Control method, system and storage medium of computing power network based on blockchain

Abstract

The present application relates to a control method, system and computer-readable storage medium for a computing power network based on blockchain. The control method for a computing power network based on blockchain models the interaction between computing power providers in the computing power network as an optimization problem with a benefit function taking resource utilization as a parameter as the optimization target and operating cost and task waiting time as constraints, and optimizes and solves the optimization problem to obtain the optimal match between the required tasks and computing power resources, thereby achieving the goal of maximizing the utilization of computing power resources in the computing power network.

Description

Technical Field

[0001] The present application relates to the technical field of blockchain-based computing power network, and more specifically, to a control method, system and computer-readable storage medium for a blockchain-based computing power network. Background Art

[0002] As a new type of network architecture, computing network Figure 1 As shown in the figure, the core idea is to connect distributed computing power with the network through the joint participation of multiple computing power providers and multiple computing power demanders, integrate the ubiquitous and dynamically distributed computing, network, storage and other computing power resources in the network, and intelligently schedule and optimize their allocation. The computing power network currently mainly includes two modes: cloud-edge-end collaboration and computing-network integration. As services, data, and content gradually shift from centralized to coordinated and distributed, ubiquitous computing that integrates computing and network has also put forward new demands on the development of computing-network integration technology. Therefore, in order to break the status quo of computing power resource islands, balance the distribution of computing power resources, and give play to the advantages of distributed computing power resource pooling, studying the scheduling of computing power resources between multiple computing power providers under the computing power network architecture has become a basic and cutting-edge key scientific issue.

[0003] The sharing and allocation of distributed computing resources in the computing network is essentially a negotiation and cooperation between distributed nodes. However, the lack of trust between multiple computing providers hinders the sharing of resources. As a technology for multi-party co-construction, sharing and co-management, blockchain has been widely used in computing networks because its consensus mechanism is used to ensure that nodes reach a consensus on the validity and consistency of data and information in a distributed system. In a computing network that has reached a trust consensus, by optimizing the scheduling and precise allocation of computing resources, the competition for shared computing resources can be reduced and the overall efficiency of the computing network can be improved. Therefore, how to achieve bilateral matching of multiple demand tasks and multiple computing resources in the computing network is of great significance to achieving distributed consensus on computing resources and improving the overall computing resource utilization of the computing network. Summary of the invention

[0004] The technical problem to be solved by the present application is to provide a control method, system and computer-readable storage medium for a blockchain-based computing network that can achieve bilateral matching of required tasks and computing resources to maximize the utilization of computing resources, in response to the above-mentioned defects of the prior art.

[0005] In order to solve the technical problem, the present application proposes a control method for a computing power network based on blockchain in the first aspect, the method comprising: modeling the interaction relationship between each computing power provider in the computing power network as an optimization problem with a benefit function taking resource utilization as a parameter as an optimization target and operating cost and task waiting allocation time as constraints, optimizing and solving the optimization problem to obtain the optimal match between the required tasks and the computing power resources, wherein the overall benefit function of each computing power provider in the computing power network is expressed as:

[0006]

[0007] The constraints are:

[0008] Subject to Time i ≥time i ,i∈(1,n),

[0009]

[0010] Among them, Reward j Service for computing power providers j ,j∈{1,2,3,…}, QoE is the satisfaction index of the computing power demander, The electricity cost involved in the operating cost is Cost is the environmental treatment fee involved in the operating cost. j Is a constant, referring to the computing power provider Service j ,j∈{1,2,3,…}, n is the number of tasks to be assigned by the computing power demander, Time i time is the longest waiting time that the computing power demander can accept. i The actual waiting time of the computing power demander.

[0011] In one embodiment of the method according to the first aspect of the present application, the computing power demander's satisfaction measurement indicator QoE is calculated by the following formula:

[0012]

[0013] Among them, s represents the number of computing power demanders who receive computing power services.

[0014] According to an embodiment of the control method of the computing power network based on blockchain described in the first aspect of the present application, the computing power provider Service j ,j∈{1,2,3,…}total reward Reward j is represented as:

[0015]

[0016] Among them, Rev i For the computing resources needed by the computing power demand side, TR j Service for computing power providers j , the sum of resources of j∈{1,2,3,…}, Com i ={1,0} indicates the completion status of the task.

[0017] According to an embodiment of the control method of the computing power network based on blockchain described in the first aspect of the present application, the method further includes: allocating corresponding weighted benefits to each computing power provider based on the contribution value of each computing power provider participating in the consensus process in the consensus process, wherein a computing power provider Service j ,j∈{1,2,3,…}’s contribution to a task i is:

[0018]

[0019] Among them, Rev i Resource is the computing power resource required by the computing power demander. j Service for computing power providers j ,j∈{1,2,3,…} are the available resources of the current cooperation members.

[0020] According to an embodiment of the control method of the computing power network based on blockchain described in the first aspect of the present application, the method further includes: j ,j∈{1,2,3,…}, and use the task average contribution value as the basis for dynamically updating the credit value of the computing power provider, where the task average contribution value is calculated as follows:

[0021]

[0022] According to an embodiment of the control method of the computing power network based on the blockchain as described in the first aspect of the present application, the method also includes: dynamically updating the real-time credit value of each computing power provider in the computing power network according to the participation of each computing power provider in the consensus process, dividing each computing power provider into a main control layer, a coordination layer and a peripheral layer based on the credit value, and selecting a new master node from the main control layer, wherein the main control layer is composed of trusted high-performance computing nodes, the coordination layer is composed of nodes dynamically selected and marked by the main control layer based on the credit value, and the peripheral layer is composed of nodes other than the main control layer and the coordination layer.

[0023] According to an embodiment of the control method of the computing power network based on blockchain described in the first aspect of the present application, the credit value of node l (l≥1) in the kth (k≥1) round of consensus is defined as Reputation l,k , then the credit value Reputation l,k The multinomial weighted formula is:

[0024] Reputation l,k =αA l,k +βB l,k +γC l,k +ηD l,k +μE l,k +Reputation l,0 ,

[0025] Among them A l represents computing power, B l Represents memory capacity, C l Represents the bandwidth level, D l represents online stability, E l Represents the interactive rating trust, Reputation l,0 represents the initial credit value, and α, β, γ, η, and μ represent the weights of these five dimensions respectively.

[0026] In order to solve its technical problems, the present application proposes a control system for a computing power network based on blockchain in the second aspect. The system includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the control method of the computing power network based on blockchain as described above is implemented.

[0027] In order to solve the technical problem, the present application proposes a computer-readable storage medium in the third aspect, which stores a computer program. When the computer program is executed by a processor, the control method of the computing power network based on the blockchain as described above is implemented.

[0028] The control method, system and computer-readable storage medium of the blockchain-based computing network implemented in this application have the following beneficial effects:

[0029] (1) This application is based on cooperative game theory, and considers relevant influencing factors such as the available computing power in the computing power network, the computing power required for the required tasks, and the cost of completing the task. It studies the matching problem between the required tasks and the computing power resources, and proposes an alliance formation algorithm based on cooperative game. By analyzing, solving and optimizing the target profit function under the equilibrium strategy, the goal of maximizing the utilization rate of computing power resources in the computing power network is achieved.

[0030] (2) This application further proposes a hierarchical distributed credit consensus mechanism to meet the needs of distributed cooperation and resource sharing among computing power providers, thereby improving the efficiency of distributed consensus in the computing power network and reducing the waste of computing power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present application will be further described below with reference to the accompanying drawings and embodiments, in which:

[0032] Figure 1 It is a schematic diagram of the computing power network architecture in the prior art;

[0033] Figure 2 This is a logical structure diagram of a control system of a computing power network based on blockchain according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. In addition, the embodiments in the present application and the features in the embodiments may be combined with each other in the absence of conflict.

[0035] The computing power network based on blockchain solves the problem of reaching a trust consensus between computing power providers. Under the guarantee of shared allocation of distributed computing power resources, in order to maximize the utilization of widely distributed computing power resources in the computing power network, it is necessary to fully consider the bilateral supply and demand relationship between demand tasks and computing power resources. In addition, since different tasks have different requirements, such as low-latency response tasks or high-computing resource tasks, and the resources of a single computing power provider are limited and cannot respond to multiple intensive service requests at the same time, the computing power provider still needs to cooperate with other computing power providers to achieve resource sharing and collaborative work. Therefore, based on cooperative game theory, this application proposes a control method for a computing power network based on blockchain, which models the interactive relationship between the computing power providers in the computing power network as an optimization problem with a benefit function with resource utilization as a parameter as the optimization target and operating costs and task waiting time as constraints, and optimizes and solves the optimization problem to obtain the optimal match between demand tasks and computing power resources.

[0036] Specifically, in the computing power network, resource scheduling and computing power sharing are carried out. Each computing power provider needs to provide idle computing power to jointly complete the required tasks and maximize the overall computing power network efficiency. That is, each computing power provider has the same objective function and forms a cooperative relationship with each other. Therefore, the control method of the computing power network based on blockchain in this application selects cooperative game to model the relationship between each computing power provider. The specific definition of the cooperative game is as follows:

[0037] 1) Participants: various computing power providers;

[0038] 2) Strategy: whether to join a new alliance or leave the current alliance;

[0039] 3) Profit function: a function with the overall computing resource utilization as a parameter.

[0040] At the same time, in order to perform bilateral matching of tasks and resources, the computing power demander’s satisfaction with the task completion must be considered. The control method of the computing power network based on blockchain in this application formalizes the computing power demander’s satisfaction as the time spent waiting for the task to be assigned. j ,j∈{1,2,3,…} needs to consider its own construction cost and operation cost, among which the construction cost is constant and the operation cost involves electricity cost and environmental treatment fees Etc., so the benefits of each party depend on the operating costs and the use of its own computing resources.

[0041] Currently, a computing power demander has n tasks to be assigned. i , the longest waiting time that i∈(1,n) can accept is Time i , the actual waiting time is time i , the computing resources required are Rev i , computing power provider Service j , the sum of resources of j∈{1,2,3,…} is TR j , according to the completion of the taskCom i ={1,0}, the total reward of the computing power provider j can be expressed as:

[0042]

[0043] In addition, the available resource information of each computing power provider is independent of each other. Only when a computing power provider decides to cooperate with other computing power providers, the information will be shared with each other. j is public information. j ,j∈{1,2,3,…} can be based on the available resources of the current cooperation members. j As well as the task undertaken by each computing power provider, the probability of the available resources of other computing power providers can be inferred based on the Bayesian formula, that is:

[0044]

[0045] Among them, X = {X1, X2, X3, ...} represents the set of the number of tasks undertaken by all computing power providers. The probability inference of the above formula (1) is also known as belief in game theory. P(X|Resource j ) and P(Resource j ) can be directly calculated based on the data shared after the collaboration. In order to avoid underflow caused by a small data set, the above formula (1) is changed to the following formula:

[0046]

[0047] Finally, the overall profit function of each computing power provider in the computing power network can be expressed as:

[0048]

[0049] The constraints are:

[0050] Subject to Time i ≥time i ,i∈(1,n) (4)

[0051]

[0052] Among them, Cost j Is a constant, referring to the computing power provider Service j ,j∈{1,2,3,…}, n is the number of tasks to be assigned by the computing power demander, and QoE (Quality of Experience) is the satisfaction measurement indicator of the computing power demander. Specifically, QoE is calculated by the following formula:

[0053]

[0054] Among them, s represents the number of computing power demanders who receive computing power services.

[0055] The above optimization objective formula (3) requires that the resource utilization rate of the computing power provider and the computing power demander's satisfaction with the task completion are maximized, and at the same time, the cost expenditure of the computing power provider is minimized. The constraint formula (4) requires that the computing power demander's waiting time for each task cannot exceed the corresponding waiting upper bound, and the constraint formula (5) requires that the computing power provider's electricity and environmental costs cannot exceed the cost budget Cost j. Combining the optimization problem formed by the optimization objective formula (3) and the constraint condition formulas (4)-(5), it is theoretically proved that the cooperative alliance formation algorithm can converge to a stable equilibrium point and reach a suboptimal solution at a faster convergence speed. According to the computing power requirements of the demand task, the idle computing power of the computing power provider, the waiting delay, etc., after the optimization target finds the equilibrium point, it is considered that the task and the demand are optimally matched. By completing the corresponding demand task according to the corresponding computing power provider, the goal of maximizing the utilization of computing power resources in the computing power network can be achieved.

[0056] Furthermore, the control method of the computing power network based on blockchain in the present application also allocates corresponding weighted benefits to each computing power provider based on the contribution value of each computing power provider participating in the consensus process. j ,j∈{1,2,3,…} For the contribution degree of a task i, this application proposes the following contribution measurement indicators to complete the final profit distribution:

[0057]

[0058] in, Service for computing power providers j ,j∈{1,2,3,…} is the contribution value of a task i, Rev i Resource is the computing power resource required by the computing power demander. j Service for computing power providers j ,j∈{1,2,3,…} are the available resources of the current cooperation members.

[0059] Furthermore, the control method of the computing power network based on blockchain in the present application also controls the computing power provider Service j , the average contribution value of the task j∈{1,2,3,…} is calculated as follows:

[0060]

[0061] The average contribution value of the task will serve as a basis for dynamically updating the credit value of the computing power provider to encourage each computing power provider to actively participate in the coordinated allocation of computing power resources within a certain period.

[0062] Furthermore, according to the control method of the computing power network based on blockchain in the above-mentioned embodiment of the present application, in response to the demand of distributed computing power providers in the computing power network to cooperate and share computing power resources, a hierarchical distributed credit consensus model is proposed based on the dynamic process of consensus nodes generating valid blocks and uploading them to the chain, so as to promote trust cooperation and resource sharing among computing power providers.

[0063] Specifically, the control method of the computing power network based on blockchain of the present application dynamically updates the real-time credit value of each computing power provider according to the participation of each computing power provider in the consensus process in the computing power network, and divides each computing power provider into three layers based on the credit value, namely the main control layer, the coordination layer and the peripheral layer. Among them, the main control layer is composed of trusted high-performance computing nodes arranged in advance, and the new master node is preferentially selected from the main control layer to reduce the consumption generated during the selection. The coordination layer is composed of nodes dynamically selected and marked by the main control layer based on the credit value, and the peripheral layer is composed of nodes other than the main control layer and the coordination layer. Due to the low trust value, these nodes do not participate in the consensus process, but they can be marked into the coordination layer by the main control layer by improving the trust value.

[0064] Each new computing power provider that enters will receive a unique ID and initial credit value, which is accumulated as the computing power provider and other computing power providers reach consensus. Positive credit rewards can motivate computing power providers to participate in consensus behaviors to a greater extent, while negative credit reduces the weight of the member in the consensus. Define the credit value of node l (l≥1) in the kth (k≥1) round of consensus as Reputation l,k , then calculate the credit value Reputation l,k The multinomial weighted formula is:

[0065] Reputation l,k =αA l,k +βB l,k +γC l,k +ηD l,k +μE l,k +Reputation l,0 , (9)

[0066] Among them A l represents computing power, B l Represents memory capacity, C l Represents the bandwidth level, D l represents online stability, E l Represents the interactive rating trust, Reputation l,0 Represents the initial credit value, and α, β, γ, η, and μ represent the weights of these five dimensions respectively. The first four terms of this expression reflect the objective processing capability of the node, and the fifth term reflects the forwarding and communication completed during the distributed interaction of the node. According to the credit value calculated by the above formula (9), this application can divide the nodes into three layers: the main control layer, the coordination layer, and the peripheral layer.

[0067] As the number of computing power providers increases, the interactive information will grow exponentially, the performance of the consensus algorithm will decline, and the scalability will be limited to a certain extent, resulting in a large waste of resources. Therefore, the control method of the blockchain-based computing power network of the present application further considers using a suitable parallel distributed architecture to improve the algorithm in order to propose a more scalable and lightweight consensus algorithm. For a blockchain-based computing power network, multiple master nodes can be used to simultaneously calculate the same view unit task in parallel. When one of the master nodes completes a complete consensus process first, the main control layer notifies other master nodes to stop the corresponding process to reduce the additional consensus cost.

[0068] Based on the control method of the computing power network based on blockchain described above, the present application also proposes a control system 10 of the computing power network based on blockchain. Figure 2 As shown, the control system 10 of the computing power network based on blockchain includes a processor 11 and a memory 12, and the processor 11 and the memory 12 are communicatively connected. The memory 12 stores a computer program, and when the computer program is executed by the processor 11, the processor 11 implements the control method of the computing power network based on blockchain of the aforementioned embodiment of the present application.

[0069] The present application also proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the control method of the computing power network based on the blockchain of the aforementioned embodiment of the present application.

[0070] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A control method for a computing power network based on blockchain, characterized in that: The method includes: modeling the interaction relationship between each computing power provider in the computing power network as an optimization problem with a benefit function taking resource utilization as a parameter as an optimization target and operating cost and task waiting allocation time as constraints, optimizing and solving the optimization problem to obtain the optimal match between the required tasks and the computing power resources, wherein the overall benefit function of each computing power provider in the computing power network is expressed as: The constraints are: Subject to Time i ≥time i ,i∈(1,n), Among them, Reward j Service for computing power providers j ,j∈{1,2,3,…}, QoE is the satisfaction index of the computing power demander, The electricity cost involved in the operating cost is Cost is the environmental treatment fee involved in the operating cost. j Is a constant, referring to the computing power provider Service j ,j∈{1,2,3,…}, n is the number of tasks to be assigned by the computing power demander, Time i time is the longest waiting time that the computing power demander can accept. i The actual waiting time of the computing power demander.

2. The method according to claim 1, characterized in that The QoE, a measure of the computing power demander's satisfaction, is calculated by the following formula: Among them, s represents the number of computing power demanders who receive computing power services.

3. The method according to claim 1, characterized in that The computing power provider Service j ,j∈{1,2,3,…}total reward Reward j is represented as: Among them, Rev i For the computing resources needed by the computing power demand side, TR j Service for computing power providers j , the sum of resources of j∈{1,2,3,…}, Com i ={1,0} indicates the completion status of the task.

4. The method according to claim 1, characterized in that: The method further includes: allocating corresponding weighted benefits to each computing power provider based on the contribution value of each computing power provider participating in the consensus process, wherein a computing power provider Service j ,j∈{1,2,3,…}’s contribution to a task i is: Among them, Rev i Resource is the computing power resource required by the computing power demander. j Service for computing power providers j ,j∈{1,2,3,…} are the available resources of the current cooperation members.

5. The method according to claim 4, characterized in that The method also includes: performing a certain period T on the computing power provider Service j ,j∈{1,2,3,…}, and use the task average contribution value as the basis for dynamically updating the credit value of the computing power provider, where the task average contribution value is calculated as follows:

6. The method according to claim 1, characterized in that The method also includes: dynamically updating the real-time credit value of each computing power provider according to the participation of each computing power provider in the consensus process in the computing power network, dividing each computing power provider into a main control layer, a coordination layer and a peripheral layer based on the credit value, and selecting a new master node from the main control layer, wherein the main control layer is composed of trusted high-performance computing nodes, the coordination layer is composed of nodes dynamically selected and marked by the main control layer based on the credit value, and the peripheral layer is composed of nodes other than the main control layer and the coordination layer.

7. The method according to claim 6, characterized in that Define the credit value of node l (l≥1) in the kth (k≥1) round of consensus as Reputation l,k , then the credit value Reputation l,k The multinomial weighted formula is: Reputation l,k =αA l,k +βB l,k +γC l,k +ηD l,k +μE l,k +Reputation l,0 , Among them A l,k represents the computing power of node l during the kth round of consensus, B l,k represents the memory capacity of node l during the kth round of consensus, C l,k represents the bandwidth level of node l during the kth round of consensus, D l,k represents the online stability of node l during the kth round of consensus, E l,k Reputation represents the interactive rating trust of node l in the kth round of consensus. l,0 represents the initial credit value, and α, β, γ, η, and μ represent the weights of these five dimensions respectively.

8. A control system based on a computing power network of blockchain, characterized in that: The system includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the control method of the computing power network based on blockchain as described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, a control method for a computing power network based on blockchain as described in any one of claims 1 to 7 is implemented.

Images