Power dispatching method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a power dispatching method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: when terminal information of a terminal meets a first preset condition, decrypting encrypted current state information of a to-be-analyzed power grid sent by the terminal to obtain the current state information; performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information; inputting the feature vector into a pre-trained state prediction model to obtain prediction state information of the to-be-analyzed power grid; generating a plurality of candidate power dispatching instructions according to the current state information and the predicted state information; screening out the candidate power dispatching instruction of which the target information meets a second preset condition from the candidate power dispatching instructions, and taking the candidate power dispatching instruction as a target power dispatching instruction; and performing power dispatching processing on power resources in the to-be-analyzed power grid according to the target power dispatching instruction. By adopting the method, the power dispatching accuracy of the power grid can be improved.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a power dispatching method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] At present, in order to ensure the safe and stable operation of the power grid, it is crucial to dispatch power to the power grid.

[0003] In traditional technology, in the process of power dispatching of power grids, manual experience judgment is generally adopted; however, this method has subjective factors and is prone to errors, resulting in low accuracy of power dispatching of power grids. Summary of the invention

[0004] Based on this, it is necessary to provide a power dispatching method, device, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of power dispatching of the power grid in response to the above technical problems.

[0005] In a first aspect, the present application provides a power dispatching method, comprising:

[0006] Obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal;

[0007] In the case where the terminal information meets the first preset condition, decrypting the encrypted current state information to obtain the current state information of the power grid to be analyzed;

[0008] Performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information;

[0009] Inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed;

[0010] generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information;

[0011] Acquire target information of each of the candidate power dispatching instructions, and select, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed;

[0012] According to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed.

[0013] In one embodiment, generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information includes:

[0014] Inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed, and a predicted probability of each of the predicted power dispatch instructions;

[0015] From the predicted power dispatching instructions, the predicted power dispatching instructions whose predicted probability is greater than the preset probability are screened out as a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed.

[0016] In one embodiment, before inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed and the predicted probability of each of the predicted power dispatch instructions, the method further includes:

[0017] Determining a plurality of candidate power dispatch instruction prediction models associated with the power grid to be analyzed, and obtaining a prediction accuracy rate of each of the candidate power dispatch instruction prediction models;

[0018] From each of the candidate power dispatching instruction prediction models, the candidate power dispatching instruction prediction models whose prediction accuracy is greater than the preset accuracy are selected as the multiple pre-trained power dispatching instruction prediction models.

[0019] In one embodiment, obtaining the terminal information of the terminal includes:

[0020] Obtaining request frequency information and source information corresponding to the terminal;

[0021] Preprocessing the request frequency information and the source information to obtain preprocessed request frequency information and preprocessed source information;

[0022] The preprocessed request frequency information and the preprocessed source information are combined to obtain terminal information of the terminal.

[0023] In one of the embodiments, after performing power dispatch processing on the power resources in the power grid to be analyzed according to the target power dispatch instruction, the method further includes:

[0024] Extracting key status information from the current status information, and determining a backup server associated with the power grid to be analyzed;

[0025] Generate backup request information corresponding to the key state information, and send the backup request information to the backup server, so that the backup server performs backup processing on the key state information according to the backup request information.

[0026] In one embodiment, the pre-trained state prediction model is trained in the following manner:

[0027] Obtaining encrypted current sample state information of the sample power grid sent by the sample terminal, and obtaining sample terminal information of the sample terminal;

[0028] In the case where the sample terminal information satisfies the first preset condition, decrypting the encrypted current sample state information to obtain the current sample state information of the sample power grid;

[0029] Performing feature extraction processing on the current sample state information to obtain a sample feature vector corresponding to the current sample state information;

[0030] Inputting the sample feature vector into a state prediction model to be trained to obtain predicted state information of the sample power grid;

[0031] The actual state information of the sample power grid is obtained, and according to the difference between the predicted state information of the sample power grid and the actual state information, the state prediction model to be trained is iteratively trained to obtain the pre-trained state prediction model.

[0032] In a second aspect, the present application also provides a power dispatching device, comprising:

[0033] An information acquisition module, used to acquire encrypted current state information of the power grid to be analyzed sent by the terminal, and to acquire terminal information of the terminal;

[0034] An information processing module, configured to decrypt the encrypted current state information to obtain the current state information of the power grid to be analyzed when the terminal information satisfies a first preset condition;

[0035] A feature extraction module, used to perform feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information;

[0036] A state prediction module, used for inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed;

[0037] An instruction generation module, used for generating a plurality of candidate power dispatch instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information;

[0038] An instruction screening module, used for obtaining target information of each of the candidate power dispatching instructions, and screening out, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed;

[0039] The resource scheduling module is used to perform power scheduling processing on the power resources in the power grid to be analyzed according to the target power scheduling instruction.

[0040] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0041] Obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal;

[0042] In the case where the terminal information meets the first preset condition, decrypting the encrypted current state information to obtain the current state information of the power grid to be analyzed;

[0043] Performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information;

[0044] Inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed;

[0045] generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information;

[0046] Acquire target information of each of the candidate power dispatching instructions, and select, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed;

[0047] According to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0049] Obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal;

[0050] In the case where the terminal information meets the first preset condition, decrypting the encrypted current state information to obtain the current state information of the power grid to be analyzed;

[0051] Performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information;

[0052] Inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed;

[0053] generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information;

[0054] Acquire target information of each of the candidate power dispatching instructions, and select, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed;

[0055] According to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed.

[0056] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0057] Obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal;

[0058] In the case where the terminal information meets the first preset condition, decrypting the encrypted current state information to obtain the current state information of the power grid to be analyzed;

[0059] Performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information;

[0060] Inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed;

[0061] generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information;

[0062] Acquire target information of each of the candidate power dispatching instructions, and select, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed;

[0063] According to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed.

[0064] The above-mentioned power dispatching method, device, computer equipment, storage medium and computer program product first obtain the encrypted current state information of the power grid to be analyzed sent by the terminal, and obtain the terminal information of the terminal. When the terminal information meets the first preset condition, the encrypted current state information is decrypted to obtain the current state information of the power grid to be analyzed, and then the current state information is subjected to feature extraction processing to obtain the feature vector corresponding to the current state information, and the feature vector is input into a pre-trained state prediction model to obtain the predicted state information of the power grid to be analyzed. Then, based on the current state information and the predicted state information, a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed are generated. Then, the target information of each candidate power dispatching instruction is obtained, and from each candidate power dispatching instruction, the candidate power dispatching instruction whose target information meets the second preset condition is screened out as the target power dispatching instruction corresponding to the power grid to be analyzed. Finally, according to the target power dispatching instruction, the power resources in the power grid to be analyzed are subjected to power dispatch processing. In this way, in the process of power dispatching of the power grid, by inputting the decrypted current state information into the state prediction model, more accurate predicted state information can be obtained, and from multiple candidate power dispatching instructions, candidate power dispatching instructions whose target information meets the preset conditions can be screened out, so that more accurate candidate power dispatching instructions can be obtained, thereby ensuring that the candidate power dispatching instructions meet the operation requirements of the power grid, which is conducive to improving the power dispatching accuracy of the power grid; moreover, the entire method does not require human intervention, avoiding the subjective factors and prone to errors in the method of using human experience judgment, which leads to the defect of low power dispatching accuracy of the power grid, and further improves the power dispatching accuracy of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0066] Figure 1 A schematic diagram of a flow chart of a power dispatching method in one embodiment;

[0067] Figure 2 A schematic flow chart of steps for generating a plurality of candidate power dispatching instructions corresponding to a power grid to be analyzed in one embodiment;

[0068] Figure 3 is a flow chart of a power dispatching method in another embodiment;

[0069] Figure 4A schematic diagram of a power grid intelligent security defense and dispatch coordination system in one embodiment;

[0070] Figure 5 is a structural block diagram of a power dispatching device in one embodiment;

[0071] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0074] In an exemplary embodiment, Figure 1 As shown, a power dispatching method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablet computers; the server can be implemented with an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0075] Step S101, obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal.

[0076] The power grid to be analyzed refers to the power grid system that requires power dispatching.

[0077] The encrypted current state information refers to the encrypted current state information of the power grid to be analyzed.

[0078] The current state information of the power grid to be analyzed refers to the state information of the power grid to be analyzed at the current time, including the internal and external real-time data of the power grid to be analyzed. The real-time data inside the power grid to be analyzed includes the monitoring data and equipment state information of the power plant and substation, and the real-time data outside the power grid to be analyzed includes the power generation data of the wind farm and the weather forecast data of the weather station.

[0079] The terminal information refers to information associated with the terminal, including the request frequency and source IP (Internet Protocol) address of the terminal.

[0080] Exemplarily, the server establishes a network path with the terminal in response to a power dispatch instruction for the power grid to be analyzed; then, the server obtains the encrypted current status information of the power grid to be analyzed sent by the terminal through the network path; then, the server obtains the request frequency and source IP address of the terminal, and uses the request frequency and source IP address of the terminal as the terminal information of the terminal.

[0081] Step S102: when the terminal information meets the first preset condition, the encrypted current state information is decrypted to obtain the current state information of the power grid to be analyzed.

[0082] The first preset condition refers to a pre-set judgment condition for terminal information, such as the request frequency is not greater than the preset frequency, and the source IP address is not in the preset blacklist. It should be noted that the first preset condition depends on the situation.

[0083] Exemplarily, when the terminal information meets the first preset condition, the server obtains the key corresponding to the encrypted current status information; then, the server uses the key to decrypt the encrypted current status information to obtain the current status information of the power grid to be analyzed.

[0084] Step S103: perform feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information.

[0085] The feature extraction process refers to the process of obtaining a feature vector corresponding to the current state information based on the current state information.

[0086] Among them, the feature vector is used to represent the characterization vector corresponding to the current state information.

[0087] Exemplarily, the server identifies the data type of the current state information; then, based on the data type of the current state information, the server queries the correspondence between the data type and the feature extraction model to obtain a target feature extraction model corresponding to the data type of the current state information; then, the server inputs the current state information into the target feature extraction model, performs feature extraction processing on the current state information through the target feature extraction model, and obtains a feature vector corresponding to the current state information.

[0088] Step S104, inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed.

[0089] The state prediction model refers to a network model that can obtain the predicted state information of the power grid to be analyzed by using the characteristic vector corresponding to the current state information of the power grid to be analyzed, such as a state space model, a transfer function model, etc.

[0090] The predicted state information refers to the state information of the power grid to be analyzed in the future (such as the next week or the next month).

[0091] Exemplarily, the server inputs the feature vector corresponding to the current state information of the power grid to be analyzed into a pre-trained state prediction model to obtain multiple candidate state information and the prediction probability of each candidate state information; then, the server selects the candidate state information with the highest prediction probability from each candidate state information as the predicted state information of the power grid to be analyzed.

[0092] Step S105, generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information.

[0093] The candidate power dispatching instruction refers to the power dispatching instruction to be selected.

[0094] Exemplarily, the server inputs the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of candidate power dispatch instructions corresponding to the power grid to be analyzed.

[0095] Step S106, obtaining target information of each candidate power dispatching instruction, and screening out the candidate power dispatching instructions whose target information meets the second preset condition from the candidate power dispatching instructions as the target power dispatching instructions corresponding to the power grid to be analyzed.

[0096] The target information includes the power generation cost, power outage probability and carbon dioxide emissions of each candidate power dispatch instruction.

[0097] The second preset condition refers to a pre-set judgment condition for the target information, such as the power generation cost is not greater than the preset cost, the power outage probability is not greater than the preset probability, and the carbon dioxide emission is not greater than the preset threshold, etc. It should be noted that the second preset condition depends on the circumstances.

[0098] The target power dispatch instruction refers to a candidate power dispatch instruction whose target information meets the second preset condition.

[0099] Exemplarily, the server obtains the power generation cost, power outage probability and carbon dioxide emissions of each candidate power dispatching instruction; then, the server combines the power generation cost, power outage probability and carbon dioxide emissions for each candidate power dispatching instruction to obtain the target information of each candidate power dispatching instruction; then, the server screens out the candidate power dispatching instructions whose target information meets the second preset condition from each candidate power dispatching instruction, and uses the candidate power dispatching instruction as the target power dispatching instruction corresponding to the power grid to be analyzed.

[0100] Step S107: performing power dispatch processing on the power resources in the power grid to be analyzed according to the target power dispatch instruction.

[0101] Among them, the power resources in the power grid to be analyzed include power generation resources, transmission resources and energy storage resources in the power grid to be analyzed.

[0102] Among them, power dispatch processing refers to the corresponding processing process of adjusting the power resources in the power grid to be analyzed.

[0103] Exemplarily, the server obtains power generation resources, transmission resources and energy storage resources in the power grid to be analyzed, all of which are used as power resources in the power grid to be analyzed; then, the server performs power dispatch processing on the power resources in the power grid to be analyzed according to the target power dispatch instruction.

[0104] In the above-mentioned power dispatching method, the encrypted current state information of the power grid to be analyzed sent by the terminal is first obtained, and the terminal information of the terminal is obtained. When the terminal information meets the first preset condition, the encrypted current state information is decrypted to obtain the current state information of the power grid to be analyzed. The current state information is then subjected to feature extraction to obtain a feature vector corresponding to the current state information, and the feature vector is input into a pre-trained state prediction model to obtain the predicted state information of the power grid to be analyzed. Next, based on the current state information and the predicted state information, a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed are generated. Then, the target information of each candidate power dispatching instruction is obtained, and from each candidate power dispatching instruction, the candidate power dispatching instruction whose target information meets the second preset condition is screened out as the target power dispatching instruction corresponding to the power grid to be analyzed. Finally, according to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed. In this way, in the process of power dispatching of the power grid, by inputting the decrypted current state information into the state prediction model, more accurate predicted state information can be obtained, and from multiple candidate power dispatching instructions, candidate power dispatching instructions whose target information meets the preset conditions can be screened out, so that more accurate candidate power dispatching instructions can be obtained, thereby ensuring that the candidate power dispatching instructions meet the operation requirements of the power grid, which is conducive to improving the power dispatching accuracy of the power grid; moreover, the entire method does not require human intervention, avoiding the subjective factors and prone to errors in the method of using human experience judgment, which leads to the defect of low power dispatching accuracy of the power grid, and further improves the power dispatching accuracy of the power grid.

[0105] In an exemplary embodiment, the above step S105, generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information, specifically includes the following steps:

[0106] Step S201, inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed, and a predicted probability of each predicted power dispatch instruction.

[0107] Step S202 , screening out predicted power dispatching instructions with predicted probabilities greater than preset probabilities from the predicted power dispatching instructions as multiple candidate power dispatching instructions corresponding to the power grid to be analyzed.

[0108] Among them, the pre-trained power dispatching instruction prediction model is used to represent the pre-trained power dispatching instruction prediction model.

[0109] Among them, the power dispatch instruction prediction model refers to a network model that can use the current state information and predicted state information corresponding to the power grid to be analyzed to obtain multiple candidate power dispatch instructions corresponding to the power grid to be analyzed, such as a recursive neural network model, a convolutional neural network model, etc.

[0110] The predicted power dispatching instructions are used to represent the power dispatching instructions output by multiple pre-trained power dispatching instruction prediction models.

[0111] The prediction probability of each predicted power dispatch instruction refers to the possibility that each predicted power dispatch instruction is correct as determined by multiple pre-trained power dispatch instruction prediction models.

[0112] The preset probability refers to a preset probability threshold, such as 80%. It should be noted that the preset probability depends on the situation.

[0113] Exemplarily, the server preprocesses the current state information and the predicted state information to obtain preprocessed current state information and preprocessed predicted state information; then, the server inputs the preprocessed current state information and the preprocessed predicted state information into multiple pre-trained power dispatching instruction prediction models to obtain multiple predicted power dispatching instructions corresponding to the power grid to be analyzed, and the predicted probability of each predicted power dispatching instruction; then, the server screens out the predicted power dispatching instructions with a predicted probability greater than a preset probability from each predicted power dispatching instruction, and uses these predicted power dispatching instructions as multiple candidate power dispatching instructions corresponding to the power grid to be analyzed.

[0114] In this embodiment, by utilizing multiple different pre-trained power dispatch instruction prediction models and taking into account the current state information and predicted state information of the power grid to be analyzed, the power grid state can be analyzed from different angles and methods to obtain a variety of predicted power dispatch instructions; moreover, by screening out predicted power dispatch instructions with a predicted probability greater than a preset probability, the accuracy of the decision is improved, providing a basis for the subsequent power dispatch process.

[0115] In an exemplary embodiment, the above-mentioned step S201, before inputting the current state information and the predicted state information into multiple pre-trained power dispatching instruction prediction models to obtain multiple predicted power dispatching instructions corresponding to the power grid to be analyzed, and the predicted probability of each predicted power dispatching instruction, specifically includes the following contents: determining multiple candidate power dispatching instruction prediction models associated with the power grid to be analyzed, and obtaining the prediction accuracy of each candidate power dispatching instruction prediction model; from each candidate power dispatching instruction prediction model, screening out the candidate power dispatching instruction prediction model with a prediction accuracy greater than a preset accuracy as multiple pre-trained power dispatching instruction prediction models.

[0116] The candidate power dispatching instruction prediction model refers to the power dispatching instruction prediction model to be selected.

[0117] Among them, the prediction accuracy is used to indicate the correctness of the candidate power dispatch instruction prediction model in the historical time.

[0118] The preset accuracy rate refers to a preset accuracy rate threshold, such as 90%.

[0119] Exemplarily, the server determines multiple candidate power dispatching instruction prediction models associated with the power grid to be analyzed, and obtains the prediction accuracy of each candidate power dispatching instruction prediction model from the database; then, the server selects the candidate power dispatching instruction prediction models with a prediction accuracy greater than a preset accuracy from the candidate power dispatching instruction prediction models as multiple pre-trained power dispatching instruction prediction models.

[0120] In this embodiment, by screening out a model with a prediction accuracy greater than a preset accuracy from the candidate models as a pre-trained power dispatch instruction prediction model, it is ensured that the model ultimately used for prediction has a high reliability, thereby avoiding the use of a low-accuracy model leading to erroneous prediction results, thereby improving the prediction accuracy of the power dispatch instruction.

[0121] In an exemplary embodiment, the above step S101, obtaining the terminal information of the terminal, specifically includes the following contents: obtaining the request frequency information and source information corresponding to the terminal; preprocessing the request frequency information and the source information to obtain the preprocessed request frequency information and the preprocessed source information; combining the preprocessed request frequency information and the preprocessed source information to obtain the terminal information of the terminal.

[0122] The request frequency information refers to the request frequency of the terminal.

[0123] The source information refers to the source IP address of the terminal.

[0124] The pre-processed request frequency information refers to the request frequency information after pre-processing.

[0125] The preprocessed source information refers to the source information after preprocessing.

[0126] Exemplarily, the server obtains the number of times the terminal sends request information within a specific time period from a log file, and determines the request frequency information corresponding to the terminal based on the number; then, the server parses the request information sent by the terminal to obtain the source information corresponding to the terminal; then, the server preprocesses the request frequency information and the source information to obtain preprocessed request frequency information and preprocessed source information; for example, the server identifies abnormal values ​​and missing values ​​in the request frequency information and the source information, and processes these abnormal values ​​and missing values ​​to obtain preprocessed request frequency information and preprocessed source information; finally, the server combines the preprocessed request frequency information and the preprocessed source information in a preset combination method to obtain the terminal information of the terminal.

[0127] In this embodiment, by obtaining the request frequency information and source information corresponding to the terminal, the behavioral characteristics of the terminal can be understood from different angles; moreover, preprocessing the request frequency information and source information can remove noise, correct erroneous data and unify the data format, thereby making subsequent combined processing more accurate and reliable, which is conducive to improving the accuracy of determining the terminal information of the terminal.

[0128] In an exemplary embodiment, the above step S107, after power dispatch processing is performed on the power resources in the power grid to be analyzed according to the target power dispatch instruction, specifically includes the following contents: extracting key status information in the current status information, and determining the backup server associated with the power grid to be analyzed; generating backup request information corresponding to the key status information, and sending the backup request information to the backup server, so that the backup server performs backup processing on the key status information according to the backup request information.

[0129] The key status information refers to sub-status information in the current status information whose importance is greater than a preset importance.

[0130] The backup server is used to represent a server in a remote backup site associated with the power grid to be analyzed.

[0131] The backup request information is used to indicate the request information corresponding to the backup process of the key status information.

[0132] Exemplarily, the server determines the importance corresponding to each sub-state information in the current state information, and filters out the sub-state information whose corresponding importance is greater than the preset importance from the current state information, and uses these sub-state information as the key state information in the current state information; then, the server determines the server in the off-site backup site associated with the power grid to be analyzed as the backup server associated with the power grid to be analyzed; then, the server generates backup request information corresponding to the key state information according to the preset request format; then, the server sends the backup request information to the backup server, so that the backup server backs up the key state information according to the backup request information.

[0133] In this embodiment, by extracting key status information from the current status information and backing it up, the security of important data is ensured when facing various risks. Even if the main system fails, data is lost, or it is attacked by malicious attacks, key data can be restored from the backup server, which is conducive to ensuring the continuous and stable operation of the power grid.

[0134] In an exemplary embodiment, the power dispatching method provided in the present application also includes a training step of a pre-trained state prediction model, which specifically includes the following contents: obtaining the encrypted current sample state information of the sample power grid sent by the sample terminal, and obtaining the sample terminal information of the sample terminal; when the sample terminal information meets the first preset condition, decrypting the encrypted current sample state information to obtain the current sample state information of the sample power grid; performing feature extraction on the current sample state information to obtain a sample feature vector corresponding to the current sample state information; inputting the sample feature vector into the state prediction model to be trained to obtain the predicted state information of the sample power grid; obtaining the actual state information of the sample power grid, and iteratively training the state prediction model to be trained according to the difference between the predicted state information and the actual state information of the sample power grid to obtain the pre-trained state prediction model.

[0135] The sample terminal refers to the terminal corresponding to the training state prediction model.

[0136] The sample power grid refers to the power grid system corresponding to the training state prediction model.

[0137] The encrypted current sample state information refers to the encrypted current state information of the sample power grid.

[0138] The sample terminal information refers to the terminal information of the sample terminal.

[0139] The current sample state information refers to the current state information of the sample power grid.

[0140] The sample feature vector refers to the feature vector corresponding to the current sample state information.

[0141] The predicted state information of the sample power grid refers to the predicted value corresponding to the future state information of the sample power grid.

[0142] The actual state information of the sample power grid refers to the actual value corresponding to the future state information of the sample power grid.

[0143] Exemplarily, in response to a model training instruction for a state prediction model to be trained, the server obtains the encrypted current sample state information of the sample power grid sent by the sample terminal from the database, and obtains the sample terminal information of the sample terminal; then, when the sample terminal information satisfies a first preset condition, the server decrypts the encrypted current sample state information to obtain the current sample state information of the sample power grid; then, the server inputs the current sample state information into a feature extraction model, performs feature extraction on the current sample state information through the feature extraction model, and obtains a sample feature vector corresponding to the current sample state information; then, the server inputs the sample feature vector into the state prediction model to be trained to obtain the predicted state information of the sample power grid; then, the server obtains the actual state information of the sample power grid, and obtains a loss value based on the difference between the predicted state information and the actual state information of the sample power grid; then, the server adjusts the model parameters of the state prediction model to be trained based on the loss value; then, the server retrains the state prediction model after the model parameters are adjusted until the loss value obtained by the trained state prediction model is less than the loss value threshold, then stops the training, and uses the trained state prediction model as the pre-trained state prediction model.

[0144] In this embodiment, by pre-training the state prediction model, it is convenient to predict the predicted state information of the power grid to be analyzed after obtaining the characteristic vector corresponding to the current state information of the power grid to be analyzed in actual applications; moreover, the state prediction model receives new data in each round of iteration, and performs internal improvements and optimizations on the model, so that predictions can be made more effectively, which is beneficial to improving the prediction accuracy of the state prediction model.

[0145] In an exemplary embodiment, Figure 3 As shown, another power scheduling method is provided, which is described by taking the application of the method to a server as an example, and includes the following steps:

[0146] Step S301, obtaining encrypted current status information of the power grid to be analyzed sent by the terminal.

[0147] Step S302, obtain the request frequency information and source information corresponding to the terminal; preprocess the request frequency information and source information to obtain preprocessed request frequency information and preprocessed source information; combine the preprocessed request frequency information and preprocessed source information to obtain terminal information of the terminal.

[0148] Step S303: when the terminal information meets the first preset condition, the encrypted current state information is decrypted to obtain the current state information of the power grid to be analyzed.

[0149] Step S304: perform feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information.

[0150] Step S305 , inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed.

[0151] Step S306, determining a plurality of candidate power dispatch instruction prediction models associated with the power grid to be analyzed, and obtaining the prediction accuracy of each candidate power dispatch instruction prediction model.

[0152] Step S307 , selecting candidate power dispatching instruction prediction models with prediction accuracy greater than a preset accuracy from the candidate power dispatching instruction prediction models as a plurality of pre-trained power dispatching instruction prediction models.

[0153] Step S308, inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed, and a predicted probability of each predicted power dispatch instruction.

[0154] Step S309 , screening out predicted power dispatching instructions with predicted probabilities greater than preset probabilities from the predicted power dispatching instructions as multiple candidate power dispatching instructions corresponding to the power grid to be analyzed.

[0155] Step S310, obtaining target information of each candidate power dispatching instruction, and screening out the candidate power dispatching instructions whose target information meets the second preset condition from the candidate power dispatching instructions as the target power dispatching instructions corresponding to the power grid to be analyzed.

[0156] Step S311, performing power dispatch processing on the power resources in the power grid to be analyzed according to the target power dispatch instruction.

[0157] In the above-mentioned power dispatching method, in the process of power dispatching of the power grid, by inputting the decrypted current state information into the state prediction model, more accurate predicted state information can be obtained, and from multiple candidate power dispatching instructions, candidate power dispatching instructions whose target information meets the preset conditions are screened out, so that more accurate candidate power dispatching instructions can be obtained, thereby ensuring that the candidate power dispatching instructions meet the operation requirements of the power grid, which is conducive to improving the power dispatching accuracy of the power grid; moreover, the entire method does not require human intervention, avoiding the subjective factors and prone to errors in the method of using human experience judgment, resulting in low power dispatching accuracy of the power grid, and further improving the power dispatching accuracy of the power grid.

[0158] In an exemplary embodiment, in order to more clearly illustrate the power dispatching method provided in the embodiment of the present application, the power dispatching method is specifically described below with a specific embodiment. Figure 4 As shown, the present application also provides a power grid intelligent security defense and dispatching coordination system. In the process of power dispatching of the power grid, the encrypted current state information of the power grid to be analyzed sent by the terminal is first obtained, and the terminal information of the terminal is obtained. When the terminal information meets the first preset condition, the encrypted current state information is decrypted to obtain the current state information of the power grid to be analyzed, and then the current state information is subjected to feature extraction processing to obtain the feature vector corresponding to the current state information, and the feature vector is input into a pre-trained state prediction model to obtain the predicted state information of the power grid to be analyzed. Then, according to the current state information and the predicted state information, a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed are generated. Then, the target information of each candidate power dispatching instruction is obtained, and from each candidate power dispatching instruction, the candidate power dispatching instruction whose target information meets the second preset condition is screened out as the target power dispatching instruction corresponding to the power grid to be analyzed. Finally, according to the target power dispatching instruction, the power resources in the power grid to be analyzed are subjected to power dispatching processing. Specifically, it includes the following contents:

[0159] like Figure 4 As shown, the power grid intelligent security defense and dispatch coordination system includes:

[0160] Network security protection module, intelligent dispatching module, data integration and analysis module and visual monitoring module. The network security protection module monitors the network traffic in and out of the power grid dispatching system based on the real-time monitoring unit, identifies and blocks malicious traffic. The real-time monitoring unit includes a firewall, intrusion detection system and intrusion prevention system deployed at the network boundary. The network security protection module is also used to defend against network attacks using the threat defense unit, and detect and respond to abnormal behavior patterns in the network based on the behavior analysis unit.

[0161] The intelligent dispatching module is used to monitor the real-time operating status of the power grid dispatching system, analyze real-time data and forecast information to calculate the optimal dispatching strategy to optimize resource allocation, and perform online identification of load characteristic parameters at multiple time scales.

[0162] The data integration and analysis module is used to receive data from different data sources and transmit the processed data to the intelligent scheduling module and the network security protection module. The data integration and analysis module is also used to provide data support for the visual monitoring module to achieve monitoring and analysis.

[0163] Among them, the network security protection module integrates a variety of network security protection technologies. Through effective isolation measures, the system network is effectively isolated from the wide area Internet to reduce the threat of external risk factors. A multiple protection system is built for different risk levels, including autonomous defense, security authentication, access permission verification and other technologies to ensure the integrity and reliability of data information. Drawing on the concept of computer network security situation awareness and prediction, software and hardware technologies are used to effectively identify, predict and actively prevent risk factors in power grid operation.

[0164] The network security protection module is responsible for monitoring and defending against security threats from the network level, ensuring the data security and integrity of the power grid dispatching system, including boundary protection, security level protection system, active defense based on risk identification, etc. This module provides a secure network environment for the intelligent dispatching module to ensure the security of dispatching instructions and data transmission. At the same time, it also collaborates with the data integration and analysis module to perform security verification and filtering on data from external data sources such as wind farms.

[0165] Specifically, firewalls, intrusion detection systems (IDS) and intrusion prevention systems (IPS) deployed at the network boundary can monitor network traffic in and out of the power grid dispatching system in real time, identify and block potential malicious traffic. Advanced threat intelligence and feature libraries can be used to defend against known and unknown network attacks, including but not limited to DDoS (Distributed Denial of Service) attacks, SQL (Structured Query Language) injections, and cross-site scripting (XSS). Behavioral analysis technology can be used to detect and respond to abnormal behavior patterns in the network, such as unauthorized access attempts and signs of data leakage.

[0166] Optionally, dispatch instructions and sensitive data can be encrypted during transmission to ensure that data is not stolen or tampered with during transmission. In addition, strict access control policies can be implemented to ensure that only authorized users and systems can access key resources of the power grid dispatch system. Optionally, important data can be backed up regularly and a rapid recovery mechanism can be established to deal with data loss or damage.

[0167] Specifically, firewalls, intrusion detection systems, and intrusion prevention systems deployed at the network boundary can monitor network traffic in and out of the power grid dispatching system in real time, identify and block potential malicious traffic. With advanced threat intelligence and feature libraries, known and unknown network attacks can be defended, including but not limited to DDoS attacks, SQL injections, cross-site scripting, etc. Behavioral analysis technology can be used to detect and respond to abnormal behavior patterns in the network, such as unauthorized access attempts and signs of data leakage.

[0168] Optionally, dispatch instructions and sensitive data can be encrypted during transmission to ensure that data is not stolen or tampered with during transmission. In addition, strict access control policies can be implemented to ensure that only authorized users and systems can access key resources of the power grid dispatch system. Optionally, important data can be backed up regularly and a rapid recovery mechanism can be built to deal with data loss or damage.

[0169] Optionally, when deploying firewalls, IDS and IPS, a multi-layer protection architecture should be adopted to ensure that the protection mechanisms at different levels can work together to form a tight security line of defense. For threat intelligence and feature libraries, a real-time update mechanism should be established to ensure that the latest network attack methods can be responded to in a timely manner.

[0170] Among them, behavioral analysis technology should not only be able to detect abnormal behavior patterns, but also have the ability to automatically trigger early warning and emergency response mechanisms so that measures can be taken in the shortest possible time to curb potential threats. When encrypting dispatch instructions and sensitive data, encryption algorithms that meet industry standards and national security requirements should be selected, and encryption keys should be updated and managed regularly. Access control policies should not only clearly define the list of authorized users and systems, but also be detailed to the specific operating permissions and access time periods of different users and systems. In the process of regularly backing up important data, the integrity and availability of the backup data should be verified to ensure that the backup data can really play a role when needed. The rapid recovery mechanism should be fully drilled and tested to ensure that the normal operation of the system can be restored quickly and effectively when faced with actual data loss or damage.

[0171] Optionally, you can configure firewall rules based on business needs and security policies to restrict unauthorized network access while allowing necessary services to pass through. You can also set up a demilitarized zone (DMZ) between the internal and external networks and place servers that provide services to the outside world in the DMZ to reduce direct exposure to the internal network.

[0172] Optionally, the power grid dispatching system can be divided into different security areas, and different levels of security protection measures can be implemented according to the importance and sensitivity of the area. Optionally, a multi-layer defense strategy can be adopted, from the physical layer, network layer, system layer to the application layer, to ensure that even if one layer is breached, other layers can still provide protection.

[0173] Optionally, regular risk assessments can be conducted on the power grid dispatching system to identify potential security threats and vulnerabilities. Based on the risk assessment results, proactive defense strategies can be developed and implemented, such as vulnerability repair, security reinforcement, and emergency drills.

[0174] Among them, the network security protection module establishes a secure data transmission channel for the intelligent scheduling module to ensure the security and integrity of the scheduling instructions during transmission. The network security protection module performs strict identity authentication and authorization management on the access to the intelligent scheduling module to prevent unauthorized access and operation.

[0175] The network security protection module verifies and filters data from external data sources such as wind farms to ensure the authenticity and legitimacy of the data. In the data integration process, secure data exchange protocols and encryption technologies are used to ensure the security of data during transmission and storage.

[0176] Optionally, the network security protection module is also used to:

[0177] Dispatch instructions and sensitive data are encrypted during transmission, and based on preset access control policies, only authorized users and systems can access key resources of the power grid dispatching system.

[0178] Back up designated critical data in real time.

[0179] Specifically, during the transmission process, the dispatching instructions and sensitive data need to be encrypted, and according to the pre-set access control policy, only authorized users and systems are allowed to access the key resources of the power grid dispatching system. In addition, the designated key data should be backed up in real time. Optionally, the network security protection module should also configure firewall rules according to business needs and security policies. Such firewall rules are designed to restrict unauthorized network access and allow designated services to pass.

[0180] For example, during the transmission process, scheduling instructions and sensitive data are encrypted, which can greatly improve data security. Use advanced encryption algorithms, such as AES-256 (Advanced Encryption Standard-256, a symmetric encryption algorithm), to ensure the strength and reliability of encryption. In addition, the preset access control policy should have the ability to dynamically adjust and update the list of authorized users and systems, as well as the level of access rights they have, in a timely manner according to actual conditions. When backing up designated key data in real time, multiple off-site backup sites should be established to prevent data loss due to local disasters or failures. At the same time, the storage of backup data should follow strict security standards to ensure the integrity and confidentiality of the backup data.

[0181] Optionally, the network security protection module should not only consider current business needs and security policies when configuring firewall rules, but also predict possible future business expansion and security threat changes. For example, as the application of IoT devices in power grids increases, firewall rules should be able to effectively deal with potential risks from these devices. In addition, firewall rules should be audited and tested regularly to ensure that they always work effectively, block unauthorized network access, and ensure the smooth passage of designated services, providing solid security protection for the stable operation of the power grid dispatching system.

[0182] Optionally, the network security protection module is also used to:

[0183] Configure firewall rules based on business needs and security policies. Firewall rules are used to restrict unauthorized network access and allow specified services to pass through.

[0184] Specifically, a high-performance firewall can be deployed at the boundary of the power grid dispatching system, and the configuration rules can allow users inside the power grid dispatching system to access resources on the external network (such as the meteorological data server), while preventing unauthorized external users from accessing the internal resources of the power grid dispatching system. The firewall is also configured with an intrusion prevention function that can automatically identify and block common network attacks.

[0185] Specifically, a VPN (Virtual Private Network) channel can be established for data transmission between the intelligent dispatching module and the wind farm, and a strong encryption algorithm can be used to encrypt data for transmission. The VPN channel not only ensures the security of data transmission, but also improves the reliability and stability of data transmission. At the same time, the configuration and management of the VPN channel are uniformly responsible for the network security protection module, ensuring the consistency and effectiveness of the security policy.

[0186] Among them, the intelligent dispatching module is the core component of the power grid dispatching system. It is responsible for formulating the optimal dispatching strategy based on the real-time operating status of the power grid and the output forecast of intermittent energy such as wind farms, so as to ensure the efficient utilization of clean energy such as wind power and the overall stable operation of the power grid.

[0187] The intelligent dispatching module monitors the real-time operation status of the power grid, including key parameters such as voltage, current, and power, and receives output forecast information from intermittent energy sources such as wind farms, taking into account their uncertainty and volatility. The intelligent dispatching module comprehensively analyzes real-time data and forecast information, and uses intelligent algorithms to calculate the optimal dispatching strategy to balance the supply and demand of the power grid and optimize resource allocation. The intelligent dispatching module optimizes the dispatching strategy to maximize the use of intermittent energy such as wind power, reduce wind abandonment, improve energy efficiency, coordinate the power generation plans of traditional energy and clean energy, and ensure that the power grid can operate stably under different working conditions.

[0188] Optionally, advanced optimization algorithms such as genetic algorithms, particle swarm optimization algorithms, and deep learning can be used to quickly and accurately calculate the optimal dispatching strategy. The algorithm needs to be adaptive and robust to cope with the uncertainty and complexity of power grid operation. Considering factors such as demand-side response and distributed energy access, large-scale and refined optimization dispatching of interactive loads is carried out. By adjusting user electricity consumption behavior and managing distributed energy generation, two-way interaction and balance of power grid supply and demand can be achieved.

[0189] The intelligent dispatching module receives real-time data and forecast information from the data integration and analysis module, including the grid operation status, wind farm output forecast, etc. The intelligent dispatching module relies on the data quality and accuracy provided by the data integration and analysis module to formulate accurate dispatching strategies. The intelligent dispatching module displays the dispatching results and grid operation status to the dispatcher in an intuitive form, such as displaying the grid load situation, wind power output forecast, and dispatch instruction execution status through charts, animations, etc. It interacts with the visual monitoring module so that the dispatcher can understand the grid operation status and dispatching effect in real time, and adjust and optimize as needed. The intelligent dispatching module formulates the optimal dispatching strategy based on the real-time operation status of the grid and the wind farm output forecast, so as to achieve efficient utilization of intermittent energy such as wind power and stable operation of the grid.

[0190] It should be noted that the intelligent scheduling module can perform online identification, which can include the following implementation methods:

[0191] For example, mathematical models can be used to describe the dynamic characteristics of the system. By comparing the difference between the model prediction output and the actual system output, the model parameters can be continuously adjusted to improve the identification accuracy. Common models include state space models, transfer function models, etc. For example, algorithms such as Kalman filtering or particle filtering are used to estimate and update the system state in real time, thereby realizing online identification of the dynamic characteristics of the system.

[0192] For example, features and patterns can be directly extracted from the data collected during the operation of the system for online identification. For example, machine learning algorithms such as neural networks and support vector machines can be used to train a large amount of input and output data to establish the input-output mapping relationship of the system, thereby realizing the identification of the system.

[0193] For example, the input and output signals of the system can be analyzed and processed to extract the characteristic parameters of the signal, such as frequency, amplitude, phase, etc., in order to understand the dynamic characteristics of the system. For example, the signal processing techniques such as Fourier transform and wavelet transform can be used to analyze the signal in the frequency domain or time-frequency domain.

[0194] For example, during the operation of the control system, the controller parameters can be continuously adjusted according to the actual response of the system to adapt to the changes in the system. This method usually combines technologies such as model reference adaptive control and self-correction control to achieve both control and identification of the system.

[0195] For example, the advantages of multiple identification methods can be combined to perform multimodal online identification of the system. For example, model-based methods and data-driven methods can be used simultaneously, or different types of models can be combined to improve the accuracy and reliability of identification.

[0196] Optionally, the Data Integration and Analysis module is used to:

[0197] Through the API (Application Programming Interface) interface or message queue, real-time data from inside and outside the power grid is received and cleaned. The real-time data inside the power grid includes monitoring data and equipment status information of power plants and substations, and the real-time data outside the power grid includes wind farm power generation data and weather forecast data from weather stations.

[0198] Configure and manage all connected data sources, including data source authentication, authorization, and connection status monitoring.

[0199] Convert real-time data in different formats and standards into a format that can be recognized by the target.

[0200] Optionally, the data integration and analysis module adopts a distributed storage system, a distributed computing framework and Apache Kafka (an open source distributed event stream platform), wherein the distributed storage system is used to store massive data; the distributed computing framework is used to quickly process large-scale data sets; Apache Kafka is used for real-time data processing. The data integration and analysis module provides the intelligent dispatching module with real-time operating status and forecast data of the power grid dispatching system, supports intelligent dispatching decisions, and receives feedback on the execution results of dispatching instructions for closed-loop verification.

[0201] It should be noted that in terms of data cleaning, libraries in Python (a programming language) or Java (a programming language) can be used to process and clean data to remove duplicate, erroneous or incomplete data records. For data source verification, identity authentication can be performed based on digital certificates or API keys to ensure that only legitimate data sources can access. Authorization can be achieved through a role-based access control (RBAC) model to assign different permission levels to different data sources. In connection status monitoring, a heartbeat mechanism can be used, that is, the data source regularly sends a heartbeat signal to the data integration and analysis module to indicate that it is active. If the heartbeat signal is not received within a certain period of time, the connection is considered abnormal and the corresponding alarm and processing mechanism is triggered. In data format conversion, open source ETL (Extract, Transform, Load) tools can be used to define data conversion rules and processes to convert data in different formats into the target format. For distributed storage systems, data storage layout and copy strategies can be reasonably planned according to the characteristics and access patterns of the data to improve data reliability and access performance. Distributed computing frameworks can use cluster computing resources to quickly process large-scale data through parallel computing and optimized algorithms. For example, use APIs for data processing and analysis, and for real-time data calculation and conversion. When processing real-time data, you can configure appropriate topics and partitions, and adjust the parameters of consumers and producers according to the data flow and processing requirements to ensure efficient data transmission and processing. At the same time, you can combine components to achieve more complex real-time data processing and integration tasks.

[0202] Optionally, the intelligent scheduling module is used to:

[0203] Analyze real-time data and forecast information to obtain multiple dispatch strategies, where the forecast information includes wind farm output forecast information, which is used to determine the supply and demand status of the power grid.

[0204] The optimal solution set is determined through a multi-objective optimization algorithm and multiple scheduling strategies, where the optimal solution set adopts non-dominated sorting and crowding distance mechanisms.

[0205] It should be noted that the intelligent dispatching module first collects the real-time operation data of the power grid dispatching system, including but not limited to the output power of the power plant, the power grid load, the line flow, etc. These data provide instant system status information for dispatching decisions. In addition to real-time data, the module also integrates forecasting information, especially the output forecast of wind farms. As a renewable energy source, wind power has intermittent and fluctuating output, which poses a challenge to the supply and demand balance of the power grid. Through high-precision wind farm output forecasting, the module can more accurately judge the future supply and demand status of the power grid and provide a basis for the formulation of dispatching strategies. Based on real-time data and forecasting information, the intelligent dispatching module uses advanced algorithms and models to generate multiple possible dispatching strategies. These strategies aim to balance the supply and demand relationship of the power grid while considering multiple goals such as economy, safety and reliability. In order to select the optimal solution from multiple dispatching strategies, the module adopts a multi-objective optimization algorithm. This type of algorithm can handle multiple conflicting goals at the same time, such as minimizing the cost of power generation, maximizing system stability and reducing environmental pollution. When determining the optimal solution set, the module uses non-dominated sorting to distinguish the advantages and disadvantages of different dispatching strategies. At the same time, the crowding distance mechanism is used to maintain the diversity of the solution set and avoid falling into the local optimal solution. Through this method, the module can generate an optimal solution set containing multiple non-inferior solutions for the dispatcher to choose according to the actual situation. The intelligent dispatching module continuously monitors the real-time operating status of the power grid dispatching system, including key parameters such as voltage, frequency, and power flow. Once an abnormal situation is found, the module will immediately trigger the early warning mechanism and take corresponding emergency measures. In order to more accurately predict future load changes, the module also has the ability to online identify load characteristic parameters at multiple time scales, including short-term load forecasting (such as daily load forecasting), medium-term load forecasting (such as weekly load forecasting) and long-term load forecasting (such as annual load forecasting). Through the identification of load characteristic parameters at different time scales, the module can more comprehensively grasp the load change law and provide a more accurate basis for the formulation of dispatching strategies.

[0206] Optional, visual monitoring module for:

[0207] The operation status and dispatching effect of the power grid are displayed in real time, so that the dispatcher can intuitively see the load situation, wind power output and the execution of dispatching instructions, and make adjustments and optimizations as needed.

[0208] Optionally, the intelligent scheduling module is also used to:

[0209] Dynamically adjust and optimize scheduling strategies based on scheduling effect monitoring and feedback results.

[0210] Based on the optimized dispatching strategy, dispatching instructions are generated and sent to each power plant and wind farm through the security network.

[0211] Optionally, the real-time operating status of the power grid dispatching system includes at least: voltage, current and power.

[0212] Optionally, the data integration and analysis module is also used to:

[0213] Generate power grid operation reports according to the specified period.

[0214] The data integration and analysis module can continuously provide the intelligent dispatching module with the real-time operating status and forecast data of the power grid dispatching system, fully support intelligent dispatching decisions, and receive feedback on the execution results of dispatching instructions, and then conduct strict closed-loop verification. It provides the intelligent dispatching module with real-time operating status and forecast data, which are important bases for intelligent dispatching to make decisions. At the same time, the module also receives feedback on the results after the dispatching instructions are executed, and verifies whether the previous dispatching decisions are effective through this feedback, forming a complete closed loop to continuously optimize and improve subsequent dispatching decisions. In order to provide real-time operating status and forecast data to the intelligent dispatching module, the data integration and analysis module can establish an efficient data push mechanism. For example, using real-time database or data bus technology to ensure that data can be transmitted to the intelligent dispatching module in a low-latency and high-reliability manner. In terms of supporting intelligent dispatching decisions, data analysis and mining algorithms can be used to deeply analyze the provided data, extract key features and trends, and provide more valuable information for decision-making. When receiving feedback on the execution results of dispatching instructions, standardized data formats and interfaces can be defined to accurately and quickly obtain feedback information. At the same time, data comparison and evaluation algorithms are used to compare the actual execution results with the expected goals to quantify the effect of dispatching decisions. By establishing a data visualization platform, the process and results of closed-loop verification can be intuitively displayed, helping dispatchers to clearly understand the pros and cons of dispatch decisions and providing an intuitive basis for further optimization.

[0215] It should be noted that the network security protection module effectively identifies and blocks malicious traffic, ensures the network security of the power grid dispatching system, and reduces the risk of network attacks. It defends against network attacks, reduces potential security threats, and protects the security of dispatching instructions and sensitive data. It detects and responds to abnormal behavior patterns, promptly discovers and handles internal abnormal activities, and enhances the security and stability of the system. It solves the problem of malicious traffic intrusion, network attacks, and internal abnormal behavior that are difficult to detect and prevent at the network level of the power grid dispatching system. Compared with traditional single firewall protection, it integrates intrusion detection and defense systems to achieve more comprehensive and real-time network monitoring and protection. The use of behavioral analysis technology can actively detect and respond to abnormal behavior, improving the initiative and intelligence level of security defense.

[0216] The intelligent dispatching module monitors the real-time operation status, calculates the optimal dispatching strategy, optimizes resource allocation, and improves the efficiency and economy of power grid operation. It conducts online identification of load characteristic parameters at multiple time scales to better adapt to load changes and ensure the stable operation of the power grid. It solves the problem of unreasonable resource allocation and difficulty in coping with complex and changing load demands in traditional dispatching methods. It combines real-time data and forecast information, uses advanced algorithms to determine the optimal solution set, and improves the accuracy and adaptability of dispatching strategies.

[0217] The data integration and analysis module receives and processes data from different data sources, provides comprehensive and accurate data support for the system, and improves the scientific nature of decision-making. Unify the data format, facilitate data transmission and use, and improve data availability and compatibility. Adopt distributed storage and computing framework to improve the ability and efficiency of processing massive data. Solve the data integration and processing problems caused by diverse data sources and different formats. Solve the performance bottleneck problem of traditional data processing methods when processing large-scale data. Use advanced technical architectures, such as distributed storage and computing frameworks and real-time data processing tools, to improve the ability and speed of data processing.

[0218] The visual monitoring module displays the grid operation status and dispatching effect in real time, providing intuitive information for dispatchers to make quick decisions and adjustments. It solves the problem that it is difficult for dispatchers to intuitively understand the grid operation, resulting in delayed and inaccurate decision-making. It displays complex grid information in a more intuitive and clear way, improving the visualization of dispatching and decision-making efficiency. It realizes the intelligent, safe and efficient dispatching of the grid, and improves the overall operation performance and reliability of the grid.

[0219] Each module works together to form a complete closed-loop system, continuously optimizing dispatch strategies and improving security defense capabilities. Technical problems solved: It solves the comprehensive problems of the difficulty in balancing safety and efficiency in power grid dispatching and the isolation of information in each link. It organically integrates functions such as safety protection, dispatch optimization, data processing and visual monitoring to form a coordinated overall system, breaking through the limitations of independent operation and poor coordination of each part in the traditional power grid dispatching system.

[0220] In the above-mentioned embodiment, during the process of power dispatching of the power grid, more accurate predicted state information can be obtained by inputting the decrypted current state information into the state prediction model, and candidate power dispatching instructions whose target information meets the preset conditions are screened out from multiple candidate power dispatching instructions, so that more accurate candidate power dispatching instructions can be obtained, thereby ensuring that the candidate power dispatching instructions meet the operation requirements of the power grid, which is conducive to improving the power dispatching accuracy of the power grid; moreover, the entire method does not require human intervention, avoiding the defect of low power dispatching accuracy of the power grid caused by subjective factors and prone to errors in the method of using human experience judgment, thereby further improving the power dispatching accuracy of the power grid.

[0221] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0222] Based on the same inventive concept, the embodiment of the present application also provides a power dispatching device for implementing the power dispatching method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power dispatching device embodiments provided below can refer to the limitations of the power dispatching method above, and will not be repeated here.

[0223] In an exemplary embodiment, Figure 5 As shown, a power dispatching device is provided, including: an information acquisition module 501, an information processing module 502, a feature extraction module 503, a state prediction module 504, an instruction generation module 505, an instruction screening module 506 and a resource scheduling module 507, wherein:

[0224] The information acquisition module 501 is used to acquire the encrypted current state information of the power grid to be analyzed sent by the terminal, and acquire the terminal information of the terminal.

[0225] The information processing module 502 is used to decrypt the encrypted current state information to obtain the current state information of the power grid to be analyzed when the terminal information meets the first preset condition.

[0226] The feature extraction module 503 is used to perform feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information.

[0227] The state prediction module 504 is used to input the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed.

[0228] The instruction generation module 505 is used to generate a plurality of candidate power dispatch instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information.

[0229] The instruction screening module 506 is used to obtain target information of each candidate power dispatching instruction, and screen out the candidate power dispatching instructions whose target information meets the second preset condition from each candidate power dispatching instruction as the target power dispatching instruction corresponding to the power grid to be analyzed.

[0230] The resource scheduling module 507 is used to perform power scheduling processing on the power resources in the power grid to be analyzed according to the target power scheduling instruction.

[0231] In an exemplary embodiment, the instruction generation module 505 is also used to input the current state information and the predicted state information into multiple pre-trained power dispatching instruction prediction models to obtain multiple predicted power dispatching instructions corresponding to the power grid to be analyzed, and the predicted probability of each predicted power dispatching instruction; from each predicted power dispatching instruction, the predicted power dispatching instructions with a predicted probability greater than a preset probability are screened out as multiple candidate power dispatching instructions corresponding to the power grid to be analyzed.

[0232] In an exemplary embodiment, the power dispatching device also includes a model screening module, which is used to determine multiple candidate power dispatching instruction prediction models associated with the power grid to be analyzed, and obtain the prediction accuracy of each candidate power dispatching instruction prediction model; from each candidate power dispatching instruction prediction model, the candidate power dispatching instruction prediction model with a prediction accuracy greater than a preset accuracy is screened out as multiple pre-trained power dispatching instruction prediction models.

[0233] In an exemplary embodiment, the information acquisition module 501 is also used to obtain the request frequency information and source information corresponding to the terminal; preprocess the request frequency information and source information to obtain preprocessed request frequency information and preprocessed source information; combine the preprocessed request frequency information and preprocessed source information to obtain terminal information of the terminal.

[0234] In an exemplary embodiment, the power dispatching device also includes an information backup module, which is used to extract key status information from the current status information and determine the backup server associated with the power grid to be analyzed; generate backup request information corresponding to the key status information, and send the backup request information to the backup server, so that the backup server backs up the key status information according to the backup request information.

[0235] In an exemplary embodiment, the power dispatching device also includes a model training module, which is used to obtain the encrypted current sample state information of the sample power grid sent by the sample terminal, and to obtain the sample terminal information of the sample terminal; when the sample terminal information meets the first preset condition, the encrypted current sample state information is decrypted to obtain the current sample state information of the sample power grid; feature extraction is performed on the current sample state information to obtain a sample feature vector corresponding to the current sample state information; the sample feature vector is input into the state prediction model to be trained to obtain the predicted state information of the sample power grid; the actual state information of the sample power grid is obtained, and according to the difference between the predicted state information and the actual state information of the sample power grid, the state prediction model to be trained is iteratively trained to obtain a pre-trained state prediction model.

[0236] Each module in the above-mentioned power dispatching device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0237] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as current state information and predicted state information. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a power dispatching method is implemented.

[0238] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0239] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0240] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0241] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0242] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0243] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0244] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A power dispatching method, characterized in that: The method comprises: Obtaining encrypted current state information of the power grid to be analyzed sent by the terminal, and obtaining terminal information of the terminal; In the case where the terminal information meets the first preset condition, decrypting the encrypted current state information to obtain the current state information of the power grid to be analyzed; Performing feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information; Inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed; generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information; Acquire target information of each of the candidate power dispatching instructions, and select, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed; According to the target power dispatching instruction, power dispatching processing is performed on the power resources in the power grid to be analyzed.

2. The method according to claim 1, characterized in that The step of generating a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information includes: Inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed, and a predicted probability of each of the predicted power dispatch instructions; From the predicted power dispatching instructions, the predicted power dispatching instructions whose predicted probability is greater than the preset probability are screened out as a plurality of candidate power dispatching instructions corresponding to the power grid to be analyzed.

3. The method according to claim 2, characterized in that Before inputting the current state information and the predicted state information into a plurality of pre-trained power dispatch instruction prediction models to obtain a plurality of predicted power dispatch instructions corresponding to the power grid to be analyzed and the predicted probability of each of the predicted power dispatch instructions, the method further includes: Determining a plurality of candidate power dispatch instruction prediction models associated with the power grid to be analyzed, and obtaining a prediction accuracy rate of each of the candidate power dispatch instruction prediction models; From each of the candidate power dispatching instruction prediction models, the candidate power dispatching instruction prediction models whose prediction accuracy is greater than the preset accuracy are selected as the multiple pre-trained power dispatching instruction prediction models.

4. The method according to claim 1, characterized in that: The acquiring the terminal information of the terminal includes: Obtaining request frequency information and source information corresponding to the terminal; Preprocessing the request frequency information and the source information to obtain preprocessed request frequency information and preprocessed source information; The preprocessed request frequency information and the preprocessed source information are combined to obtain terminal information of the terminal.

5. The method according to claim 1, characterized in that: After performing power dispatch processing on the power resources in the power grid to be analyzed according to the target power dispatch instruction, the method further includes: Extracting key status information from the current status information, and determining a backup server associated with the power grid to be analyzed; Generate backup request information corresponding to the key state information, and send the backup request information to the backup server, so that the backup server performs backup processing on the key state information according to the backup request information.

6. The method according to any one of claims 1 to 5, characterized in that The pre-trained state prediction model is trained in the following way: Obtaining encrypted current sample state information of the sample power grid sent by the sample terminal, and obtaining sample terminal information of the sample terminal; In the case where the sample terminal information satisfies the first preset condition, decrypting the encrypted current sample state information to obtain the current sample state information of the sample power grid; Performing feature extraction processing on the current sample state information to obtain a sample feature vector corresponding to the current sample state information; Inputting the sample feature vector into a state prediction model to be trained to obtain predicted state information of the sample power grid; The actual state information of the sample power grid is obtained, and according to the difference between the predicted state information of the sample power grid and the actual state information, the state prediction model to be trained is iteratively trained to obtain the pre-trained state prediction model.

7. A power dispatching device, characterized in that: The device comprises: An information acquisition module, used to acquire encrypted current state information of the power grid to be analyzed sent by the terminal, and to acquire terminal information of the terminal; An information processing module, configured to decrypt the encrypted current state information to obtain the current state information of the power grid to be analyzed when the terminal information satisfies a first preset condition; A feature extraction module, used to perform feature extraction processing on the current state information to obtain a feature vector corresponding to the current state information; A state prediction module, used for inputting the feature vector into a pre-trained state prediction model to obtain predicted state information of the power grid to be analyzed; An instruction generation module, used for generating a plurality of candidate power dispatch instructions corresponding to the power grid to be analyzed according to the current state information and the predicted state information; An instruction screening module, used for obtaining target information of each of the candidate power dispatching instructions, and screening out, from the candidate power dispatching instructions, a candidate power dispatching instruction whose target information meets a second preset condition as a target power dispatching instruction corresponding to the power grid to be analyzed; The resource scheduling module is used to perform power scheduling processing on the power resources in the power grid to be analyzed according to the target power scheduling instruction.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images