[0208] For the allocation factor:

[0209] The first apportionment coefficient k1, the fourth apportionment coefficient k4 and the fifth apportionment coefficient k5 can be determined by the following calculation formula:

[0210]

[0211] in, Indicates the total annual energy consumption of all IT equipment in IDC.

[0212] The second apportionment coefficient k2 can be determined using the following calculation formula:

[0213]

[0214] in, Indicates the number of hours invested by the operation and maintenance personnel in the target intelligent computing service s. Indicates the total number of man-hours invested by operation and maintenance personnel in all intelligent computing services.

[0215] In the above embodiment, by analyzing the carbon emission behavior of the intelligent computing service throughout its life cycle, a method for calculating the energy consumption and carbon emissions of a single intelligent computing service is obtained. Based on this method, the carbon emissions of the intelligent computing service can be accurately calculated to strengthen the effective management of carbon emissions. At the same time, corresponding carbon emission bills can be provided to users.

[0216] Figure 4 is a schematic structural diagram of an electronic device provided by an exemplary embodiment. Figure 4At the hardware level, the device includes a processor 402, an internal bus 404, a network interface 406, a cache 408, and a non-volatile memory 410, and may also include hardware required for other functions. One or more embodiments of this specification may be implemented based on software, such as the processor 402 reading the corresponding computer program from the non-volatile memory 410 into the cache 408 and then running it. Of course, in addition to the software implementation, one or more embodiments of this specification do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0217] Please refer to Figure 5 , the energy consumption and carbon emission accounting device of the data center's intelligent computing service can be applied to Figure 4 The energy consumption and carbon emission accounting device may include: an equipment determination module 501, an energy consumption collection module 502, an energy consumption calculation module 503 and a carbon emission accounting module 504.

[0218] The device determination module 501 is used to determine the service devices related to the target intelligent computing service in the cloud service system, and the service devices include: non-virtualized physical hardware devices and virtualized devices; wherein the virtualized devices are virtual devices obtained by virtualizing the physical hardware devices based on virtualization technology;

[0219] The energy consumption collection module 502 is used to obtain a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of the physical hardware device that is a host device of the virtualized device;

[0220] The energy consumption calculation module 503 is used to calculate a third energy consumption used for the target intelligent computing service in the first energy consumption, and a fourth energy consumption used for the target intelligent computing service in the second energy consumption;

[0221] The carbon emission accounting module 504 is used to calculate the carbon emissions of the target intelligent computing service based on the third energy consumption and the fourth energy consumption.

[0222] In one embodiment, the energy consumption of a physical hardware device includes a static component and a dynamic component, wherein the static component represents the basic energy required to be consumed by the corresponding physical hardware device during operation, and the dynamic component represents the computing energy consumed by the corresponding physical hardware device when responding to intelligent computing services.

[0223] In one embodiment, if the host device includes a processor, the second energy consumption includes a second processor energy consumption of the processor, and the fourth energy consumption includes a fourth processor energy consumption;

[0224] The energy consumption calculation module 503 is used to calculate the static component of the fourth processor energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second processor based on the ratio of the computing power consumption used by the target intelligent computing service in the processor to the total computing power consumption of the processor; and to calculate the dynamic component of the fourth processor energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second processor based on the ratio of the computing power consumption used by the target intelligent computing service in the processor to the sum of the computing power consumption used by all intelligent computing services deployed on the processor.

[0225] In one embodiment, if the host device includes a network device, the second energy consumption includes a second network device energy consumption of the network device, and the fourth energy consumption includes a fourth network device energy consumption;

[0226] The energy consumption calculation module 503 is used to calculate the static component of the fourth network device energy consumption used for the target intelligent computing service in the static component of the second network device energy consumption based on the ratio of the maximum bandwidth provided to the target intelligent computing service in the network device and the total bandwidth of the network device; and to calculate the dynamic component of the fourth network device energy consumption used for the target intelligent computing service in the dynamic component of the second network device energy consumption based on the ratio of the bandwidth used by the target intelligent computing service in the network device and the sum of the bandwidths used by all intelligent computing services deployed on the network device.

[0227] In one embodiment, if the host device includes a storage device, the second energy consumption includes a second storage device energy consumption of the storage device, and the fourth energy consumption includes a fourth storage device energy consumption;

[0228] The energy consumption calculation module 503 is used to calculate the static component of the fourth storage device energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second storage device based on the ratio of the maximum storage space provided to the target intelligent computing service in the storage device and the total storage space of the storage device; and to calculate the dynamic component of the fourth storage device energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second storage device based on the ratio of the storage space used by the target intelligent computing service in the storage device and the sum of the storage space used by all intelligent computing services deployed on the storage device.

[0229] In one embodiment, the fourth processor energy consumption of the target intelligent computing service s is calculated based on the following formula: :

[0230]

[0231] Where g is the device ID of the processor, and j is the service ID of the intelligent computing service. represents the set of intelligent computing services j deployed on processor g; Indicates the computing power consumption used by the target intelligent computing service s in processor g, Indicates the total amount of computing power consumed by processing device g, Indicates the computing power consumption of intelligent computing service j in processor g; represents the second processor energy consumption of processor g, represents the static component of the second processor's energy consumption, Represents the dynamic component of the energy consumption of the second processor.

[0232] In one embodiment, the fourth network device energy consumption of the target intelligent computing service s is calculated based on the following formula: :

[0233]

[0234] Where n is the device number of the network device, and j is the service number of the intelligent computing service; represents the set of intelligent computing services j deployed on network device n; Indicates the maximum bandwidth provided by network device n to the target intelligent computing service s, Indicates the total bandwidth of network device n; Indicates the bandwidth used by the target intelligent computing service s in the network device n. Indicates the bandwidth used by intelligent computing service j in network device n; represents the energy consumption of the second network device of network device n, represents the static component of the energy consumption of the second network device, The dynamic component representing the energy consumption of the second network device.

[0235] In one embodiment, the fourth storage device energy consumption of the target intelligent computing service s is calculated based on the following formula: :

[0236]

[0237] Where d is the device ID of the storage device, and j is the service ID of the intelligent computing service. represents the set of intelligent computing services j deployed on storage device d; Indicates the maximum storage space provided by storage device d to the target intelligent computing service s. Represents the total storage space of storage device n; Indicates the storage space used by the target intelligent computing service s in the storage device d. Indicates the storage space used by intelligent computing service j in storage device d; represents the second storage device energy consumption of storage device d, represents the static component of the energy consumption of the second storage device, Represents the dynamic component of energy consumption of the second storage device.

[0238] In one embodiment, the carbon emission accounting module 504 is further used to calculate the carbon emission of the basic operating equipment and the carbon emission of the operation and maintenance personnel in the cloud service system related to the target intelligent computing service;

[0239] Based on the sum of the third energy consumption and the fourth energy consumption, calculate the service equipment energy consumption of the target intelligent computing service;

[0240] The first carbon emissions that need to be allocated to the target intelligent computing service in the carbon emissions of the basic operating equipment are calculated based on the first allocation coefficient, and the second carbon emissions that need to be allocated to the target intelligent computing service in the carbon emissions of the operation and maintenance personnel are calculated based on the second allocation coefficient; wherein the first allocation coefficient represents the ratio of the energy consumption of the service equipment of the target intelligent computing service to the total energy consumption of the service equipment of the data center, and the second allocation coefficient represents the ratio of the working hours of the operation and maintenance personnel for the target intelligent computing service to the total working hours of the operation and maintenance personnel;

[0241] Based on the sum of the first carbon emissions, the second carbon emissions and the third carbon emissions corresponding to the energy consumption of the service equipment, the total carbon emissions of the target intelligent computing service are calculated.

[0242] In one embodiment, the carbon emission accounting module 504 is further used to obtain the carbon emission of the cloud service system in the construction stage and the carbon emission of the cloud service system in the scrapping stage;

[0243] The fourth carbon emission amount that the target intelligent computing service needs to share in the carbon emission amount of the cloud service system in the construction phase is calculated based on the fourth allocation coefficient, and the fifth carbon emission amount that the target intelligent computing service needs to share in the carbon emission amount of the cloud service system in the scrapping phase is calculated based on the fifth allocation coefficient; wherein the fourth allocation coefficient and the fifth allocation coefficient represent the ratio of the service equipment energy consumption of the target intelligent computing service to the total service equipment energy consumption of the data center;

[0244] The first carbon emission, the second carbon emission, and the third carbon emission corresponding to the energy consumption of the service equipment are used to calculate the total carbon emission of the target intelligent computing service, including:

[0245] Based on the sum of the first carbon emissions, the second carbon emissions, the third carbon emissions, the fourth carbon emissions and the fifth carbon emissions, the total carbon emissions of the target intelligent computing service are calculated.

[0246] In one embodiment, the intelligent computing service includes an intelligent computing service; the processor includes a graphics processor GPU; and the computing power consumption includes video memory.

[0247] Based on the same concept as the above method, this specification also provides an electronic device, including: a processor; a memory for storing processor executable instructions; wherein the processor implements the steps of the method described in any of the above embodiments by running the executable instructions.

[0248] Based on the same concept as the above method, this specification also provides a computer-readable storage medium on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in any of the above embodiments are implemented.

[0249] Based on the same concept as the above method, this specification also provides a computer program product, including a computer program / instruction, which implements the steps of the method described in any of the above embodiments when executed by a processor.

Claims

1. A method for calculating energy consumption and carbon emissions of intelligent computing services in a data center, characterized in that: Applied to a server corresponding to a cloud service system providing intelligent computing services, the method includes: Determine the service equipment related to the target intelligent computing service in the cloud service system, the service equipment includes: non-virtualized physical hardware equipment and virtualized equipment; wherein the virtualized equipment is a virtual equipment obtained by virtualizing the physical hardware equipment based on virtualization technology; the energy consumption of the physical hardware equipment includes a static component and a dynamic component, wherein the static component represents the basic energy required to be consumed by the corresponding physical hardware equipment during operation, and the dynamic component represents the computing energy consumed by the corresponding physical hardware equipment when responding to the intelligent computing service; Acquire a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of a physical hardware device that is a host device of the virtualized device; Calculate and obtain the third energy consumption of the target intelligent computing service in the first energy consumption, and the fourth energy consumption of the target intelligent computing service in the second energy consumption; wherein, the calculation to obtain the fourth energy consumption of the target intelligent computing service in the second energy consumption includes: if the host device includes a processor, the second energy consumption includes the second processor energy consumption of the processor, and the fourth energy consumption includes the fourth processor energy consumption, based on the ratio of the computing power consumption used by the target intelligent computing service to the total computing power consumption of the processor in the processor, calculate the static component of the fourth processor energy consumption used for the target intelligent computing service in the static component of the second processor energy consumption; and, based on the ratio of the computing power consumption used by the target intelligent computing service to the sum of the computing power consumption used by the intelligent computing services deployed on the processor in the processor, calculate the dynamic component of the fourth processor energy consumption used for the target intelligent computing service in the dynamic component of the second processor energy consumption; if the host device includes a network device, the second energy consumption includes the second network device energy consumption of the network device, and the fourth energy consumption includes the fourth network device energy consumption, based on the maximum bandwidth and The static component of the fourth network device energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second network device is calculated based on the ratio of the total bandwidth of the network device to the ratio of the bandwidth used by the target intelligent computing service and the bandwidth used by the intelligent computing services deployed on the network device in the network device; and, based on the ratio of the bandwidth used by the target intelligent computing service and the sum of the bandwidth used by the intelligent computing services deployed on the network device in the network device, the dynamic component of the fourth network device energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second network device is calculated; if the host device includes a storage device, the second energy consumption includes the second storage device energy consumption of the storage device, and the fourth energy consumption includes the fourth storage device energy consumption, based on the ratio of the maximum storage space provided to the target intelligent computing service and the total storage space of the storage device in the storage device, the static component of the fourth storage device energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second storage device is calculated; and, based on the ratio of the storage space used by the target intelligent computing service and the sum of the storage space used by the intelligent computing services deployed on the storage device in the storage device, the dynamic component of the fourth storage device energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second storage device is calculated; Based on the third energy consumption and the fourth energy consumption, the carbon emissions of the target intelligent computing service are calculated.

2. The method according to claim 1, characterized in that The method further comprises: Calculate the carbon emissions of basic operating equipment and operation and maintenance personnel in the cloud service system related to the target intelligent computing service; The calculating the carbon emissions of the target intelligent computing service based on the third energy consumption and the fourth energy consumption includes: Based on the sum of the third energy consumption and the fourth energy consumption, calculate the service equipment energy consumption of the target intelligent computing service; The first carbon emissions that need to be allocated to the target intelligent computing service in the carbon emissions of the basic operating equipment are calculated based on the first allocation coefficient, and the second carbon emissions that need to be allocated to the target intelligent computing service in the carbon emissions of the operation and maintenance personnel are calculated based on the second allocation coefficient; wherein the first allocation coefficient represents the ratio of the energy consumption of the service equipment of the target intelligent computing service to the total energy consumption of the service equipment of the data center, and the second allocation coefficient represents the ratio of the working hours of the operation and maintenance personnel for the target intelligent computing service to the total working hours of the operation and maintenance personnel; Based on the sum of the first carbon emissions, the second carbon emissions and the third carbon emissions corresponding to the energy consumption of the service equipment, the total carbon emissions of the target intelligent computing service are calculated.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining the carbon emissions of the cloud service system during the construction phase and the carbon emissions of the cloud service system during the scrapping phase; The fourth carbon emission amount that the target intelligent computing service needs to share in the carbon emission amount of the cloud service system in the construction phase is calculated based on the fourth allocation coefficient, and the fifth carbon emission amount that the target intelligent computing service needs to share in the carbon emission amount of the cloud service system in the scrapping phase is calculated based on the fifth allocation coefficient; wherein the fourth allocation coefficient and the fifth allocation coefficient represent the ratio of the service equipment energy consumption of the target intelligent computing service to the total service equipment energy consumption of the data center; The first carbon emission, the second carbon emission, and the third carbon emission corresponding to the energy consumption of the service equipment are used to calculate the total carbon emission of the target intelligent computing service, including: Based on the sum of the first carbon emissions, the second carbon emissions, the third carbon emissions, the fourth carbon emissions and the fifth carbon emissions, the total carbon emissions of the target intelligent computing service are calculated.

4. The method according to claim 1, characterized in that: The processor includes a graphics processing unit (GPU); the computing power consumption includes video memory.

5. A carbon emissions accounting device, characterized in that: include: A device determination module is used to determine the service devices related to the target intelligent computing service in the cloud service system, wherein the service devices include: non-virtualized physical hardware devices and virtualized devices; wherein the virtualized devices are virtual devices obtained by virtualizing physical hardware devices based on virtualization technology; the energy consumption of the physical hardware devices includes a static component and a dynamic component, wherein the static component represents the basic energy required to be consumed by the corresponding physical hardware devices during operation, and the dynamic component represents the computing energy consumed by the corresponding physical hardware devices when responding to the intelligent computing service; An energy consumption collection module, used to obtain a first energy consumption of the non-virtualized physical hardware device and a second energy consumption of a physical hardware device that is a host device of the virtualized device; An energy consumption calculation module, used to calculate and obtain the third energy consumption used for the target intelligent computing service in the first energy consumption, and the fourth energy consumption used for the target intelligent computing service in the second energy consumption; wherein, the calculation to obtain the fourth energy consumption used for the target intelligent computing service in the second energy consumption includes: if the host device includes a processor, the second energy consumption includes the second processor energy consumption of the processor, and the fourth energy consumption includes the fourth processor energy consumption, based on the ratio of the computing power consumption used by the target intelligent computing service to the total computing power consumption of the processor in the processor, calculate the static component of the fourth processor energy consumption used for the target intelligent computing service in the static component of the second processor energy consumption; and, based on the ratio of the computing power consumption used by the target intelligent computing service in the processor to the sum of the computing power consumption used by the intelligent computing services deployed on the processor, calculate the dynamic component of the fourth processor energy consumption used for the target intelligent computing service in the dynamic component of the second processor energy consumption; if the host device includes a network device, the second energy consumption includes the second network device energy consumption of the network device, and the fourth energy consumption includes the fourth network device energy consumption, based on the network device provided to the target intelligent computing service The static component of the fourth network device energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second network device is calculated based on the ratio of the maximum bandwidth to the total bandwidth of the network device; and, based on the ratio of the bandwidth used by the target intelligent computing service and the sum of the bandwidths used by the intelligent computing services deployed on the network device in the network device, the dynamic component of the fourth network device energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second network device is calculated; if the host device includes a storage device, the second energy consumption includes the second storage device energy consumption of the storage device, and the fourth energy consumption includes the fourth storage device energy consumption, based on the ratio of the maximum storage space provided to the target intelligent computing service and the total storage space of the storage device in the storage device, the static component of the fourth storage device energy consumption used for the target intelligent computing service in the static component of the energy consumption of the second storage device is calculated; and, based on the ratio of the storage space used by the target intelligent computing service and the sum of the storage space used by the intelligent computing services deployed on the storage device in the storage device, the dynamic component of the fourth storage device energy consumption used for the target intelligent computing service in the dynamic component of the energy consumption of the second storage device is calculated; The carbon emission accounting module is used to calculate the carbon emissions of the target intelligent computing service based on the third energy consumption and the fourth energy consumption.

6. An electronic device, characterized in that: include: processor; A memory for storing processor-executable instructions; wherein the processor implements the steps of the method according to any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 4.

Images