Resource allocation method, device and system for energy resource and computing power resource fusion

Abstract

The invention relates to a resource allocation method, device and system for energy resource and computing power resource fusion. The method comprises the following steps: performing splitting processing on a computing power task of a first park to obtain a plurality of sub-tasks; and obtaining computing power information and energy information of the first park and the second park, inputting the plurality of sub-tasks, the computing power information and the energy information into a preset resource allocation model, and solving the resource allocation model according to the computing power information and the energy information of the first park and the second park and a preset constraint condition. And obtaining a resource allocation result under the condition that the total cost is minimized, allocating corresponding computing power resources according to the computing power allocation modes corresponding to the subtasks, and allocating corresponding energy resources according to the energy allocation modes corresponding to the subtasks. According to the scheme, reasonable distribution of the new energy can be realized while the computing power requirement of the industrial park is ensured, and the waste of the new energy is avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of cloud computing technology, and in particular to a resource allocation method, device and system for integrating energy resources with computing power resources. Background Art

[0002] In related technologies, more and more industrial parks use new energy for power supply to reduce dependence on traditional energy. When there is surplus electricity, due to the low surplus power and high energy storage costs, they usually choose to abandon the electricity. When the new energy supply cannot meet the electricity demand, traditional energy is used for power supply, resulting in waste of resources. In addition, the demand for computing power in industrial parks is also getting higher and higher. In order to solve the problem of insufficient computing power, the computing power resources of other parks are dispatched to obtain sufficient computing power. However, the traditional dispatching method only considers the principle of computing power priority, but does not consider the changes in electricity demand caused by changes in computing power allocation, resulting in an inability to balance the relationship between electricity cost and computing power demand, resulting in unnecessary waste of resources. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a resource allocation method, device and system that integrates energy resources and computing power resources.

[0004] According to a first aspect of an embodiment of the present disclosure, a resource allocation method integrating energy resources and computing power resources is provided, comprising:

[0005] In response to receiving a computing task to be executed by the first park, splitting the computing task to obtain a plurality of subtasks;

[0006] Obtain computing power information and energy information of the first park and the second park, respectively; the second park is a park other than the first park among multiple parks that share resources;

[0007] The plurality of subtasks, the computing power information and the energy information are input into a preset resource allocation model; the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model; the computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; the cost sub-model is used to determine the correlation between cost and energy consumption;

[0008] According to the computing power information and energy information of the first park and the second park respectively, the resource allocation model is solved according to the preset constraints to obtain a resource allocation result under the condition of minimizing the total cost; the resource allocation result includes a computing power allocation method and an energy allocation method corresponding to each subtask in the multiple subtasks;

[0009] For each subtask, corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask.

[0010] In some embodiments of the present application, the computing power sub-model is constructed by the following formula:

[0011] When the first Boolean variable ζ=0, the computing power allocation method is to use the computing power node server of the first park to execute the subtask, and the energy consumption of the computing power node server of the first park to execute the subtask is calculated by the following formula:

[0012] E i,local =P local *T i,local

[0013] Among them, i is the identifier of the subtask, E i,local is the energy consumption of the computing node server of the first park to execute the subtask, T i,local is the time consumed by the first park server to execute the subtask, P local is the computing power of the first park server;

[0014] When the first Boolean variable ζ=1, the computing power allocation method is to use the second park to execute the subtask, and the energy consumption of the computing power node server of the second park to execute the subtask is calculated by the following formula:

[0015] E i,remote =P i,remote *T i,remote +P i,wait *T i,line

[0016] Among them, E i,remote is the energy consumption of the computing node server in the second park to execute the subtask, P i,remote is the computing power of the computing node server executing the subtask, T i,remote The time consumed by the computing node server to execute the subtask, T i,line It is the delay of transmitting the subtask from the first industrial park to the second industrial park via the wireless link.

[0017] In some embodiments of the present application, the energy consumption sub-model is constructed by the following formula:

[0018] E i,sum =E i,local; +E i

[0019] Among them, E i,sum is the total energy consumption of the first park, E iis the daily energy consumption of the first park when calculating the i-th subtask excluding the computing overhead, E i,local The energy consumption of the computing power node server of the first park when executing the subtask;

[0020] In E i,NE_Out +E i,Storage_Out >E i,sum In the case where the second Boolean variable λ=0, it is determined that the energy allocation method is to use the energy of the first park to power the execution of the i-th subtask;

[0021] In E i,NE_Out +E i,Storage_Out <E i,sum , in the case where the second Boolean variable λ=1, the energy allocation method is to use the energy of the second park to power the execution of the i-th subtask, and the power supply of the energy of the second park to power the execution of the i-th subtask is calculated by the following formula:

[0022] E i,Trans_Out =((E i,NE_Out +E i,Storage_Out )-E i,sum )*η local,j

[0023] Among them, E i,Trans_Out is the power supply of the second park’s energy source for executing the i-th subtask, E i,Trans_Out is the amount of excess charge that can be allocated to the first park, E i,NE_Out is the power generation of the first park’s new energy, E i,Storage_Out is the discharge capacity of the first park energy storage, η local,j is the line loss rate generated by transmitting from the first park to the j-th second park.

[0024] In some embodiments of the present application, the cost sub-model is constructed by the following formula:

[0025] Cost i =(1-ζ)*E i,local +ζ*E i,remote -(1-λ)*α out *E i,Trans_Out +λ*α in *E i,Trans_In

[0026]

[0027] Among them, Cost i is the total energy consumption cost of the first park to complete the i-th subtask, α out is the power factor output through energy allocation, αin It is the electricity factor input through energy dispatching.

[0028] In some embodiments of the present application, the preset constraints include:

[0029] minCost all

[0030]

[0031] Among them, τ is the preset maximum delay, ζ i is the value corresponding to the computing power allocation method of the i-th subtask, λ i is the value corresponding to the energy allocation method of the i-th subtask.

[0032] In some embodiments of the present application, for each subtask, allocating corresponding computing resources according to the computing power allocation method corresponding to the subtask includes:

[0033] When there are multiple second parks and the computing power allocation method is to use the second park to execute the subtask, obtain server information of each park; the server information includes the number of servers, logic operation amount, matrix operation amount and storage space information;

[0034] Determine the target second park according to the server information and the computing power allocation method;

[0035] Control the target second park to execute the subtask.

[0036] According to a second aspect of an embodiment of the present disclosure, a resource allocation device integrating energy resources and computing power resources is provided, comprising:

[0037] A splitting unit, configured to split the computing task to be executed in the first park in response to receiving the computing task to be executed in the first park, and obtain a plurality of subtasks;

[0038] An acquisition unit is used to acquire computing power information and energy information of each of the first park and the second park; the second park is a park other than the first park among multiple parks that share resources;

[0039] An input unit, used to input the plurality of subtasks, the computing power information and the energy information into a preset resource allocation model; the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model; the computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; the cost sub-model is used to determine the correlation between cost and energy consumption;

[0040] A solving unit, configured to solve the resource allocation model according to the computing power information and energy information of the first park and the second park respectively and in accordance with preset constraints, to obtain a resource allocation result under the condition of minimizing the total cost; the resource allocation result includes a computing power allocation method and an energy allocation method corresponding to each of the multiple subtasks;

[0041] The allocation unit is used to allocate corresponding computing power resources according to the computing power allocation method corresponding to the subtask, and allocate corresponding energy resources according to the energy allocation method corresponding to the subtask.

[0042] According to a third aspect of an embodiment of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0043] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0044] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method as described in any one of the first aspects when executed by a processor.

[0045] The technical solution provided by the embodiment of the present disclosure may include the following beneficial effects: by splitting the computing power task of the first park, a plurality of subtasks are obtained; the computing power information and energy information of the first park and the second park are obtained, the second park is a park other than the first park among the multiple parks sharing resources, the plurality of subtasks, computing power information and energy information are input into a preset resource allocation model, the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model, according to the computing power information and energy information of the first park and the second park, the resource allocation model is solved according to the preset constraints, and the resource allocation result under the condition of minimizing the total cost is obtained, for each subtask, the corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and the corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask. By integrating the computing power resources and energy resources of multiple parks, the computing power resource allocation method and energy resource allocation method under the condition of the lowest cost are obtained, thereby achieving the reasonable allocation of new energy while ensuring the computing power demand of the park, and avoiding the waste of new energy.

[0046] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0048] Figure 1 It is a flow chart of a resource allocation method for integrating energy resources and computing power resources according to an exemplary embodiment.

[0049] Figure 2 It is a block diagram of a resource allocation device that integrates energy resources and computing power resources according to an exemplary embodiment.

[0050] Figure 3 It is a block diagram of a device for resource allocator for integrating energy resources and computing power resources according to an exemplary embodiment. DETAILED DESCRIPTION

[0051] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0052] The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments, and are not intended to limit the disclosed embodiments. The singular forms "a", "an" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0053] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at" or "when" or "in response to determination".

[0054] In addition, various forms of processes shown in the embodiments of the present disclosure may be used to reorder, add or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present application can be achieved, and this document does not limit this.

[0055] In related technologies, more and more industrial parks use new energy for power supply to reduce dependence on traditional energy. When there is surplus electricity, due to the low surplus power and high energy storage costs, they usually choose to abandon the electricity. When the new energy supply cannot meet the electricity demand, traditional energy is used for power supply, resulting in waste of resources. In addition, the demand for computing power in industrial parks is also getting higher and higher. In order to solve the problem of insufficient computing power, the computing power resources of other parks are dispatched to obtain sufficient computing power. However, the traditional dispatching method only considers the principle of computing power priority, but does not consider the changes in electricity demand caused by changes in computing power allocation, resulting in an inability to balance the relationship between electricity cost and computing power demand, resulting in unnecessary waste of resources.

[0056] In order to solve the above problems, the present disclosure provides a resource allocation method, device and system for integrating energy resources and computing power resources, by splitting the computing power task of the first park to obtain multiple subtasks; obtaining the computing power information and energy information of the first park and the second park respectively, the second park is a park other than the first park among multiple parks sharing resources, and inputting multiple subtasks, computing power information and energy information into a preset resource allocation model, the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model, according to the computing power information and energy information of the first park and the second park respectively, according to the preset constraints, the resource allocation model is solved to obtain the resource allocation result under the condition of minimizing the total cost, for each subtask, the corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and the corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask. By integrating the computing power resources and energy resources of multiple parks, the computing power resource allocation method and energy resource allocation method under the condition of the lowest cost are obtained, thereby realizing the reasonable allocation of new energy while ensuring the computing power demand of the park, and avoiding the waste of new energy.

[0057] Figure 1 is a flow chart of a resource allocation method for integrating energy resources and computing power resources according to an exemplary embodiment. Figure 1 As shown, it should be noted that the resource allocation method for integrating energy resources and computing power resources in the embodiment of the present application can be applied to the new energy computing power network, and the resource allocation method for integrating energy resources and computing power resources in the embodiment of the present application is applied to the resource allocation device for integrating energy resources and computing power resources. Figure 1 As shown, the method may include the following steps:

[0058] Step 101, in response to receiving a computing task to be executed in the first park, split the computing task into multiple subtasks.

[0059] In an embodiment of the present application, the terminal device of the first park can be used to send the computing power task to be executed to the new energy computing power network. After receiving the computing power task, the new energy computing power network splits the computing power task and obtains multiple subtasks.

[0060] For example, computing task A can be split into {A1, A2, A3, ..., A n}, and get n subtasks.

[0061] In some embodiments of the present application, the computing task may be training a deep learning model. A huge training data set may be consumed in the computing task. The training data set may be divided into multiple batches. Each batch may be processed in parallel on different servers, that is, multiple subtasks may be processed in parallel to speed up the training process.

[0062] In other embodiments of the present application, the computing task may be training a neural network model, and the neural network model may be divided into multiple layers or modules, each layer or module being a subtask, and different subtasks may be executed by different servers.

[0063] Step 102, obtaining computing power information and energy information of the first park and the second park respectively.

[0064] Among them, the second park is a park other than the first park among the multiple parks that share resources.

[0065] In some embodiments of the present application, computing power information may include the total computing power of the park, the current remaining computing power, and computing power; energy information may include the park's new energy available charge, the discharge of energy storage, and daily energy consumption.

[0066] It is understandable that when multiple parks participate in resource sharing, the parks other than the first park that initiates the application for task execution are the second parks.

[0067] Step 103, inputting multiple subtasks, computing power information and energy information into a preset resource allocation model.

[0068] Among them, the resource allocation model includes computing power sub-model, energy consumption sub-model and cost sub-model.

[0069] Among them, the computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; and the cost sub-model is used to determine the correlation between cost and energy consumption.

[0070] It is understandable that by comprehensively considering computing power factors, energy consumption factors and cost factors, it is possible to obtain a resource allocation plan with the lowest cost that meets computing power requirements and energy consumption requirements.

[0071] In some embodiments of the present application, the computing power sub-model is constructed by the following formula:

[0072] When the first Boolean variable ζ=0, the computing power allocation method is to use the computing power node server of the first park to execute the subtask, that is, to execute the subtask in the park. The energy consumption of the computing power node server of the first park to execute the subtask is calculated by the following formula:

[0073] E i,local =P local *T i,local

[0074] Among them, i is the identifier of the subtask, E i,local is the energy consumption of the computing node server in the first park to execute the subtask, T i,local is the time consumed by the first park server to execute the subtask, P local is the computing power of the first park server;

[0075] When the first Boolean variable ζ=1, the computing power allocation method is to use the second park to execute the subtask, that is, to call the computing power of the second park to execute the subtask. The energy consumption of the computing power node server of the second park to execute the subtask can be calculated by the following formula:

[0076] E i,remote =P i,remote *T i,remote +P i,wait *T i,line

[0077] Among them, E i,remote is the energy consumption of the computing node server in the second park to execute the subtask, P i,remote is the computing power of the computing node server executing the subtask, T i,remote The time consumed by the computing node server to execute the subtask, T i,line It is the delay of transmitting the subtask from the first industrial park to the second industrial park via the wireless link.

[0078] In some embodiments of the present application, the energy consumption sub-model is constructed by the following formula:

[0079] E i,sum =E i,kocal +E i

[0080] Among them, E i,sum is the total energy consumption of the first park, E i is the daily energy consumption of the first park when calculating the i-th subtask excluding the computational overhead, E i,local The energy consumption of the computing power node server in the first park when executing subtasks.

[0081] In E i,NE_Out +E i,Storage_Out >E i,sum In the case of , the second Boolean variable λ=0, and the energy allocation method is determined to use the energy of the first park to supply power for executing the i-th subtask.

[0082] It is understandable that if the new energy power generation of the first park plus the energy storage discharge power can exceed the total load of the park, the excess power can be deployed through the new energy computing power network and transmitted to other parks.

[0083] In E i,NE_Out +E i,Storage_Out <E i,sum , the second Boolean variable λ=1, that is, when the power generation inside the first park plus the energy storage discharge of the first park cannot meet the total load of the park, the energy allocation method is to use the energy of the second park to power the execution of the i-th subtask. The power supply of the energy of the second park to power the execution of the i-th subtask is calculated by the following formula:

[0084] E i,Trans_Out =((E i,NE_Out +E i,Storage_Out )-E i,sum )*η local,j

[0085] Among them, E i,Trans_Out is the power supply of the second park’s energy source for executing the i-th subtask, E i,Trans_Out is the amount of excess charge that can be allocated in the first park, E i,NE_Out is the power generation of new energy in the first park, E i,Storage_Out is the discharge capacity of the first park energy storage, η local,j is the line loss rate generated by transmitting from the first park to the jth second park.

[0086] In some embodiments of the present application, the cost sub-model is constructed by the following formula:

[0087] Cost i =(1-ζ)*E i,local +ζ*E i,remote -(1-λ)*α out *E i,Trans_Out +λ*α in *E i,Trans_In

[0088]

[0089] Among them, Cost i is the total energy consumption cost of the first park to complete the i-th subtask, α outis the power factor output through energy allocation, α in It is the electricity factor input through energy dispatching.

[0090] Step 104, based on the computing power information and energy information of the first park and the second park respectively, solve the resource allocation model according to the preset constraints to obtain the resource allocation result under the condition of minimizing the total cost.

[0091] Among them, the resource allocation result includes the computing power allocation method and energy allocation method corresponding to each subtask in multiple subtasks.

[0092] In some embodiments of the present application, the preset constraints include:

[0093] minCost all

[0094]

[0095] Among them, τ is the preset maximum delay, ζ i is the value corresponding to the computing power allocation method of the i-th subtask, λ i is the value corresponding to the energy allocation method of the i-th subtask.

[0096] It can be understood that the result of solving the resource allocation model includes the values ​​of ζ and λ corresponding to each subtask.

[0097] In one embodiment, a single-objective optimization particle swarm algorithm can be used to solve the resource allocation model. The particle swarm algorithm is used to optimize and solve the resource allocation model as follows:

[0098] Initialize the parameters of the particle swarm optimization algorithm; including the population size, maximum number of iterations, particle dimension, inertia weight, and learning factor;

[0099] Determine the structure of particles and initialize the position and velocity of particles in the particle swarm; use the Newton-Raphson method to calculate the power flow, calculate the fitness value of each particle, set the current position of each particle as the individual extreme value, and then evaluate all particles, that is, select the individual with the smallest fitness value as the group extreme value (group optimal solution), and the particle with the smallest fitness as the particle optimal solution;

[0100] Update the speed and position of all particles according to the global optimal solution and the particle optimal solution. If the number of iterations is not reached, repeat the above steps. If the number of iterations is reached, output the updated position and speed of the particles.

[0101] Step 105: for each subtask, allocate corresponding computing power resources according to the computing power allocation method corresponding to the subtask, and allocate corresponding energy resources according to the energy allocation method corresponding to the subtask.

[0102] In some embodiments of the present application, for each subtask, corresponding computing resources are allocated according to the computing power allocation method corresponding to the subtask, which may specifically include the following steps:

[0103] When there are multiple second parks and the computing power allocation method is to use the second park to execute subtasks, obtain server information of each park; the server information includes the number of servers, logical operation amount, matrix operation amount and storage space information;

[0104] Determine the target second park based on server information and computing power allocation method;

[0105] Control the target second park to execute subtasks.

[0106] In one embodiment, the most appropriate computing task execution strategy (i.e., computing power allocation method) is obtained based on the solution set obtained by solving the resource allocation model. The solution set may include the z corresponding to each subtask. i , i , η local,j 、T i,remote 、T i,line The values ​​of the parameters are combined with the information on the number of computing node servers, logical operations, matrix operations, and storage space size at this time, and Pareto solves each solution in the solution set to obtain the optimal solution set, select the solution with the lowest task execution delay, and finally perform task allocation and energy allocation according to this group of solutions. That is, according to the solution set obtained by solving the resource allocation model, it can be determined whether it is necessary to rely on computing resources from other parks to execute subtasks, and whether it is necessary to rely on energy resources from other parks to execute subtasks. On this basis, the Pareto solution is used to determine which second park's computing resources need to be used and which park's new energy resources need to be used to execute subtasks.

[0107] According to a resource allocation method for integrating energy resources and computing power resources proposed in an embodiment of the present application, the computing power task of the first park is split and processed to obtain multiple subtasks; the computing power information and energy information of the first park and the second park are obtained, and the second park is a park other than the first park among multiple parks that share resources, and the multiple subtasks, computing power information and energy information are input into a preset resource allocation model, and the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model. According to the computing power information and energy information of the first park and the second park, the resource allocation model is solved according to the preset constraints to obtain the resource allocation result under the condition of minimizing the total cost. For each subtask, the corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and the corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask. By integrating the computing power resources and energy resources of multiple parks, the computing power resource allocation method and energy resource allocation method under the condition of the lowest cost are obtained, thereby achieving the reasonable allocation of new energy while ensuring the computing power demand of the park, and avoiding the waste of new energy.

[0108] Figure 2 1 is a block diagram of a resource allocation device for integrating energy resources and computing power resources according to an exemplary embodiment. Figure 2 The device includes a splitting unit 201, an acquisition unit 202, an input unit 203, a solving unit 204 and an allocation unit 205.

[0109] The splitting unit 201 is used to split the computing task to be executed in the first park in response to receiving the computing task to be executed in the first park, and obtain multiple subtasks;

[0110] An acquisition unit 202 is used to acquire computing power information and energy information of the first park and the second park respectively; the second park is a park other than the first park among the multiple parks sharing resources;

[0111] The input unit 203 is used to input multiple subtasks, computing power information and energy information into a preset resource allocation model; the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model; the computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; the cost sub-model is used to determine the correlation between cost and energy consumption;

[0112] The solving unit 204 is used to solve the resource allocation model according to the computing power information and energy information of the first park and the second park respectively and according to the preset constraint conditions to obtain the resource allocation result under the condition of minimizing the total cost; the resource allocation result includes the computing power allocation method and the energy allocation method corresponding to each subtask in the multiple subtasks;

[0113] The allocation unit 205 is used to allocate corresponding computing power resources according to the computing power allocation method corresponding to the subtask, and allocate corresponding energy resources according to the energy allocation method corresponding to the subtask.

[0114] In some embodiments of the application, the computing power sub-model is constructed by the following formula:

[0115] When the first Boolean variable ζ=0, the computing power allocation method is to use the computing power node server of the first park to execute the subtask, and the energy consumption of the computing power node server of the first park to execute the subtask is calculated by the following formula:

[0116] E i,local =P local *T i,local

[0117] Among them, i is the identifier of the subtask, E i,local is the energy consumption of the computing node server in the first park to execute the subtask, T i,local is the time consumed by the first park server to execute the subtask, P local is the computing power of the first park server;

[0118] When the first Boolean variable ζ=1, the computing power allocation method is to use the second park to execute the subtask, and the energy consumption of the computing power node server of the second park to execute the subtask is calculated by the following formula:

[0119] E i,remote =P i,remote *T i,remote +P i,wait *T i,line

[0120] Among them, E i,remote is the energy consumption of the computing node server in the second park to execute the subtask, P i,remote is the computing power of the computing node server executing the subtask, T i,remote The time consumed by the computing node server to execute the subtask, T i,line It is the delay of transmitting the subtask from the first industrial park to the second industrial park via the wireless link.

[0121] In some embodiments of the application, the energy consumption sub-model is constructed by the following formula:

[0122] E i,sum =E i,kocal +E i

[0123] Among them, E i,sum is the total energy consumption of the first park, E iis the daily energy consumption of the first park when calculating the i-th subtask excluding the computational overhead, E i,local The energy consumption of the computing node server in the first park when executing subtasks;

[0124] In E i,NE_Out +E i,Storage_Out >E i,sum In the case of , the second Boolean variable λ=0, and the energy allocation method is determined to use the energy of the first park to power the execution of the i-th subtask;

[0125] In E i,NE_Out +E i,Storage_Out <E i,sum , in the case of, the second Boolean variable λ=1, the energy allocation method is to use the energy of the second park to power the execution of the i-th subtask, and the power supply of the energy of the second park to power the execution of the i-th subtask is calculated by the following formula:

[0126] E i,Trans_Out =((E i,NE_Out +E i,Storage_Out )-E i,sum )*η local,j

[0127] Among them, E i,Trans_Out is the power supply of the second park’s energy source for executing the i-th subtask, E i,Trans_Out is the amount of excess charge that can be allocated in the first park, E i,NE_Out is the power generation of new energy in the first park, E i,Storage_Out is the discharge capacity of the first park energy storage, η local,j is the line loss rate generated by transmitting from the first park to the jth second park.

[0128] In some embodiments of the present invention, the cost sub-model is constructed by the following formula:

[0129] Cost i =(1-ζ)*E i,local +ζ*E i,remote -(1-λ)*α out *E i,Trans_Out +λ*α in *E i,Trans_In

[0130]

[0131] Among them, Cost i is the total energy consumption cost of the first park to complete the i-th subtask, α out is the power factor output through energy allocation, α in It is the electricity factor input through energy dispatching.

[0132] In some embodiments of the application, the preset constraints include:

[0133] minCost all

[0134]

[0135] Among them, τ is the preset maximum delay, ζ i is the value corresponding to the computing power allocation method of the i-th subtask, λ i is the value corresponding to the energy allocation method of the i-th subtask.

[0136] In some embodiments of the present invention, the allocation unit 205 may be specifically used for:

[0137] When there are multiple second parks and the computing power allocation method is to use the second park to execute subtasks, obtain server information of each park; the server information includes the number of servers, logical operation amount, matrix operation amount and storage space information;

[0138] Determine the target second park based on server information and computing power allocation method;

[0139] Control the target second park to execute subtasks.

[0140] In the embodiment of the present application, the most suitable computing task execution strategy can be obtained based on the solution set obtained by solving the resource allocation model. The solution set includes a set of ζ corresponding to each subtask i , i , η local,j 、T i,remote 、T i,line The value of the parameter is combined with the information on the number of computing node servers, logical operations, matrix operations, and storage space size at this time, and Pareto solution is performed on each solution to obtain the optimal solution set, and the solution that can meet the lowest latency is selected. Finally, task allocation and energy allocation are performed according to this set of solutions. That is, the result of the Pareto solution of the above data includes the computing power scheduling object and energy scheduling object for each subtask.

[0141] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0142] According to the resource allocation device for integrating energy resources and computing power resources proposed in the embodiment of the present application, the computing power task of the first park is split and processed to obtain multiple subtasks; the computing power information and energy information of the first park and the second park are obtained, and the second park is a park other than the first park among the multiple parks that share resources, and the multiple subtasks, computing power information and energy information are input into a preset resource allocation model, and the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model. According to the computing power information and energy information of the first park and the second park, the resource allocation model is solved according to the preset constraints to obtain the resource allocation result under the condition of minimizing the total cost. For each subtask, the corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and the corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask. By integrating the computing power resources and energy resources of multiple parks, the computing power resource allocation method and energy resource allocation method under the condition of the lowest cost are obtained, thereby achieving the reasonable allocation of new energy while ensuring the computing power demand of the park, and avoiding the waste of new energy.

[0143] Figure 3 300 is a block diagram of a device for a resource allocation method for integrating energy resources and computing power resources according to an exemplary embodiment. For example, the device 300 may be an electronic device, such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0144] Reference Figure 3 , the device 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 312 , a sensor component 314 , and a communication component 316 .

[0145] The processing component 302 generally controls the overall operation of the device 300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0146] The memory 304 is configured to store various types of data to support operations on the device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0147] The power component 306 provides power to the various components of the device 300. The power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 300.

[0148] The multimedia component 308 includes a screen that provides an output interface between the device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front camera and / or a rear camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0149] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), and when the device 300 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 304 or sent via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0150] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0151] The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the device 300. For example, the sensor assembly 314 can detect the open / closed state of the device 300, the relative positioning of components, such as the display and keypad of the device 300, the sensor assembly 314 can also detect the position change of the device 300 or a component of the device 300, the presence or absence of user contact with the device 300, the orientation or acceleration / deceleration of the device 300, and the temperature change of the device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0152] The communication component 316 is configured to facilitate wired or wireless communication between the device 300 and other devices. The device 300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0153] In an exemplary embodiment, the apparatus 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0154] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, and the instructions can be executed by the processor 320 of the device 300 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0155] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, which implements the above method when executed by the processor 320 of the device 300 .

[0156] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0157] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A resource allocation method integrating energy resources and computing power resources, characterized in that: include: In response to receiving a computing task to be executed by the first park, splitting the computing task to obtain a plurality of subtasks; Obtain computing power information and energy information of the first park and the second park, respectively; the second park is a park other than the first park among multiple parks that share resources; Inputting the plurality of subtasks, the computing power information and the energy information into a preset resource allocation model; the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model; The computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; the cost sub-model is used to determine the correlation between cost and energy consumption; According to the computing power information and energy information of the first park and the second park respectively, the resource allocation model is solved according to the preset constraints to obtain a resource allocation result under the condition of minimizing the total cost; the resource allocation result includes a computing power allocation method and an energy allocation method corresponding to each subtask in the multiple subtasks; For each subtask, corresponding computing power resources are allocated according to the computing power allocation method corresponding to the subtask, and corresponding energy resources are allocated according to the energy allocation method corresponding to the subtask.

2. The resource allocation method for integrating energy resources and computing power resources according to claim 1 is characterized in that: The computing power sub-model is constructed by the following formula: When the first Boolean variable ζ=0, the computing power allocation method is to use the computing power node server of the first park to execute the subtask, and the energy consumption of the computing power node server of the first park to execute the subtask is calculated by the following formula: E i,local ＝ local * i,local Among them, i is the identifier of the subtask, E i,local is the energy consumption of the computing node server of the first park to execute the subtask, T i, is the time consumed by the first park server to execute the subtask, P local is the computing power of the first park server; When the first Boolean variable ζ=1, the computing power allocation method is to use the second park to execute the subtask, and the energy consumption of the computing power node server of the second park to execute the subtask is calculated by the following formula: E i,remote ＝ i,remote * i,remote + i,wait * i,line in, i,remote is the energy consumption of the computing node server in the second park to execute the subtask, P i,remote is the computing power of the computing node server executing the subtask, T i, The time consumed by the computing node server to execute the subtask, T i,line It is the delay of transmitting the subtask from the first industrial park to the second industrial park via the wireless link.

3. The resource allocation method for integrating energy resources and computing power resources according to claim 1 is characterized in that: The energy consumption sub-model is constructed by the following formula: E i,sum ＝ i,local + i Among them, E i,sum is the total energy consumption of the first park, E i is the daily energy consumption of the first park when calculating the i-th subtask excluding the computing overhead, E i,local The energy consumption of the computing power node server of the first park when executing the subtask; In E i,_ +E i,rage_ >E i, In the case where the second Boolean variable λ=0, it is determined that the energy allocation method is to use the energy of the first park to power the execution of the i-th subtask; In E i,_ +E i,torage_Out <E i, , in the case where the second Boolean variable λ=1, the energy allocation method is to use the energy of the second park to power the execution of the i-th subtask, and the power supply of the energy of the second park to power the execution of the i-th subtask is calculated by the following formula: AND i,Trans_Out =((And i,_ +E i,torage_Out )- i,sum )* local,j Among them, E i,Trans_Out is the power supply of the second park’s energy source for executing the i-th subtask, E i,Trans_Out is the amount of excess charge that can be allocated to the first park, E i,_ is the power generation of the first park’s new energy, E i,torage_Out is the discharge capacity of the first park energy storage, η local,j is the line loss rate generated by transmitting from the first park to the j-th second park.

4. The resource allocation method for integrating energy resources and computing power resources according to claim 1 is characterized in that: The cost sub-model is constructed by the following formula: Cost i =(1-z)* i,local +g* i,remote -(1-)* out * i,Trans_Out +* in * i,Trans_In Among them, Cost i is the total energy consumption cost of the first park to complete the i-th subtask, α 0ut is the power factor output through energy allocation, α in It is the electricity factor input through energy dispatching.

5. The resource allocation method for integrating energy resources and computing power resources according to claim 4 is characterized in that: The preset constraints include: min all Among them, τ is the preset maximum delay, ζ i is the value corresponding to the computing power allocation method of the i-th subtask, i is the value corresponding to the energy allocation method of the i-th subtask.

6. The resource allocation method for integrating energy resources and computing power resources according to claim 1 is characterized in that: For each subtask, allocating corresponding computing resources according to the computing power allocation method corresponding to the subtask includes: When there are multiple second parks and the computing power allocation method is to use the second park to execute the subtask, obtain server information of each park; the server information includes the number of servers, logic operation amount, matrix operation amount and storage space information; Determine the target second park according to the server information and the computing power allocation method; Control the target second park to execute the subtask.

7. A resource allocation device integrating energy resources and computing power resources, characterized in that: include: A splitting unit, configured to split the computing task to be executed in the first park in response to receiving the computing task to be executed in the first park, and obtain a plurality of subtasks; An acquisition unit is used to acquire computing power information and energy information of each of the first park and the second park; the second park is a park other than the first park among multiple parks that share resources; An input unit, used to input the plurality of subtasks, the computing power information and the energy information into a preset resource allocation model; the resource allocation model includes a computing power sub-model, an energy consumption sub-model and a cost sub-model; The computing power sub-model is used to determine the correlation between computing power and energy consumption; the energy consumption sub-model is used to determine the supply and demand relationship of energy; the cost sub-model is used to determine the correlation between cost and energy consumption; A solving unit, configured to solve the resource allocation model according to the computing power information and energy information of the first park and the second park respectively and in accordance with preset constraints, to obtain a resource allocation result under the condition of minimizing the total cost; the resource allocation result includes a computing power allocation method and an energy allocation method corresponding to each of the multiple subtasks; The allocation unit is used to allocate corresponding computing power resources according to the computing power allocation method corresponding to the subtask, and allocate corresponding energy resources according to the energy allocation method corresponding to the subtask.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 6 when executed by a processor.

Images