FPGA Circuit and Method for Solving Microgrid Economic Dispatch Problem Based on Neural Dynamics Optimization Algorithm

Abstract

This invention provides an FPGA circuit and method for solving the economic dispatch problem of microgrids based on a neurodynamic optimization algorithm. The FPGA circuit includes a top-level module, which comprises a Runge-Kutta control module, a state control module, and a counting module. The Runge-Kutta control module includes a G module and at least one Runge-Kutta module LGKTi. The G module includes at least one gradient calculation module Gi. The number of Runge-Kutta modules LGKTi and gradient calculation modules Gi is configured to be at least the number of generators n. The gradient calculation module Gi in the G module is used to calculate the gradient information data in the Runge-Kutta formula and send the gradient information data to the corresponding Runge-Kutta module LGKTi. The Runge-Kutta module LGKTi is used to calculate the slope of each stage in the Runge-Kutta formula and iteratively update the generator output power vector. This invention has advantages such as high efficiency, reconfigurability, and low energy consumption.

Description

Technical Field

[0001] This invention belongs to the field of smart microgrids, and in particular, it relates to an FPGA circuit and method for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm. Background Technology

[0002] The power resources in a smart grid are widely distributed, involving the scheduling of multiple links such as generation, transmission, and distribution. Economic dispatch, as a crucial issue in power system operation, aims to minimize system operating costs by optimizing load demand allocation and rationally scheduling generation plans, while meeting system-level and unit-level operational constraints. To reduce economic costs and ensure power supply reliability, it is necessary to develop efficient dispatch algorithms and utilize high-performance hardware platforms.

[0003] Neurodynamics algorithms, as simulation algorithms based on neuron models, can simulate the dynamic behavior of neurons and perform data processing and analysis during the simulation process. Compared with traditional computational methods, this algorithm has better computational speed, higher parallelism, higher accuracy, and lower energy consumption. In power systems, economic dispatching problems involve a large amount of data processing and analysis, and the high efficiency of neurodynamics algorithms makes them an ideal choice. FPGA (Field Programmable Gate Array) is an integrated circuit chip that is easy to implement, reasonably priced, and flexible in design, and possesses the advantage of high parallelism. Therefore, implementing neurodynamics algorithms on FPGA hardware can accelerate computation and improve dispatching efficiency and computational speed. At the same time, FPGAs can also be flexibly optimized to further improve algorithm performance and efficiency.

[0004] Although many mature economic dispatch algorithms have been proposed by researchers both domestically and internationally, research on hardware implementations of economic dispatch problems is scarce. Traditional computer architectures often suffer from slow computation speed, high power consumption, and large size, making it difficult to meet the real-time, reliability, and efficiency requirements of power systems. However, FPGA hardware implementation of economic dispatch problems can fully leverage its high parallelism, significantly improving algorithm solution speed and dispatch efficiency. Furthermore, the FPGA-based implementation of the economic dispatch problem-solving circuit employs IP core packaging technology, encapsulating the solution circuit into a reusable IP core. This greatly simplifies the user experience and integration process, improving system maintainability and scalability. This allows the economic dispatch problem-solving IP core to be flexibly applied to various embedded system design environments. Summary of the Invention

[0005] To address at least one technical problem in the prior art, this invention provides an FPGA circuit and method for solving the microgrid economic dispatch problem based on a neurodynamics optimization algorithm. This enables the solution of the microgrid economic dispatch problem using the neurodynamics algorithm within an FPGA circuit, offering advantages such as high efficiency, reconfigurability, and low energy consumption. It represents a novel solution for solving power system economic dispatch problems. To achieve the above technical objectives, the technical solution adopted in this invention is as follows:

[0006] In a first aspect, embodiments of the present invention provide an FPGA circuit for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm, including a top-level module;

[0007] The top-level module includes a Runge-Kutta control module, a state control module, and a counting module; the Runge-Kutta control module includes a G module and at least one Runge-Kutta module LGKTi; the G module includes at least one gradient calculation module Gi; the number of the Runge-Kutta module LGKTi and the gradient calculation module Gi are respectively configured to be at least the number of generators n;

[0008] The solution to the microgrid economic dispatch problem based on the neurodynamics optimization algorithm includes:

[0009] Define the generator's power generation cost function and its constraints;

[0010] Define a neurodynamics optimization algorithm;

[0011] Discretize the neurodynamics optimization algorithm to obtain the Runge-Kutta formula;

[0012] The top-level module is used to input the generator output power vector, and the generator output power vector is sent to the Longge-Kutta control module through the state control module;

[0013] The gradient calculation module Gi in the G module is used to calculate the gradient information data in the Runge-Kutta formula and send the gradient information data to the corresponding Runge-Kutta module LGKTi.

[0014] The Runge-Kutta module LGKTi is used to calculate the slope of each stage in the Runge-Kutta formula and iteratively update the generator output power vector to obtain the iteratively updated generator output power vector.

[0015] The state control module uses a finite state machine to control the loop, including three states: S1, S2, and S3. The state control module configures the corresponding states according to the iterative update process of the generator output power vector.

[0016] The counting module is used to count the number of iterations.

[0017] Furthermore, the generator's power generation cost function and its constraints are expressed as follows:

[0018]

[0019] Where C(P) represents the generator cost function, p i Let P be the output power of the i-th generator, and let P be the generator output power vector of the n generators, i.e., [p1, p2, ..., pn]. i …p n ], α i β i γ i These are cost parameters, where α i >0; D represents the total power demand in the power grid;

[0020] The neurodynamic optimization algorithm is expressed as:

[0021]

[0022] Where L(P,λ)=f(P)+λ T h(P) is the Lagrange function, and λ is the Lagrange multiplier;

[0023]

[0024] Discretizing formula (3) yields the Runge-Kutta formula, which is expressed as:

[0025]

[0026] Where h is the iteration step size, and K1, K2, K3, and K4 are the slopes of each stage in the Runge-Kutta formula; P j It is the generator output power vector at the j-th iteration.

[0027] Furthermore, the Runge-Kutta module LGKTi includes a K1 module, a K2 module, a K3 module, a K4 module, and an update module; the K1, K2, K3, and K4 modules are respectively used to calculate the slopes K1, K2, K3, and K4 of each stage in the Runge-Kutta formula; the update module is used to iteratively update the generator output power vector according to the slopes K1, K2, K3, and K4 of each stage, and send the updated generator output power vector to the state control module.

[0028] Furthermore, the K1, K2, K3, and K4 modules each include a floating-point multiplier and a floating-point adder.

[0029] Furthermore, the G module is instantiated from a gradient calculation module Gi of multiple dimensions.

[0030] Furthermore, the gradient calculation module Gi and the Runge-Kutta module LGKTi are in one-to-one correspondence and are associated with the output power p of the i-th generator. i correspond.

[0031] Furthermore, the gradient calculation module Gi internally includes a floating-point multiplier and a floating-point adder.

[0032] Furthermore, the FPGA circuit for solving the microgrid economic dispatch problem based on the neural dynamics optimization algorithm is packaged with an IP core, and the cost parameter α is... i β i and γ i The iteration step size h and the maximum number of iterations are set as IP core parameters.

[0033] Secondly, embodiments of the present invention provide a method for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm, using an FPGA circuit for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm as described above, and including the following steps:

[0034] Step S1, Initial value P of generator output power vector j When the top-level module is input, the state control module enters state S1.

[0035] Step S2, the state control module initializes the generator output power vector P. j Send to the Longgekuta control module;

[0036] Step S3: The gradient calculation modules Gi in module G calculate the gradient information data. Pj L(P j ,λ) and send to the Runge-Kutta module LGKTi; calculate the stage slope K1 through the K1 module inside the Runge-Kutta module LGKTi of each dimension and transmit it to the internal K2 module and update module;

[0037] Step S4, the K2 module inside the Runge-Kutta module LGKTi in each dimension sends (P) j The data (+K1 / 2,λ+K1 / 2) are fed to the various gradient calculation modules Gi in module G;

[0038] Step S5: The gradient calculation modules Gi in module G calculate the gradient information data. Pj L(P j +K1 / 2,λ+K1 / 2) and send it to the Runge-Kutta module LGKTi; calculate the stage slope K2 through the K2 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K3 module and update module;

[0039] Step S6, the K3 module inside the Runge-Kutta module LGKTi in each dimension sends (P) j The data (+K2 / 2,λ+K2 / 2) are fed to the various gradient calculation modules Gi in module G;

[0040] Step S7: The gradient calculation modules Gi in module G calculate the gradient information data. Pj L(P j +K2 / 2,λ+K2 / 2) and send it to the Runge-Kutta module LGKTi; calculate the stage slope K3 through the K3 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K4 module and update module;

[0041] Step S8, the K4 module inside the Runge-Kutta module LGKTi in each dimension sends (P) j The data (+K3,λ+K3) are fed to the various gradient calculation modules Gi in module G;

[0042] Step S9: The gradient calculation modules Gi in module G calculate the gradient information data. Pj L(P j +K3,λ+K3) and send it to the Runge-Kutta module LGKTi; calculate the stage slope K4 through the K4 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K4 module and update module;

[0043] Step S10, update the module according to formula P j+1 =P j Iteratively update the generator output power vector using +(K1+2K2+2K3+K4) / 6; then update the generator output power vector P after iterative updates. j+1 Send to the status control module;

[0044] After each iteration of the generator output power vector is completed, the counting module increments the iteration count by 1. After each iteration of the generator output power vector is completed, the state control module enters state S2, at which point it checks for convergence. If the convergence condition is not met, the state control module remains in state S2 and proceeds to steps S1 to S10. If the convergence condition is met after one iteration, the state control module enters state S3. At this point, the top-level module outputs the generator output power vector Min_P corresponding to the minimum generator cost minC(P).

[0045] Furthermore, the convergence conditions include the number of iterations reaching the maximum number of iterations, or the minimum generator cost minC(P) being less than a preset threshold.

[0046] The beneficial effects of the technical solution provided by the embodiments of this invention are as follows: Compared with traditional computing methods, the advantages of this invention, implemented using FPGA hardware, lie in its high degree of parallelism and reconfigurability, fully leveraging the computing advantages of FPGA. The advantages of FPGA hardware implementation are high parallelism and reconfigurability; on the one hand, it can fully utilize the computing advantages of the FPGA parallel architecture, thereby significantly improving the algorithm solution speed and scheduling efficiency; on the other hand, the FPGA circuit can be packaged into a reusable IP core, enabling flexible IP core usage. FPGA hardware consumes less power than traditional computer architectures. This invention has broad application prospects and can also provide new ideas and methods for the research and solution of economic dispatch problems in smart microgrids. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the top-level module structure in an embodiment of the present invention.

[0048] Figure 2 This is a diagram of the internal structure of the Rungekuta module in an embodiment of the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0050] In the description of the embodiments of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the present invention. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0051] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can also refer to the internal connection of two components; and they can refer to a wireless connection or a wired connection. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0052] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0053] like Figure 1 As shown and Figure 2 As shown, this embodiment of the invention proposes an FPGA circuit for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm, including a top-level module;

[0054] The top-level module includes a Runge-Kutta control module, a state control module, and a counting module; the Runge-Kutta control module includes a G module and at least one Runge-Kutta module LGKTi; the G module includes at least one gradient calculation module Gi; the number of the Runge-Kutta module LGKTi and the gradient calculation module Gi are respectively configured to be at least the number of generators n;

[0055] The solution to the microgrid economic dispatch problem based on the neurodynamics optimization algorithm includes:

[0056] Define the generator's power generation cost function and its constraints;

[0057] Define a neurodynamics optimization algorithm;

[0058] Discretize the neurodynamics optimization algorithm to obtain the Runge-Kutta formula;

[0059] The top-level module is used to input the generator output power vector, and the generator output power vector is sent to the Longge-Kutta control module through the state control module;

[0060] The gradient calculation module Gi in the G module is used to calculate the gradient information data in the Runge-Kutta formula and send the gradient information data to the corresponding Runge-Kutta module LGKTi.

[0061] The Runge-Kutta module LGKTi is used to calculate the slope of each stage in the Runge-Kutta formula and iteratively update the generator output power vector to obtain the iteratively updated generator output power vector.

[0062] The state control module uses a finite state machine to control the loop, including three states: S1, S2, and S3. The state control module configures the corresponding states according to the iterative update process of the generator output power vector.

[0063] The counting module is used to count the number of iterations.

[0064] This invention proposes an FPGA circuit for solving the economic dispatch problem of microgrids based on a neurodynamics optimization algorithm. This allows for the exploration of the application prospects of neurodynamics algorithms in FPGAs and provides new ideas and methods for the research and solution of economic dispatch problems in smart microgrids. The advantages of FPGA hardware implementation lie in its high parallelism and reconfigurability. On the one hand, it fully leverages the computational advantages of the FPGA's parallel architecture, thereby significantly improving the algorithm's solution speed and scheduling efficiency. On the other hand, the FPGA circuit can be packaged into a reusable IP core, enabling flexible IP core usage.

[0065] The following is a detailed description of an FPGA circuit for solving the economic dispatch problem of microgrids based on a neural dynamics optimization algorithm, through a specific embodiment;

[0066] The generator's power generation cost function and its constraints are expressed as follows:

[0067]

[0068] Where C(P) represents the generator cost function, p i Let P be the output power of the i-th generator, and let P be the generator output power vector of the n generators, i.e., [p1, p2, ..., pn]. i …p n ], α i β i γ i These are cost parameters, where α i >0; D represents the total power demand in the power grid; the prerequisite for economic dispatch of smart microgrids is to meet the supply and demand balance;

[0069] The neurodynamic optimization algorithm is expressed as:

[0070]

[0071] Where L(P,λ)=f(P)+λ T h(P) is the Lagrange function, and λ is the Lagrange multiplier;

[0072]

[0073] Discretizing formula (3) yields the Runge-Kutta formula, which is expressed as:

[0074]

[0075] Where h is the iteration step size, and K1, K2, K3, and K4 are the slopes of each stage in the Runge-Kutta formula; P j It is the generator output power vector at the j-th iteration;

[0076] likeFigure 2 As shown, the Runge-Kutta module LGKTi includes modules K1, K2, K3, K4, and an update module. Modules K1, K2, K3, and K4 are used to calculate the slopes K1, K2, K3, and K4 of each stage in the Runge-Kutta formula, respectively. The update module is used to iteratively update the generator output power vector according to the slopes K1, K2, K3, and K4 of each stage, and send the updated generator output power vector to the state control module.

[0077] Specifically, the K1, K2, K3, and K4 modules include floating-point multipliers and floating-point adders to calculate the slopes K1, K2, K3, and K4 at each stage.

[0078] Specifically, the G module is instantiated from a multi-dimensional gradient calculation module Gi; its main function is to calculate the gradient information data in the Runge-Kutta formula, i.e.

[0079] Specifically, the gradient calculation module Gi and the Runge-Kutta module LGKTi are in one-to-one correspondence and are associated with the output power p of the i-th generator. i Correspondingly, it can fully leverage the computational advantages of the FPGA parallel architecture, thereby significantly improving the algorithm's solution speed and scheduling efficiency.

[0080] Specifically, the gradient calculation module Gi includes a floating-point multiplier and a floating-point adder to perform gradient information data calculation.

[0081] Specifically, the FPGA circuit for solving the microgrid economic dispatch problem based on the neurodynamics optimization algorithm is packaged with an IP core, and the cost parameter α is... i β i and γ i The iteration step size h and the maximum number of iterations are set as IP core parameters; when using this IP core, users can input the corresponding parameters in the IP core user interface and achieve flexible calling without modifying the code.

[0082] like Figure 1 , Figure 2 As shown in the figure, an embodiment of the present invention proposes a method for solving the economic dispatch problem of microgrids based on a neurodynamic optimization algorithm. The method, based on the aforementioned FPGA circuit for solving the economic dispatch problem of microgrids using a neurodynamic optimization algorithm, includes:

[0083] Step S1, as follows Figure 1 and Figure 2 As shown in ①, the initial value P of the generator output power vector. j When the top-level module is input, the state control module enters state S1.

[0084] Step S2, as follows Figure 1 and Figure 2 As shown in ②, the state control module initializes the generator output power vector P. j Send to the Longgekuta control module;

[0085] Step S3, as follows Figure 1 and Figure 2 As shown in ③, the gradient calculation modules Gi in module G calculate gradient information data. And send it to the Runge-Kutta module LGKTi; calculate the stage slope K1 through the K1 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K2 module and update module;

[0086] Step S4, as follows Figure 1 and Figure 2 As shown in ④, the K2 module inside the Runge-Kutta module LGKTi in each dimension sends (P) j The data (+K1 / 2,λ+K1 / 2) are fed to the various gradient calculation modules Gi in module G;

[0087] Step S5, as follows Figure 1 and Figure 2 As shown in ⑤, the gradient calculation modules Gi in module G calculate gradient information data. And send it to the Runge-Kutta module LGKTi; calculate the stage slope K2 through the K2 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K3 module and update module;

[0088] Step S6, as follows Figure 1 and Figure 2 As shown in ⑥, the K3 module inside the Runge-Kutta module LGKTi in each dimension sends (P) j The data (+K2 / 2,λ+K2 / 2) are fed to the various gradient calculation modules Gi in module G;

[0089] Step S7, as follows Figure 1 and Figure 2 As shown in ⑦, the gradient calculation modules Gi in module G calculate gradient information data. And send it to the Runge-Kutta module LGKTi; calculate the stage slope K3 through the K3 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K4 module and update module;

[0090] Step S8, as follows Figure 1 and Figure 2 As shown in ⑧, the K4 module inside the Runge-Kutta (LGKTi) module in each dimension sends (P) jThe data (+K3,λ+K3) are fed to the various gradient calculation modules Gi in module G;

[0091] Step S9, as follows Figure 1 and Figure 2 As shown in ⑨, the gradient calculation modules Gi in module G calculate gradient information data. And send it to the Runge-Kutta module LGKTi; calculate the stage slope K4 through the K4 module inside the Runge-Kutta module LGKTi in each dimension and transmit it to the internal K4 module and update module;

[0092] Step S10, as follows Figure 1 and Figure 2 As shown in ①0, the update module updates according to formula P. j+1 =P j Iteratively update the generator output power vector using +(K1+2K2+2K3+K4) / 6; then update the generator output power vector P after iterative updates. j+1 Send to the status control module;

[0093] After each iteration of the generator output power vector is completed, the counting module increments the iteration count by 1. After each iteration of the generator output power vector is completed, the state control module enters state S2, at which point it checks for convergence. If the convergence condition is not met, the state control module remains in state S2 and proceeds to steps S1 to S10. If the convergence condition is met after one iteration, the state control module enters state S3. At this point, the top-level module outputs the generator output power vector Min_P corresponding to the minimum generator cost minC(P).

[0094] Specifically, the convergence conditions include the number of iterations reaching the maximum number of iterations, or the minimum generator cost minC(P) being less than a preset threshold.

[0095] Finally, it should be noted that the above specific embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An FPGA circuit for solving micro-grid economic dispatch problem based on neural dynamics optimization algorithm, comprising a top-level module; characterized in that, the top-level module comprises a Runge-Kutta control module, a state control module and a counting module; the Runge-Kutta control module comprises a G module and at least one Runge-Kutta module LGKTi; the G module comprises at least one gradient calculation module Gi; the number of the Runge-Kutta module LGKTi and the gradient calculation module Gi is configured to be at least the number of generators n respectively; the solving of the micro-grid economic dispatch problem based on the neural dynamics optimization algorithm comprises: defining the generation cost function of the generator and its constraints; defining the neural dynamics optimization algorithm; discretizing the neural dynamics optimization algorithm to obtain the Runge-Kutta formula; the top-level module is used to input the generator output power vector, and the state control module sends the generator output power vector to the Runge-Kutta control module; the gradient calculation module Gi in the G module is used to calculate the gradient information data in the Runge-Kutta formula and send the gradient information data to the corresponding Runge-Kutta module LGKTi; the Runge-Kutta module LGKTi is used to calculate the slope of each stage in the Runge-Kutta formula and iteratively update the generator output power vector to obtain the iteratively updated generator output power vector; the state control module adopts a finite state machine control cycle, including three states S1, S2 and S3; the state control module configures the corresponding state according to the iterative update process of the generator output power vector; the counting module is used to count the number of iterations; the generation cost function of the generator and its constraints are represented as: Where C(P) represents the generator cost function, p i Let P be the output power of the i-th generator, and let P be the generator output power vector of the n generators, i.e., [p1, p2, ..., pn]. i …p n ], α i β i γ i These are cost parameters, where α i >0; D represents the total power demand in the power grid; the neural dynamics optimization algorithm is represented as: Wherein, L(P, λ) = f(P) + λ T h(P) is a Lagrangian function, and λ is a Lagrangian multiplier. discretizing formula (3) to obtain the Runge-Kutta formula, represented as: K1 = h▽ Pj L(P j ,λ). K2 = h▽ Pj L(P j + K1 / 2, λ + K1 / 2). K3 = h▽ Pj L(P j + K2 / 2, λ + K2 / 2); (5) K4 = h▽ Pj L(P j + K3, λ + K3); P j+1 = P j + (K1+2K2+2K3+K4) / 6; where h is the iteration step size, K1, K2, K3, K4 are the slopes of each stage in the Runge-Kutta formula; P j is the generator output power vector at the jth iteration.

2. The FPGA circuit for solving micro-grid economic dispatch problem based on neural dynamics optimization algorithm according to claim 1, characterized in that, the Runge-Kutta module LGKTi comprises a K1 module, a K2 module, a K3 module, a K4 module and an update module; the K1 module, the K2 module, the K3 module and the K4 module are respectively used to calculate the slope K1, K2, K3 and K4 of each stage in the Runge-Kutta formula; the update module is used to iteratively update the generator output power vector according to the slope K1, K2, K3 and K4 of each stage and send the updated generator output power vector to the state control module.

3. The FPGA circuit for solving micro-grid economic dispatch problem based on neural dynamics optimization algorithm according to claim 2, characterized in that, the K1 module, the K2 module, the K3 module and the K4 module internally comprise a floating-point multiplier and a floating-point adder.

4. The FPGA circuit for solving micro-grid economic dispatch problem based on neural dynamics optimization algorithm according to claim 2, characterized in that, the G module is instantiated by multiple-dimensional gradient calculation modules Gi.

5. The FPGA circuit for solving micro-grid economic dispatch problem based on neural dynamics optimization algorithm according to claim 2, characterized in that, The gradient calculation module Gi and the Runge-Kutta module LGKTi correspond one-to-one, and the i-th generator output power p i Corresponding.

6. The FPGA circuit for solving the microgrid economic dispatch problem based on the neural-dynamics optimization algorithm according to claim 2, wherein the gradient calculation module Gi comprises a floating-point multiplier and a floating-point adder.

7. The FPGA circuit for solving the microgrid economic dispatch problem based on the neural-dynamics optimization algorithm according to claim 2, wherein the method comprises the following steps: The count module adds 1 to the iteration number each time the iteration of the generator output power vector is completed, and the state control module enters the S2 state each time the iteration of the generator output power vector is completed, at which time the detection of the iteration convergence is performed; if the convergence condition is not met after the iteration is completed, the state control module remains in the S2 state, and the steps S1-S10 are performed again; if the convergence condition is met after the iteration is completed, the state control module enters the S3 state; at this time, the top-level module outputs the generator output power vector Min_P corresponding to the minimum generator cost minC(P). The FPGA circuit for solving the micro-grid economic dispatch problem based on the neural dynamics optimization algorithm adopts IP core packaging, and cost parameters α i , β i and γ i and iteration step h and the maximum number of iterations are set as IP core parameters.

8. A method for solving the economic dispatch problem of microgrid based on the neural dynamics optimization algorithm, the FPGA circuit for solving the economic dispatch problem of microgrid based on the neural dynamics optimization algorithm according to any one of claims 2-7, characterized in that, 9. The method for solving the microgrid economic dispatch problem based on the neural-dynamics optimization algorithm according to claim 8, wherein the convergence condition comprises that the iteration number reaches a maximum iteration number, or the minimum generator cost minC(P) is less than a preset threshold. Step S1, initial value of generator output power vector P j Input top-level module, state control module enters S1 state; Step S2, the state control module sends the generator output power vector initial value P j to the Runge-Kutta control module; Step S3, each gradient calculation module Gi in the G module calculates gradient information data and sends to the Runge-Kutta module LGKTi; the stage slope K1 is calculated by the K1 module inside the Runge-Kutta module LGKTi of each dimension and is transmitted to the K2 module and the update module inside. Step S4, the K2 module inside the Runge-Kutta module LGKTi of each dimension sends (P j + K1 / 2, λ + K1 / 2) data to each gradient calculation module Gi in the G module; Step S5, each gradient calculation module Gi in the G module calculates gradient information data and sends to the Runge-Kutta module LGKTi; the K2 module inside the Runge-Kutta module LGKTi of each dimension calculates the stage slope K2 and transmits to the K3 module and the update module inside. Step S6, the K3 module inside the Runge-Kutta module LGKTi of each dimension sends (P j + K2 / 2, λ + K2 / 2) data to each gradient calculation module Gi in the G module; Step S7, each gradient calculation module Gi in the G module calculates gradient information data and sends to the Runge-Kutta module LGKTi; the stage slope K3 is calculated by the K3 module inside the Runge-Kutta module LGKTi of each dimension and is transmitted to the K4 module and the update module inside. Step S8, the K4 module inside the Runge-Kutta module LGKTi of each dimension sends (P j + K3, λ + K3) data to each gradient calculation module Gi in the G module; Step S9, each gradient calculation module Gi in the G module calculates gradient information data and sends to the Runge-Kutta module LGKTi; the stage slope K4 is calculated by the K4 module inside the Runge-Kutta module LGKTi of each dimension and is transmitted to the internal K4 module and the update module; Step S10, the update module updates the generator output power vector P according to the formula P j+1 = P j + (K1+2K2+2K3+K4) / 6 iteratively; sends the iteratively updated generator output power vector P j+1 to the state control module; ​ ​ ​

Images