A scheduling method, a scheduling system, and a storage medium

Abstract

This application provides a scheduling method, which includes: a scheduling system receiving a resource request or a service request; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; responding to the resource request or service request, and determining a target node based on the first resource information or first service information, demand information, and node information; wherein the node information includes node performance information and node energy consumption information. This application differs from the traditional nearest-neighbor scheduling method by comprehensively considering the node's performance information and energy consumption information, thereby scheduling service requests to the optimal target node and improving the computational efficiency of network resources.

Description

Technical Field

[0001] This invention relates to the field of computing network technology, and in particular to a scheduling method, scheduling system and storage medium. Background Technology

[0002] When a user requests a service, because the network status and data center resource information are not mutually aware, the nearest service node may be selected to process the user's request based on a proximity-based scheduling method. However, this scheduling method cannot route the request to the optimal service node, affecting the user experience and consequently reducing the computational efficiency of network resources. Summary of the Invention

[0003] This application provides a scheduling method, scheduling system, and storage medium that can schedule service requests to the best service node, thereby improving the efficiency of network computing resources.

[0004] The technical solution of this application embodiment is implemented as follows:

[0005] In a first aspect, embodiments of this application provide a scheduling method, which is applied to a scheduling system, and the method includes:

[0006] Receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information;

[0007] Responding to the resource request or the service request, and determining the target node based on the first resource information or the first service information, the demand information, and the node information; wherein, the node information includes node performance information and node energy consumption information.

[0008] Secondly, embodiments of this application provide a scheduling system, the scheduling system comprising: a receiving unit and a determining unit;

[0009] The receiving unit is configured to receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information.

[0010] The determining unit is configured to respond to the resource request or the service request, and determine the target node based on the first resource information or the first service information, the demand information, and the node information; wherein the node information includes node performance information and node energy consumption information.

[0011] Thirdly, embodiments of this application provide a scheduling system, which includes: a processor and a memory; wherein,

[0012] The memory is used to store computer programs that can run on the processor;

[0013] The processor is configured to execute the scheduling method described above when running the computer program.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium, characterized in that the storage medium stores computer program code, and when the computer program code is executed by a computer, it implements the scheduling method described above.

[0015] This application provides a scheduling method, scheduling system, and storage medium. The method includes: receiving a resource request or a service request; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; responding to the resource request or service request, and determining a target node based on the first resource information or first service information, demand information, and node information; wherein the node information includes node performance information and node energy consumption information. In other words, after receiving a resource request or service request, the scheduling system can determine the target node based on the first resource information included in the resource request or the first service information, demand information, and node information included in the service request. The node information includes node performance information and node energy consumption information. Therefore, this application, when selecting a target node, differs from the traditional nearest-neighbor scheduling method by comprehensively considering the node's performance and energy consumption information, thereby scheduling service requests to the optimal target node and improving the computational efficiency of network resources. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 1 ;

[0017] Figure 2 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 2 ;

[0018] Figure 3 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 3 ;

[0019] Figure 4 This is a schematic diagram of the composition structure of the scheduling system proposed in the embodiments of this application. Figure 1 ;

[0020] Figure 5 This is a schematic diagram of the composition structure of the scheduling system proposed in the embodiments of this application. Figure 2 . Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the relevant application and not for limiting the application. Furthermore, it should be noted that, for ease of description, only the parts related to the relevant application are shown in the accompanying drawings.

[0022] Because the network status and data center resource information are not aware of each other, when a user requests a service, the network cannot send the request to the best service node, affecting the user experience and reducing the computing efficiency of network resources.

[0023] Currently, load balancing in traditional computing power service scheduling assumes that the energy consumption performance of computing power providers is consistent, without considering the energy consumption of computing power nodes. Traditional computing tasks will adopt a scheduling method of processing the nearest node, without taking into account the power supply, computing power supply, and computing power service demand, thus failing to schedule business requests to the best service node.

[0024] To address the current problem of failing to schedule service requests to the optimal service node, thereby reducing the computational efficiency of network resources, this application provides a scheduling method, a scheduling system, and a storage medium. The method includes: receiving a resource request or a service request; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; responding to the resource request or service request, and determining a target node based on the first resource information or first service information, demand information, and node information; wherein the node information includes node performance information and node energy consumption information. In other words, after receiving a resource request or service request, the scheduling system can determine the target node based on the first resource information included in the resource request or the first service information, demand information, and node information included in the service request. This node information includes node performance information and node energy consumption information. Therefore, this application, in selecting a target node, differs from the traditional nearest-neighbor scheduling method by comprehensively considering both node performance and energy consumption information, thereby scheduling service requests to the optimal target node and improving the computational efficiency of network resources.

[0025] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0026] Example 1

[0027] This application provides a scheduling method. Figure 1 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 1 ,like Figure 1 As shown, the scheduling method may include the following steps:

[0028] Step 101: Receive resource requests or service requests; wherein the resource requests or service requests include first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information.

[0029] In the embodiments of this application, the scheduling system can receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information.

[0030] It should be noted that, in the embodiments of this application, the scheduling system may be a computing power scheduling system, and this application does not specifically limit the type of scheduling system.

[0031] It should be noted that, in the embodiments of this application, the resource request may include first resource information, which may include resource type, resource location information, available resource quantity, etc. This application does not specifically limit the parameter type and number of parameters included in the first resource information.

[0032] It should be noted that, in the embodiments of this application, the service request may include first service information, which may include service identification information, service location information, load information, service response latency, etc. This application does not specifically limit the parameter types and number of parameters included in the first service information.

[0033] It should be noted that, in the embodiments of this application, the performance requirement information includes at least computing power requirements and network requirements. This application does not specifically limit the types and number of parameters included in the performance requirement information.

[0034] It should be noted that, in the embodiments of this application, the energy consumption demand information includes any one of the following: energy consumption level demand information, low energy consumption demand information, and energy type demand information. This application does not specifically limit the parameter type and number of parameters included in the energy consumption demand information.

[0035] Step 102: Respond to resource requests or service requests, and determine the target node based on the first resource information or first service information, demand information, and node information; wherein, the node information includes node performance information and node energy consumption information.

[0036] In the embodiments of this application, after receiving a resource request or service request, the scheduling system can respond to the resource request or service request and determine the target node based on the first resource information or first service information, demand information, and node information; wherein, the node information includes node performance information and node energy consumption information.

[0037] It should be noted that, in the embodiments of this application, node performance information may include any one of network information and computing power information; node energy consumption information may include any one of energy consumption classification information, energy consumption parameter information, and energy type information. This application does not specifically limit the types of information included in node performance information and computing power information.

[0038] It should be noted that, in the embodiments of this application, the computing power information includes the second resource information or the second service information corresponding to the node; wherein, the second resource information includes at least resource type, resource location information, available resource quantity, and resource response time; the second service information includes at least service identification information, service location information, load information, and service response latency. This application does not specifically limit the types of information included in the second resource information and the second service information.

[0039] It should be noted that, in the embodiments of this application, network information represents network performance information between the requester and the node, and network information includes at least latency and bandwidth; this application does not specifically limit the types of information included in network information.

[0040] It should be noted that, in the embodiments of this application, when the scheduling system determines the target node, it can determine the first node list based on the first resource information or the first service information, the performance requirement information and the node performance information, and then determine the target node based on the first node list, the energy consumption requirement information and the node energy consumption information.

[0041] For example, in an embodiment of this application, it is assumed that the scheduling system filters out a first list of nodes that meet the performance requirements as [node 1, node 2, node 3... node 7] based on the first resource information or first service information, performance requirement information and node performance information. Then, the system can determine the target nodes [node 1, node 2] that meet the energy consumption requirements based on the first list of nodes, energy consumption requirement information and node energy consumption information. That is, the target nodes determined by the scheduling system take into account both energy consumption requirements and performance requirements.

[0042] It should be noted that, in the embodiments of this application, when determining the target node, the scheduling system may also determine the second node list based on the first resource information or the first service information; and determine the target node based on the second node list, demand information, and node information.

[0043] Furthermore, in the embodiments of this application, when the scheduling system determines the target node based on the second node list, demand information, and node information, it can determine the comprehensive index corresponding to each node in the second node list based on the second node list, demand information, and node information; and then determine the target node based on the comprehensive index.

[0044] It should be noted that, in the embodiments of this application, when the scheduling system determines the comprehensive index corresponding to each node in the second node list based on the second node list, demand information, and node information, it can determine the first parameter value corresponding to each node in the second node list based on energy consumption demand information and energy consumption information; it can also determine the second parameter value corresponding to each node in the second node list based on performance demand information; and then it can determine the comprehensive index corresponding to each node in the second node list based on the first parameter value and the second parameter value.

[0045] It should be noted that, in the embodiments of this application, the first parameter value may be an energy consumption weight value, and this application does not specifically limit the type and size of the first parameter value.

[0046] It should be noted that, in the embodiments of this application, the second parameter value can be a performance weight value, and this application does not specifically limit the type and size of the second parameter value.

[0047] It should be noted that, in the embodiments of this application, the scheduling system can determine the target node in different ways. For example, it can filter out a first list of nodes that meet the performance requirements based on the first resource information or first service information, performance requirement information, and node performance information. Furthermore, it can determine the target node that meets the energy consumption requirements based on the first list of nodes, energy consumption requirement information, and node energy consumption information. Alternatively, it can determine a second list of nodes based on the first resource information or first service information. Then, it can determine the comprehensive index corresponding to each node in the second list based on the second list of nodes, requirement information, and node information. Finally, it can determine the target node based on the comprehensive index.

[0048] In other words, in the embodiments of this application, when the scheduling system determines the target node, it considers not only the network performance information between the requester and the node, but also the node's energy consumption information, so that nodes with lower energy consumption can be given priority; thereby, the service request can be scheduled to the best target node, thereby improving the efficiency of network computing resources.

[0049] It should be noted that, in the embodiments of this application, Figure 2 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 2 ,like Figure 2As shown, before the scheduling system determines the target node based on the first resource information or first service information, demand information, and node information, i.e. before step 102, it may also include the following steps:

[0050] Step 103: Receive energy consumption information reported by any node; wherein, the energy consumption information is used to reflect the energy consumption level of the node; wherein, the energy consumption information includes any one of the following: energy consumption classification information, energy consumption parameter information, and energy type information, and the energy consumption classification information is generated based on historical energy consumption information.

[0051] It should be noted that, in the embodiments of this application, when the scheduling system receives energy consumption information reported by any node, it may receive the energy consumption information when any node reports it through a triggered update; or, it may receive the energy consumption information when any node registers.

[0052] It should be noted that, in the embodiments of this application, the scheduling system can determine the packet type between itself and the first scheduling center; wherein, the packet type includes any one of the following: power supply information query packet, power supply information response packet, and power supply information update packet; and can also determine the identification method corresponding to the node between itself and the first scheduling center.

[0053] In other words, in the embodiments of this application, the scheduling system can agree on different interaction packet types with the first scheduling center and determine the identification method corresponding to the node with the first scheduling center. Through the identification method corresponding to the node, it can be ensured that the corresponding node can be found through the identification information corresponding to the node.

[0054] It should be noted that in the embodiments of this application, the first dispatch center may be a power dispatch center, and this application does not specifically limit the type of the first dispatch center.

[0055] It should be noted that, in the embodiments of this application, the dispatching system can send a power supply information query request to the first dispatching center; wherein, the power supply information query request includes the identification information corresponding to the node and the identification information corresponding to the power supply information query packet; then, it can receive the power supply information corresponding to the node; wherein, the power supply information response packet includes the power supply information corresponding to the node and the identification information corresponding to the power supply information response packet.

[0056] Furthermore, in the embodiments of this application, the scheduling system can store power supply information; wherein, the power supply information is the power supply information identified by the first scheduling center within the effective state time, so as to determine the target node by querying the power supply information.

[0057] In other words, in the embodiments of this application, when determining the target node, the scheduling system can also consider the power supply information corresponding to the node and the power load of the first scheduling center. By communicating with the first scheduling center, the system can select a node with sufficient power supply as the target node, thereby achieving peak shaving and valley filling of power through coordinated scheduling.

[0058] It should be noted that, in the embodiments of this application, the first dispatch center determines the peak or off-peak power supply periods based on historical information; and only during peak power supply periods, a power supply information query request is sent to the first dispatch center.

[0059] It should be noted that, in the embodiments of this application, the dispatching system may send a power supply information query request to the first dispatching center only during peak power supply periods to query the power supply information corresponding to the nodes in the relevant node list, while not actively initiating a power supply information query request during off-peak periods, which can reduce invalid information interaction.

[0060] It should be noted that, in the embodiments of this application, when there is an update to the power supply information, the dispatching system can receive a notification message sent by the first dispatching center; wherein the notification message carries the identification information corresponding to the current node, the power supply information corresponding to the current node, and the identification information corresponding to the power supply information update package.

[0061] In other words, in the embodiments of this application, the dispatching system can obtain power supply information in three different ways: Method 1: The dispatching system can send a power supply information query request to the first dispatching center to obtain the power supply information corresponding to the node, that is, it can obtain power supply information through active query; Method 2: Only during the peak power supply period, the dispatching system sends a power supply information query request to the first dispatching center to query the power supply information corresponding to the node in the relevant node list; Method 3: The dispatching system can receive notification information sent by the first dispatching center; wherein the notification information carries the identification information corresponding to the current node, the power supply information corresponding to the current node, and the identification information corresponding to the power supply information update package. This application does not specifically limit the method of obtaining power supply information.

[0062] In summary, the scheduling system can determine target nodes in different ways. When determining target nodes, it considers not only the network performance information between the requester and the node, but also the node's energy consumption information, thus prioritizing nodes with lower energy consumption. Simultaneously, it can consider the power supply information corresponding to the node and the power load situation of the first scheduling center. Through information exchange with the first scheduling center, nodes with sufficient power supply are selected as target nodes. This allows for peak shaving and valley filling of power through collaborative scheduling, enabling service requests to be scheduled to the optimal target node, thereby improving the efficiency of network computing resources.

[0063] This application provides a scheduling method, which includes: receiving a resource request or a service request; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; responding to the resource request or service request, and determining a target node based on the first resource information or first service information, demand information, and node information; wherein the node information includes node performance information and node energy consumption information. In other words, after receiving a resource request or service request, the scheduling system can determine the target node based on the first resource information included in the resource request or the first service information, demand information, and node information included in the service request. The node information includes node performance information and node energy consumption information. Therefore, this application, when selecting a target node, differs from the traditional nearest-neighbor scheduling method by comprehensively considering both node performance information and energy consumption information, thereby scheduling service requests to the optimal target node and improving the computational efficiency of network resources.

[0064] Example 2

[0065] Based on the above embodiments, another embodiment of this application provides a scheduling method. When performing computing power service scheduling, this method can take energy consumption factors into consideration to assist scheduling decisions. On the other hand, since power consumption is the main source of energy consumption for computing power providers (nodes), the method can coordinate power supply and computing power supply, as well as computing power service demand, to complete the coordinated scheduling of computing power and power. This enables mutual awareness of network status and data center service and resource status, and schedules user requests to the best data center for computation, thus ensuring user experience.

[0066] It should be noted that, in the embodiments of this application, on the one hand, the scheduling of computing power tasks can be considered based on power consumption factors. When a service request can be provided on multiple computing power providers (nodes), the computing power provider (node) with lower power consumption is given priority; or when a service can be deployed on multiple computing power nodes, the computing power node with lower power consumption is given priority; global power consumption optimization is considered. On the other hand, the scheduling of computing power tasks can be considered based on the load of the power system (first dispatch center). Computing power tasks are reflected as grid load in the power grid. For non-real-time services, the introduction of additional latency can be tolerated. The computing power dispatch center (dispatch system) can dispatch computing power tasks from peak to valley, thereby realizing the spatial transfer of power load through the scheduling of computing power tasks.

[0067] It should be noted that, in the embodiments of this application, two computing power network scheduling schemes are proposed. Scheme 1: computing power network scheduling that considers the power supply status of the scheduling system; Scheme 2: computing power scheduling that supports energy consumption demand and energy consumption status awareness. Scheme 1 will be described in detail below. During load balancing, this application differs from the traditional scheduling method of processing computing tasks locally. It not only considers whether the computing power provider can meet the service demand and whether the computing power provider (node) meets the energy consumption demand, but also considers the power supply status of the computing power provider (node) and the power load status of the entire power system. Information is exchanged between the computing power scheduling center (scheduling system) and the power scheduling system (first scheduling center) to realize the relief of power supply pressure by scheduling computing power tasks to "valley".

[0068] Furthermore, in the embodiments of this application, Figure 3 This is a schematic diagram of the scheduling method proposed in the embodiments of this application. Figure 3 ,like Figure 3As shown, the computing power network scheduling system considering power supply status includes the following steps: 1. When the computing power dispatch center (dispatch system) receives a computing power service request, it reads the computing power service demand information, including latency, computing type, energy consumption requirements, etc.; 2. The computing power dispatch center (dispatch system) combines the computing power status information of the computing power providers and the demand information of the service requests to initially generate a list of computing power providers that meet the computing power requirements; 3. Based on the initially screened list, the computing power dispatch center (dispatch system) requests the network controller to obtain the network information between the computing power requester and the corresponding computing power provider (node), including bandwidth, latency, etc.; 4. Based on the network information, the computing power dispatch center (dispatch system) finally generates a list of computing power providers that meet the requirements; 5. Add information interaction with the power dispatch center (first dispatch center) and... The process involves: 1. Obtaining power supply information from the list of computing power providers. Optionally, this information can be transmitted via a RESTful interface, carrying the identifier information of the computing power providers in the list; 2. The computing power dispatch center (dispatch system) and the power dispatch center (first dispatch center) need to negotiate and establish a unified provider identification mechanism (identification method corresponding to nodes) to ensure that the identifier can uniquely find the corresponding computing power provider (node). The power dispatch center returns the power supply status from the list of computing power providers. Power supply information can be fed back in two categories: idle and busy; or in terms of level; 3. Based on the received power supply information, the computing power dispatch center comprehensively judges and dispatches the current computing power service request to computing power nodes in the provider list with sufficient power supply, realizing the spatial transfer of power load through the coordinated scheduling of computing power and power.

[0069] It should be noted that, in the embodiments of this application, the scheduling system can consider the power supply information corresponding to the node and the power load of the first scheduling center. Through information exchange with the first scheduling center, the current computing power service request can be scheduled to the computing power node with sufficient power supply in the supplier list, so as to achieve peak shaving and valley filling of power through collaborative scheduling.

[0070] It should be noted that, in the embodiments of this application, the computing power scheduling center (scheduling system) and the power scheduling center (first scheduling center) need to agree on different interaction package types, including power supply information query package; power supply information response package; and power supply information update package.

[0071] In other words, in the embodiments of this application, the scheduling system and the first scheduling center can agree on different interaction packet types and determine a supplier identification mechanism (the identification method corresponding to the node) with the first scheduling center. Through the identification method corresponding to the node, it can be ensured that the corresponding node can be found through the identification information corresponding to the node.

[0072] It should be noted that in the embodiments of this application, when the computing power scheduling center obtains the power supply information corresponding to the node, it can obtain it in the following different ways: (1) active query method; (2) power supply information sending mechanism optimization method; (3) not actively query, but receive active notification information from the power dispatching system.

[0073] Furthermore, in the embodiments of this application, the process by which the computing power scheduling center (scheduling system) obtains the power supply information corresponding to a node through active querying may include the following steps: 1. The computing power scheduling center sends a power supply information query request to the power scheduling center (first scheduling center) based on the list of computing power suppliers, carrying supplier identification information (identification information corresponding to the node) and power supply information query packet identification information; 2. The power scheduling center (first scheduling center) reads the packet type information and node identification information, and queries the computing power supply nodes corresponding to the identification information respectively; 3. Returns the current power supply status of the corresponding node, carrying the power supply information response identification packet information; or only returns the node information with good current power supply status; 4. The power scheduling center may combine historical experience data to indicate the effective time of the status.

[0074] Furthermore, in the embodiments of this application, obtaining power supply information through the optimized power supply information transmission mechanism may include the following steps: 1. The power dispatch center (first dispatch center) generates power supply busy period information based on historical experience; 2. The computing power dispatch center only interacts with the power dispatch center during busy periods to query the power supply information of computing power providers in the relevant list, and does not actively initiate such interactions during non-busy periods to reduce invalid information interaction.

[0075] Furthermore, in the embodiments of this application, the computing power dispatch center does not actively query, but receives active notification information from the power dispatch system to obtain power supply information, which may include the following steps: 1. The computing power dispatch center does not actively send query information. If no power supply update information is received, it is assumed to be not busy and does not need to consider power supply information; 2. The computing power dispatch center only receives active request information from the power system (first dispatch center), carrying power supply idle node identification information and corresponding power supply message update packet identification information; 3. The power dispatch center can combine historical experience data to indicate the effective time of the status.

[0076] In other words, in the embodiments of this application, the dispatching system can obtain power supply information in three different ways: Method 1: The dispatching system can send a power supply information query request to the first dispatching center to obtain the power supply information corresponding to the node, that is, it can obtain power supply information through active query; Method 2: Only during the peak power supply period, the dispatching system sends a power supply information query request to the first dispatching center to query the power supply information corresponding to the node in the relevant node list; Method 3: The dispatching system can receive notification information sent by the first dispatching center; wherein the notification information carries the identification information corresponding to the current node, the power supply information corresponding to the current node, and the identification information corresponding to the power supply information update package. This application does not specifically limit the method of obtaining power supply information.

[0077] It should be noted that, in the embodiments of this application, the following optimizations can be made to the power supply information sending mechanism: 1. When sending supply information for the first time, the power center identification information, current power supply status, suggested status validity time, and packet identification information are carried; 2. If there is a status change, a notification message is actively sent to the computing power dispatch center; the packet type information is also included; if no information is sent, the system defaults to the current status; 3. The computing power dispatch center stores the power supply status corresponding to the power center identification information for the status validity time, and directly queries this record for dispatching; reducing information interaction with the power dispatch center.

[0078] It should be noted that, in the embodiments of this application, Scheme 2 can support computing power scheduling that is aware of energy consumption demand and energy consumption status. Scheme 2 will be explained below. Traditional load balancing in computing power service scheduling assumes that the energy consumption performance of computing power providers is consistent, only considering the computing power performance and service performance of the computing power providers, without considering the energy consumption of computing power nodes. This application proposes a scheme for coordinated scheduling of energy consumption and computing power, taking energy consumption as a factor in computing power scheduling, supporting computing power requesters (if they need to select suitable computing power nodes and deploy computing power services) to propose computing power requirements, network requirements, and energy consumption requirements, such as energy consumption level requirement information. Alternatively, energy type demand information (green electricity, non-green electricity); computing power providers can conduct energy consumption classification assessments based on historical energy consumption information and report the classification information to the computing power dispatch center. This reporting can be done in the following ways: 1. Adding interaction and processes for classification information and energy type information with the computing power dispatch center; computing power energy consumption classification information and energy type information can be reported using a triggered update method; 2. Computing power energy consumption classification information and energy type information can be carried along when the computing power center registers with the dispatch center; thus, the computing power dispatch center can make selections based on energy consumption demand, provider performance, and energy consumption information.

[0079] Furthermore, in the embodiments of this application, when the scheduling system determines the target supplier (target node), it can first meet the performance requirements and generate a supplier list (first node list). Then, it can combine energy consumption information (node ​​energy consumption information) and energy consumption demand information in the supplier list to further select the target supplier (target node) that meets the requirements.

[0080] For example, in an embodiment of this application, it is assumed that the scheduling system filters out a first list of nodes that meet the performance requirements as [node 1, node 2, node 3... node 7] based on the first resource information or first service information, performance requirement information and node performance information. Then, the system can determine the target nodes [node 1, node 2] that meet the energy consumption requirements based on the first list of nodes, energy consumption requirement information and node energy consumption information. That is, the target nodes determined by the scheduling system take into account both energy consumption requirements and performance requirements.

[0081] Furthermore, in the embodiments of this application, when determining the target supplier (target node), the scheduling system can also determine it through weighted calculation. When the computing power demander specifies the weight values ​​of energy consumption demand and performance demand, the comprehensive performance (comprehensive index) of the computing power supplier (node) is calculated by weighted calculation; or when the user has no demand, the computing power scheduling center collects relevant energy consumption information, and a triggered update method can also be adopted. When a service request can be provided on multiple computing power suppliers, the computing power supplier with lower energy consumption is given priority; or when the service can be deployed on multiple computing power nodes, the computing power node with lower energy consumption is given priority; considering global energy consumption optimization, optionally, the node energy consumption information can be further measured by the energy consumption information (data energy consumption ratio) required for the node to process a unit of data. For computing power service nodes, the data energy consumption ratio over a period of time needs to be measured as energy consumption parameter information.

[0082] It should be noted that, in the embodiments of this application, when the scheduling system determines the comprehensive index corresponding to each node, it can determine the first parameter value corresponding to each node in the second node list based on energy consumption demand information and energy consumption information; it can also determine the second parameter value corresponding to each node in the second node list based on performance demand information; and then determine the comprehensive index corresponding to each node in the second node list based on the first parameter value and the second parameter value.

[0083] It should be noted that, in the embodiments of this application, the first parameter value may be an energy consumption weight value, and this application does not specifically limit the type and size of the first parameter value.

[0084] It should be noted that, in the embodiments of this application, the second parameter value can be a performance weight value, and this application does not specifically limit the type and size of the second parameter value.

[0085] It should be noted that, in the embodiments of this application, the scheduling system can determine the target node in different ways. It can first meet the performance requirements and generate a supplier list (first node list), and then combine energy consumption information (node ​​energy consumption information) and energy consumption demand information in the supplier list to further select the target supplier (target node) that meets the requirements. Alternatively, it can be determined by weighted calculation. When the computing power demander specifies the weight values ​​of energy consumption demand and performance demand, the comprehensive performance of the computing power supplier is calculated by weighting; and then the target node can be determined based on the comprehensive performance.

[0086] In other words, in the embodiments of this application, when the scheduling system determines the target node, it considers not only the network performance information between the requester and the node, but also the node's energy consumption information, so that nodes with lower energy consumption can be given priority; thereby, the service request can be scheduled to the best target node, thereby improving the efficiency of network computing resources.

[0087] In summary, the scheduling system can determine target nodes in different ways. When determining target nodes, it considers not only the network performance information between the requester and the node, but also the node's energy consumption information, thus prioritizing nodes with lower energy consumption. Simultaneously, it can consider the power supply information corresponding to the node and the power load situation of the first scheduling center. Through information exchange with the first scheduling center, nodes with sufficient power supply are selected as target nodes. This allows for peak shaving and valley filling of power through collaborative scheduling, enabling service requests to be scheduled to the optimal target node, thereby improving the efficiency of network computing resources.

[0088] This application provides a scheduling method, which includes: receiving a resource request or a service request; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; responding to the resource request or service request, and determining a target node based on the first resource information or first service information, demand information, and node information; wherein the node information includes node performance information and node energy consumption information. In other words, after receiving a resource request or service request, the scheduling system can determine the target node based on the first resource information included in the resource request or the first service information, demand information, and node information included in the service request. The node information includes node performance information and node energy consumption information. Therefore, this application, when selecting a target node, differs from the traditional nearest-neighbor scheduling method by comprehensively considering both node performance information and energy consumption information, thereby scheduling service requests to the optimal target node and improving the computational efficiency of network resources.

[0089] Example 3

[0090] Based on the above embodiments, this application provides a scheduling system. Figure 4 A schematic diagram of the scheduling system's structure. Figure 1 ,like Figure 4 As shown, the scheduling system 10 includes: a receiving unit 11 and a determining unit 12;

[0091] The receiving unit 11 is configured to receive resource requests or service requests; wherein the resource request or the service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information.

[0092] The determining unit 12 is used to respond to the resource request or the service request, and to determine the target node based on the first resource information or the first service information, the demand information, and the node information; wherein the node information includes node performance information and node energy consumption information.

[0093] In the embodiments of this application, further, Figure 5 A schematic diagram of the scheduling system's structure. Figure 2 ,like Figure 5 As shown, the scheduling system 10 proposed in this application embodiment may further include a processor 13, a memory 14 storing instructions executable by the processor 13, and further, the scheduling system 10 may also include a communication interface 15 and a bus 16 for connecting the processor 13, the memory 14 and the communication interface 15.

[0094] In the embodiments of this application, the processor 13 can be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), controller, microcontroller, and microprocessor. It is understood that for different devices, the electronic device used to implement the above-mentioned processor function can also be other, and this application embodiment does not specifically limit it. The scheduling system 10 may also include a memory 14, which can be connected to the processor 13. The memory 14 is used to store executable program code, which includes computer operation instructions. The memory 14 may include high-speed RAM memory and may also include non-volatile memory, such as at least two disk drives.

[0095] In embodiments of this application, bus 16 is used to connect communication interface 15, processor 13 and memory 14 and the mutual communication between these devices.

[0096] In embodiments of this application, memory 14 is used to store instructions and data.

[0097] Further, in embodiments of this application, the processor 13 is configured to receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; respond to the resource request or service request, and determine a target node based on the first resource information or first service information, the demand information, and node information; wherein the node information includes node performance information and node energy consumption information.

[0098] In practical applications, the aforementioned memory 14 can be volatile memory, such as random-access memory (RAM); or non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD); or a combination of the above types of memory, and provide instructions and data to the processor 13.

[0099] This application provides a scheduling system that can receive resource requests or service requests. The resource request or service request includes first resource information or first service information and demand information. The demand information includes at least performance demand information and energy consumption demand information. The system responds to the resource request or service request and determines a target node based on the first resource information or first service information, demand information, and node information. The node information includes node performance information and node energy consumption information. In other words, after receiving a resource request or service request, the scheduling system can determine the target node based on the first resource information included in the resource request or the first service information and demand information included in the service request, as well as the node information. The node information includes node performance information and node energy consumption information. Therefore, this application, when selecting a target node, differs from the traditional nearest-neighbor scheduling method by comprehensively considering both node performance and energy consumption information, thereby scheduling service requests to the optimal target node and improving network computing resource efficiency.

[0100] This application provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the scheduling method described above.

[0101] Specifically, the program instructions corresponding to a scheduling method in this embodiment can be stored on storage media such as optical discs, hard disks, and USB flash drives. When the program instructions corresponding to a scheduling method in the storage media are read or executed by an electronic device, the following steps are included:

[0102] Receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information;

[0103] Responding to the resource request or the service request, and determining the target node based on the first resource information or the first service information, the demand information, and the node information; wherein, the node information includes node performance information and node energy consumption information.

[0104] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0105] This application is described with reference to schematic and / or block diagrams of implementations of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the schematic and / or block diagrams can be implemented by computer program instructions, and combinations of blocks in the schematic and / or block diagrams can be implemented. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the schematic and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0106] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in the implementation flow diagram. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0107] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0108] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application.

Claims

1. A scheduling method, characterized in that, The method includes: Receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information; Responding to the resource request or the service request, and determining the target node based on the first resource information or the first service information, the demand information, and the node information; wherein, the node information includes node performance information and node energy consumption information, the node performance information includes any one of network information and computing power information, and the node energy consumption information includes any one of energy consumption classification information, energy consumption parameter information, and energy type information; The step of determining the target node based on the first resource information or the first service information, the demand information, and the node information includes: The second node list is determined based on the first resource information or the first service information; The target node is determined based on the second node list, the requirement information, and the node information; The step of determining the target node based on the second node list, the demand information, and the node information includes: Based on the energy consumption demand information and the energy consumption information, determine the first parameter value corresponding to each node in the second node list; The second parameter value corresponding to each node in the second node list is determined based on the performance requirement information. The comprehensive index corresponding to each node in the second node list is determined based on the first parameter value and the second parameter value; The target node is determined based on the comprehensive indicators.

2. The method according to claim 1, characterized in that, The performance requirement information includes at least computing power requirements and network requirements; the energy consumption requirement information includes any one of the following: energy consumption classification requirement information, low energy consumption requirement information, and energy type requirement information.

3. The method according to claim 2, characterized in that, The computing power information includes second resource information or second service information corresponding to the node; wherein, the second resource information includes at least resource type, resource location information, available resource quantity, and resource response time; the second service information includes at least service identification information, service location information, load information, and service response latency; the network information represents the network performance information between the requester and the node, and the network information includes at least latency and bandwidth.

4. The method according to claim 1, characterized in that, Before determining the target node based on the first resource information or the first service information, the demand information, and the node information, the method further includes: Receive energy consumption information reported by any node; wherein the energy consumption information is used to reflect the energy consumption level corresponding to the node; wherein the energy consumption information includes any one of the energy consumption classification information, the energy consumption parameter information, and the energy type information, and the energy consumption classification information is generated based on historical energy consumption information.

5. The method according to claim 4, characterized in that, The process of receiving energy consumption information reported by any node includes: When any of the nodes reports via a triggered update, the energy consumption information is received; or... Upon registration at any of the nodes, the energy consumption information is received.

6. The method according to claim 1, characterized in that, The method further includes: Determine the packet type between the power supply information query packet and the first dispatch center; wherein, the packet type includes any one of the following: power supply information query packet, power supply information response packet, and power supply information update packet; The identifier corresponding to the node is determined through a method that communicates with the first scheduling center.

7. The method according to claim 6, characterized in that, The method further includes: Send a power supply information query request to the first dispatch center; wherein, the power supply information query request includes the identification information corresponding to the node and the identification information corresponding to the power supply information query package; Receive the power supply information corresponding to the node; wherein, the power supply information response packet includes the power supply information corresponding to the node and the identification information corresponding to the power supply information response packet.

8. The method according to claim 7, characterized in that, After receiving the power supply information corresponding to the node, the method further includes: The power supply information is stored; wherein the power supply information is the power supply information identified by the first dispatch center during the effective state time, so as to determine the target node by querying the power supply information.

9. The method according to claim 7, characterized in that, The method further includes: The first dispatch center determines peak or off-peak power supply periods based on historical information. The power supply information query request is sent to the first dispatch center only during the peak power supply period.

10. The method according to claim 7, characterized in that, The method further includes: When the power supply information is updated, a notification message is received from the first dispatch center; wherein the notification message carries the identification information corresponding to the current node, the power supply information corresponding to the current node, and the identification information corresponding to the power supply information update package.

11. A scheduling system, characterized in that, The scheduling system includes: a receiving unit and a determining unit; The receiving unit is configured to receive resource requests or service requests; wherein the resource request or service request includes first resource information or first service information and demand information; wherein the demand information includes at least performance demand information and energy consumption demand information. The determining unit is configured to respond to the resource request or the service request, and determine a target node based on the first resource information or the first service information, the demand information, and node information; wherein the node information includes node performance information and node energy consumption information, the node performance information includes any one of network information and computing power information, and the node energy consumption information includes any one of energy consumption classification information, energy consumption parameter information, and energy type information; wherein determining the target node based on the first resource information or the first service information, the demand information, and node information includes: determining a second node list based on the first resource information or the first service information; determining the target node based on the second node list, the demand information, and the node information; wherein determining the target node based on the second node list, the demand information, and the node information includes: determining a first parameter value corresponding to each node in the second node list based on the energy consumption demand information and the energy consumption information; determining a second parameter value corresponding to each node in the second node list based on the performance demand information; determining a comprehensive index corresponding to each node in the second node list based on the first parameter value and the second parameter value; and determining the target node based on the comprehensive index.

12. A scheduling system, characterized in that, The scheduling system includes: a processor and a memory; wherein, The memory is used to store computer programs that can run on the processor; The processor is configured to perform the method as described in any one of claims 1-10 when running the computer program.

13. A computer-readable storage medium, characterized in that, The storage medium stores computer program code, which, when executed by a computer, performs the method described in any one of claims 1-10.

Images