Resource configuration method and device of micro-grid edge computing terminal, terminal and medium

Abstract

This invention discloses a resource allocation method, apparatus, terminal, and medium for a microgrid edge computing terminal. The resource allocation method for a microgrid edge computing terminal includes: obtaining a target function to be optimized associated with a computational resource cost function and a delay benefit function, as well as target constraints; generating a target optimization model based on the target function to be optimized and the target constraints; calculating the target additional capacity of each target edge node based on the microgrid edge node service data and the target optimization model, and allocating resources to each target edge node according to the target additional capacity. The technical solution of this invention can rationally allocate resources while considering delay constraints.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a resource allocation method, apparatus, terminal and medium for a microgrid edge computing terminal. Background Technology

[0002] Driven by dual carbon targets, more renewable energy sources will be integrated into low-voltage distribution networks in the form of distributed power sources, prompting some low-voltage distribution networks to transform into microgrids, becoming an important feature of the new power system. With the integration of distributed power sources, distributed energy storage, and electricity consumption information visualization devices, the types and number of microgrid services are constantly increasing, requiring real-time and precise control of these devices to meet diversified business processing needs.

[0003] The existing configuration of edge computing terminal resources in microgrids suffers from drawbacks such as redundant and blind configuration. When computing resources are scarce, services cannot be completed on time, while when computing resources are abundant, they become idle and wasted. Therefore, optimizing the configuration of computing resources in microgrid cloud-edge collaborative systems is of great significance in minimizing service latency and economic costs. Summary of the Invention

[0004] This invention provides a resource allocation method, device, terminal, and medium for a microgrid edge computing terminal, which can rationally allocate resources under the condition of considering latency constraints.

[0005] According to one aspect of the present invention, a resource allocation method for a microgrid edge computing terminal is provided, comprising:

[0006] Obtain the target function to be optimized, which is associated with the computational resource cost function and the delay benefit function, as well as the target constraints;

[0007] Generate an objective optimization model based on the objective function to be optimized and the objective constraints;

[0008] Based on the microgrid edge node business data and the target optimization model, the target additional capacity of each target edge node is calculated, and resources are allocated to each target edge node according to the target additional capacity.

[0009] According to another aspect of the present invention, a resource allocation device for a microgrid edge computing terminal is provided, comprising:

[0010] The data acquisition module is used to acquire the target function to be optimized associated with the computing resource cost function and the time delay benefit function, as well as the target constraints.

[0011] The objective optimization model generation module is used to generate an objective optimization model based on the objective function to be optimized and the objective constraints.

[0012] The target capacity calculation module is used to calculate the target capacity of each target edge node based on the microgrid edge node business data and the target optimization model, so as to allocate resources to each target edge node according to the target capacity of each target edge node.

[0013] According to another aspect of the present invention, a microgrid edge computing terminal is provided, the microgrid edge computing terminal comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to execute the resource allocation method of the microgrid edge computing terminal according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the resource allocation method of a microgrid edge computing terminal according to any embodiment of the present invention.

[0018] The technical solution of this invention obtains the target optimization function associated with the computational resource cost function and the delay benefit function, as well as the target constraints, and then generates a target optimization model based on the target optimization function and the target constraints. Since the target optimization function is correlated with the computational resource function and the delay benefit function, the target optimization function can estimate the computational cost and delay benefit of microgrid nodes. Based on the microgrid edge node business data and the target optimization model, the target additional capacity of each target edge node is calculated. Resource allocation for each target edge node is then performed based on its target additional capacity. This approach comprehensively considers both computational resource cost and delay benefit, achieving a reasonable allocation of target edge node capacity. It solves the problem of unreasonable resource allocation in existing microgrid edge computing terminals and enables reasonable resource allocation under the condition of considering delay constraints.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating a resource allocation method for a microgrid edge computing terminal provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a resource allocation method for a microgrid edge computing terminal provided in Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram illustrating the configuration of a microgrid edge computing terminal service provided in Embodiment 2 of the present invention;

[0024] Figure 4 This is a flowchart illustrating a multi-objective resource allocation method for microgrid edge computing terminals that considers service weights, provided in Embodiment 2 of the present invention.

[0025] Figure 5 This is a schematic diagram of the structure of a resource allocation device for a microgrid edge computing terminal provided in Embodiment 3 of the present invention;

[0026] Figure 6 A schematic diagram of the structure of a microgrid edge computing terminal that can be used to implement an embodiment of the present invention is shown. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a resource configuration method for a microgrid edge computing terminal according to Embodiment 1 of the present invention. This embodiment is applicable to situations where the capacity of microgrid nodes is reasonably configured. This method can be executed by a resource configuration device of the microgrid edge computing terminal, which can be implemented in hardware and / or software and can be configured within the microgrid edge computing terminal. Figure 1 As shown, the method includes:

[0031] S110. Obtain the target function to be optimized, which is associated with the resource cost function and the time delay benefit function, as well as the target constraints.

[0032] The computational resource cost function determines the computational resource cost consumed by the computing terminal during computation. The latency benefit function describes the efficiency level of the computing service. The target optimization function is the result of data processing of the computational resource cost function and the latency benefit function based on resource allocation requirements. The target constraints are constraints that match the target optimization function.

[0033] In this embodiment of the invention, the computing resource cost function and the delay benefit function associated with the microgrid computing service can be obtained first. Then, the computing resource cost function is maximized and the delay benefit function is minimized to obtain the target function to be optimized. Then, the constraint conditions that match the target function to be optimized, i.e., the target constraint conditions, can be obtained.

[0034] S120. Generate the target optimization model based on the target function to be optimized and the target constraints.

[0035] The target optimization model can be an optimization model determined based on the target function to be optimized and the target constraints, and is used to calculate the optimal capacity of microgrid nodes when performing calculations.

[0036] In this embodiment of the invention, the target function to be optimized can be normalized, and a target optimization model for microgrid computing resource allocation can be established based on the normalized target function to be optimized and the target constraints.

[0037] S130. Based on the microgrid edge node business data and the target optimization model, calculate the target additional capacity of each target edge node, and allocate resources to each target edge node according to the target additional capacity of each target edge node.

[0038] The microgrid edge node service data can be relevant data generated when edge nodes in a microgrid execute services. This data may include the type of service, the service offloading status, the amount of data input during service execution, the amount of computing resources used, and the data transmission rate. The target edge node can be an edge node in the microgrid that requires capacity adjustment. The target added capacity can be the capacity that needs to be added to the target edge node.

[0039] In this embodiment of the invention, the service data of microgrid edge nodes can be filtered to determine the service data of target edge nodes. The service data of target edge nodes can be parsed to determine the parameters that need to be input into the target optimization model. The determined parameters are then input into the target optimization model. Based on the output of the target optimization model, the target additional capacity of each target edge node is determined. Based on the target additional capacity of each target edge node, the corresponding capacity adjustment of each target edge node is carried out to complete the resource allocation of the target edge nodes.

[0040] The technical solution of this invention obtains the target optimization function associated with the computational resource cost function and the delay benefit function, as well as the target constraints, and then generates a target optimization model based on the target optimization function and the target constraints. Since the target optimization function is correlated with the computational resource function and the delay benefit function, the target optimization function can estimate the computational cost and delay benefit of microgrid nodes. Based on the microgrid edge node business data and the target optimization model, the target additional capacity of each target edge node is calculated. Resource allocation for each target edge node is then performed based on its target additional capacity. This approach comprehensively considers both computational resource cost and delay benefit, achieving a reasonable allocation of target edge node capacity. It solves the problem of unreasonable resource allocation in existing microgrid edge computing terminals and enables reasonable resource allocation under the condition of considering delay constraints.

[0041] Example 2

[0042] Figure 2 This is a flowchart of a resource allocation method for a microgrid edge computing terminal provided in Embodiment 2 of the present invention. This embodiment is a specific embodiment based on the above embodiment, and provides specific optional implementation methods for generating a target optimization model based on the target function to be optimized and the target constraints. Figure 2 As shown, the method includes:

[0043] S210. Obtain the target function to be optimized, which includes the computational resource cost function and the delay benefit function, as well as the target constraints.

[0044] Generally, cloud-edge collaboration in microgrid automation systems enables flexible expansion of functional applications and maximizes the utilization of computing resources. Under the cloud-edge collaboration architecture, some microgrid services are executed locally on the edge computing terminal, while others are offloaded to other nodes in the cloud-edge collaboration system for processing.

[0045] In an optional embodiment of the present invention, the target function to be optimized includes:

[0046]

[0047] Among them, C sum Let C represent the resource cost function, where t represents the ordinal number of the working period of the edge node, T represents the working time interval of the edge node, i represents the ordinal number of the edge node, I represents the set of edge nodes, and C represents the resource cost function. inv,i Let C represent the investment cost of the i-th edge node. op,i C represents the operating cost of the i-th edge node. re,i,C C represents the cost of the i-th edge node renting computing resources from other edge nodes. re,i,E Let μ represent the cost of renting cloud node computing resources for the i-th edge node, and let μ represent the latency benefit function. t This represents the latency benefit of the edge node during time period t.

[0048] In an optional embodiment of the present invention, C inv,i =θ△R i ; Where θ is the investment cost required for the construction unit to build edge computing terminal capacity, a is the first influence coefficient of computing load on operating cost, b is the second influence coefficient of computing load on operating cost, c is the third influence coefficient of computing load on operating cost, and L t,k,l The number of instructions required to complete the l-th type k service in time period t. l is the service sequence number of the same type of service, ΔR. i λ represents the additional capacity for i edge nodes. k This represents the number of k types of business.

[0049] The first, second, and third influence coefficients can be set according to actual needs. All three coefficients are greater than 0.

[0050] In an optional embodiment of the present invention, Where, α i,j The rental price represents the cost required to transfer a unit of computational load from node i to node j, α. i,0 The cost per unit of cloud computing resources required to rent a unit of cloud computing resources for edge node i per unit of time. The cloud computing resource capacity leased for edge node i, τ is the lease duration, and λ is the value of the leased resources. k This represents the number of k types of business.

[0051] In an optional embodiment of the present invention, the target constraint includes:

[0052]

[0053] in, V represents the unloading coefficient. t,k,l R represents the amount of computing resources used during the execution of the l-th k-th business in time period t. i Represents the capacity of i edge nodes, ΔR i This represents the additional capacity added to the i edge nodes. β represents the set of edge computing nodes, redundant nodes, and cloud nodes. i,j This represents the resource sharing rate between rentable edge node i and node j. v k This indicates the upper limit of computing resources used during business processing. λ represents the lower limit of the amount of computing resources used during business processing, l represents the ordinal number of the same type of business, and λ represents the lower limit of the amount of computing resources used during business processing. t,k λ represents the number of service requests of type k during time period t. k This represents the number of k types of business requests, where k represents the type of business request. A This indicates the types of service requests that cannot tolerate latency exceeding limits in computing services, where K represents the set of computing service request types, I represents the set of edge nodes, and β... i,j d represents the resource sharing rate of edge node i to edge node j. t,k,l D represents the latency of the l-th type k service during time period t. t,k,l This represents the latency threshold for the l-th type k service during time period t.

[0054] S220. Normalize the objective function to be optimized to obtain the normalized objective function.

[0055] The normalized objective optimization function can be the optimization function obtained by normalizing the objective function to be optimized.

[0056] In this embodiment of the invention, the target function to be optimized can be normalized based on any known normalization function to obtain a normalized target optimization function.

[0057] Optionally, both the computational resource cost function and the delay benefit function can be normalized, and weight coefficients can be assigned to the normalized computational resource cost function and the normalized delay benefit function. The difference between the normalized computational resource cost function and the normalized delay benefit function and the corresponding weight coefficient can be used as the normalized objective optimization function.

[0058] S230, Obtain supplementary constraints.

[0059] Among them, supplementary constraints can be used to constrain the target's capacity increase, preventing the target's capacity increase from becoming infinitely large.

[0060] In this embodiment of the invention, supplementary constraints can be generated based on the maximum capacity of the target edge node.

[0061] S240. Generate the objective optimization model based on the normalized objective optimization function, supplementary constraints, and objective constraints.

[0062] In this embodiment of the invention, the supplementary constraints and the target constraints can be used as complete constraints, thereby using the complete constraints and the normalized target optimization function as the target optimization model.

[0063] S250. Based on the microgrid edge node business data and the target optimization model, calculate the target additional capacity of each target edge node, and allocate resources to each target edge node according to the target additional capacity of each target edge node.

[0064] In an optional embodiment of the present invention, calculating the target additional capacity of each target edge node based on the microgrid edge node service data and the target optimization model may include: determining the data to be compared and the optimal solution set of PF (Kalman Filter) based on the improved differential evolution algorithm, the microgrid edge node service data and the target optimization model; and determining the target additional capacity of each target edge node based on the data to be compared and the optimal solution set of PF.

[0065] The improved differential evolution algorithm can be an algorithm obtained by improving the differential evolution algorithm based on any known improvement mechanism. The comparison data can be the minimum computational resource cost and minimum delay benefit calculated using the improved differential evolution algorithm, considering only computational resource cost or only delay benefit. The optimal solution set for PF can be the solution set obtained based on the improved differential evolution algorithm, microgrid edge node service data, and the target optimization model, used to determine the target additional capacity of the target edge node.

[0066] In this embodiment of the invention, the service data of the target edge node in the microgrid edge node service data can be parsed to extract the parameters that need to be input into the target optimization model. Then, the improved differential evolution algorithm is used to solve the optimization problem corresponding to the target optimization model with improved parameters, so as to obtain the data to be compared and the PF optimal solution set. The Euclidean distance between each solution in the PF optimal solution set and the data to be compared is calculated. Based on the Euclidean distances corresponding to each solution in the PF optimal solution set, the target additional capacity of each target edge node is determined.

[0067] Figure 3 This is a schematic diagram illustrating the configuration of a microgrid edge computing terminal service provided in Embodiment 2 of the present invention, as shown below. Figure 3 As shown, computing services in the power distribution system can be categorized into three types—A, B, and C—based on their tolerance for delay exceeding limits. The impact of delay exceeding limits on efficiency varies depending on the type of service. Type A computing services cannot tolerate delay exceeding limits, such as fault location, status monitoring, topology identification, interruptible load control, battery system alarms, and fault isolation—services related to safe operation. Type B computing services can tolerate delay exceeding limits, but with diminishing returns, such as electricity consumption information visualization services, electric vehicle charging services, business demand analysis, charge / discharge management, and nodal price analysis—services related to customer marketing. Type C computing services can tolerate delay exceeding limits, but with benefits plummeting to zero, such as line loss analysis, photovoltaic grid connection management, cloud-edge data acquisition, equipment status assessment, data fusion, and power quality analysis—services related to economic operation. The efficiency models for delay exceeding limits for each type of service are shown below:

[0068] When d k >D k hour,

[0069] Where, d k For business processing latency; D k For business time limits; B k For efficiency; k is the business category; m and n are constants, and m < 0. m and n are set based on experience in practical applications.

[0070] Service latency can reflect the processing effect of various computing services in a micronet, including both communication latency and computing latency caused by data transmission between nodes. The formula for calculating the latency of the l-th type k service in time period t, combined with the offloading coefficient, is as follows:

[0071]

[0072]

[0073] Among them, C k Refers to the computational complexity coefficient of type k computing tasks; A t,k,l,i The amount of input data required for the execution of the l-th type k service in time period t; v t,k,l It represents the amount of computing resources used during the execution of the l-th k-type business in time period t; Let n be the data transmission speed of the nth data transmission process; This is the unloading coefficient. Indicates the computation delay. Indicates communication delay.

[0074] Usable benefit ratio μ t The following expression describes the efficiency level of the calculation business during time period t:

[0075]

[0076] Among them, B k,max λ represents the benefit value when the latency of service type k does not exceed the limit. k B is the number of k types of business. t,k,l This represents the delay benefit of l types of k services during time period t.

[0077] The multi-objective optimization problem model for resource allocation of microgrid edge computing terminals with business weights is as follows:

[0078]

[0079]

[0080]

[0081]

[0082]

[0083]

[0084] Constraints C1, C2, and C3 ensure that computing resources do not exceed limits; constraint C4 ensures that Class A computing services do not exceed latency limits; constraint C5 ensures that all services are executed without duplicate execution.

[0085] Since the multi-objective optimization problem model is a multi-objective programming problem, this invention uses a linear weighting method to transform it into a set of single-objective optimization problems to obtain its effective solution set. To uniformly handle two objectives with inconsistent units and large numerical differences, a linear normalization function is constructed to normalize the two objectives. The normalization function used is as follows:

[0086]

[0087] Among them, g j For the j-th objective function value, and Let f be the minimum and maximum values ​​of the j-th objective function when other objective functions are ignored. j Let f1 be the normalized value of the j-th objective function, where j = 1, 2. t f2 = μ t In order to make C t If there is a maximum value, establish supplementary constraints: The supplementary constraint is abbreviated as C6.

[0088] Based on the normalization method, the normalized objective function is obtained as follows:

[0089]

[0090] stC1,C2,C3,C4,C5,C6

[0091] Here, ω1 and ω2 are weight coefficients, satisfying ω1∈[0,1] and ω2=1-ω1. By traversing ω1 on [0,1] with a certain step size, a sufficient number of optimal solutions for PF can be obtained.

[0092] The mixed-integer nonlinear programming model established in this scheme is constrained; therefore, an improved differential evolution algorithm should be used to solve the model in this paper. A penalty function method is used to construct the fitness function, and a penalty factor that gradually increases with the number of iterations is selected to balance the algorithm's search capability and evolutionary capability, resulting in the following equation:

[0093]

[0094] Where, k p u is a penalty factor that gradually increases with the number of iterations. p Let be the unbalance quantity corresponding to the p-th constraint.

[0095] The solution steps based on the improved differential evolution algorithm are as follows: (1) Solve for the ideal point (data to be compared): Let ω1 and ω2 be equal to 0 respectively, and use the improved differential evolution algorithm to solve for C. tmin and u tminThe ideal point is defined as (μ tmin C tmin (2) Solve for the PF optimal solution set. Given a step size, traverse the weights and use the improved differential evolution algorithm to solve for the cloud edge resource allocation results, obtaining a sufficient number of PF optimal solutions to form the PF optimal solution set. (3) Determine the comprehensive optimal solution. Use Euclidean distance to measure the distance from each point in the PF optimal solution set to the ideal point, and take the closest one as the comprehensive optimal solution. The Euclidean distance calculation formula is:

[0096] Figure 4 This is a flowchart illustrating a multi-objective resource allocation method for microgrid edge computing terminals considering service weights, as provided in Embodiment 2 of the present invention. Figure 4 As shown, firstly, information on edge computing nodes, cloud node computing resources, and various computing services is obtained. Then, the processing latency of each service on the edge computing terminal is calculated, followed by the efficiency ratio of edge computing terminal processing services. Furthermore, the investment cost, operating cost, and leasing cost of edge computing terminal resource configuration are calculated. The objectives in the multi-objective optimization problem model are normalized, and an improved differential evolution algorithm is used to solve for the ideal point. Finally, the optimal solution set of PF is determined, and the resource configuration amount of the edge computing terminal is obtained.

[0097] The technical solution of this invention obtains the target optimization function associated with the computational resource cost function and the delay benefit function, as well as the target constraints, and then generates a target optimization model based on the target optimization function and the target constraints. Since the target optimization function is correlated with the computational resource function and the delay benefit function, the target optimization function can estimate the computational cost and delay benefit of microgrid nodes. The target optimization function is then normalized to obtain a normalized target optimization function, achieving unified processing of targets with inconsistent units and large data differences. Supplementary constraints are obtained, and then a target optimization model is generated based on the normalized target optimization function, the supplementary constraints, and the target constraints. Furthermore, based on the microgrid edge node business data and the target optimization model, the target additional capacity of each target edge node is calculated. Resource allocation for each target edge node is then performed based on its target additional capacity. This comprehensively considers both computational resource cost and delay benefit, achieving a reasonable allocation of target edge node capacity. This solves the problem of unreasonable resource allocation in existing microgrid edge computing terminals, enabling reasonable resource allocation under the condition of considering delay constraints.

[0098] Example 3

[0099] Figure 5 This is a schematic diagram of the resource allocation device for a microgrid edge computing terminal provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes: a data acquisition module 310, a target optimization model generation module 320, and a target capacity addition calculation module 330, wherein...

[0100] The data acquisition module 310 is used to acquire the target function to be optimized associated with the computing resource cost function and the time delay benefit function, as well as the target constraints.

[0101] The target optimization model generation module 320 is used to generate a target optimization model based on the target function to be optimized and the target constraints.

[0102] The target additional capacity calculation module 330 is used to calculate the target additional capacity of each target edge node based on the microgrid edge node business data and the target optimization model, so as to allocate resources to each target edge node according to the target additional capacity of each target edge node.

[0103] The technical solution of this invention obtains the target optimization function associated with the computational resource cost function and the delay benefit function, as well as the target constraints, and then generates a target optimization model based on the target optimization function and the target constraints. Since the target optimization function is correlated with the computational resource function and the delay benefit function, the target optimization function can estimate the computational cost and delay benefit of microgrid nodes. Based on the microgrid edge node business data and the target optimization model, the target additional capacity of each target edge node is calculated. Resource allocation for each target edge node is then performed based on its target additional capacity. This approach comprehensively considers both computational resource cost and delay benefit, achieving a reasonable allocation of target edge node capacity. It solves the problem of unreasonable resource allocation in existing microgrid edge computing terminals and enables reasonable resource allocation under the condition of considering delay constraints.

[0104] Optional, the target function to be optimized includes:

[0105]

[0106] Among them, C sum Let C represent the resource cost function, where t represents the ordinal number of the working period of the edge node, T represents the working time interval of the edge node, i represents the ordinal number of the edge node, I represents the set of edge nodes, and C represents the resource cost function. inv,i Let C represent the investment cost of the i-th edge node. op,i C represents the operating cost of the i-th edge node. re,i,C C represents the cost of the i-th edge node renting computing resources from other edge nodes. re,i,E Let μ represent the cost of renting cloud node computing resources for the i-th edge node, and let μ represent the latency benefit function. tThis represents the latency benefit of the edge node during time period t.

[0107] Optional target constraints include:

[0108]

[0109] in, V represents the unloading coefficient. t,k,l R represents the amount of computing resources used during the execution of the l-th k-th business in time period t. i Represents the capacity of i edge nodes, ΔR i This represents the additional capacity added to the i edge nodes. β represents the set of edge computing nodes, redundant nodes, and cloud nodes. i,j This represents the resource sharing rate between rentable edge node i and node j. v k This indicates the upper limit of computing resources used during business processing. λ represents the lower limit of the amount of computing resources used during business processing, l represents the ordinal number of the same type of business, and λ represents the lower limit of the amount of computing resources used during business processing. t,k λ represents the number of service requests of type k during time period t. k This represents the number of k types of business requests, where k represents the type of business request. A This indicates the types of service requests that cannot tolerate latency exceeding limits in computing services, where K represents the set of computing service request types, I represents the set of edge nodes, and β... i,j d represents the resource sharing rate of edge node i to edge node j. t,k,l D represents the latency of the l-th type k service during time period t. t,k,l This represents the latency threshold for the l-th type k service during time period t.

[0110] Optional, C inv,i =θ△R i ; Where θ is the investment cost required for the construction unit to build edge computing terminal capacity, a is the first influence coefficient of computing load on operating cost, b is the second influence coefficient of computing load on operating cost, c is the third influence coefficient of computing load on operating cost, and L t,k,l The number of instructions required to complete the l-th type k service in time period t.

[0111] Optional, Where, α i,j The rental price represents the cost required to transfer a unit of computational load from node i to node j, α. i,0 The cost per unit of cloud computing resources required to rent a unit of cloud computing resources for edge node i per unit of time. τ represents the cloud computing resource capacity rented by edge node i, and τ represents the rental period.

[0112] Optionally, the target optimization model generation module 320 is specifically used to normalize the target function to be optimized to obtain a normalized target optimization function; obtain supplementary constraints; and generate the target optimization model based on the normalized target optimization function, the supplementary constraints, and the target constraints.

[0113] Optionally, the target capacity calculation module 330 is specifically used to determine the comparison data and the Kalman filter PF optimal solution set based on the improved differential evolution algorithm, microgrid edge node business data and the target optimization model; and to determine the target capacity of each target edge node based on the comparison data and the Kalman filter PF optimal solution set.

[0114] The resource configuration device provided in the embodiments of the present invention can execute the resource configuration method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0115] Example 4

[0116] Figure 6 A schematic diagram of a microgrid edge computing terminal that can be used to implement embodiments of the present invention is shown. (Microgrid edge computing terminal)

[0117] like Figure 6 As shown, the microgrid edge computing terminal 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the microgrid edge computing terminal 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0118] Multiple components in the microgrid edge computing terminal 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the microgrid edge computing terminal 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0119] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the resource allocation method for a microgrid edge computing terminal.

[0120] In some embodiments, the resource configuration method of the microgrid edge computing terminal can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the microgrid edge computing terminal 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the resource configuration method of the microgrid edge computing terminal described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the resource configuration method of the microgrid edge computing terminal by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0124] To provide user interaction, the systems and techniques described herein can be implemented on a microgrid edge computing terminal, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the microgrid edge computing terminal. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0126] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0127] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A resource allocation method for a microgrid edge computing terminal, characterized in that, include: Obtain the target function to be optimized, which is associated with the computational resource cost function and the delay benefit function, as well as the target constraints; The process of generating a target optimization model based on the target function to be optimized and the target constraints includes: normalizing the target function to be optimized to obtain a normalized target optimization function; obtaining supplementary constraints; and generating the target optimization model based on the normalized target optimization function, the supplementary constraints, and the target constraints. Based on the microgrid edge node service data and the target optimization model, the target additional capacity of each target edge node is calculated, so as to allocate resources to each target edge node according to the target additional capacity of each target edge node. The objective function to be optimized includes: in, This represents the function for calculating resource costs. t This indicates the ordinal number of the working time period of the edge node. T This indicates the working time interval of the edge node. Indicates the ordinal number of the edge node. I Represents the set of edge nodes. Indicates the first The investment cost of each edge node Indicates the first The operating cost of each edge node, Indicates the first The cost of an edge node renting computing resources from other edge nodes Indicates the first The cost of renting cloud node computing resources for an edge node Represents the time delay benefit function. Indicates in t The latency benefits of nodes at the edge of a time period; The objective constraints include: in, Indicates the unloading coefficient. express Time period indivual The amount of computing resources used during the execution of similar business processes. Indicates the first The capacity of each edge node, Indicates the first The increased capacity of each edge node This indicates the lower limit of the amount of computing resources used during business processing. This indicates the upper limit of computing resources used during business processing. Indicates the ordinal number of a similar business. express t The time period service request type is The number of businesses, express k Number of business types Indicates the type of business request. This indicates the type of service request that cannot be accepted by the computing service due to latency exceeding the limit. This represents a set of computational service request types. I Represents the set of edge nodes. Indicates the first i The edge node pair j Resource sharing rate of each edge node Indicates in t Time period l indivual k Latency of similar services Indicates in t Time period l indivual k Latency threshold for similar services.

2. The method according to claim 1, characterized in that, ； ； in, The investment cost required for the construction unit to build edge computing terminal capacity. To calculate the first impact factor of load on operating costs, To calculate the second impact factor of load on operating costs, To calculate the third impact factor of load on operating costs, To complete Time period indivual Number of instructions required for this type of business.

3. The method according to claim 2, characterized in that, ； ； in, The rental price represents the node. To the node The cost required to transfer the unit load. For edge nodes The cost per unit time required to rent cloud computing resources from a unit. For edge nodes Rented cloud computing resource capacity, For rental duration.

4. The method according to claim 1, characterized in that, Based on the microgrid edge node service data and the aforementioned target optimization model, the target additional capacity for each target edge node is calculated, including: Based on the improved differential evolution algorithm, microgrid edge node business data, and the target optimization model, the data to be compared and the set of optimal solutions for the Kalman filter PF are determined. Based on the data to be compared and the optimal solution set of the Kalman filter PF, the target additional capacity of each target edge node is determined.

5. A resource allocation device for a microgrid edge computing terminal, characterized in that, include: The data acquisition module is used to acquire the target function to be optimized associated with the computing resource cost function and the time delay benefit function, as well as the target constraints. The objective optimization model generation module is used to generate an objective optimization model based on the objective function to be optimized and the objective constraints. The target capacity calculation module is used to calculate the target capacity of each target edge node based on the microgrid edge node business data and the target optimization model, so as to allocate resources to each target edge node according to the target capacity of each target edge node. The target optimization model generation module is specifically used to normalize the target function to be optimized to obtain a normalized target optimization function; and to obtain supplementary constraints. The objective optimization model is generated based on the normalized objective optimization function, the supplementary constraints, and the objective constraints. The objective function to be optimized includes: in, This represents the function for calculating resource costs. t This indicates the ordinal number of the working time period of the edge node. T This indicates the working time interval of the edge node. Indicates the ordinal number of the edge node. I Represents the set of edge nodes. Indicates the first The investment cost of each edge node Indicates the first The operating cost of each edge node, Indicates the first The cost of an edge node renting computing resources from other edge nodes Indicates the first The cost of renting cloud node computing resources for an edge node Represents the time delay benefit function. Indicates in t The latency benefits of nodes at the edge of a time period; The objective constraints include: in, Indicates the unloading coefficient. express Time period indivual The amount of computing resources used during the execution of similar business processes. Indicates the first The capacity of each edge node, Indicates the first The increased capacity of each edge node This indicates the lower limit of the amount of computing resources used during business processing. This indicates the upper limit of computing resources used during business processing. Indicates the ordinal number of a similar business. express t The time period service request type is The number of businesses, express k Number of business types Indicates the type of business request. This indicates the type of service request that cannot be accepted by the computing service due to latency exceeding the limit. This represents a set of computational service request types. I Represents the set of edge nodes. Indicates the first i The edge node pair j Resource sharing rate of each edge node Indicates in t Time period l indivual k Latency of similar services Indicates in t Time period l indivual k Latency threshold for similar services.

6. A microgrid edge computing terminal, characterized in that, The microgrid edge computing terminal includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the resource allocation method of the microgrid edge computing terminal according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the resource allocation method of the microgrid edge computing terminal according to any one of claims 1-4.

Images