Calculation power contribution degree evaluation method, device and system
Computing the target computing power through Stackelberg game method and normalization method provides the contribution degree of nodes, solving the problem of lack of contribution assessment of computing power transactions to multiple suppliers in the existing technology, optimizing the resource supply strategy, improving transaction efficiency and accuracy.
Patent Information
- Application Number
- CN202310646653.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-02
- Publication Date
- 2024-11-01
AI Technical Summary
The existing computing power trading process lacks a method to evaluate the contribution of multiple suppliers, resulting in the inability to effectively select the resource supply strategy that best suits computing power tasks.
Using Stackelberg game method and normalization method, the contribution correlation information of the subtask is sent to the target computing power supply node through the proxy node, generate and update the resource supply strategy, calculate the contribution degree of each target computing power supply node, and then select the optimal one. resource supply strategy.
It has achieved the evaluation of contribution to multiple suppliers and the optimization of resource supply strategies, and improved the efficiency and accuracy of computing power transactions.
Smart Images

Figure CN118885285A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a computing power contribution evaluation method, device and system. Background Art
[0002] Currently, in wide area, regional and metropolitan area network environments, there are various types of computing power resources, such as eastern computing power, western computing power, regional computing power, metropolitan computing power, edge computing power, etc. These computing power often belong to different organizations or institutions. The computing power transaction between different organizations or institutions is usually a transaction and pricing strategy for computing power suppliers to provide users with computing power. Such strategies often make the roles of both parties in the computing power transaction relatively fixed. The existing computing power transaction process lacks a method to evaluate the contribution of multiple suppliers. Summary of the invention
[0003] The technical problem to be solved by the present invention is to provide a computing power contribution evaluation method, device and system in response to the above-mentioned deficiencies in the prior art, so that the target computing power providing node provides multiple resource supply strategies, and then selects a strategy that is more in line with the computing power task from the multiple strategies according to the Stackelberg game method and calculates the contribution of each target computing power providing node, so as to solve the problem that the existing computing power trading process lacks a method for evaluating the contribution of multiple suppliers.
[0004] In a first aspect, the present invention provides a computing power contribution evaluation method, which is applied to a proxy node, comprising:
[0005] Step S11, sending a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply strategy according to the strategy set in response to receiving the strategy set;
[0006] Step S12, receiving the second resource supply strategy sent by the target computing power providing node;
[0007] Step S13, updating the policy set according to the second resource supply policy;
[0008] Step S14, determining whether the current time meets the preset time threshold, if so, executing step S15, otherwise, returning to step S11;
[0009] Step S15, obtaining the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculating the contribution of the target computing power providing node for executing each subtask according to the normalization method.
[0010] Preferably, the step S11, before sending the strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, further includes:
[0011] Acquire target computing task information, wherein the computing task includes at least one subtask, and the computing task information includes contribution association information of the at least one subtask;
[0012] Sending contribution association information of each subtask to at least one target computing power providing node, so that the target computing power providing node generates a first resource supply strategy according to the contribution association information;
[0013] Receiving a first resource provisioning strategy sent by the target computing power providing node;
[0014] A policy set is generated according to the first resource provisioning policy.
[0015] Preferably, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0016] Preferably, the policy set includes a first policy set and a second policy set;
[0017] The step of sending a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node includes:
[0018] The first policy set is sent to the target computing power providing node.
[0019] Preferably, the updating of the policy set according to the second resource supply policy includes:
[0020] Updating the first policy set according to the second resource provisioning policy;
[0021] The second resource provisioning policy is added to the second policy set.
[0022] Preferably, the step of obtaining a target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy includes:
[0023] According to the Stackelberg game strategy, the target computing power providing node for executing each subtask is obtained from the second strategy set.
[0024] Preferably, the step of obtaining a target computing power providing node for executing each subtask from the second strategy set according to the Stackelberg game strategy specifically includes:
[0025] All first resource supply strategies and / or second resource supply strategies in the second strategy set that meet the requirements of each of the subtasks are combined into a candidate strategy list;
[0026] The target computing power providing node for executing each subtask is determined from the list of alternative strategies.
[0027] Preferably, the method further comprises:
[0028] Determine whether the transaction is completed according to the share authorization proof mechanism DPoS. If so, the transaction is carried out, otherwise, return to step S11.
[0029] In a second aspect, the present invention further provides a computing power contribution evaluation method, which is applied to a target computing power providing node, comprising:
[0030] Step S21, in response to receiving a policy set sent by the proxy node, generating a second resource supply policy according to the policy set, wherein the policy set is generated according to contribution association information of at least one subtask;
[0031] Step S22, sending the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and then determines whether the current time meets the preset time threshold. When it is judged to be yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
[0032] Preferably, the step S21, in response to receiving the policy set sent by the proxy node, before generating the second resource provisioning policy according to the policy set, further comprises:
[0033] Receiving contribution association information of a subtask sent by the proxy node, wherein the contribution association information is sent by the proxy node after obtaining target computing power task information, the computing power task includes at least one subtask, and the computing power task information includes contribution association information of at least one subtask;
[0034] generating a first resource supply strategy according to the contribution association information;
[0035] The first resource supply policy is sent to the proxy node, so that the proxy node generates a policy set according to the first resource supply policy.
[0036] Preferably, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0037] In a third aspect, the present invention further provides a computing power contribution evaluation device, which is arranged in a proxy node and includes:
[0038] A set sending module, used to send a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply strategy according to the strategy set in response to receiving the strategy set;
[0039] A first receiving module, connected to the collective sending module, configured to receive the second resource supply strategy sent by the target computing power providing node;
[0040] an updating module, connected to the first receiving module, and configured to update a policy set according to the second resource provisioning policy;
[0041] A judgment module, connected to the update module, for judging whether the current time meets a preset time threshold, and if so, executing the contribution module, otherwise, returning to the collection sending module;
[0042] The contribution module is connected to the judgment module and is used to obtain the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculate the contribution of the target computing power providing node for executing each subtask according to the normalization method.
[0043] In a fourth aspect, the present invention further provides a computing power contribution evaluation device, which is arranged at a target computing power providing node, comprising:
[0044] A response module, configured to generate a second resource supply strategy according to the strategy set in response to receiving the strategy set sent by the proxy node, wherein the strategy set is generated according to the contribution association information of at least one subtask;
[0045] A first sending module is connected to the response module and is used to send the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and then determines whether the current time meets the preset time threshold. When the judgment is yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
[0046] In a fifth aspect, the present invention also provides a computing power contribution evaluation device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the computing power contribution evaluation method described in the first aspect above, or to implement the computing power contribution evaluation method described in the second aspect above.
[0047] In a sixth aspect, the present invention further provides a computing power contribution evaluation system, comprising a proxy node and a target computing power providing node;
[0048] The proxy node is used to execute the computing power contribution evaluation method described in the first aspect above;
[0049] The target computing power providing node is used to execute the computing power contribution evaluation method described in the second aspect above.
[0050] The computing power contribution evaluation method, device and system provided by the present invention include: a proxy node sends a policy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply policy according to the policy set in response to receiving the policy set; then receives the second resource supply policy sent by the target computing power providing node and updates the policy set according to the second resource supply policy; when it is determined that the current time does not meet the preset time threshold, repeats the above steps; when it is determined that the current time meets the preset time threshold, obtains the target computing power providing node that executes each subtask from the policy set according to the Stackelberg game strategy, and calculates the contribution of the target computing power providing node that executes each subtask according to the normalization method. Since the present invention enables the target computing power providing node to provide multiple resource supply policies, a policy that is more suitable for the computing power task is selected from the multiple policies according to the Stackelberg game method and the contribution of each target computing power providing node is calculated, thereby solving the problem that the existing computing power transaction process lacks a method for evaluating the contribution of multiple suppliers. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 This is a flowchart of a computing power contribution evaluation method according to Embodiment 1 of the present invention;
[0052] Figure 2 This is a flow chart of a computing power contribution evaluation method according to Embodiment 2 of the present invention;
[0053] Figure 3 This is a schematic diagram of the structure of a computing power contribution evaluation device according to Embodiment 3 of the present invention;
[0054] Figure 4 This is a schematic diagram of the structure of a computing power contribution evaluation device according to Embodiment 4 of the present invention;
[0055] Figure 5 This is a structural diagram of a computing power contribution evaluation device according to Example 5 of the present invention. DETAILED DESCRIPTION
[0056] In order to enable those skilled in the art to better understand the technical solution of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.
[0057] It should be understood that the specific embodiments and drawings described herein are only used to explain the present invention rather than to limit the present invention.
[0058] It can be understood that, in the absence of conflict, the various embodiments of the present invention and the various features in the embodiments can be combined with each other.
[0059] It can be understood that, for the convenience of description, the drawings of the present invention only show the parts related to the present invention, while the parts irrelevant to the present invention are not shown in the drawings.
[0060] It can be understood that each unit and module involved in the embodiments of the present invention may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.
[0061] It can be understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in an order different from that marked in the drawings.
[0062] It is understood that the flowcharts and block diagrams of the present invention illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the embodiments of the present invention. Each box in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or by a combination of hardware and computer instructions.
[0063] It can be understood that the units and modules involved in the embodiments of the present invention can be implemented by software or hardware. For example, the units and modules can be located in a processor.
[0064] Embodiment 1:
[0065] This embodiment provides a computing power contribution evaluation method, which is applied to proxy nodes, such as Figure 1 As shown, the method includes:
[0066] Step S11, sending a policy set generated according to contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply policy according to the policy set in response to receiving the policy set.
[0067] In this embodiment, for the scenario where multiple computing power providing nodes jointly execute computing power tasks centered on tasks, the proxy node can select a specific computing power providing node for the computing power task.
[0068] The contribution correlation information of the subtask is r i =(c i ,t i ,b i ,g i ), where r i For the i-th subtask, complete task r i , the computing power required is ci , the computing power usage time is t i , network latency, bandwidth and other performance requirements are b i , the contribution is g i It should be noted that c i 、b i ,t i Complete the task i The minimum requirement, and the contribution g i Satisfies the following formula:
[0069]
[0070] That is, the sum of the contributions of all subtasks is 1.
[0071] Optionally, before sending the policy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node in step S11, the step further includes:
[0072] Acquire target computing task information, wherein the computing task includes at least one subtask, and the computing task information includes contribution association information of the at least one subtask;
[0073] Sending contribution association information of each subtask to at least one target computing power providing node, so that the target computing power providing node generates a first resource supply strategy according to the contribution association information;
[0074] Receiving a first resource provisioning strategy sent by the target computing power providing node;
[0075] A policy set is generated according to the first resource provisioning policy.
[0076] In this embodiment, the computing task R is composed of at least one subtask, that is, R = {r 1 ,r 2 …r n}, the utility function for completing task R is G(r 1 ,r 2 …r n ).
[0077] Optionally, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ijThe computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0078] In this embodiment, the sum of the utility functions of the target computing power providing nodes is U(u ij )=Σ i u ij .
[0079] Optionally, the policy set includes a first policy set and a second policy set;
[0080] The step of sending a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node includes:
[0081] The first policy set is sent to the target computing power providing node.
[0082] Step S12, receiving the second resource supply strategy sent by the target computing power providing node.
[0083] In this embodiment, the same target computing power providing node can provide resource supply strategies for the same subtask multiple times. However, each time a resource supply strategy is provided for the same subtask, the provided c i 、b i ,t i Not less than the previous time, and hope to be recognized g' i Must not be higher than the previous time.
[0084] Step S13: updating the policy set according to the second resource provisioning policy.
[0085] Optionally, updating the policy set according to the second resource supply policy includes:
[0086] Updating the first policy set according to the second resource provisioning policy;
[0087] The second resource provisioning policy is added to the second policy set.
[0088] In this embodiment, the policy set is continuously updated so that the target computing power providing node can propose a new resource supply strategy according to the new policy set.
[0089] Step S14, determine whether the current time meets the preset time threshold, if so, execute step S15, otherwise, return to step S11.
[0090] In this embodiment, when the proxy node is looking for a target computing power providing node for a computing power task, it will open a bidding window period. During the bidding window period, it will continuously collect resource supply strategies provided by each target computing power providing node and add them to the strategy set.
[0091] Step S15, obtaining the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculating the contribution of the target computing power providing node for executing each subtask according to the normalization method.
[0092] In this embodiment, in the resource supply strategy for each subtask that is finally selected, the sum of the contributions requested by each target computing power providing node to execute the i-th subtask may not be equal to 1, so a normalization calculation is required to recalculate the contribution of executing each subtask in proportion.
[0093] Optionally, obtaining a target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy includes:
[0094] According to the Stackelberg game strategy, the target computing power providing node for executing each subtask is obtained from the second strategy set.
[0095] Optionally, the acquiring a target computing power providing node for executing each subtask from the second strategy set according to the Stackelberg game strategy specifically includes:
[0096] All first resource supply strategies and / or second resource supply strategies in the second strategy set that meet the requirements of each of the subtasks are combined into a candidate strategy list;
[0097] The target computing power providing node for executing each subtask is determined from the list of alternative strategies.
[0098] In this embodiment, the proxy node finds all target computing power providing nodes that satisfy the following formula in the second strategy set to form a candidate strategy list:
[0099]
[0100] in, Provide configuration for resources that can complete each subtask.
[0101] The proxy node then Find the target computing power providing node that satisfies the following formula:
[0102]
[0103] in, The utility function of the node that provides the target computing power for the i-th node.
[0104] Optionally, it also includes:
[0105] Determine whether the transaction is completed according to the share authorization proof mechanism DPoS. If so, the transaction is carried out, otherwise, return to step S11.
[0106] In this embodiment, when a transaction is reached between the proxy node and the target computing power providing node, the proxy node needs to send the transaction result to other proxy nodes within a certain range, and reach a consensus after obtaining recognition.
[0107] In a specific embodiment, the computing power contribution evaluation method may include the following steps:
[0108] Step 1: The agent node collects task information R = {r 1 ,r 2 …r n}, open the bidding window period Δt;
[0109] Step 2: The agent sends resource requirements and proposed contribution information to the computing power providing nodes within its jurisdiction. i =(c i ,t i ,b i ,g i ), i∈{1, 2, …n}, and wait for the resource supply strategy of the computing power provider node;
[0110] Step 3: The computing node proposes a resource supply strategy to the agent, such as node j providing resource c for subtask i i 、b i ,t i , the contribution that is expected to be recognized is g' i ,Right now
[0111] Step 4: The agent adds the resource supply strategies of the collected computing nodes to set B, and sends the updated set B to each computing node, waiting for the next round of bids from the computing nodes;
[0112] Step 5: Update set A according to the resource supply strategy and repeat step 4 until the bidding window Δt ends;
[0113] Step 6: The agent searches for a strategy that satisfies the following formula in set A and determines the optimal resource supply configuration for each subtask, namely
[0114]
[0115] Among them, G(r 1 ,r 2 …r n ) is the utility function for completing task R;
[0116] Step 7: Proxy Based Find a strategy that satisfies the following formula and confirm the resource supply node for each task;
[0117]
[0118] U(u ij )=∑ i u ij The sum of the utility functions of the nodes providing computing power;
[0119] Step 8: Use the normalization method to recalculate the contribution of each subtask in proportion The proxy node sends the transaction information to other proxies within a preset range;
[0120] Step 9: When the node agent receives the approval information from other agents within the preset range, the transaction is completed, otherwise it returns to step 4 to re-quote.
[0121] The computing power contribution evaluation method provided by the embodiment of the present invention comprises the following steps: the proxy node sends a policy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply policy according to the policy set in response to receiving the policy set; then receives the second resource supply policy sent by the target computing power providing node and updates the policy set according to the second resource supply policy; when it is determined that the current time does not meet the preset time threshold, repeats the above steps; when it is determined that the current time meets the preset time threshold, obtains the target computing power providing node for executing each subtask from the policy set according to the Stackelberg game strategy, and calculates the contribution of the target computing power providing node for executing each subtask according to the normalization method. Since the present invention enables the target computing power providing node to provide multiple resource supply policies, a policy that is more suitable for the computing power task is selected from the multiple policies according to the Stackelberg game method and the contribution of each target computing power providing node is calculated, thereby solving the problem that the existing computing power transaction process lacks a method for evaluating the contribution of multiple suppliers.
[0122] Embodiment 2:
[0123] This embodiment provides a computing power contribution evaluation method, which is applied to a target computing power providing node, such as Figure 2 As shown, the method includes
[0124] Step S21 : in response to receiving a policy set sent by the proxy node, generating a second resource supply policy according to the policy set, wherein the policy set is generated according to contribution association information of at least one subtask.
[0125] In this embodiment, for the scenario where multiple computing power providing nodes jointly execute computing power tasks centered on tasks, the proxy node can select a specific computing power providing node for the computing power task.
[0126] The contribution correlation information of the subtask is r i =(c i ,t i ,b i ,g i ), where r i For the i-th subtask, complete task r i , the computing power required is c i , the computing power usage time is t i , network latency, bandwidth and other performance requirements are b i , the contribution is g i It should be noted that c i 、b i ,t i Complete the task i The minimum requirement, and the contribution g i Satisfies the following formula:
[0127]
[0128] That is, the sum of the contributions of all subtasks is 1.
[0129] Optionally, the step S21, in response to receiving the policy set sent by the proxy node, before generating the second resource provisioning policy according to the policy set, further includes:
[0130] Receiving contribution association information of a subtask sent by the proxy node, wherein the contribution association information is sent by the proxy node after obtaining target computing power task information, the computing power task includes at least one subtask, and the computing power task information includes contribution association information of at least one subtask;
[0131] generating a first resource supply strategy according to the contribution association information;
[0132] The first resource supply policy is sent to the proxy node, so that the proxy node generates a policy set according to the first resource supply policy.
[0133] In this embodiment, the computing task R is composed of at least one subtask, that is, R = {r 1 ,r 2 …r n}, the utility function for completing task R is G(r 1 ,r 2 …r n ).
[0134] Step S22, sending the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and then determines whether the current time meets the preset time threshold. When it is judged to be yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
[0135] In this embodiment, when the proxy node is looking for a target computing power providing node for a computing power task, it will open a bidding window period. During the bidding window period, it will continuously collect resource supply strategies provided by each target computing power providing node and add them to the strategy set.
[0136] In the resource supply strategy finally selected for each subtask, the sum of the contributions requested by each target computing power provider node to execute the i-th subtask may not be equal to 1, so it is necessary to perform normalization calculation and recalculate the contribution of executing each subtask proportionally.
[0137] Optionally, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0138] Embodiment 3:
[0139] This embodiment provides a computing power contribution evaluation device, which is set in a proxy node, such as Figure 3As shown, including:
[0140] A set sending module 101 is used to send a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply strategy according to the strategy set in response to receiving the strategy set;
[0141] A first receiving module 102, connected to the set sending module 101, is used to receive the second resource supply strategy sent by the target computing power providing node;
[0142] An updating module 103, connected to the first receiving module 102, and configured to update a policy set according to the second resource provisioning policy;
[0143] The judgment module 104 is connected to the update module 103 and is used to judge whether the current time meets the preset time threshold. If so, the contribution module 105 is executed, otherwise, the collection sending module 101 is returned;
[0144] The contribution module 105 is connected to the judgment module 104, and is used to obtain the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculate the contribution of the target computing power providing node for executing each subtask according to the normalization method.
[0145] Preferably, the device further comprises:
[0146] An acquisition module, used to acquire target computing task information, wherein the computing task includes at least one subtask, and the computing task information includes contribution correlation information of at least one subtask;
[0147] A second sending module is used to send the contribution association information of each subtask to at least one target computing power providing node, so that the target computing power providing node generates a first resource supply strategy according to the contribution association information;
[0148] A second receiving module is used to receive a first resource provision strategy sent by the target computing power providing node;
[0149] The first generating module is used to generate a policy set according to the first resource supply policy.
[0150] Preferably, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ijThe first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0151] Preferably, the policy set includes a first policy set and a second policy set;
[0152] The collective sending module 101 includes:
[0153] A set sending unit is used to send the first strategy set to the target computing power providing node.
[0154] Preferably, the updating module 103 includes:
[0155] an updating unit, configured to update the first policy set according to the second resource provisioning policy;
[0156] An adding unit is used to add the second resource supply strategy to the second strategy set.
[0157] Preferably, the contribution module 105 includes:
[0158] The game unit is used to obtain the target computing power providing node for executing each subtask from the second strategy set according to the Stackelberg game strategy.
[0159] Preferably, the gaming unit specifically includes:
[0160] An alternative unit, configured to form an alternative strategy list by combining all first resource supply strategies and / or second resource supply strategies in the second strategy set that meet the requirements of each subtask;
[0161] The execution unit is used to determine the target computing power providing node for executing each subtask from the list of alternative strategies.
[0162] Preferably, the device further comprises:
[0163] The authorization module is used to determine whether the transaction is completed according to the share authorization proof mechanism DPoS. If so, the transaction is carried out; otherwise, the collection sending module 101 is returned.
[0164] Embodiment 4:
[0165] This embodiment provides a computing power contribution evaluation device, which is arranged at a target computing power providing node, such as Figure 4 As shown, including:
[0166] A response module 201 is used to generate a second resource supply strategy according to the strategy set in response to receiving the strategy set sent by the proxy node, wherein the strategy set is generated according to the contribution association information of at least one subtask;
[0167] The first sending module 202 is connected to the response module 201, and is used to send the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and determines whether the current time meets the preset time threshold. When the judgment is yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
[0168] Preferably, the device further comprises:
[0169] A third receiving module is used to receive the contribution association information of the subtask sent by the proxy node, wherein the contribution association information is sent by the proxy node after obtaining the target computing power task information, the computing power task includes at least one subtask, and the computing power task information includes the contribution association information of at least one subtask;
[0170] A second generating module, configured to generate a first resource supply strategy according to the contribution correlation information;
[0171] The second sending module is used to send the first resource supply policy to the proxy node, so that the proxy node generates a policy set according to the first resource supply policy.
[0172] Preferably, the first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ijThe network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
[0173] Embodiment 5:
[0174] This embodiment provides a computing power contribution evaluation device, including a memory 301 and a processor 302, wherein the memory 301 stores a computer program, and the processor 302 is configured to run the computer program to implement the computing power contribution evaluation method as described in Example 1, or to implement the computing power contribution evaluation method as described in Example 2.
[0175] Embodiment 6:
[0176] This embodiment provides a computing power contribution evaluation system, including a proxy node and a target computing power providing node;
[0177] The proxy node is used to execute the computing power contribution evaluation method described in Example 1;
[0178] The target computing power providing node is used to execute the computing power contribution evaluation method described in Example 2.
[0179] The computing power contribution evaluation method, device and system provided in Examples 2 to 6 combine the cloud, edge and end multi-level computing power scheduling technology and blockchain technology. The proxy node receives the computing power demand sent by the end-side device and determines whether there is computing power that meets the computing power demand on the edge of the computing power network. If so, the computing power is obtained from the edge of the computing power network. Otherwise, the computing power demand is sent to the cloud side of the computing power network to obtain computing power from the cloud side of the computing power network. The cloud side then receives the computing power demand sent by the proxy node, obtains computing power according to the computing power demand, and returns the obtained computing power to the proxy node. Finally, the edge device calculates the evidence information according to the obtained computing power and returns the obtained computing power to the end-side device, and broadcasts the evidence information to the blockchain to complete the evidence. Since the present invention adopts a cloud, edge and end multi-level computing power scheduling method and uses blockchain technology to perform computing power contribution evaluation, it can use the computing power network to perform computing power scheduling to achieve a low latency effect while using blockchain for trusted evidence of computing power services, thereby solving the problem of excessive latency in the existing method of using blockchain for computing power scheduling.
[0180] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.
Claims
1. A method for evaluating computing power contribution, characterized in that: Applied to a proxy node, the method comprises: Step S11, sending a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply strategy according to the strategy set in response to receiving the strategy set; Step S12, receiving the second resource supply strategy sent by the target computing power providing node; Step S13, updating the policy set according to the second resource supply policy; Step S14, determining whether the current time meets the preset time threshold, if so, executing step S15, otherwise, returning to step S11; Step S15, obtaining the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculating the contribution of the target computing power providing node for executing each subtask according to the normalization method.
2. The computing power contribution evaluation method according to claim 1 is characterized in that: The step S11, before sending the strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, further includes: Acquire target computing task information, wherein the computing task includes at least one subtask, and the computing task information includes contribution association information of the at least one subtask; Sending contribution association information of each subtask to at least one target computing power providing node, so that the target computing power providing node generates a first resource supply strategy according to the contribution association information; Receiving a first resource provisioning strategy sent by the target computing power providing node; A policy set is generated according to the first resource provisioning policy.
3. The computing power contribution evaluation method according to claim 2 is characterized in that: The first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
4. The computing power contribution evaluation method according to claim 1 is characterized in that: The policy set includes a first policy set and a second policy set; The step of sending a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node includes: The first policy set is sent to the target computing power providing node.
5. The computing power contribution evaluation method according to claim 4 is characterized in that: The updating of the strategy set according to the second resource supply strategy includes: Updating the first policy set according to the second resource provisioning policy; The second resource provisioning policy is added to the second policy set.
6. The computing power contribution evaluation method according to claim 4 is characterized in that: The step of obtaining a target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy includes: According to the Stackelberg game strategy, the target computing power providing node for executing each subtask is obtained from the second strategy set.
7. The computing power contribution evaluation method according to claim 6, characterized in that: The step of obtaining a target computing power providing node for executing each subtask from the second strategy set according to the Stackelberg game strategy specifically includes: All first resource supply strategies and / or second resource supply strategies in the second strategy set that meet the requirements of each of the subtasks are combined into a candidate strategy list; The target computing power providing node for executing each subtask is determined from the list of alternative strategies.
8. The computing power contribution evaluation method according to claim 1, characterized in that: Also includes: Determine whether the transaction is completed according to the share authorization proof mechanism DPoS. If so, the transaction is carried out, otherwise, return to step S11.
9. A method for evaluating computing power contribution, characterized in that: Applied to the target computing power providing node, the method includes: Step S21, in response to receiving a policy set sent by the proxy node, generating a second resource supply policy according to the policy set, wherein the policy set is generated according to contribution association information of at least one subtask; Step S22, sending the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and then determines whether the current time meets the preset time threshold. When it is judged to be yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
10. The computing power contribution evaluation method according to claim 9, characterized in that: The step S21, in response to receiving the policy set sent by the proxy node, before generating the second resource provisioning policy according to the policy set, further includes: Receiving contribution association information of the subtask sent by the proxy node, wherein the contribution association information is sent by the proxy node after obtaining target computing power task information, the computing power task includes at least one subtask, and the computing power task information includes contribution association information of at least one subtask; generating a first resource supply strategy according to the contribution association information; The first resource supply policy is sent to the proxy node, so that the proxy node generates a policy set according to the first resource supply policy.
11. The computing power contribution evaluation method according to claim 9, characterized in that: The first resource provisioning strategy and the second resource provisioning strategy are u ij (c ij ,t ij ,b ij ,g' i ), where u ij The first resource supply strategy or the second resource supply strategy provided by the j-th target computing power providing node for executing the i-th subtask, c ij The computing power provided by the node providing the jth target computing power to execute the i-th subtask, t ij The duration of computing power provided by the node providing the jth target computing power to execute the i-th subtask, b ij The network latency and bandwidth provided by the node providing the jth target computing power to execute the i-th subtask, g' i Provides the contribution requested by the node for executing the i-th subtask to the j-th target computing power.
12. A computing power contribution evaluation device, characterized in that: Set at the proxy node, the device includes: A set sending module, used to send a strategy set generated according to the contribution association information of at least one subtask to at least one target computing power providing node, so that the target computing power providing node generates a second resource supply strategy according to the strategy set in response to receiving the strategy set; A first receiving module, connected to the collective sending module, configured to receive the second resource supply strategy sent by the target computing power providing node; an updating module, connected to the first receiving module, and configured to update a policy set according to the second resource provisioning policy; A judgment module, connected to the update module, for judging whether the current time meets a preset time threshold, and if so, executing the contribution module, otherwise, returning to the collection sending module; The contribution module is connected to the judgment module and is used to obtain the target computing power providing node for executing each subtask from the strategy set according to the Stackelberg game strategy, and calculate the contribution of the target computing power providing node for executing each subtask according to the normalization method.
13. A computing power contribution evaluation device, characterized in that: Set at the target computing power providing node, the device includes: A response module, configured to generate a second resource supply strategy according to the strategy set in response to receiving the strategy set sent by the proxy node, wherein the strategy set is generated according to the contribution association information of at least one subtask; A first sending module is connected to the response module and is used to send the second resource supply strategy to the proxy node, so that the proxy node updates the strategy set according to the second resource supply strategy and then determines whether the current time meets the preset time threshold. When the judgment is yes, the target computing power providing node for executing each subtask is obtained from the strategy set according to the Stackelberg game strategy, and the contribution of the target computing power providing node for executing each subtask is calculated according to the normalization method.
14. A computing power contribution evaluation device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and the processor is configured to run the computer program to implement the computing power contribution evaluation method as described in any one of claims 1-8, or to implement the computing power contribution evaluation method as described in claims 9-11.
15. A computing power contribution evaluation system, characterized in that: Including proxy nodes and target computing power providing nodes; The proxy node is used to execute the computing power contribution evaluation method described in any one of claims 1 to 8; The target computing power providing node is used to execute the computing power contribution evaluation method described in any one of claims 9-11.
