Computing power scheduling method, device, equipment, medium and product

Abstract

The invention provides a computing power scheduling method, device and equipment, a medium and a product, relates to the technical field of computing power resource scheduling, and aims to solve the technical problem of realizing computing power scheduling on the basis of comprehensively considering low cost and low emission. The computing power scheduling method comprises the following steps: acquiring computing power information, electricity consumption information and carbon emission information of a plurality of computing power nodes and task information of a task to be scheduled, determining an energy consumption index and a carbon emission index of each computing power node in the plurality of computing power nodes according to the computing power information, the electricity consumption information and the carbon emission information, and scheduling the energy consumption index and the carbon emission index of each computing power node in the plurality of computing power nodes according to the task information of the task to be scheduled. And determining a time delay index of the scheduling path corresponding to each computing power node in the plurality of computing power nodes, determining a target computing power node from the plurality of computing power nodes according to the energy consumption index, the carbon emission index and the time delay index, and scheduling the target computing power node to process the task to be scheduled.

Description

Technical Field

[0001] This application relates to the field of computing power resource scheduling technology, and in particular to a computing power scheduling method, device, equipment, medium and product. Background Technology

[0002] With the rapid development of the digital economy, the demand for computing power is growing exponentially. As the core carrier of computing power, data centers are facing increasingly prominent issues of rising energy consumption and carbon emissions. The deep integration of the digital economy and green development has made low emissions a core constraint on computing power scheduling.

[0003] In related technologies, computing power scheduling often focuses on efficient resource utilization, single low emissions, or demand forecasting, such as scheduling computing power tasks to computing power nodes with a large amount of green electricity application. However, carbon emission factors vary in different regions, and focusing only on the amount of green electricity application will result in low emissions but high costs during computing power scheduling, affecting the actual emission reduction effect.

[0004] Therefore, how to achieve computing power scheduling for different regions while taking into account both low cost and low emissions is an urgent problem to be solved. Summary of the Invention

[0005] This disclosure provides a computing power scheduling method, apparatus, device, medium, and product, aiming to solve the technical problem of achieving computing power scheduling while comprehensively considering low cost and low emissions.

[0006] To achieve the above objectives, this application adopts the following technical solution: Firstly, a computing power scheduling method is provided, including: acquiring computing power information, electricity consumption information, and carbon emission information of multiple computing power nodes, as well as task information of tasks to be scheduled; determining the energy consumption index and carbon emission index of each computing power node among the multiple computing power nodes based on the computing power information, electricity consumption information, and carbon emission information; determining the latency index of the scheduling path corresponding to each computing power node among the multiple computing power nodes based on the task information of tasks to be scheduled; determining the target computing power node from the multiple computing power nodes based on the energy consumption index, carbon emission index, and latency index; and scheduling the target computing power node to process the tasks to be scheduled.

[0007] Optionally, based on computing power information, electricity consumption information, and carbon emission information, determine the energy consumption index and carbon emission index of each computing power node among multiple computing power nodes, including: determining the energy consumption index of each computing power node among multiple computing power nodes based on computing power information and electricity consumption information; and determining the carbon emission index of each computing power node among multiple computing power nodes based on electricity consumption information and carbon emission information.

[0008] Optionally, the computing power information includes: the remaining computing power and the corresponding electricity demand; the electricity consumption information includes: electricity price information. Based on the computing power information and electricity consumption information, the energy consumption index of each computing power node among multiple computing power nodes is determined, including: for each computing power node, determining the energy consumption cost of the computing power node based on the remaining computing power, electricity demand, and electricity price information; the energy consumption cost satisfies the following formula:

[0009] Among them, C i P is used to represent energy consumption cost. i Q represents the amount of electricity demand, and E represents the remaining computing power. i Used to represent electricity price information; based on the energy consumption cost of the computing power nodes, the energy consumption index of each computing power node among multiple computing power nodes is determined; the energy consumption index is proportional to the energy consumption cost.

[0010] Optionally, the electricity consumption information includes: green electricity consumption, total electricity consumption, and the proportion of green electricity in the power grid; the carbon emission information includes: carbon emission factor. Based on the electricity consumption information and carbon emission information, the carbon emission index of each computing node among multiple computing nodes is determined, including: for each computing node, the green electricity proportion of the computing node is determined by summing the ratio of green electricity consumption to total electricity consumption with the proportion of green electricity in the power grid; based on the green electricity proportion of the computing node, the green electricity absorption factor of each computing node among multiple computing nodes is determined; the green electricity absorption factor is inversely proportional to the green electricity proportion of the computing node; the green electricity absorption factor and the carbon emission factor are weighted and summed to determine the carbon emission index of each computing node among multiple computing nodes.

[0011] Optionally, the task information includes: task processing latency; based on the task information of the task to be scheduled, determine the latency index of the scheduling path corresponding to each computing power node among multiple computing power nodes, including: for each computing power node, determine the sum of the task processing latency, the transmission latency of transmitting the task to be scheduled to the computing power node, the transmission latency of receiving the task processing result of the computing power node, and the queuing latency of waiting for computing power resources at the computing power node as the latency index of the scheduling path corresponding to the computing power node.

[0012] Optionally, a target computing power node is determined from multiple computing power nodes based on energy consumption indicators, carbon emission indicators, and latency indicators. This includes: for each computing power node, a weighted sum of energy consumption indicators, carbon emission indicators, and latency indicators is calculated to determine the comprehensive performance index of the computing power node; the target computing power node is determined based on the comprehensive performance index of each computing power node; and the comprehensive performance index of the target computing power node is less than the performance index threshold.

[0013] Optionally, the overall performance index of the target computing node is the minimum value among the overall performance indices of multiple computing nodes.

[0014] Optionally, the computing power information includes: the remaining computing power, and the task information also includes: the computing power requirement; the remaining computing power of the computing power node is greater than or equal to the computing power requirement of the task to be scheduled.

[0015] Secondly, a computing power scheduling device is provided, which includes a communication unit and a processing unit; The communication unit is used to acquire computing power information, electricity consumption information, and carbon emission information of multiple computing power nodes, as well as task information of tasks to be scheduled; the processing unit is used to determine the energy consumption index and carbon emission index of each computing power node among the multiple computing power nodes based on the computing power information, electricity consumption information, and carbon emission information; the processing unit is also used to determine the latency index of the corresponding scheduling path of each computing power node among the multiple computing power nodes based on the task information of tasks to be scheduled; the processing unit is also used to determine the target computing power node from the multiple computing power nodes based on the energy consumption index, carbon emission index, and latency index; the processing unit is also used to schedule the target computing power node to process the tasks to be scheduled.

[0016] Optionally, the processing unit is specifically used to: determine the energy consumption index of each computing node among multiple computing nodes based on computing power information and electricity consumption information; and determine the carbon emission index of each computing node among multiple computing nodes based on electricity consumption information and carbon emission information.

[0017] Optionally, the computing power information includes: the remaining computing power and the corresponding power demand; the electricity consumption information includes: electricity price information. The processing unit is specifically used to: for each computing node, determine the energy consumption cost of the computing node based on the remaining computing power, power demand, and electricity price information; the energy consumption cost satisfies the following formula:

[0018] Where Ci represents energy consumption cost, Pi represents electricity demand, Q represents remaining computing power, and Ei represents electricity price information; based on the energy consumption cost of the computing power nodes, the energy consumption index of each computing power node among multiple computing power nodes is determined; the energy consumption index is proportional to the energy consumption cost.

[0019] Optionally, the electricity consumption information includes: green electricity consumption, total electricity consumption, and the proportion of green electricity in the power grid; the carbon emission information includes: carbon emission factor; the processing unit is specifically used to: determine the green electricity proportion of each computing node by summing the ratio of green electricity consumption to total electricity consumption with the proportion of green electricity in the power grid; determine the green electricity absorption factor of each computing node among multiple computing nodes based on the green electricity proportion of the computing node; the green electricity absorption factor is inversely proportional to the green electricity proportion of the computing node; and determine the carbon emission index of each computing node among multiple computing nodes by weighted summation of the green electricity absorption factor and the carbon emission factor.

[0020] Optionally, the task information includes: task processing latency; the processing unit is specifically used to: for each computing power node, determine the sum of the task processing latency, the transmission latency of transmitting the task to be scheduled to the computing power node, the transmission latency of receiving the task processing result from the computing power node, and the queuing latency of waiting for computing power resources at the computing power node as the latency index of the corresponding scheduling path of the computing power node.

[0021] Optionally, the processing unit is specifically used to: for each computing node, calculate the weighted sum of energy consumption, carbon emission, and latency indicators to determine the comprehensive performance index of the computing node; determine the target computing node based on the comprehensive performance index of each computing node; the comprehensive performance index of the target computing node is less than the performance index threshold.

[0022] Optionally, the overall performance index of the target computing node is the minimum value among the overall performance indices of multiple computing nodes.

[0023] Optionally, the computing power information includes: the remaining computing power, and the task information also includes: the computing power requirement; the remaining computing power of the computing power node is greater than or equal to the computing power requirement of the task to be scheduled.

[0024] Thirdly, a computing power scheduling device is provided, including a memory and a processor; the memory is used to store computer execution instructions, and the processor is connected to the memory via a bus; when the computing power scheduling device is running, the processor executes the computer execution instructions stored in the memory, so that the computing power scheduling device executes the computing power scheduling method of the first aspect.

[0025] The computing power scheduling device can be an electronic device or a component of an electronic device, such as a chip system within an electronic device. This chip system supports the electronic device in implementing the functions involved in the first aspect and any of its possible implementations, such as acquiring and determining the data and / or information involved in the aforementioned computing power scheduling method. The chip system includes chips, but may also include other discrete devices or circuit structures.

[0026] Fourthly, a computer-readable storage medium is provided, comprising computer-executable instructions that, when executed on a computer, cause the computer to perform the computing power scheduling method described in the first aspect.

[0027] Fifthly, a computer program product is also provided, which includes a computer program or instructions that, when executed on a computing power scheduling device, cause the computing power scheduling device to perform the computing power scheduling method as described in the first aspect above.

[0028] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the computing power scheduling device, or it may be packaged separately from the processor of the computing power scheduling device; this application does not limit this.

[0029] The descriptions of the second, third, fourth, and fifth aspects of this application can be referenced to the detailed description of the first aspect.

[0030] In the embodiments of this application, the name of the aforementioned computing power scheduling device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. For example, the receiving unit may also be called a receiving module, receiver, etc. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0031] The technical solution provided in this application brings at least the following beneficial effects: Based on any of the above aspects, embodiments of this application provide a computing power scheduling method. First, computing power information, electricity consumption information, and carbon emission information of multiple computing power nodes, as well as task information of the task to be scheduled, are obtained. Then, based on the computing power information, electricity consumption information, and carbon emission information, the energy consumption index and carbon emission index of each computing power node among the multiple computing power nodes are determined. Next, based on the task information of the task to be scheduled, the latency index of the scheduling path corresponding to each computing power node among the multiple computing power nodes is determined. Then, based on the energy consumption index, carbon emission index, and latency index, a target computing power node is determined from the multiple computing power nodes, and the target computing power node is scheduled to process the task to be scheduled.

[0032] As can be seen from the above, this application determines the energy consumption and carbon emission indicators of each computing power node by acquiring its computing power information, electricity consumption information, and carbon emission information. This application also determines the latency indicator of the corresponding scheduling path for each computing power node based on the task information of the tasks to be scheduled. By comprehensively considering these three core factors—energy consumption, carbon emission, and latency—this application aims to achieve rational scheduling of computing power under the premise of low cost and low emissions.

[0033] The beneficial effects of the first, second, third, fourth, and fifth aspects of this application can all be referred to in the analysis of the above-mentioned beneficial effects, and will not be repeated here. Attached Figure Description

[0034] Figure 1 This application provides a schematic diagram of the structure of a computing power scheduling system according to an embodiment of the present application. Figure 2 A schematic diagram of a hardware structure of a communication device provided in an embodiment of this application; Figure 3 A flowchart illustrating a computing power scheduling method provided in an embodiment of this application; Figure 4 A flowchart illustrating another computing power scheduling method provided in this application embodiment; Figure 5 A flowchart illustrating another computing power scheduling method provided in this application embodiment; Figure 6 This application provides a schematic diagram of a computing node selection process. Figure 7 This application provides a schematic diagram of the workflow of a computing power scheduling device according to an embodiment of the present application. Figure 8 This is a schematic diagram of a computing power scheduling device provided in an embodiment of this application. Detailed Implementation

[0035] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0036] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0037] To facilitate a clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0038] Before providing a detailed introduction to the computing power scheduling method provided in this application, let's briefly introduce the application scenarios and implementation environment involved in this application.

[0039] First, a brief introduction to the application scenarios involved in this application will be given.

[0040] As described in the background section, with the rapid development of the digital economy, the demand for computing power is growing exponentially. As the core carrier of computing power, data centers are facing increasingly prominent issues of rising energy consumption, carbon emissions, and operating costs. With the deep integration of the digital economy and green development, low emissions have become a core constraint on computing power scheduling.

[0041] Meanwhile, the rapid iteration of technologies such as artificial intelligence and big data has further increased the complexity of computing tasks and the volume of data processing. Data centers are constrained by resources such as physical space, power supply capacity, and cooling efficiency, and can only provide limited computing power. Therefore, computing power scheduling is needed to break through the bottleneck of computing resources that a single data center can provide.

[0042] In related technologies, computing power scheduling focuses on efficient resource utilization, single low emissions, or demand forecasting, such as scheduling computing power tasks to computing power nodes with a large amount of green electricity application.

[0043] However, carbon emission factors vary across different regions, affecting the actual carbon emission reduction calculation results. The amount of green electricity used is not directly proportional to the actual carbon emission reduction. Furthermore, green electricity has regional characteristics; focusing solely on the amount of green electricity used can result in low emissions but high costs during power dispatch, impacting the actual emission reduction effect.

[0044] Therefore, cost control should be a key consideration in the evolution of computing power scheduling technology. How to achieve computing power scheduling on the basis of low cost and low emissions is an urgent problem to be solved.

[0045] To address the aforementioned issues, this application provides a computing power scheduling method. First, it acquires computing power information, electricity consumption information, and carbon emission information of multiple computing power nodes, as well as task information of the task to be scheduled. Then, based on the computing power information, electricity consumption information, and carbon emission information, it determines the energy consumption index and carbon emission index of each of the multiple computing power nodes. Next, based on the task information of the task to be scheduled, it determines the latency index of the scheduling path corresponding to each of the multiple computing power nodes. Finally, based on the energy consumption index, carbon emission index, and latency index, it determines a target computing power node from the multiple computing power nodes and schedules the target computing power node to process the task to be scheduled.

[0046] As shown above, this application determines the energy consumption and carbon emission indicators of each computing node by acquiring its computing power information, electricity consumption information, and carbon emission information. This application also determines the latency indicator of the corresponding scheduling path for each computing node based on the task information of the tasks to be scheduled. By comprehensively considering these three core factors—energy consumption, carbon emission, and latency—the application aims to achieve rational scheduling of computing power under the premise of low cost and low emissions.

[0047] The implementation environment for the above-mentioned computing power scheduling method can be the computing power scheduling system provided in the embodiments of this application.

[0048] Figure 1 A schematic diagram of the computing power scheduling system provided in an embodiment of this application is shown. Figure 1 As shown, the computing power scheduling system includes a computing power scheduling device 101 and a data acquisition device 102.

[0049] The computing power scheduling device 101 is communicatively connected to the data acquisition device 102.

[0050] In practical applications, the computing power scheduling device 101 can connect to any number of data acquisition devices 102. For ease of understanding, Figure 1 The following is an example of a computing power scheduling device 101 connected to a data acquisition device 102.

[0051] In this embodiment of the application, the data acquisition device is used to collect computing power information, electricity consumption information and carbon emission information of the computing power node.

[0052] Specifically, the data acquisition equipment is used to collect the remaining computing power, the corresponding electricity demand, electricity price information, green electricity consumption, total electricity consumption, the proportion of green electricity in the power grid, the carbon emission factor coefficient of the power grid, task attributes, computing power demand, task scheduling delay demand, task processing time period information, and task processing delay.

[0053] Optionally, the physical device of the computing power scheduling device 101 can be a server, a terminal, or other types of electronic devices, and this application embodiment does not limit it.

[0054] Optionally, the aforementioned terminal may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing device connected to a wireless modem. The wireless terminal may communicate with one or more core networks via a radio access network (RAN). The wireless terminal may be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, or a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network, such as a mobile phone, tablet computer, laptop computer, netbook, or personal digital assistant (PDA).

[0055] Optionally, the server mentioned above can be one of the servers in a server cluster (composed of multiple servers), a chip in the server, a system-on-a-chip in the server, or a virtual machine (VM) deployed on a physical machine. This application embodiment does not limit this.

[0056] Optionally, the computing power scheduling device 101 and the data acquisition device 102 can be two independently configured devices, or they can be integrated into the same device. When the computing power scheduling device 101 and the data acquisition device 102 are integrated into the same device, the data acquisition device 102 can be the communication module of the computing power scheduling device 101.

[0057] It is easy to understand that when the computing power scheduling device 101 and the data acquisition device 102 are integrated into the same device, the communication method between the computing power scheduling device 101 and the data acquisition device 102 is the same as the communication method between internal modules of the device. In this case, the communication process between the two is the same as when the computing power scheduling device 101 and the data acquisition device 102 are independent of each other.

[0058] For ease of understanding, this application uses the example of computing power scheduling device 101 and data acquisition device 102 operating independently as an illustration.

[0059] The computing power scheduling equipment in the computing power scheduling system includes, for example: Figure 2 The included components. The following are examples... Figure 2 Taking the communication device shown as an example, the hardware structure of the computing power scheduling device is introduced.

[0060] Figure 2 The diagram shown is a hardware structure schematic of a communication device provided in an embodiment of this application. The communication device includes a processor 21, a memory 22, a communication interface 23, and a bus 24. The processor 21, the memory 22, and the communication interface 23 are connected via the bus 24.

[0061] Processor 21 is the control center of the communication device. It can be a single processor or a collective term for multiple processing elements. For example, processor 21 can be a general-purpose central processing unit (CPU) or other general-purpose processors. Among them, the general-purpose processor can be a microprocessor or any conventional processor.

[0062] As one embodiment, processor 21 may include one or more CPUs, for example Figure 2 CPU0 and CPU1 are shown in the diagram.

[0063] The memory 22 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0064] In one possible implementation, the memory 22 can exist independently of the processor 21. The memory 22 can be connected to the processor 21 via a bus 24 and is used to store instructions or program code. When the processor 21 calls and executes the instructions or program code stored in the memory 22, it can implement the computing power scheduling method provided in the following embodiments of this application.

[0065] In this embodiment, the software programs stored in memory 22 differ for each communication device, resulting in different functions implemented by the communication devices. The functions performed by each device will be described in conjunction with the following flowcharts.

[0066] In another possible implementation, the memory 22 can also be integrated with the processor 21.

[0067] Communication interface 23 is used for connecting the communication device to other devices via a communication network, which may be Ethernet, wireless access network, wireless local area network (WLAN), etc. Communication interface 23 may include a receiving unit for receiving data and a sending unit for sending data.

[0068] Bus 24 can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0069] It should be pointed out that, Figure 2 The structure shown does not constitute a limitation on the communication device, except Figure 2 In addition to the components shown, the communication device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0070] The computing power scheduling method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0071] The computing power scheduling method provided in this application embodiment is applied to Figure 1 The computing power scheduling device 101 in the computing power scheduling system shown is, for example Figure 3 As shown, the computing power scheduling method provided in this application includes: S301. Obtain computing power information, electricity consumption information, and carbon emission information of multiple computing power nodes, as well as task information of tasks to be scheduled.

[0072] The computing power information includes: the remaining computing power and the corresponding electricity demand.

[0073] Electricity consumption information includes: electricity price information, green electricity consumption, total electricity consumption, and the proportion of green electricity in the power grid (which can also be referred to as the proportion of green electricity absorbed by the power grid in the region where the computing node is located).

[0074] Carbon emission information includes: carbon emission factors.

[0075] Task information includes: task attributes, computing power requirements, task scheduling latency requirements, task processing time period information, and task processing latency.

[0076] Among them, green electricity consumption includes, but is not limited to: the power generation of new energy power generation equipment in the region where the computing node is located, green electricity introduced from other regions, and green electricity purchased.

[0077] In this embodiment, the electricity price information includes peak and off-peak electricity prices for the region where the computing node is located, as well as electricity prices for each time period. Green electricity refers to renewable electrical energy output through new energy power generation equipment (such as photovoltaic power generation equipment and wind power generation equipment). The green electricity ratio and green electricity consumption ratio both refer to the ratio of renewable electrical energy to total electrical energy.

[0078] Combination Figure 1 Data acquisition equipment can obtain computing power information, electricity consumption information, and carbon emission information of computing power nodes from electricity meters, energy consumption management systems, computing network resource management systems, and power grid energy management systems deployed in the area where the computing power nodes are located.

[0079] The computing power scheduling equipment can obtain computing power information, electricity consumption information and carbon emission information of computing power nodes from the data acquisition equipment.

[0080] The computing power scheduling device can also obtain task information of the tasks to be processed from the front-end interactive device.

[0081] Computing nodes can be computing nodes in the same region or computing nodes in different regions.

[0082] S302. Based on computing power information, electricity consumption information, and carbon emission information, determine the energy consumption index and carbon emission index of each computing power node among multiple computing power nodes.

[0083] Energy consumption indicators are used to represent the energy cost of computing nodes, while carbon emission indicators are used to represent the carbon emissions of computing nodes.

[0084] In some embodiments, the computing power scheduling device can directly calculate the energy consumption index and carbon emission index of each computing power node among multiple computing power nodes based on computing power information, electricity consumption information and carbon emission information.

[0085] In other embodiments, the computing power scheduling device can input the computing power information, electricity consumption information and carbon emission information of the computing power node into the computing power scheduling model to output the energy consumption index and carbon emission index of the computing power node.

[0086] S303. Based on the task information of the task to be scheduled, determine the latency index of the scheduling path corresponding to each computing power node among multiple computing power nodes.

[0087] In this embodiment of the application, for each computing power node, the sum of the task processing latency, the transmission latency of transmitting the task to be scheduled to the computing power node, the transmission latency of receiving the task processing result from the computing power node, and the queuing latency of waiting for computing power resources at the computing power node is determined as the latency index of the scheduling path corresponding to the computing power node.

[0088] In some embodiments, the computing power scheduling device can determine the scheduling latency of the corresponding scheduling path of a computing power node as the sum of the task processing latency, the transmission latency of transmitting the task to be scheduled to the computing power node, the transmission latency of receiving the task processing result from the computing power node, and the queuing latency of waiting for computing power resources at the computing power node. Based on the scheduling latency, multiple computing power nodes are sorted, and the order of the computing power nodes is used as the latency indicator.

[0089] Among them, scheduling delay is directly proportional to the delay index.

[0090] Optionally, scheduling delay may also include: environmental interference delay and task scheduling delay.

[0091] S304. Based on energy consumption indicators, carbon emission indicators, and latency indicators, determine the target computing node from multiple computing nodes.

[0092] In this embodiment, the computing power scheduling device uses a multi-dimensional approach, considering energy consumption, carbon emissions, and latency, to select target computing power nodes. This not only accurately matches the computing power requirements of different tasks to be scheduled but also improves the resource utilization of computing power nodes. While reducing costs and carbon emissions, it ensures the response efficiency of the tasks to be scheduled.

[0093] S305. Schedule the target computing power node to process the tasks to be scheduled.

[0094] In this embodiment of the application, the computing power scheduling device can schedule the target computing power node based on the scheduling path corresponding to the target computing power node in order to process the task to be scheduled.

[0095] In one example, the computing power scheduling device generates scheduling instructions based on the scheduling path corresponding to the target computing power node. These instructions include, but are not limited to, the identification (ID) of the target computing power node, the computing power allocated to the task, the task start time, the task end time, and the allocated transmission bandwidth. The computing power scheduling device then sends these instructions to the task initiator, the scheduling path node, and the target computing power node through the computing power scheduling protocol, thus completing the scheduling process until the target computing power node processes the task to be scheduled and sends the result back to the task initiator.

[0096] In the above embodiments, the computing power scheduling device obtains basic information about computing power nodes and tasks to be scheduled, calculates energy consumption indicators, carbon emission indicators, and latency indicators, and determines the target computing power node from multiple computing power nodes based on these three indicators to achieve computing power scheduling.

[0097] In some embodiments, combined with Figure 3 ,like Figure 4 As shown, in S302, based on computing power information, electricity consumption information, and carbon emission information, the energy consumption index and carbon emission index of each computing power node among multiple computing power nodes are determined, specifically including: S401. Based on computing power information and electricity consumption information, determine the energy consumption index of each computing power node among multiple computing power nodes.

[0098] In some embodiments, computing power information includes: remaining computing power and the corresponding electricity demand; electricity consumption information includes: electricity price information. Based on the computing power information and electricity consumption information, the energy consumption index of each computing node among multiple computing nodes is determined, specifically including: S4011. For each computing node, determine the energy consumption cost of the computing node based on the remaining computing power, power demand, and electricity price information. The energy consumption cost satisfies the following formula:

[0099] Among them, C i P is used to represent energy consumption cost. iQ represents the amount of electricity demand, and E represents the remaining computing power. i Used to display electricity price information.

[0100] In some examples, the computing power scheduling device also considers the task processing time of the task to be scheduled. Based on the average remaining computing power during the task processing time, the power demand corresponding to the average remaining computing power during the task processing time, and the average electricity price information during the task processing time, the energy consumption cost of the computing power node during the processing time is determined. The energy consumption cost during the processing time satisfies the following formula:

[0101] Among them, C i (t) a-b P is used to represent the energy consumption cost during the task processing period of the i-th computing node. i (t) a-b Q represents the energy demand corresponding to the average remaining computing power during the task processing period of the i-th computing node. i (t) a-b E represents the average remaining computing power during the task processing period of the i-th computing node. i (t) a-b ) is used to represent the average electricity price information during the task processing period of the i-th computing node.

[0102] S4012. Based on the energy consumption cost of the computing power nodes, determine the energy consumption index of each computing power node among multiple computing power nodes.

[0103] Among them, the energy consumption index is directly proportional to the energy consumption cost.

[0104] In some examples, the computing power scheduling device can sort the computing power nodes according to the energy consumption cost of each computing power node among multiple computing power nodes to obtain a first list, where the order of the computing power nodes is the energy consumption index of that computing power node.

[0105] The first list includes: the ID of the computing node, the name of the computing node, the energy cost of the computing node, and the energy consumption index of the computing node.

[0106] It should be noted that when sorting computing nodes, they can be sorted either from high to low energy consumption cost or from low to high. If energy consumption cost is sorted from high to low, the energy consumption index is inversely proportional to the energy consumption cost; the lower the energy consumption cost, the higher the energy consumption index, resulting in a higher overall energy consumption index for the subsequently determined computing nodes, indicating lower energy consumption cost. If energy consumption cost is sorted from low to high, the energy consumption index is directly proportional to the energy consumption cost; the lower the energy consumption cost, the lower the energy consumption index, resulting in a lower overall energy consumption index for the subsequently determined computing nodes, indicating lower energy consumption cost. In practical implementation, the sorting of computing nodes should ensure logical consistency to guarantee the accuracy of node selection.

[0107] In this embodiment of the application, in order to illustrate the selection of the target computing node, one method is selected for explanation, namely, the energy consumption index is proportional to the energy consumption cost.

[0108] S402. Based on electricity consumption information and carbon emission information, determine the carbon emission index for each computing node among multiple computing nodes.

[0109] In some embodiments, electricity consumption information includes: green electricity consumption, total electricity consumption, and the proportion of green electricity in the power grid; carbon emission information includes: carbon emission factor. Based on the electricity consumption information and carbon emission information, the carbon emission index of each computing node in a plurality of computing nodes is determined, specifically including: S4021. For each computing node, the green electricity ratio of the computing node is determined by the sum of the ratio of green electricity consumption to total electricity consumption and the green electricity ratio in the power grid.

[0110] Among them, green electricity consumption includes, but is not limited to: the power generation of new energy power generation equipment in the region where the computing node is located, green electricity introduced from other regions, and green electricity purchased.

[0111] The ratio of green electricity consumption to total electricity consumption is the green electricity self-consumption ratio of computing power nodes, and the green electricity self-consumption ratio of computing power nodes satisfies the following formula:

[0112] Among them, G i (t) a-b W represents the percentage of green electricity self-consumption by the computing node during the task processing period of the i-th computing node. i (t) a-b R represents the power generation of new energy power generation equipment in the region to which the i-th computing node belongs during the task processing period of the i-th computing node. i (t) a-b ) is used to represent the amount of green electricity introduced from other areas during the task processing period of the i-th computing node, O i (t) a-b) is used to represent the green electricity purchased during the task processing period of the i-th computing node, and is used to represent U i (t) a-b The total power consumption during the task processing period of the i-th computing node.

[0113] The green electricity ratio of computing power nodes (also known as the comprehensive green electricity consumption ratio of computing power nodes) satisfies the following formula:

[0114] Among them, T i (t) a-b G is used to represent the green electricity ratio of the i-th computing node. i (t) a-b D is used to represent the green electricity self-consumption rate of the i-th computing node during the task processing period. i (t) a-b ) is used to represent the proportion of green electricity in the power grid during the task processing period of the i-th computing node.

[0115] S4022. Based on the green electricity ratio of the computing power nodes, determine the green electricity absorption factor for each computing power node among multiple computing power nodes.

[0116] Among them, the green electricity consumption factor is inversely proportional to the proportion of green electricity in computing power nodes.

[0117] In some examples, the computing power scheduling device can sort the computing power nodes according to the green electricity ratio of each computing power node among multiple computing power nodes, and the order of the computing power nodes is the green electricity absorption factor of that computing power node.

[0118] It should be noted that when sorting computing nodes, they can be sorted from high to low based on their green energy consumption factor, or from low to high. If the green energy consumption ratio of the computing nodes is sorted from high to low, the green energy consumption factor is inversely proportional to the green energy consumption ratio; the lower the green energy consumption ratio, the higher the green energy consumption factor, and the higher the overall energy consumption index of the subsequently determined computing nodes, indicating a lower green energy consumption ratio. If the green energy consumption ratio of the computing nodes is sorted from low to high, the green energy consumption factor is directly proportional to the green energy consumption ratio; the higher the green energy consumption ratio, the higher the green energy consumption factor, and the higher the overall energy consumption index of the subsequently determined computing nodes, indicating a higher green energy consumption ratio. In the specific implementation process, the sorting of computing nodes should ensure consistency in logic to guarantee the accuracy of the selected computing nodes.

[0119] S4023. Weighted summation of green electricity consumption factor and carbon emission factor to determine the carbon emission index of each computing node in multiple computing power nodes.

[0120] In this embodiment, the carbon emission factor is obtained by ranking the computing nodes according to the grid carbon emission factor coefficient of the region to which each computing node belongs. The grid carbon emission factor coefficient of the region to which the computing node belongs is directly proportional to the carbon emission factor; the smaller the grid carbon emission factor coefficient, the smaller the carbon emission factor.

[0121] It should be noted that the power grid carbon emission factor coefficient of the region where the computing node is located can also be proportional to the carbon emission factor. This will affect the comprehensive energy consumption index of the computing node determined subsequently. In the specific implementation process, when sorting the computing nodes, the logical consistency should be ensured to ensure the accuracy of the selected computing nodes.

[0122] The computing power scheduling equipment can set the weights of green energy consumption factors and carbon emission factors according to the needs of different regions to determine the carbon emission indicators of computing power nodes. The carbon emission indicators satisfy the following formula:

[0123] Among them, F i H is used to represent the carbon emission index of the i-th computing node. i J is used to represent the green energy consumption factor of the i-th computing node. i The carbon emission factor of the i-th computing node is represented by m, which is the weight of the green electricity consumption factor, and n is the weight of the carbon emission factor. The sum of m and n is 1, and both m and n are greater than zero and less than one.

[0124] In the embodiments of this application, the smaller the carbon emission index, the smaller the green electricity consumption factor; the larger the proportion of green electricity, the smaller the carbon emission factor and the smaller the grid carbon emission factor coefficient.

[0125] The computing power scheduling device can sort the computing power nodes according to the carbon emission index of each computing power node in the multiple computing power nodes to obtain a second list. The order of the computing power nodes is the carbon emission index of that computing power node.

[0126] The second list includes: the ID of the computing node, the name of the computing node, the proportion of green electricity, the grid carbon emission factor coefficient, the weight of the green electricity consumption factor, the weight of the carbon emission factor, and the carbon emission index.

[0127] In some embodiments, combined with Figure 4 ,like Figure 5 As shown, in S304, the target computing node is determined from multiple computing nodes based on energy consumption, carbon emission, and latency indicators. Specifically, this includes: S501. For each computing node, the energy consumption index, carbon emission index, and latency index are weighted and summed to determine the comprehensive performance index of the computing node.

[0128] In one implementation, the computing power scheduling device can directly calculate the comprehensive performance index of the computing power node by weighted summation of energy consumption index, carbon emission index and latency index.

[0129] The overall performance index of a computing node satisfies the following formula:

[0130] Among them, Z i C is used to represent the comprehensive performance index of the i-th computing node. i ’ F is used to represent the energy consumption index of the i-th computing node. i X is used to represent the carbon emission index of the i-th computing node. i The latency index is used to represent the latency index of the i-th computing node. p is the weight of the energy consumption index, q is the weight of the carbon emission index, and s is the weight of the latency index. The sum of p, q and s is 1. p, q and s are all greater than zero and less than one.

[0131] In another implementation, the computing power scheduling device can first perform a weighted summation of energy consumption indicators and carbon emission indicators to obtain a third list. Then, the weighted summation result of the energy consumption indicators and carbon emission indicators is combined with the latency indicator to determine the comprehensive performance indicators of the computing power nodes.

[0132] The third list includes: the ID of the computing node, the name of the data center to which the computing node belongs, the order of the computing node in the first list, and the order of the computing node in the second list.

[0133] In this implementation, overlapping computing nodes in the first and second lists can be retained, other computing nodes can be removed, and the latency index of the scheduling path corresponding to each computing node can be determined according to the task information of the task to be scheduled, which can reduce the amount of computation.

[0134] In the above implementation, the overall level of low cost and low emissions satisfies the following formula:

[0135] Among them, K i C is used to represent the overall low cost and low emission level of the i-th computing node. i ’ Fi is used to represent the energy consumption index of the i-th computing node, Fi is used to represent the carbon emission index of the i-th computing node, p is the weight of the energy consumption index, q is the weight of the carbon emission index, the sum of p and q is 1, and both p and q are greater than zero and less than one.

[0136] Alternatively, the overall level of low cost and low emissions can also be calculated using the following formula:

[0137] Among them, K i L is used to represent the overall low cost and low emission level of the i-th computing node. i R is used to represent the order of the i-th computing node in the first list. i The order of the i-th computing power node in the second list is used to represent the order of the i-th computing power node in the first list. p is the weight of the order of the i-th computing power node in the first list, and q is the weight of the order of the i-th computing power node in the second list. The sum of p and q is 1. Both p and q are greater than zero and less than one.

[0138] The overall performance index of a computing node can also be expressed using the following formula:

[0139] Among them, Z i K is used to represent the comprehensive performance index of the i-th computing node. i X is used to represent the overall low cost and low emission level of the i-th computing node. i The latency index is used to represent the latency of the i-th computing node. f is the weight of the overall low cost and low emission level, and s is the weight of the latency index. The sum of f and s is 1. Both f and s are greater than zero and less than one.

[0140] S502. Determine the target computing node based on the comprehensive performance indicators of each computing node.

[0141] The overall performance index of the target computing node is greater than the performance index threshold.

[0142] The computing power scheduling device can sort the computing power nodes from low to high according to their comprehensive performance index, resulting in a fourth list. The computing power node corresponding to the minimum comprehensive performance index is the target computing power node.

[0143] Optionally, the computing power scheduling device can identify multiple computing power nodes whose comprehensive performance index is less than the performance index threshold as target computing power nodes.

[0144] In this embodiment of the application, the computing power scheduling device can perform preliminary screening of computing power nodes based on the remaining amount of computing power nodes and the computing power requirements of the tasks to be scheduled.

[0145] If the remaining computing power of a computing node is greater than or equal to the computing power requirement of the task to be scheduled, it means that the computing power node can handle the task to be scheduled.

[0146] In some embodiments, the maximum load rate of the computing node may also be considered. For details, please refer to... Figure 6 The diagram shown illustrates the initial screening process for computing power nodes.

[0147] First, obtain the remaining computing power n of the computing power node. Then, obtain the maximum load rate a of the computing power node and the computing power requirement s of the task to be scheduled. Next, determine whether n×a is greater than or equal to s. If n×a is greater than or equal to the computing power requirement s of the task to be scheduled, it means that the computing power node can handle the task to be scheduled, and the computing power node is retained. If n×a is less than the computing power requirement s of the task to be scheduled, it means that the computing power node cannot handle the task to be scheduled, and the computing power node is removed.

[0148] Optionally, in this embodiment of the application, after fully scheduling the target computing power node and processing the task to be scheduled, the computing power scheduling device can also obtain the task completion rate, the actual task latency, and the actual load rate of the target computing power node. If the task is not completed, or the actual task latency is greater than the task scheduling latency requirement, or the actual load rate of the target computing power node is greater than the preset load rate, the task scheduling is determined to have failed, and feedback adjustment is triggered. The suboptimal computing power node is selected from the fourth list, the scheduling command is re-executed, and the process is repeated in a loop until the task scheduling is successful.

[0149] Based on the above embodiments, this application also provides a schematic diagram of the workflow of a computing power scheduling device. For example... Figure 7 As shown.

[0150] First, enter the preliminary list of computing power nodes, which is the result of the preliminary screening of computing power nodes.

[0151] Then, determine the energy consumption cost of the computing nodes and sort them from low to high to obtain the first list.

[0152] Simultaneously, the green electricity ratio of each computing node is determined and sorted from highest to lowest to obtain the green electricity consumption factor. Then, the grid carbon emission factor coefficients of the regions where each computing node is located are compared and sorted from lowest to highest to obtain the carbon emission factor. Next, a weight *m* is assigned to the green electricity consumption factor, and a weight *n* is assigned to the carbon emission factor to determine the carbon emission indicators. These indicators are then sorted from lowest to highest to obtain the second list.

[0153] Next, extract multiple computing power nodes from the first list and multiple computing power nodes from the second list.

[0154] Among them, the computing nodes extracted from the first list are the computing nodes with the lowest energy consumption cost, and the computing nodes extracted from the second list are the computing nodes with the lowest carbon emission index (it should be noted that in this embodiment of the application, the lower the carbon emission index, the higher the proportion of green electricity and the lower the carbon emission factor coefficient of the power grid).

[0155] Next, it is determined whether the extracted computing nodes exist simultaneously in the first list and the second list.

[0156] If a computing power node does not exist in both the first and second lists, then that computing power node is removed.

[0157] If a computing node exists in both the first and second lists, assign a weight p to the energy consumption index and a weight q to the carbon emission index to determine the overall low-cost and low-emission level.

[0158] Sort the overall levels of low cost and low emissions from low to high, and output the third list.

[0159] Next, the latency metrics for the scheduling paths corresponding to different computing power nodes are determined.

[0160] Next, a weight m is assigned to the overall low cost and low emission level, and a weight s is assigned to the latency index to determine the overall performance index of the computing node.

[0161] The computing node with the lowest overall performance index is the target computing node.

[0162] Next, the scheduling command is executed, and it is determined whether feedback adjustment is triggered.

[0163] If feedback adjustment is triggered, a suboptimal computing node needs to be selected again, and the scheduling command needs to be re-executed until the task scheduling is successful.

[0164] If no feedback adjustment is triggered, it means that the task scheduling was successful and the process ends.

[0165] As can be seen from the above, in the embodiments of this application, the computing power scheduling device integrates three core factors: electricity price information, carbon emission factor, and green electricity consumption level. By organically coupling these three core factors and introducing a dynamic weight adjustment mechanism, the computing power scheduling device also takes into account scheduling latency. This application fully considers the differences in the regions to which different computing power nodes belong, so as to achieve computing power scheduling oriented towards low cost and low emissions.

[0166] In addition, the computing power scheduling equipment can also realize multiple stages such as optimal path decision-making for computing power scheduling, execution and feedback of computing power scheduling, so as to achieve multi-level control of low-cost and low-emission computing power scheduling and further improve the stability and feasibility of the system.

[0167] The foregoing mainly describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the above functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0168] This application embodiment can divide the computing power scheduling device into functional modules according to the above method example. For example, each function can be divided into its own functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. Optionally, the module division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0169] Figure 8 A schematic diagram of a computing power scheduling device provided in an embodiment of this application is shown. Figure 8 As shown, the computing power scheduling device includes a communication unit 801 and a processing unit 802. The communication unit 801 is used to acquire computing power information, power consumption information, and carbon emission information of multiple computing power nodes, as well as task information of tasks to be scheduled. The processing unit 802 is used to determine the energy consumption index and carbon emission index of each computing power node among the multiple computing power nodes based on the computing power information, power consumption information, and carbon emission information. The processing unit 802 is also used to determine the latency index of the scheduling path corresponding to each computing power node among the multiple computing power nodes based on the task information of tasks to be scheduled. The processing unit 802 is also used to determine the target computing power node from the multiple computing power nodes based on the energy consumption index, carbon emission index, and latency index. The processing unit 802 is also used to schedule the target computing power node to process the tasks to be scheduled.

[0170] Optionally, the processing unit 802 is specifically used to: determine the energy consumption index of each computing node among multiple computing nodes based on computing power information and electricity consumption information; and determine the carbon emission index of each computing node among multiple computing nodes based on electricity consumption information and carbon emission information.

[0171] Optionally, the computing power information includes: the remaining computing power and the corresponding power demand; the electricity consumption information includes: electricity price information. The processing unit 802 is specifically used to: for each computing node, determine the energy consumption cost of the computing node based on the remaining computing power, power demand, and electricity price information; the energy consumption cost satisfies the following formula:

[0172] Where Ci represents energy consumption cost, Pi represents electricity demand, Q represents remaining computing power, and Ei represents electricity price information; based on the energy consumption cost of the computing power nodes, the energy consumption index of each computing power node among multiple computing power nodes is determined; the energy consumption index is proportional to the energy consumption cost.

[0173] Optionally, the electricity consumption information includes: green electricity consumption, total electricity consumption, and the proportion of green electricity in the power grid; the carbon emission information includes: carbon emission factor; the processing unit 802 is specifically used to: determine the green electricity proportion of each computing node by summing the ratio of green electricity consumption to total electricity consumption with the proportion of green electricity in the power grid; determine the green electricity absorption factor of each computing node among multiple computing nodes based on the green electricity proportion of the computing node; the green electricity absorption factor is inversely proportional to the green electricity proportion of the computing node; and determine the carbon emission index of each computing node among multiple computing nodes by weighted summation of the green electricity absorption factor and the carbon emission factor.

[0174] Optionally, the task information includes: task processing latency; the processing unit 802 is specifically used to: for each computing power node, determine the sum of the task processing latency, the transmission latency of transmitting the task to be scheduled to the computing power node, the transmission latency of receiving the task processing result from the computing power node, and the queuing latency of waiting for computing power resources at the computing power node as the latency index of the corresponding scheduling path of the computing power node.

[0175] Optionally, the processing unit 802 is specifically used for: for each computing power node, weighted summing of energy consumption indicators, carbon emission indicators and latency indicators to determine the comprehensive performance index of the computing power node; determining the target computing power node based on the comprehensive performance index of each computing power node; the comprehensive performance index of the target computing power node is less than the performance index threshold.

[0176] Optionally, the overall performance index of the target computing node is the minimum value among the overall performance indices of multiple computing nodes.

[0177] Optionally, the computing power information includes: the remaining computing power, and the task information also includes: the computing power requirement; the remaining computing power of the computing power node is greater than or equal to the computing power requirement of the task to be scheduled.

[0178] This application also provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are run on a computer, the computer performs the computing power scheduling method provided in the above embodiments.

[0179] This application also provides a computer program that can be directly loaded into a memory and contains software code. After being loaded and executed by a computer, the computer program can implement the computing power scheduling method provided in the above embodiments.

[0180] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this application can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer-readable storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a general-purpose or special-purpose computer.

[0181] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0182] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and other division methods may exist in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate; components shown as units may be one physical unit or multiple physical units, i.e., they may be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0183] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, in essence, or the part that contributes to general technology, or all or part of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0184] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A computing power scheduling method, characterized in that, The method comprises: obtaining computing power information, electricity consumption information and carbon emission information of a plurality of computing power nodes, and task information of a to-be-scheduled task; determining an energy consumption index and a carbon emission index of each computing power node in the plurality of computing power nodes according to the computing power information, the electricity consumption information and the carbon emission information; determining a time delay index of a corresponding scheduling path of each computing power node in the plurality of computing power nodes according to the task information of the to-be-scheduled task; determining a target computing power node from the plurality of computing power nodes according to the energy consumption index, the carbon emission index and the time delay index; scheduling the target computing power node to process the to-be-scheduled task.

2. The computing power scheduling method of claim 1, wherein, The method comprises: determining the energy consumption index of each computing power node in the plurality of computing power nodes according to the computing power information and the electricity consumption information; determining the carbon emission index of each computing power node in the plurality of computing power nodes according to the electricity consumption information and the carbon emission information.

3. The computing power scheduling method of claim 2, wherein, The computing power information comprises a computing power remaining amount and an electricity demand amount corresponding to the computing power remaining amount; the electricity consumption information comprises electricity price information; the method comprises: for each computing power node, determining an energy consumption cost of the computing power node according to the computing power remaining amount, the electricity demand amount and the electricity price information; the energy consumption cost satisfies the following formula: Among them, C i P is used to represent energy consumption cost. i Q represents the amount of electricity demand, and E represents the remaining computing power. i Used to display electricity price information; determining the energy consumption index of each computing power node in the plurality of computing power nodes according to the energy consumption cost of the computing power node; the energy consumption index is proportional to the energy consumption cost.

4. The computing power scheduling method of claim 2, wherein, The electricity consumption information comprises green electricity consumption, total electricity consumption and a green electricity proportion in a power grid; the carbon emission information comprises a carbon emission factor; the method comprises: for each computing power node, determining a green electricity proportion of the computing power node by summing a ratio of the green electricity consumption to the total electricity consumption and the green electricity proportion in the power grid; determining a green electricity consumption factor of each computing power node in the plurality of computing power nodes according to the green electricity proportion of the computing power node; the green electricity consumption factor is inversely proportional to the green electricity proportion of the computing power node; determining the carbon emission index of each computing power node in the plurality of computing power nodes by weighted sum of the green electricity consumption factor and the carbon emission factor.

5. The computing power scheduling method of claim 1, wherein, The task information comprises a task processing time delay; the method comprises: for each computing power node, determining a time delay index of a corresponding scheduling path of the computing power node by summing the task processing time delay, a transmission time delay of transmitting the to-be-scheduled task to the computing power node, a transmission time delay of receiving a task processing result of the computing power node, and a queuing time delay of waiting for a computing power resource in the computing power node.

6. The computing power scheduling method of claim 1, wherein, The target computing power node is determined from the plurality of computing power nodes according to the energy consumption index, the carbon emission index, and the time delay index, including: For each computing power node, the energy consumption index, the carbon emission index, and the time delay index are weighted and summed to determine a comprehensive performance index of the computing power node. According to the comprehensive performance index of each computing power node, the target computing power node is determined; the comprehensive performance index of the target computing power node is less than a performance index threshold.

7. The computing power scheduling method of claim 6, wherein, The comprehensive performance index of the target computing power node is the minimum value among the comprehensive performance indexes of the plurality of computing power nodes.

8. The computing power scheduling method of claim 1, wherein, The computing power information includes a computing power remaining amount, and the task information further includes a computing power demand amount. The remaining amount of the computing power node is greater than or equal to the computing power demand amount of the task to be scheduled.

9. A computing power scheduling apparatus, characterized by comprising: The device includes a communication unit and a processing unit. The communication unit is configured to obtain computing power information, power consumption information, and carbon emission information of a plurality of computing power nodes, and task information of a task to be scheduled. The processing unit is configured to determine an energy consumption index and a carbon emission index of each computing power node in the plurality of computing power nodes according to the computing power information, the power consumption information, and the carbon emission information. The processing unit is further configured to determine a time delay index of a corresponding scheduling path of each computing power node in the plurality of computing power nodes according to the task information of the task to be scheduled. The processing unit is further configured to determine a target computing power node from the plurality of computing power nodes according to the energy consumption index, the carbon emission index, and the time delay index. The processing unit is further configured to schedule the target computing power node to process the task to be scheduled.

10. A computing power scheduling device, characterized by, including: A processor and a memory; wherein the memory is configured to store one or more programs, the one or more programs including computer execution instructions, when the device is running, the processor executes the computer execution instructions stored in the memory to enable the device to perform the computing power scheduling method of any one of claims 1 to 8.

11. A computer readable storage medium characterized by, When the computer execution instructions stored in the computer readable storage medium are executed by the processor of the computing power scheduling device, the computing power scheduling device can perform the computing power scheduling method as claimed in any one of claims 1 to 8.

12. A computer program product, characterised in that, The computer program product includes a computer program or instructions, when the computer program or instructions are run on a computer, so that the computer executes the computing power scheduling method as claimed in any one of claims 1 to 8.

Images