Flexible electric equipment intelligent interaction method and system based on edge calculation

Abstract

The invention relates to a flexible electric equipment intelligent interaction method and system based on edge calculation, and belongs to the technical field of electric equipment intelligent interaction. The method comprises the following steps: acquiring user power consumption data and user side adjustable resource data, presetting a power grid edge calculation framework, and constructing a cloud edge collaborative flexible resource regulation and control model according to the power grid edge calculation framework; obtaining user electricity utilization preprocessing data through a data preprocessing model according to the user electricity utilization data; obtaining a controllable load regulation and control prediction result through a regulation and control prediction model according to the electricity utilization preprocessing data of the user; obtaining user side actual adjustable resources, and obtaining a flexible resource regulation and control decision through an ADMM algorithm according to the controllable load regulation and control prediction result and the user side actual adjustable resources; and the edge node regulates and controls the flexible electric equipment according to the flexible resource regulation and control decision. The intelligent interaction of the flexible electric equipment based on edge calculation is realized, the response time is shortened, and the data security is ensured at the same time.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent interaction of electrical equipment, and specifically relates to an intelligent interaction method and system for flexible electrical equipment based on edge computing. Background Art

[0002] As the scale of grid connection of new energy such as photovoltaics continues to increase, its volatility and uncertainty have brought huge challenges to the system. By fully mobilizing flexible resources on the user side, the elasticity of distribution network regulation and the stability of system operation can be improved.

[0003] The traditional cloud-based centralized method relies on sending all IoT data to the cloud for processing, which increases response time and the risk of data leakage. The initial adaptive control method only targets a single type of device, resulting in decentralized resource management and difficulty in achieving cross-device collaborative control. Therefore, the above methods are still insufficient in reducing latency and ensuring data security while calling user-side flexible resources to improve the elastic regulation of the distribution network and realize intelligent interaction of flexible power devices. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides an intelligent interaction method for flexible electrical equipment based on edge computing.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for intelligent interaction of flexible electrical equipment based on edge computing, comprising:

[0007] Obtain user electricity consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model based on the power grid edge computing architecture, wherein the cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model;

[0008] Obtaining user electricity consumption preprocessing data through the data preprocessing model according to the user electricity consumption data;

[0009] Obtaining a controllable load regulation prediction result through the regulation prediction model according to the user's electricity consumption preprocessing data;

[0010] Acquire the actual adjustable resources on the user side, and obtain a flexible resource regulation decision through the ADMM algorithm according to the controllable load regulation prediction result and the actual adjustable resources on the user side;

[0011] The edge nodes regulate the flexible power-consuming equipment according to the flexible resource regulation decisions.

[0012] Preferably, the power grid edge computing architecture includes a cloud server, an edge server and an end server, the cloud server is a distribution network control center, the edge server is a feeder terminal device, and the end server is a flexible power consumption device.

[0013] Preferably, obtaining the user electricity consumption preprocessing data through the data preprocessing model according to the user electricity consumption data includes:

[0014] The flexible power-consuming device uploads the user-side adjustable resource data and the user power consumption data to the feeder terminal device through a data encryption model;

[0015] Filling missing values ​​by linear difference calculation according to the user's electricity consumption data to obtain complete electricity consumption data of the user;

[0016] Obtaining the user's electricity consumption preprocessing data through data normalization according to the user's electricity consumption complete data;

[0017] The feeder terminal device uploads the user's electricity preprocessing data and the user-side adjustable resource data to the distribution network control center through the TLS security protocol.

[0018] Preferably, the data encryption model specifically includes the following steps:

[0019] Encrypt the user-side adjustable resource data and the user power usage data by using an AES encryption algorithm to obtain user-side adjustable resource encrypted data and user power usage encrypted data;

[0020] The flexible power-consuming device uploads the user-side adjustable resource encrypted data and the user power usage encrypted data to the feeder terminal device through the TLS security protocol;

[0021] The feeder terminal device decrypts the user-side adjustable resource encrypted data and the user power usage encrypted data through the AES encryption algorithm to obtain the user-side adjustable resource data and the user power usage data.

[0022] Preferably, obtaining the controllable load regulation prediction result through the regulation prediction model according to the user's electricity consumption preprocessing data includes:

[0023] The distribution network control center predicts the user power consumption data by using an LSTM algorithm to obtain user power consumption prediction data;

[0024] Obtaining a controllable resource regulation result through a particle swarm algorithm model according to the user power consumption forecast data and the user-side adjustable resource data;

[0025] The distribution network control center sends the controllable resource regulation result to the feeder terminal device through the TLS security protocol.

[0026] Preferably, the particle swarm algorithm model includes:

[0027] S601: Preset a determination target and a determination constraint condition, and initialize the control particle according to the user-side adjustable resource data, the user power consumption forecast data, the determination target and the determination constraint condition;

[0028] S602: Obtaining historical regulated particle fitness values, evaluating the regulated particles through a multi-objective fitness function to obtain regulated particle fitness values, wherein the historical regulated particle fitness values ​​carry historical particle labels, and the regulated particle fitness values ​​carry particle labels;

[0029] S603: Obtain the updated history regulated particle fitness value through particle label determination according to the regulated particle fitness value;

[0030] The particle label judgment includes judging whether the particle label is equal to the historical particle label, and if so, adding the regulated particle fitness value to the historical regulated particle fitness value to obtain the updated historical regulated particle fitness value;

[0031] If not, continue to step S604;

[0032] S604: obtaining a global optimal control particle by sorting the fitness values ​​of the control particles, wherein the global optimal control particle carries an iteration number label; obtaining an individual optimal control particle by sorting the fitness values ​​of the update history control particles;

[0033] S605: Obtaining an updated regulated particle group through update calculation according to the global optimal regulated particle and the individual optimal regulated particle;

[0034] S606: Obtain the maximum number of iterations, and determine the controllable load control prediction result according to the number of iterations of the updated control particle swarm.

[0035] Preferably, the iteration number judgment includes judging whether the maximum iteration number is equal to the iteration number label, and if so, obtaining the controllable load control prediction result according to the global optimal control particle;

[0036] If no, repeat step S602 to step S605 until the maximum number of iterations is equal to the iteration number label.

[0037] An edge computing-based flexible power equipment intelligent interaction system and an edge computing-based flexible power equipment intelligent interaction method include a data acquisition module, a data preprocessing module, a control prediction module, a control correction module, and a control implementation module, including:

[0038] The data acquisition module is used to obtain user power consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model according to the power grid edge computing architecture. The cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model;

[0039] The data preprocessing module is used to obtain user power consumption preprocessing data through the data preprocessing model according to the user power consumption data;

[0040] The control prediction module is used to obtain a controllable load control prediction result through the control prediction model according to the user power consumption preprocessing data;

[0041] The control and correction module obtains the actual adjustable resources on the user side, and is used to obtain a flexible resource control decision through the ADMM algorithm according to the controllable load control prediction result and the actual adjustable resources on the user side;

[0042] The control implementation module is used by the edge node to control the flexible power-consuming equipment according to the flexible resource control decision.

[0043] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned intelligent interaction method for flexible electrical equipment based on edge computing is implemented.

[0044] A storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the above-mentioned intelligent interaction method for flexible electrical equipment based on edge computing.

[0045] The beneficial effects of the present invention are:

[0046] (1) The edge computing architecture can effectively process data from sensors and smart devices. By performing preliminary processing and analysis on the edge side, the need to transmit data to the cloud is reduced, thereby reducing latency and improving response speed.

[0047] (2) The data is uploaded from the flexible power-consuming device to the feeder terminal device, the feeder terminal device uploads the data to the distribution network control center, and the distribution network control center sends the data to the feeder terminal device. The encrypted and secure transmission is performed during the process to ensure the security of data transmission.

[0048] (3) By filling missing values ​​in user electricity consumption data during the data preprocessing stage, the integrity of the data is ensured and the impact of missing data on subsequent algorithms is avoided; by normalizing user electricity consumption data, the data is standardized to improve the efficiency of the algorithm.

[0049] (4) Through edge computing, it is possible to support the access of different types of flexible power-consuming devices, and at the same time, perform preliminary processing and analysis of data on the edge server side, reducing the need to transmit data to the cloud, thereby reducing latency and improving response speed.

[0050] (5) Through cloud-edge collaboration, data analysis and processing are performed on the edge server, and the controllable load regulation is predicted on the cloud server. According to the controllable load regulation prediction results, corrections are made on the edge server to obtain flexible resource regulation decisions, thereby realizing intelligent interaction of flexible power-consuming equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0052] Figure 1 This invention discloses an intelligent interaction method for flexible electrical equipment based on edge computing. DETAILED DESCRIPTION

[0053] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0054] See also Figure 1 , a flexible power-consuming device intelligent interaction method based on edge computing, comprising:

[0055] S1: Obtain user electricity consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model according to the power grid edge computing architecture. The cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model.

[0056] S2: obtaining user electricity consumption preprocessing data through the data preprocessing model according to the user electricity consumption data;

[0057] S3: Obtaining a controllable load regulation prediction result through the regulation prediction model according to the user's electricity consumption preprocessing data;

[0058] S4: Acquire the actual adjustable resources on the user side, and obtain a flexible resource regulation decision through the ADMM algorithm according to the controllable load regulation prediction result and the actual adjustable resources on the user side;

[0059] S5: The edge node regulates the flexible power-consuming equipment according to the flexible resource regulation decision.

[0060] In this embodiment, by carrying out the power grid edge computing architecture, the power grid edge computing architecture is a distributed architecture, including a cloud server, 10 edge servers and 100 end servers, each edge server includes 10 end servers, the cloud server is the distribution network control center, the edge server is the feeder terminal device, and the end server is the flexible power consumption device; the entire process of the power grid edge computing architecture includes the flexible device uploading the user-side adjustable resource data and the user power consumption data to the feeder terminal device through a data encryption model; the feeder terminal device obtains the user power consumption pre-processing data by inputting the user power consumption data into the data pre-processing model processing data; the feeder terminal device uploads the user-side adjustable resource data and the user power pre-processing data to the distribution network control center through the TLS security protocol; the distribution network control center regulates the user-side adjustable resource data through the regulation and prediction model to obtain the controllable load regulation prediction result; the distribution network control center sends the controllable load regulation prediction result to the feeder terminal device through the TLS security protocol; the feeder terminal device corrects the controllable load regulation prediction result through the ADMM algorithm to obtain the flexible resource regulation decision; the feeder terminal device regulates the flexible power equipment according to the flexible resource regulation decision.

[0061] It should be noted that the feeder terminal equipment can process and analyze data, and can also regulate flexible resources; the flexible power-consuming equipment is an adjustable power equipment that can be dynamically adjusted according to the needs of the power grid.

[0062] In step S2, obtaining user power consumption preprocessing data through the data preprocessing model according to the user power consumption data includes:

[0063] S201: The flexible power-consuming device uploads the user-side adjustable resource data and the user power consumption data to the feeder terminal device through the data encryption model;

[0064] S202: Filling missing values ​​by linear difference calculation according to the user's electricity consumption data to obtain complete user electricity consumption data;

[0065] S203: Obtain the user's electricity consumption pre-processing data through data normalization according to the user's electricity consumption complete data.

[0066] S204: The feeder terminal device uploads the user's electricity preprocessing data and the user-side adjustable resource data to the distribution network control center through the TLS security protocol.

[0067] Specifically, the data encryption model includes the following steps:

[0068] S201-1: Encrypt the user-side adjustable resource data and the user power usage data by using an AES encryption algorithm to obtain user-side adjustable resource encrypted data and user power usage encrypted data;

[0069] S201-2: The flexible power-consuming device uploads the user-side adjustable resource encrypted data and the user power usage encrypted data to the feeder terminal device through the TLS security protocol;

[0070] S201 - 3 : The feeder terminal device decrypts the user-side adjustable resource encrypted data and the user electricity usage encrypted data through an AES encryption algorithm to obtain the user-side adjustable resource data and the user electricity usage data.

[0071] In step S3, the regulation prediction model includes:

[0072] S301: The distribution network control center predicts the user power consumption data by using an LSTM algorithm to obtain user power consumption prediction data;

[0073] S302: Obtaining a controllable resource regulation result through a particle swarm algorithm model according to the user power consumption prediction data and the user-side adjustable resource data;

[0074] S303: The distribution network control center sends the controllable resource regulation result to the feeder terminal device through the TLS security protocol.

[0075] Specifically, the particle swarm algorithm model includes:

[0076] S302-1: Obtain the electricity price of a time period, the electricity consumption of a time period, the total amount of flexible resources in a time period, the utilization of flexible resources in a time period, the user demand in a time period, and the actual load in a time period, preset a target and a constraint, and initialize a control particle according to the user-side adjustable resource data, the user electricity consumption forecast data, the confirmed target, and the confirmed constraint. The control particle is a particle in a particle swarm, and the control particle represents a control scheme;

[0077] S302-2: Obtain the fitness value of the historical control particle, and evaluate the control particle through a multi-objective fitness function according to the electricity price in the time period, the electricity consumption in the time period, the total amount of flexible resources in the time period, the flexible resource utilization in the time period, the user demand in the time period, and the actual load in the time period to obtain the fitness value of the control particle. The fitness value of the historical control particle carries a historical particle label, and the fitness value of the control particle carries a particle label;

[0078] The multi-objective fitness function expression is:

[0079]

[0080] Wherein, f(x) is the multi-objective fitness function, ω 1 ,ω 1 ,ω 1 are weight coefficients, f 1 (x) is the fitness function that minimizes the cost, f 2 (x) is the fitness function for maximizing the utilization rate of flexible resources, f 3 (x) is the load matching fitness function, n represents the number of time periods, i represents the i-th time period, C i represents the electricity price in the ith period, P i represents the power consumption in the ith period, U i represents the flexible resource utilization in the i-th period, R i represents the total amount of flexible resources in the ith period, D i represents the user demand in the i-th period, L i represents the actual load in the ith period;

[0081] S302-3: Obtain the updated historical regulated particle fitness value through particle label determination according to the regulated particle fitness value;

[0082] The particle label judgment includes judging whether the particle label is equal to the historical particle label, and if so, adding the regulated particle fitness value to the historical regulated particle fitness value to obtain the updated historical regulated particle fitness value;

[0083] If not, proceed to step S302-4;

[0084] S302-4: obtaining a global optimal control particle by sorting the fitness values ​​of the control particles, wherein the global optimal control particle carries an iteration number label; obtaining an individual optimal control particle by sorting the fitness values ​​of the update history control particles;

[0085] S302-5: Obtaining an updated regulated particle group through update calculation according to the global optimal regulated particle and the individual optimal regulated particle;

[0086] The update calculation expression is:

[0087] v i (t+1)=ω·v i (t)+c 1 ·r 1 ·(pBest i -x i (t))+c 2 ·r 2 ·(gBest-x i (t)),

[0088] x i (t+1)=x i (t)+v i (t+1),

[0089] Among them, v i represents the speed of the controlled particle, i represents the i-th controlled particle, ω is the inertia weight, t represents the time, c 1 represents the learning factor of the individual optimal control particle, r 1 and r 2 is a random number, pBest i represents the optimal control particle of the individual, x i represents the position of the controlled particle, c 2 represents the learning factor of the global optimal control particle, gBest represents the global optimal control particle, and the updated control particle group is obtained according to the control particle speed and the control particle position;

[0090] S302-6: Obtaining the maximum number of iterations, and determining the controllable load control prediction result according to the number of iterations of the updated control particle swarm;

[0091] The iteration number judgment includes judging whether the maximum iteration number is equal to the iteration number label, and if so, obtaining the controllable load control prediction result according to the global optimal control particle;

[0092] If no, repeat steps S302-2 to S302-5 until the maximum number of iterations is equal to the iteration number label.

[0093] In this embodiment, the user-side adjustable resource data received by the distribution network control center is the adjustable resources of all flexible power devices; the actual adjustable resources on the user side are the adjustable resources of the flexible power devices contained in each feeder terminal device received at the current moment, and the actual adjustable resources on the user side and the controllable load control prediction results are subjected to parameter correction through the ADMM algorithm to obtain a flexible resource control decision.

[0094] An edge computing-based flexible power equipment intelligent interaction system and an edge computing-based flexible power equipment intelligent interaction method include a data acquisition module, a data preprocessing module, a control prediction module, a control correction module, and a control implementation module, including:

[0095] The data acquisition module is used to obtain user power consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model according to the power grid edge computing architecture. The cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model;

[0096] The data preprocessing module is used to obtain user power consumption preprocessing data through the data preprocessing model according to the user power consumption data;

[0097] The control prediction module is used to obtain a controllable load control prediction result through the control prediction model according to the user power consumption preprocessing data;

[0098] The control and correction module is used to obtain the actual adjustable resources on the user side, and obtain the flexible resource control decision through the ADMM algorithm according to the controllable load control prediction result and the actual adjustable resources on the user side;

[0099] The control implementation module is used by the edge node to control the flexible power-consuming equipment according to the flexible resource control decision.

[0100] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.

[0101] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0102] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0103] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A method for intelligent interaction of flexible electrical equipment based on edge computing, characterized in that: The following steps are involved: Obtain user electricity consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model based on the power grid edge computing architecture, wherein the cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model; Obtaining user electricity consumption preprocessing data through the data preprocessing model according to the user electricity consumption data; Obtaining a controllable load regulation prediction result through the regulation prediction model according to the user's electricity consumption preprocessing data; Acquire the actual adjustable resources on the user side, and obtain a flexible resource regulation decision through the ADMM algorithm according to the controllable load regulation prediction result and the actual adjustable resources on the user side; The edge nodes regulate the flexible power-consuming equipment according to the flexible resource regulation decisions.

2. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 1 is characterized in that: The power grid edge computing architecture includes a cloud server, an edge server and an end server. The cloud server is a distribution network control center, the edge server is a feeder terminal device, and the end server is a flexible power consumption device.

3. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 1 is characterized in that: Obtaining user electricity consumption preprocessing data through the data preprocessing model according to the user electricity consumption data includes: The flexible power-consuming device uploads the user-side adjustable resource data and the user power consumption data to the feeder terminal device through a data encryption model; Filling missing values ​​by linear difference calculation according to the user's electricity consumption data to obtain complete electricity consumption data of the user; Obtaining the user's electricity consumption preprocessing data through data normalization according to the user's electricity consumption complete data; The feeder terminal device uploads the user's electricity preprocessing data and the user-side adjustable resource data to the distribution network control center through the TLS security protocol.

4. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 3 is characterized in that: The data encryption model specifically includes the following steps: Encrypt the user-side adjustable resource data and the user power usage data by using an AES encryption algorithm to obtain user-side adjustable resource encrypted data and user power usage encrypted data; The flexible power-consuming device uploads the user-side adjustable resource encrypted data and the user power usage encrypted data to the feeder terminal device through the TLS security protocol; The feeder terminal device decrypts the user-side adjustable resource encrypted data and the user power usage encrypted data through the AES encryption algorithm to obtain the user-side adjustable resource data and the user power usage data.

5. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 1 is characterized in that: The obtaining of the controllable load regulation prediction result by the regulation prediction model according to the user power consumption preprocessing data includes: The distribution network control center predicts the user power consumption data by using an LSTM algorithm to obtain user power consumption prediction data; Obtaining a controllable resource regulation result through a particle swarm algorithm model according to the user power consumption forecast data and the user-side adjustable resource data; The distribution network control center sends the controllable resource regulation result to the feeder terminal device through the TLS security protocol.

6. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 5 is characterized in that: The particle swarm algorithm model includes: S601: Preset a determination target and a determination constraint condition, and initialize a control particle according to the user-side adjustable resource data, the user power consumption forecast data, the determination target and the determination constraint condition; S602: Obtaining historical regulated particle fitness values, evaluating the regulated particles through a multi-objective fitness function to obtain regulated particle fitness values, wherein the historical regulated particle fitness values ​​carry historical particle labels, and the regulated particle fitness values ​​carry particle labels; S603: Obtain the updated history regulated particle fitness value through particle label determination according to the regulated particle fitness value; The particle label judgment includes judging whether the particle label is equal to the historical particle label, and if so, adding the regulated particle fitness value to the historical regulated particle fitness value to obtain the updated historical regulated particle fitness value; If not, continue to step S604; S604: obtaining a global optimal control particle by sorting the fitness values ​​of the control particles, wherein the global optimal control particle carries an iteration number label; obtaining an individual optimal control particle by sorting the fitness values ​​of the update history control particles; S605: Obtaining an updated regulated particle group through update calculation according to the global optimal regulated particle and the individual optimal regulated particle; S606: Obtain the maximum number of iterations, and determine the controllable load control prediction result according to the number of iterations of the updated control particle swarm.

7. The method for intelligent interaction of flexible electrical equipment based on edge computing according to claim 6 is characterized in that: The iteration number judgment includes judging whether the maximum iteration number is equal to the iteration number label, and if so, obtaining the controllable load control prediction result according to the global optimal control particle; If no, repeat step S602 to step S605 until the maximum number of iterations is equal to the iteration number label.

8. An edge computing-based flexible power equipment intelligent interaction system using the edge computing-based flexible power equipment intelligent interaction method according to claim 1, comprising a data acquisition module, a data preprocessing module, a control prediction module, a control correction module, and a control implementation module, characterized in that: include: The data acquisition module is used to obtain user power consumption data and user-side adjustable resource data, preset a power grid edge computing architecture, and build a cloud-edge collaborative flexible resource regulation model according to the power grid edge computing architecture. The cloud-edge collaborative flexible resource regulation model includes a data preprocessing model and a regulation prediction model; The data preprocessing module is used to obtain user power consumption preprocessing data through the data preprocessing model according to the user power consumption data; The control prediction module is used to obtain a controllable load control prediction result through the control prediction model according to the user power consumption preprocessing data; The control and correction module is used to obtain the actual adjustable resources on the user side, and obtain the flexible resource control decision through the ADMM algorithm according to the controllable load control prediction result and the actual adjustable resources on the user side; The control implementation module is used by the edge node to control the flexible power-consuming equipment according to the flexible resource control decision.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the intelligent interaction method of flexible electrical equipment based on edge computing as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions, when executed by a computer processor, are used to execute the intelligent interaction method for flexible electrical equipment based on edge computing as described in any one of claims 1 to 7.

Images