Block chain-based power grid power dispatching method and system, medium and equipment

Abstract

The invention belongs to the technical field of power grid power dispatching, and discloses a power grid power dispatching method and system based on a block chain, a medium and equipment. The system comprises a power grid data acquisition module, a change data acquisition module, a feature vector calculation module, a risk prediction module, a dynamic scheduling decision module, a multi-energy coordination module, a block chain storage module and an acceptance enhancement module, and is characterized in that a power grid data set and a change data set are preprocessed to obtain a feature vector set; and the multi-energy coordination module is used for analyzing the feature vector set to obtain a risk prediction value and analyzing the risk prediction value to obtain a dynamic scheduling decision report, and the multi-energy coordination module is used for analyzing the dynamic scheduling decision report, executing an analysis result and storing the feature vector set, the risk prediction value, the dynamic scheduling decision report and execution measure records. And the block chain operation is simplified.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid dispatching, and more specifically, to a blockchain-based power grid dispatching method, system, medium, and equipment. Background Art

[0002] Power dispatching is an effective management method adopted to ensure the safe and stable operation of the power grid, reliable external power supply, and orderly progress of various power production tasks. The power system consists of substations of various voltages and transmission and distribution lines as a whole, which is called the power grid. With the rapid development of my country's economy, electricity, as the main energy source used in today's society, has also been widely used in my country, and the power grid, as the main mode of transmission of electricity, is also spread across the country. Thanks to the rapid development of science and technology, in terms of power dispatching, the use of blockchain can effectively reduce the power dispatching workload of staff. In the power dispatching process, it is easy for sudden natural disasters, insufficient power generation or high electricity demand to cause insufficient power supply in the power grid, resulting in inconvenience in electricity use. Moreover, since blockchain is an emerging technology, it is difficult for staff to be familiar with it for a while, which leads to resistance from staff to upgrade the power dispatching system.

[0003] The patent with application announcement number CN111091272A discloses a microgrid power dispatching system based on blockchain. By obtaining the microgrid power information and power user power consumption information stored in the server and analyzing them, direct dispatching users, indirect dispatching users and non-dispatching users are obtained. The power dispatching command is sent to the mobile terminal of the indirect dispatching user through the user activity module. After receiving the power dispatching command, the indirect dispatching user sends a dispatching instruction or a non-dispatching instruction to the user activity module. When the user activity module receives the dispatching instruction of the indirect dispatching user, the indirect dispatching user is marked as a direct dispatching user. When the user activity module receives a non-dispatching instruction or does not receive the instruction of the indirect dispatching user within a preset time, the indirect dispatching user is marked as a non-dispatching user. The user activity module sends the power consumption information of the directly dispatching user to the power dispatching module. Through power consumption analysis of the power users and instruction confirmation, some non-power users are removed, so that the power generated by the microgrid is evenly dispatched to active power users, avoiding the allocation of power to some inactive users, resulting in unreasonable dispatching.

[0004] However, although the above-mentioned blockchain-based microgrid power dispatching system achieves the purpose of reasonable power distribution to a certain extent by analyzing and processing microgrid power information and power users' power consumption information, it is prone to power dispatching risks during the power grid dispatching process due to the susceptibility to sudden natural disasters and unstable supply and demand relationships. In addition, blockchain technology is an emerging technology, and power grid practitioners are easily affected by lack of familiarity, resulting in resistance to new technologies. Therefore, how to effectively predict the risks of power grid dispatching and reduce the generation of resistance has become a major problem that the current power grid industry needs to face.

[0005] In view of this, the present invention proposes a blockchain-based power grid dispatching method, system, medium and equipment to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including:

[0007] A power grid data acquisition module is used to collect power grid data sets, including line load data, line impedance data and maximum load data;

[0008] A change data acquisition module is used to collect change data sets, including real-time load data, line temperature data, and ambient wind speed data;

[0009] A feature vector calculation module is used to pre-process the power grid data set and the change data set to obtain a feature vector set;

[0010] Furthermore, the methods for preprocessing the power grid dataset and the change dataset include:

[0011] Q1, normalize the power grid data set and the change data set. The specific calculation formula for normalization is:

[0012] ;

[0013] in, For the The processed basic data items, Contains all basic data items in the power grid dataset and change dataset, For the Basic data items, For the The minimum allowed value of a basic data item, For the The maximum allowed value of a basic data item;

[0014] Q2: Calculate the safety feature based on the line load data and the maximum load data. The specific calculation formula for the safety feature is:

[0015] ;

[0016] Get security feature data ,in, is the line load data, is the maximum load data of the line;

[0017] Q3, by passing the line temperature data and ambient wind speed data Perform weighted summation to obtain environmental characteristic data ;

[0018] Q4, by extracting the change characteristics of real-time load data, the specific calculation formula of the change characteristics is:

[0019] ;

[0020] Get change feature data ,in, The current time point Real-time load data, For the previous time point Real-time load data, is the time interval;

[0021] Q5, by extracting stable features from line load data, line impedance data, and real-time load data, the specific calculation formula for stable features is:

[0022] ;

[0023] Get stable characteristic data ,in, is the line impedance data, is the line length, is the material safety factor;

[0024] Q6: Pack security feature data, environmental feature data, change feature data, and stable feature data to obtain a feature vector set. ;

[0025] The risk prediction module is used to analyze the feature vector set and obtain the risk prediction value;

[0026] Furthermore, the risk prediction module also includes a historical data retrieval module, a system model support module, a parameter input module and a prediction value transmission module, wherein:

[0027] The historical data retrieval module is used to support the system in extracting the historical feature vector set stored in the database;

[0028] The system model support module is used to support the system in establishing the required model;

[0029] The parameter input module is used to support manual input of region segmentation data and time folding data;

[0030] The predicted value transmission module is used to support the system in transmitting the risk prediction value;

[0031] Furthermore, the specific steps for analyzing the feature vector set are:

[0032] Step 1: Based on the historical data retrieval module, a set of historical feature vectors stored in the database is extracted and grouped and labeled accordingly according to the order of timestamps from recent to far. The labeling results are U1, U2, U3, ..., Un, and the labeling results are used as the sample set;

[0033] Step 2: Based on the system model support module, the sample set is divided into an 80% training set and a 20% validation set to establish a risk prediction model;

[0034] Step 3: Substitute into the calculation formula:

[0035] ;

[0036] Get the first risk prediction value ,in, is the activation function, is the number of groups of historical feature datasets, For the Dynamic weight factors for group historical feature datasets, For the The residual convolution block function of the group historical feature dataset, The current time point The historical feature dataset of For time point The historical feature dataset of is the historical time offset, is the number of backtracking time steps, is the number of backtracking time steps The attention weight factor, is element-wise multiplication, is the feature enhancement function, To go back in time The historical feature dataset of is the time step;

[0037] Step 4: Based on the region segmentation data in the parameter input module, substitute the calculation formula: , and obtain the spatial risk prediction value ,in, For regional segmentation data, For the A sub-model for region segmentation data, For the training set Middle A historical feature dataset of regional segmentation data, For cross-region test sets Historical feature datasets in ;

[0038] Step 5: Based on the time folding data in the parameter input module, substitute the calculation formula:

[0039] , and get the time risk prediction value ,in, Fold the data for time, is the timestamp, is the training set time period, is the test set time period;

[0040] Step 6: Based on the first risk prediction value, spatial risk prediction value, and temporal risk prediction value in steps 3 to 5, substitute the following formula: , and obtain the risk prediction value ,in, and To verify the weight factor;

[0041] Step 7: Based on the prediction value transmission module, the risk prediction value is transmitted to the dynamic scheduling decision module;

[0042] Dynamic scheduling decision module, used to analyze risk prediction values ​​and obtain dynamic scheduling decision reports;

[0043] Furthermore, the risk prediction value can be analyzed by:

[0044] When the risk prediction value is less than 0.3, a green dispatch report is generated; when the risk prediction value is greater than or equal to 0.3 and less than 0.7, a yellow dispatch report is generated; when the risk prediction value is greater than or equal to 0.7, a red dispatch report is generated;

[0045] The green dispatch report includes a statement that the current power risk of the power grid is low and that staff are requested to work normally according to the work plan;

[0046] The yellow dispatch report includes a description of the current power grid risk and asks staff to promptly notify the power station to activate the backup power supply;

[0047] The red dispatch report includes a statement that the current power risk of the power grid is high and the staff is requested to immediately cut off non-critical loads;

[0048] Pack the green scheduling report, yellow scheduling report and red scheduling report to obtain a dynamic scheduling decision report;

[0049] Multi-energy coordination module, used to analyze dynamic scheduling decision reports and implement analysis results;

[0050] Furthermore, the dynamic scheduling decision report is analyzed and the analysis results are executed in the following ways:

[0051] When the dynamic dispatch decision report is a red dispatch report, the backup power supply is activated, the incremental power generation value of the generator set is adjusted, and the power consumption of commercial users is reduced, including:

[0052] The power generation increment value is obtained by multiplying the change characteristic data by the adjustment coefficient;

[0053] The reduction in commercial user electricity consumption is obtained by multiplying the line load data by the real-time load data and dividing by 10;

[0054] The blockchain storage module is used to store feature vector sets, risk prediction values, dynamic scheduling decision reports, and execution measure records;

[0055] Furthermore, the storage methods of the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record include:

[0056] Integrate the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record to obtain a storage data set;

[0057] Divide the storage data set file into R data blocks;

[0058] Calculate the hash value for each data block separately;

[0059] Build a Merkle tree based on the hash value of each data block and get the root hash value;

[0060] Encrypt the stored data set based on the public key;

[0061] Upload the encrypted stored data set to the blockchain;

[0062] Acceptance enhancement module for simplifying blockchain operations;

[0063] Furthermore, the methods for simplifying blockchain operations include:

[0064] Generate a risk heat map with corresponding colors based on the dynamic scheduling decision report;

[0065] The user clicks the confirmation button to execute the execution measures in the multi-energy coordination module, and the system background automatically generates the corresponding blockchain operation;

[0066] Further, S1: collecting a power grid data set, the power grid data set including line load data, line impedance data and maximum load data;

[0067] S2: Collecting change data sets, which include real-time load data, line temperature data, and ambient wind speed data;

[0068] S3: Preprocess the power grid dataset and the change dataset to obtain a feature vector set;

[0069] S4: Analyze the feature vector set to obtain the risk prediction value;

[0070] S5: Analyze the risk prediction value and obtain a dynamic scheduling decision report;

[0071] S6: Multi-energy coordination module, used to analyze dynamic scheduling decision reports and implement analysis results;

[0072] S7: storing the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record;

[0073] S8: Simplify blockchain operations.

[0074] The technical effects and advantages of the blockchain-based power grid dispatching method, system, medium and equipment of the present invention are as follows:

[0075] The present invention collects a power grid data set, which includes line load data, line impedance data and maximum load data, collects a change data set, which includes real-time load data, line temperature data and ambient wind speed data, pre-processes the power grid data set and the change data set to obtain a feature vector set, analyzes the feature vector set to obtain a risk prediction value, analyzes the risk prediction value to obtain a dynamic scheduling decision report, and a multi-energy coordination module is used to analyze the dynamic scheduling decision report and execute the analysis results, stores the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record, and simplifies the blockchain operation, so that the system has the ability to accurately predict the power scheduling risks that may occur in the future time period under the interference of dynamic factor fluctuations, thereby It greatly reduces the inconvenience of electricity use caused by emergencies, thereby effectively improving the practicality of the system. In addition, the present invention also provides staff with clear and effective auxiliary decision-making through analysis of risk prediction values, thereby effectively reducing the decision-making time required for staff when facing emergencies, thereby effectively protecting the interests of enterprises and people. At the same time, through the analysis of decision-making reports, the system can have the ability to assist staff in completing emergency operations, thereby greatly reducing the hazards of sudden high-risk events. Moreover, by simplifying the operation of blockchain technology, it can effectively enhance the control of staff over new technologies, thereby effectively reducing the resistance of staff. Overall, the present invention has the significant advantages of strong risk prediction accuracy, good auxiliary risk reduction effect and high staff acceptance of new technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 This is a schematic diagram of the blockchain-based power grid dispatching system of the present invention;

[0077] Figure 2 Schematic diagram of the blockchain-based power grid dispatching method of the present invention. DETAILED DESCRIPTION

[0078] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0079] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0080] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0081] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0082] In practice, the server-side devices deployed in a blockchain-based power grid dispatching system may consist of one or more devices. The aforementioned blockchain-based power grid dispatching system can be implemented as a service instance, a virtual machine, or hardware devices. For example, the blockchain-based power grid dispatching system can be implemented as a service instance deployed on one or more devices in a cloud node. Simply put, the blockchain-based power grid dispatching system can be understood as software deployed on a cloud node, providing the blockchain-based power grid dispatching system to each user. Alternatively, the blockchain-based power grid dispatching system can be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing each user. Alternatively, the blockchain-based power grid dispatching system can be implemented as a server-side device composed of numerous hardware devices of the same or different types, with one or more hardware devices configured to provide the blockchain-based power grid dispatching system to each user.

[0083] In terms of implementation, the blockchain-based power grid dispatching system and the user end are mutually compatible. Specifically, if the blockchain-based power grid dispatching system is an application installed on a cloud service platform, the user end is the client that establishes a communication connection with the application. Alternatively, if the blockchain-based power grid dispatching system is implemented as a website, the user end is implemented as a webpage. Alternatively, if the blockchain-based power grid dispatching system is implemented as a cloud service platform, the user end is implemented as a mini-program within an instant messaging application.

[0084] like Figure 1 , which is a system architecture diagram of a blockchain-based power grid dispatching system provided by one embodiment of the present invention.

[0085] The blockchain-based power grid dispatching system of the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (such as a mobile service operator's server, server cluster, etc.), or it can be developed as a website. According to the functions implemented, the blockchain-based power grid dispatching system can include a power grid data acquisition module, a change data acquisition module, a feature vector calculation module, a risk prediction module, a dynamic scheduling decision module, a multi-energy coordination module, a blockchain storage module and an acceptance enhancement module. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0086] In an embodiment of the present invention, in the power grid and electric power dispatching system based on blockchain, each of the above modules can be implemented independently and called with other modules. The call here can be understood as that a certain module can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information acquisition module to obtain the information collected by the information acquisition module. Based on the above characteristics, in the power grid and electric power dispatching system based on blockchain provided by an embodiment of the present invention, the scope of application of the power grid and electric power dispatching system architecture based on blockchain can be adjusted by adding modules and directly calling them without modifying the program code, so as to achieve cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the power grid and electric power dispatching system based on blockchain. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0087] Example 1

[0088] See also Figure 1 As shown, the blockchain-based power grid dispatching system described in this embodiment includes:

[0089] The power grid data acquisition module is used to collect power grid data sets, which include line load data, line impedance data and maximum load data;

[0090] It should be explained that the maximum load value of the power grid lines in the specified area is collected through the equipment nameplate to obtain the line load data; the resistance value of the power grid lines in the specified area is collected through the line design drawing parameters to obtain the line impedance data; the historical peak value records of the power grid lines in the specified area are collected through the database, and the quotient with the line load data is calculated to obtain the maximum load data;

[0091] The change data acquisition module is used to collect the change data set, which includes real-time load data, line temperature data and ambient wind speed data;

[0092] It should be explained that the real-time load values ​​of the power grid lines in the specified area are collected by smart meters to obtain real-time load data; the temperature values ​​of the power grid lines in the specified area are collected by temperature sensors to obtain line temperature data; and the wind speed values ​​in the specified area are collected by micro-weather stations to obtain ambient wind speed data.

[0093] The characteristic vector calculation module is used to pre-process the power grid data set and the change data set to obtain a characteristic vector set;

[0094] Furthermore, the pre-processing methods for the power grid dataset and the change dataset include:

[0095] Q1, normalize the power grid data set and the change data set. The specific calculation formula for normalization is:

[0096] ;

[0097] in, For the The processed basic data items, Contains all basic data items in the power grid dataset and change dataset, For the Basic data items, For the The minimum allowed value of a basic data item, For the The maximum allowed value of a basic data item;

[0098] Q2: Calculate the safety feature based on the line load data and the maximum load data. The specific calculation formula for the safety feature is:

[0099] ;

[0100] Get security feature data ,in, is the line load data, is the maximum load data of the line;

[0101] Q3, by passing the line temperature data and ambient wind speed data Perform weighted summation to obtain environmental characteristic data ;

[0102] Q4, by extracting the change characteristics of real-time load data, the specific calculation formula of the change characteristics is:

[0103] ;

[0104] Get change feature data ,in, The current time point Real-time load data, For the previous time point Real-time load data, is the time interval;

[0105] Q5, by extracting stable features from line load data, line impedance data, and real-time load data, the specific calculation formula for stable features is:

[0106] ;

[0107] Get stable characteristic data ,in, is the line impedance data, is the line length, is the material safety factor;

[0108] Q6: Pack security feature data, environmental feature data, change feature data, and stable feature data to obtain a feature vector set. ;

[0109] The risk prediction module is used to analyze the feature vector set to obtain a risk prediction value;

[0110] Furthermore, the risk prediction module also includes a historical data retrieval module, a system model support module, a parameter input module and a prediction value transmission module, wherein:

[0111] The historical data retrieval module is used to support the system in extracting the historical feature vector set stored in the database;

[0112] The system model support module is used to support the system in establishing the required model;

[0113] The parameter input module is used to support manual input of region segmentation data and time folding data;

[0114] The predicted value transmission module is used to support the system in transmitting the risk prediction value;

[0115] Furthermore, the specific steps for analyzing the feature vector set are:

[0116] Step 1: Based on the historical data retrieval module, a set of historical feature vectors stored in the database is extracted and grouped and labeled accordingly according to the order of timestamps from recent to far. The labeling results are U1, U2, U3, ..., Un, and the labeling results are used as the sample set;

[0117] Step 2: Based on the system model support module, the sample set is divided into an 80% training set and a 20% validation set to establish a risk prediction model;

[0118] Step 3: Substitute into the calculation formula:

[0119] ;

[0120] Get the first risk prediction value ,in, is the activation function, is the number of groups of historical feature datasets, For the Dynamic weight factors for group historical feature datasets, For the The residual convolution block function of the group historical feature dataset, The current time point The historical feature dataset of For time point The historical feature dataset of is the historical time offset, is the number of backtracking time steps, is the number of backtracking time steps The attention weight factor, is element-wise multiplication, is the feature enhancement function, To go back in time The historical feature dataset of is the time step;

[0121] It needs to be explained that the activation function is used to convert

[0122] The output value range is constrained between 0 and 1; the residual convolution block function includes three convolution layers, batch normalization, and LeakyReLU activation function; the feature enhancement function includes a fully connected layer and an ELU activation function;

[0123] Step 4: Based on the region segmentation data in the parameter input module, substitute the calculation formula: , and obtain the spatial risk prediction value ,in, For regional segmentation data, For the A sub-model for region segmentation data, For the training set Middle A historical feature dataset of regional segmentation data, For cross-region test sets Historical feature datasets in ;

[0124] Step 5: Based on the time folding data in the parameter input module, substitute the calculation formula:

[0125] , and get the time risk prediction value ,in, Fold the data for time, is the timestamp, is the training set time period, is the test set time period;

[0126] Step 6: Based on the first risk prediction value, spatial risk prediction value, and temporal risk prediction value in steps 3 to 5, substitute the following formula: , and obtain the risk prediction value ,in, and To verify the weight factor;

[0127] Step 7: Based on the prediction value transmission module, the risk prediction value is transmitted to the dynamic scheduling decision module;

[0128] The dynamic scheduling decision module is used to analyze the risk prediction value and obtain a dynamic scheduling decision report;

[0129] Further, the methods for analyzing the risk prediction value include:

[0130] When the risk prediction value is less than 0.3, a green dispatch report is generated; when the risk prediction value is greater than or equal to 0.3 and less than 0.7, a yellow dispatch report is generated; when the risk prediction value is greater than or equal to 0.7, a red dispatch report is generated;

[0131] The green dispatch report includes a statement that the current power risk of the power grid is low and that staff are requested to work normally according to the work plan;

[0132] The yellow dispatch report includes a description of the current power grid risk and asks staff to promptly notify the power station to activate the backup power supply;

[0133] The red dispatch report includes a statement that the current power risk of the power grid is high and the staff is requested to immediately cut off non-critical loads;

[0134] Pack the green scheduling report, yellow scheduling report and red scheduling report to obtain a dynamic scheduling decision report;

[0135] The multi-energy coordination module is used to analyze the dynamic scheduling decision report and execute the analysis results;

[0136] Furthermore, the dynamic scheduling decision report is analyzed and the analysis results are executed in the following ways:

[0137] When the dynamic dispatch decision report is a red dispatch report, the backup power supply is activated, the incremental power generation value of the generator set is adjusted, and the power consumption of commercial users is reduced, including:

[0138] The power generation increment value is obtained by multiplying the change characteristic data by the adjustment coefficient;

[0139] The reduction in commercial user electricity consumption is obtained by multiplying the line load data by the real-time load data and dividing by 10;

[0140] The blockchain storage module is used to store feature vector sets, risk prediction values, dynamic scheduling decision reports, and execution measure records;

[0141] Furthermore, the storage methods for the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record include:

[0142] Integrate the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record to obtain a storage data set;

[0143] Divide the storage data set file into R data blocks;

[0144] Calculate the hash value for each data block separately;

[0145] Build a Merkle tree based on the hash value of each data block and get the root hash value;

[0146] Encrypt the stored data set based on the public key;

[0147] Upload the encrypted stored data set to the blockchain;

[0148] The acceptance enhancement module is used to simplify blockchain operations;

[0149] Further, ways to simplify blockchain operations include:

[0150] Generate a risk heat map with corresponding colors based on the dynamic scheduling decision report;

[0151] It should be explained that the corresponding colors include red, yellow and green;

[0152] The user clicks the confirmation button to execute the execution measures in the multi-energy coordination module, and the system background automatically generates the corresponding blockchain operation;

[0153] This embodiment has the beneficial effects of collecting power grid data sets, which include line load data, line impedance data and maximum load data, collecting change data sets, which include real-time load data, line temperature data and ambient wind speed data, preprocessing the power grid data sets and change data sets to obtain feature vector sets, analyzing the feature vector sets to obtain risk prediction values, analyzing the risk prediction values ​​to obtain dynamic scheduling decision reports, and multi-energy coordination modules for analyzing dynamic scheduling decision reports and executing analysis results, storing feature vector sets, risk prediction values, dynamic scheduling decision reports and execution measure records, and simplifying blockchain operations, so that the system has the ability to accurately predict the power scheduling risks that may occur in future time periods under the interference of dynamic factor fluctuations. , thereby greatly reducing the inconvenience of electricity use caused by emergencies, and effectively improving the practicality of the system. In addition, the present invention also provides staff with clear and effective auxiliary decision-making through analysis of risk prediction values, thereby effectively reducing the decision-making time required for staff in the face of emergencies, and thus effectively protecting the interests of enterprises and people. At the same time, through the analysis of decision-making reports, the system can have the ability to assist staff in completing emergency operations, thereby greatly reducing the harmfulness of sudden high-risk events. Moreover, by simplifying the operation of blockchain technology, the staff's control over new technologies can be effectively enhanced, thereby effectively reducing the staff's resistance. Overall, the present invention has the significant advantages of strong risk prediction accuracy, good auxiliary risk reduction effect and high staff acceptance of new technologies.

[0154] Example 2

[0155] See also Figure 2 As shown, for the parts not described in detail in this embodiment, please refer to the description of Example 1. A blockchain-based power grid dispatching method is provided, the method comprising: S1: collecting a power grid data set, the power grid data set including line load data, line impedance data, and maximum load data;

[0156] S2: Collecting change data sets, which include real-time load data, line temperature data, and ambient wind speed data;

[0157] S3: Preprocess the power grid dataset and the change dataset to obtain a feature vector set;

[0158] S4: Analyze the feature vector set to obtain the risk prediction value;

[0159] S5: Analyze the risk prediction value and obtain a dynamic scheduling decision report;

[0160] S6: Multi-energy coordination module, used to analyze dynamic scheduling decision reports and implement analysis results;

[0161] S7: storing the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record;

[0162] S8: Simplify blockchain operations.

[0163] Example 3

[0164] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0165] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0166] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0167] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0168] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. The power grid dispatching system based on blockchain is characterized by: The system includes: a power grid data acquisition module, a change data acquisition module, a feature vector calculation module, a risk prediction module, a dynamic scheduling decision module, a multi-energy coordination module, a blockchain storage module and an acceptance enhancement module, wherein: The power grid data acquisition module is used to collect power grid data sets, which include line load data, line impedance data and maximum load data; The change data acquisition module is used to collect the change data set, which includes real-time load data, line temperature data and ambient wind speed data; The characteristic vector calculation module is used to pre-process the power grid data set and the change data set to obtain a characteristic vector set; The risk prediction module is used to analyze the feature vector set to obtain a risk prediction value; The dynamic scheduling decision module is used to analyze the risk prediction value and obtain a dynamic scheduling decision report; The multi-energy coordination module is used to analyze the dynamic scheduling decision report and execute the analysis results; The blockchain storage module is used to store feature vector sets, risk prediction values, dynamic scheduling decision reports, and execution measure records; The acceptance enhancement module is used to simplify blockchain operations.

2. The blockchain-based power grid dispatching system according to claim 1, characterized in that: Methods for preprocessing power grid datasets and change datasets include: Q1, normalize the power grid data set and the change data set. The specific calculation formula for normalization is: ； in, For the The processed basic data items, Contains all basic data items in the power grid dataset and change dataset, For the Basic data items, For the The minimum allowed value of a basic data item, For the The maximum allowed value of a basic data item; Q2: Calculate the safety feature based on the line load data and the maximum load data. The specific calculation formula for the safety feature is: ； Get security feature data ,in, is the line load data, is the maximum load data of the line; Q3, by passing the line temperature data and ambient wind speed data Perform weighted summation to obtain environmental characteristic data ; Q4, by extracting the change characteristics of real-time load data, the specific calculation formula of the change characteristics is: ； Get change feature data ,in, The current time point Real-time load data, For the previous time point Real-time load data, is the time interval; Q5, by extracting stable features from line load data, line impedance data, and real-time load data, the specific calculation formula for stable features is: ； Get stable characteristic data ,in, is the line impedance data, is the line length, is the material safety factor; Q6: Pack security feature data, environmental feature data, change feature data, and stable feature data to obtain a feature vector set. .

3. The blockchain-based power grid dispatching system according to claim 1, characterized in that: The specific steps for analyzing the feature vector set are: Step 1: Based on the historical data retrieval module, a set of historical feature vectors stored in the database is extracted and grouped and labeled accordingly according to the order of timestamps from recent to far. The labeling results are U1, U2, U3, ..., Un, and the labeling results are used as the sample set; Step 2: Based on the system model support module, the sample set is divided into an 80% training set and a 20% validation set to establish a risk prediction model; Step 3: Substitute into the calculation formula: ； Get the first risk prediction value ,in, is the activation function, is the number of groups of historical feature datasets, For the Dynamic weight factors for group historical feature datasets, For the The residual convolution block function of the group historical feature dataset, The current time point The historical feature dataset of For time point The historical feature dataset of is the historical time offset, is the number of backtracking time steps, is the number of backtracking time steps The attention weight factor, is element-wise multiplication, is the feature enhancement function, To go back in time The historical feature dataset of is the time step; Step 4: Based on the region segmentation data in the parameter input module, substitute the calculation formula: , and obtain the spatial risk prediction value ,in, For regional segmentation data, For the A sub-model for region segmentation data, For the training set Middle A historical feature dataset of regional segmentation data, For cross-region test sets Historical feature datasets in ; Step 5: Based on the time folding data in the parameter input module, substitute the calculation formula: , and get the time risk prediction value ,in, Fold the data for time, is the timestamp, is the training set time period, is the test set time period; Step 6: Based on the first risk prediction value, spatial risk prediction value, and temporal risk prediction value in steps 3 to 5, substitute the following formula: , and obtain the risk prediction value ,in, and To verify the weight factor; Step 7: Based on the prediction value transmission module, the risk prediction value is transmitted to the dynamic scheduling decision module.

4. The blockchain-based power grid dispatching system according to claim 1, characterized in that: Methods for analyzing risk prediction values ​​include: When the risk prediction value is less than 0.3, a green dispatch report is generated; when the risk prediction value is greater than or equal to 0.3 and less than 0.7, a yellow dispatch report is generated; when the risk prediction value is greater than or equal to 0.7, a red dispatch report is generated; The green dispatch report includes a statement that the current power risk of the power grid is low and that staff are requested to work normally according to the work plan; The yellow dispatch report includes a description of the current power grid risk and asks staff to promptly notify the power station to activate the backup power supply; The red dispatch report includes a statement that the current power risk of the power grid is high and the staff is requested to immediately cut off non-critical loads; The green scheduling report, yellow scheduling report and red scheduling report are packaged to obtain a dynamic scheduling decision report.

5. The blockchain-based power grid dispatching system according to claim 1, characterized in that: Methods for analyzing the dynamic scheduling decision report and executing the analysis results include: When the dynamic dispatch decision report is a red dispatch report, the backup power supply is activated, the incremental power generation value of the generator set is adjusted, and the power consumption of commercial users is reduced, including: The power generation increment value is obtained by multiplying the change characteristic data by the adjustment coefficient; The reduction in commercial customer electricity consumption is calculated by multiplying the line load data by the real-time load data and dividing by 10.

6. The blockchain-based power grid dispatching system according to claim 1, characterized in that: The storage methods for the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record include: Integrate the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record to obtain a storage data set; Divide the storage data set file into R data blocks; Calculate the hash value for each data block separately; Build a Merkle tree based on the hash value of each data block and get the root hash value; Encrypt the stored data set based on the public key; Upload the encrypted stored data set to the blockchain.

7. The blockchain-based power grid dispatching system according to claim 6, characterized in that: Ways to simplify blockchain operations include: Generate a risk heat map with corresponding colors based on the dynamic scheduling decision report; The user clicks the confirmation button to execute the execution measures in the multi-energy coordination module, and the system background automatically generates the corresponding blockchain operations.

8. A blockchain-based power grid dispatching method, implemented according to the blockchain-based power grid dispatching system according to any one of claims 1 to 7, characterized in that: The following steps are included: S1: Collect power grid data sets, including line load data, line impedance data, and maximum load data; S2: Collecting change data sets, which include real-time load data, line temperature data, and ambient wind speed data; S3: Preprocess the power grid dataset and the change dataset to obtain a feature vector set; S4: Analyze the feature vector set to obtain the risk prediction value; S5: Analyze the risk prediction value and obtain a dynamic scheduling decision report; S6: Multi-energy coordination module, used to analyze dynamic scheduling decision reports and implement analysis results; S7: storing the feature vector set, risk prediction value, dynamic scheduling decision report and execution measure record; S8: Simplify blockchain operations.

9. A computer-readable storage medium, characterized in that The storage medium stores instructions, which, when executed on a computer, enable the computer to execute the blockchain-based power grid dispatching system according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: one or more processors; One or more memories; the one or more memories store one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device executes the blockchain-based power grid dispatching system according to any one of claims 1 to 7.

Images