Pumped storage unit load control method, device, computer equipment, storage medium and computer program product

Abstract

The present application relates to a method, device, computer equipment, storage medium and computer program product for load control of a pumped storage unit. The method comprises: determining target control information of the pumped storage unit to be analyzed according to preset load information and current state information of the pumped storage unit to be analyzed; generating target control instructions of the pumped storage unit to be analyzed according to the target control information and unit parameters of the pumped storage unit to be analyzed; obtaining updated state information of the pumped storage unit to be analyzed according to the target control instructions and the current state information; controlling the pumped storage unit to be analyzed to adjust the load according to the updated state information, and obtaining the current load information of the pumped storage unit to be analyzed, and if the difference between the preset load information and the current load information meets the preset conditions, the obtained current load information is used as the target load information of the pumped storage unit to be analyzed. The use of this method can improve the load control accuracy of the pumped storage unit.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for load control of a pumped storage unit. Background Art

[0002] In the power system, in order to enhance the backup capacity of the power grid, it is crucial to control the load of the pumped storage unit in a timely manner.

[0003] In traditional technology, manual control is generally used in the process of load control of pumped storage units; however, this manual control method has subjective factors and is prone to errors, resulting in low load control accuracy of pumped storage units. Summary of the invention

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

[0005] In a first aspect, the present application provides a pumped storage unit load control method, comprising:

[0006] Acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time;

[0007] Determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information;

[0008] generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed;

[0009] According to the target control instruction, the current state information is updated to obtain updated state information of the pumped-storage unit to be analyzed;

[0010] According to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust its load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset condition, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

[0011] In one embodiment, obtaining preset load information and current state information of the pumped storage unit to be analyzed includes:

[0012] Acquiring target operating condition information of the pumped-storage unit to be analyzed;

[0013] According to the target operating condition information, the corresponding relationship between the operating condition information and the load information is queried to obtain the load information corresponding to the target operating condition information as the preset load information.

[0014] In one embodiment, determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information includes:

[0015] Determining target state information corresponding to the preset load information;

[0016] Preprocessing the target state information and the current state information to obtain preprocessed target state information and preprocessed current state information;

[0017] According to the difference between the pre-processed target state information and the pre-processed current state information, the target control information of the pumped-storage unit to be analyzed is determined.

[0018] In one embodiment, determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information includes:

[0019] Performing feature extraction processing on the preset load information and the current state information respectively to obtain a first feature vector corresponding to the preset load information and a second feature vector corresponding to the current state information;

[0020] fusing the first eigenvector and the second eigenvector to obtain a fused eigenvector corresponding to the pumped-storage unit to be analyzed;

[0021] The fused feature vector is input into a pre-trained control information prediction model to obtain control information corresponding to the fused feature vector as the target control information.

[0022] In one embodiment, the pre-trained control information prediction model is trained in the following manner:

[0023] Obtain preset sample load information and current sample status information of the sample pumped storage unit;

[0024] Performing feature extraction processing on the preset sample load information and the current sample state information respectively to obtain a first sample feature vector corresponding to the preset sample load information and a second sample feature vector corresponding to the current sample state information;

[0025] Performing fusion processing on the first sample feature vector and the second sample feature vector to obtain a fused sample feature vector corresponding to the sample pumped-storage unit;

[0026] Inputting the fused sample feature vector into the control information prediction model to be trained to obtain the target control information corresponding to the fused sample feature vector;

[0027] The actual control information corresponding to the fused sample feature vector is obtained, and according to the difference between the actual control information corresponding to the fused sample feature vector and the target control information, the control information prediction model to be trained is iteratively trained to obtain the pre-trained control information prediction model.

[0028] In one embodiment, generating a target control instruction of the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed includes:

[0029] Determining the importance of each of the unit parameters through a pre-trained importance prediction model;

[0030] From the unit parameters, select the unit parameters whose importance is greater than the preset importance as the key unit parameters of the pumped-storage unit to be analyzed;

[0031] A target control instruction of the pumped-storage unit to be analyzed is generated according to the target control information and the key unit parameters.

[0032] In a second aspect, the present application also provides a pumped storage unit load control device, comprising:

[0033] An information acquisition module, used to acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time;

[0034] An information determination module, used to determine the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information;

[0035] An instruction generation module, used for generating a target control instruction of the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed;

[0036] An information updating module, used for updating the current state information according to the target control instruction to obtain updated state information of the pumped-storage unit to be analyzed;

[0037] A load control module is used to control the pumped-storage unit to be analyzed to adjust its load according to the updated state information, obtain the current load information of the pumped-storage unit to be analyzed, and when the difference between the preset load information and the current load information does not meet the preset conditions, use the updated state information as the new current state information, and jump to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then use the current load information obtained for the last time as the target load information of the pumped-storage unit to be analyzed.

[0038] 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:

[0039] Acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time;

[0040] Determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information;

[0041] generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed;

[0042] According to the target control instruction, the current state information is updated to obtain updated state information of the pumped-storage unit to be analyzed;

[0043] According to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust its load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset condition, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

[0044] 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:

[0045] Acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time;

[0046] Determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information;

[0047] generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed;

[0048] According to the target control instruction, the current state information is updated to obtain updated state information of the pumped-storage unit to be analyzed;

[0049] According to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust its load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset condition, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

[0050] 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:

[0051] Acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time;

[0052] Determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information;

[0053] generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed;

[0054] According to the target control instruction, the current state information is updated to obtain updated state information of the pumped-storage unit to be analyzed;

[0055] According to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust its load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset condition, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

[0056] The pumped-storage unit load control method, device, computer equipment, storage medium and computer program product first obtain preset load information and current state information of the pumped-storage unit to be analyzed, and determine target control information of the pumped-storage unit to be analyzed based on the preset load information and the current state information, and then generate target control instructions for the pumped-storage unit to be analyzed based on the target control information and the unit parameters of the pumped-storage unit to be analyzed, and then, according to the target control instructions, update the current state information to obtain updated state information of the pumped-storage unit to be analyzed, and then, according to the updated state information, generate the target control instructions for the pumped-storage unit to be analyzed. The updated state information is used to control the pumped-storage unit to be analyzed to adjust the load, and the current load information of the pumped-storage unit to be analyzed is obtained. When the difference between the preset load information and the current load information does not meet the preset conditions, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed. In this way, in the process of load control of the pumped-storage unit, after obtaining the preset load information and current state information of the pumped-storage unit to be analyzed, a target control instruction is further generated to drive the pumped-storage unit to adjust the load, by constantly comparing the preset load information with the actual current load information, as long as the difference between the two does not meet the preset conditions, adjustments are continuously made to ensure that the final actual load of the unit matches the preset load as accurately as possible, thereby achieving high-precision control of the load of the pumped-storage unit, which is beneficial to improving the load control accuracy of the pumped-storage unit; moreover, the entire process does not require human intervention, thus avoiding the subjective factors in the manual control method, which is prone to errors and leads to the defect of low load control accuracy of the pumped-storage unit, thereby improving the load control accuracy of the pumped-storage unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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.

[0058] Figure 1 A schematic flow chart of a method for controlling a load of a pumped storage unit in one embodiment;

[0059] Figure 2 A schematic flow chart of a method for controlling a load of a pumped storage unit in another embodiment;

[0060] Figure 3 A schematic flow chart of a method for controlling a load of a pumped storage unit in another embodiment;

[0061] Figure 4 A schematic diagram of a flow chart of a pumped storage unit control program in one embodiment;

[0062] Figure 5 is a structural block diagram of a load control device for a pumped storage unit in one embodiment;

[0063] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0064] 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.

[0065] 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.

[0066] At present, in the power grid system, pumped-storage units are responsible for the important tasks of peak load regulation and frequency regulation, and emergency standby, and are an indispensable stable power source in the construction of the power grid system. Since the tasks of this type of unit are different from those of conventional water and thermal power generation units, their control methods and operating conditions are also much more complicated, requiring them to have higher standby capacity. In order to enhance the standby capacity of the power grid, it is crucial to timely control the load of the pumped-storage unit. However, in the process of load control of the pumped-storage unit, manual control is generally adopted; however, this manual control method has subjective factors and is prone to errors, resulting in a low load control accuracy of the pumped-storage unit. Therefore, the present application provides a load control method for a pumped-storage unit, which can solve the problem of low load control accuracy of the pumped-storage unit and achieve the effect of improving the load control accuracy of the pumped-storage unit.

[0067] In an exemplary embodiment, Figure 1As shown, a method for load control of a pumped storage unit 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:

[0068] Step S101, obtaining preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time.

[0069] The pumped-storage unit to be analyzed refers to the pumped-storage unit that needs to be subjected to load control processing.

[0070] The preset load information refers to the load setting value of the pumped storage unit to be analyzed.

[0071] The current state information at least includes the power information, speed information and guide vane opening information of the pumped storage unit to be analyzed at the current time.

[0072] The current time refers to the current time point.

[0073] The power information refers to the active power value of the pumped storage unit to be analyzed.

[0074] The speed information refers to the actual operating speed value of the pumped storage unit to be analyzed.

[0075] The guide vane opening information refers to the guide vane opening value of the pumped storage unit to be analyzed.

[0076] Exemplarily, the server obtains the load regulation range and operating information of the candidate pumped-storage units; then, the server selects the candidate pumped-storage units whose load regulation range and operating information meet the preset conditions from each candidate pumped-storage unit as the pumped-storage units to be analyzed; then, the server obtains the preset load information of the pumped-storage units to be analyzed, as well as the power information, speed information and guide vane opening information of the pumped-storage units to be analyzed at the current time from the database; then, the server uses the power information, speed information and guide vane opening information of the pumped-storage units to be analyzed at the current time as the current status information of the pumped-storage units to be analyzed.

[0077] Step S102, determining target control information of the pumped-storage unit to be analyzed according to preset load information and current state information.

[0078] The target control information is used to represent the TSLG (Turbine Speed ​​Governor) governor control strategy of the pumped storage unit to be analyzed at the current time.

[0079] Exemplarily, the server queries the correspondence between load information, status information and control information based on preset load information and current status information, and obtains control information corresponding to the preset load information and current status information as target control information of the pumped-storage unit to be analyzed.

[0080] Step S103, generating a target control instruction of the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed.

[0081] Among them, the unit parameters include the hydraulic parameters (such as rated head, design flow), mechanical parameters (such as rated speed, runaway speed), electrical parameters (such as rated power, rated voltage), structure and size parameters (such as unit length, unit width, unit height), etc. of the pumped storage unit to be analyzed.

[0082] Among them, the target control instruction refers to the instruction information for controlling the pumped storage unit to be analyzed.

[0083] Exemplarily, the server generates a control instruction corresponding to the target control information and the unit parameters of the pumped-storage unit to be analyzed based on the target control information and the unit parameters of the pumped-storage unit to be analyzed as the target control instruction of the pumped-storage unit to be analyzed.

[0084] Step S104, updating the current status information according to the target control instruction to obtain updated status information of the pumped storage unit to be analyzed.

[0085] The updated state information refers to the current state information after the update process.

[0086] Exemplarily, the server performs an integrity check on the target control instruction and obtains a check result corresponding to the target control instruction; when the check result indicates that the target control instruction is passed, the server updates the current status information according to the target control instruction and obtains the updated current status information as the updated status information of the pumped-storage unit to be analyzed.

[0087] Step S105, according to the updated state information, control the pumped-storage unit to be analyzed to adjust the load, obtain the current load information of the pumped-storage unit to be analyzed, and when the difference between the preset load information and the current load information does not meet the preset conditions, use the updated state information as the new current state information, and jump to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then use the current load information obtained for the last time as the target load information of the pumped-storage unit to be analyzed.

[0088] The current load information refers to the load value of the pumped storage unit to be analyzed at the current time.

[0089] The preset condition refers to a pre-set judgment condition, which is used to judge the difference between the preset load information and the current load information, and can be a preset load difference. It should be noted that the preset condition depends on the situation.

[0090] Exemplarily, the server controls the pumped-storage unit to be analyzed to adjust its load according to the updated status information, obtains the load information of the pumped-storage unit to be analyzed at the current time as the current load information (the current load information here is the current load information obtained for the first time), and the server judges the current load information; when the difference between the preset load information and the current load information does not meet the preset conditions, the server uses the updated status information as the new current status information, and jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current status information, and then controls the pumped-storage unit to be analyzed to adjust its load according to the updated status information, obtains the current load information of the pumped-storage unit to be analyzed (the current load information here is the current load information obtained for the second time), and the server judges the current load information again; until the difference between the preset load information and the current load information meets the preset conditions, the current load information is used as the current load information obtained for the last time; then, the server uses the current load information obtained for the last time as the target load information of the pumped-storage unit to be analyzed.

[0091] In the above-mentioned pumped-storage unit load control method, the preset load information and current state information of the pumped-storage unit to be analyzed are first obtained, and the target control information of the pumped-storage unit to be analyzed is determined according to the preset load information and the current state information, and then the target control instruction of the pumped-storage unit to be analyzed is generated according to the target control information and the unit parameters of the pumped-storage unit to be analyzed. Then, according to the target control instruction, the current state information is updated to obtain the updated state information of the pumped-storage unit to be analyzed. Then, according to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust the load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information is jumped to, until the difference between the preset load information and the current load information meets the preset condition, the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed. In this way, in the process of load control of the pumped-storage unit, after obtaining the preset load information and current state information of the pumped-storage unit to be analyzed, a target control instruction is further generated to drive the pumped-storage unit to adjust the load, by constantly comparing the preset load information with the actual current load information, as long as the difference between the two does not meet the preset conditions, adjustments are continuously made to ensure that the final actual load of the unit matches the preset load as accurately as possible, thereby achieving high-precision control of the load of the pumped-storage unit, which is beneficial to improving the load control accuracy of the pumped-storage unit; moreover, the entire process does not require human intervention, thus avoiding the subjective factors in the manual control method, which is prone to errors and leads to the defect of low load control accuracy of the pumped-storage unit, thereby improving the load control accuracy of the pumped-storage unit.

[0092] In an exemplary embodiment, the above step S101, obtaining the preset load information and current status information of the pumped-storage unit to be analyzed, specifically includes the following contents: obtaining the target operating condition information of the pumped-storage unit to be analyzed; according to the target operating condition information, querying the correspondence between the operating condition information and the load information, and obtaining the load information corresponding to the target operating condition information as the preset load information.

[0093] Among them, the target operating condition information refers to the operating condition of the pumped-storage unit to be analyzed at the current time, such as power generation, pumping, power generation phase adjustment, pumping phase adjustment, traction machine and shutdown, etc.

[0094] The corresponding relationship between the working condition information and the load information is used to indicate the association information between the working condition information and the load information. For example, working condition information A corresponds to load information a, working condition information B corresponds to load information b, and working condition information C corresponds to load information c.

[0095] Exemplarily, the server determines the target operating condition information of the pumped-storage unit to be analyzed based on the operating condition of the pumped-storage unit to be analyzed at the current time; then, the server queries the correspondence between the operating condition information and the load information based on the target operating condition information, obtains the load information corresponding to the target operating condition information, and uses the load information as the preset load information.

[0096] In this embodiment, the preset load information is determined by the correspondence between the operating condition information and the load information, thereby ensuring that the preset load information is closely matched with the target operating condition information of the pumped-storage unit to be analyzed, avoiding the inaccuracy that may occur due to arbitrary human setting or empirical load estimation, and is conducive to improving the accuracy of determining the preset load information.

[0097] In an exemplary embodiment, the above step S102, based on the preset load information and the current state information, determines the target control information of the pumped-storage unit to be analyzed, specifically including the following contents: determining the target state information corresponding to the preset load information; preprocessing the target state information and the current state information to obtain the preprocessed target state information and the preprocessed current state information; and determining the target control information of the pumped-storage unit to be analyzed based on the difference between the preprocessed target state information and the preprocessed current state information.

[0098] The target state information is used to represent the planned values ​​corresponding to the state information of the pumped-storage unit to be analyzed, including the planned values ​​corresponding to the power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed.

[0099] The pre-processed target state information refers to the pre-processed target state information.

[0100] The pre-processed current state information refers to the pre-processed current state information.

[0101] Exemplarily, the server queries the correspondence between the load information and the state information based on the preset load information of the pumped-storage unit to be analyzed, and obtains the target state information corresponding to the preset load information; then, the server preprocesses the target state information and the current state information to obtain the preprocessed target state information and the preprocessed current state information; for example, the server performs denoising processing on the target state information and the current state information to obtain the preprocessed target state information and the preprocessed current state information; then, the server performs difference processing on the preprocessed target state information and the preprocessed current state information to obtain the direct difference between the preprocessed target state information and the preprocessed current state information as the difference between the preprocessed target state information and the preprocessed current state information; then, the server determines the target control information of the pumped-storage unit to be analyzed based on the difference between the preprocessed target state information and the preprocessed current state information.

[0102] In this embodiment, by determining the target state information corresponding to the preset load information, the ideal operating state that the pumped-storage unit should be in when the preset load information is expected to be reached can be clearly determined; moreover, preprocessing the target state information and the current state information is beneficial to reducing interference factors that may exist in the original data, thereby improving the accuracy of determining subsequent target control information.

[0103] In an exemplary embodiment, the above step S102 determines the target control information of the pumped-storage unit to be analyzed based on the preset load information and the current state information, and specifically includes the following contents: performing feature extraction processing on the preset load information and the current state information respectively to obtain a first feature vector corresponding to the preset load information, and a second feature vector corresponding to the current state information; fusing the first feature vector and the second feature vector to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; inputting the fused feature vector into a pre-trained control information prediction model to obtain control information corresponding to the fused feature vector as the target control information.

[0104] The first eigenvector refers to the eigenvector corresponding to the preset load information.

[0105] The second eigenvector refers to the eigenvector corresponding to the current state information.

[0106] The fused feature vector refers to a feature vector obtained by fusing the first feature vector and the second feature vector.

[0107] Among them, the control information prediction model refers to a network model that can use the fused feature vector corresponding to the pumped-storage unit to be analyzed to obtain the target control information of the pumped-storage unit to be analyzed, such as a deep neural network model, a convolutional neural network model, etc.

[0108] Exemplarily, the server uses the preset load information as the main data and the current state information as the auxiliary data, and inputs them into the feature extraction model for feature extraction processing to obtain the first feature vector corresponding to the preset load information; then, the server uses the current state information as the main data and the preset load information as the auxiliary data, and inputs them into the feature extraction model for feature extraction processing to obtain the second feature vector corresponding to the current state information; then, the server obtains the first weight corresponding to the preset load information and the second weight corresponding to the current state information; then, the server fuses the first feature vector and the second feature vector according to the first weight and the second weight, and obtains the fused feature vector corresponding to the pumped-storage unit to be analyzed; then, the server inputs the fused feature vector into the pre-trained control information prediction model, and obtains the control information corresponding to the fused feature vector as the target control information through the pre-trained control information prediction model.

[0109] In this embodiment, by utilizing a pre-trained control information prediction model, target control information is generated based on a fused feature vector corresponding to preset load information and current state information. Thus, with the help of the model's powerful learning and mapping capabilities, the corresponding target control information can be accurately obtained, which is beneficial to improving the accuracy of determining the target control information of the pumped-storage unit to be analyzed.

[0110] In an exemplary embodiment, the load control method of the pumped-storage unit provided in the present application also includes a training step of a pre-trained control information prediction model, which specifically includes the following contents: obtaining preset sample load information and current sample state information of the sample pumped-storage unit; performing feature extraction processing on the preset sample load information and the current sample state information respectively to obtain a first sample feature vector corresponding to the preset sample load information, and a second sample feature vector corresponding to the current sample state information; performing fusion processing on the first sample feature vector and the second sample feature vector to obtain a fused sample feature vector corresponding to the sample pumped-storage unit; inputting the fused sample feature vector into the control information prediction model to be trained to obtain target control information corresponding to the fused sample feature vector; obtaining the actual control information corresponding to the fused sample feature vector, and iteratively training the control information prediction model to be trained according to the difference between the actual control information corresponding to the fused sample feature vector and the target control information to obtain the pre-trained control information prediction model.

[0111] The sample pumped-storage unit refers to a pumped-storage unit used to train the control information prediction model to be trained.

[0112] The preset sample load information refers to the load setting value of the sample pumped-storage unit.

[0113] The current sample status information at least includes the power information, speed information and guide vane opening information of the sample pumped storage unit at the current time.

[0114] The first sample feature vector refers to a feature vector corresponding to the preset sample load information.

[0115] The second sample feature vector refers to the feature vector corresponding to the current sample state information.

[0116] The fused sample feature vector refers to a feature vector obtained by fusing the first sample feature vector and the second sample feature vector.

[0117] The target control information corresponding to the fused sample feature vector refers to the predicted value of the control information corresponding to the fused sample feature vector.

[0118] The actual control information corresponding to the fused sample feature vector refers to the actual value of the control information corresponding to the fused sample feature vector.

[0119] Exemplarily, in response to a model training instruction for a control information prediction model to be trained, the server obtains preset sample load information and current sample state information of a sample pumped-storage unit from a database; then, the server performs feature extraction processing on the preset sample load information and the current sample state information respectively to obtain a first sample feature vector corresponding to the preset sample load information and a second sample feature vector corresponding to the current sample state information; then, the server performs fusion processing on the first sample feature vector and the second sample feature vector to obtain a fused sample feature vector corresponding to the sample pumped-storage unit; then, the server inputs the fused sample feature vector into the control information prediction model to be trained to obtain target control information corresponding to the fused sample feature vector; then, the server obtains the actual control information corresponding to the fused sample feature vector, and obtains a loss value based on the difference between the actual control information corresponding to the fused sample feature vector and the target control information; then, the server adjusts the model parameters of the control information prediction model to be trained based on the loss value; then, the server retrains the control information prediction model after the model parameters are adjusted until the loss value obtained by the trained control information prediction model is less than the loss value threshold, then stops the training, and uses the trained control information prediction model as the pre-trained control information prediction model.

[0120] In this embodiment, by pre-training the control information prediction model, it is convenient to predict the target control information of the pumped-storage unit to be analyzed after obtaining the fused feature vector corresponding to the pumped-storage unit to be analyzed in actual applications; moreover, the control information prediction model receives new data in each round of iteration, and performs internal improvements and optimizations on the model, so as to be able to perform predictions more effectively, which is beneficial to improving the prediction accuracy of the control information prediction model.

[0121] In an exemplary embodiment, the above-mentioned step S103 generates a target control instruction for the pumped-storage unit to be analyzed based on the target control information and the unit parameters of the pumped-storage unit to be analyzed, and specifically includes the following contents: determining the importance of each unit parameter through a pre-trained importance prediction model; screening out unit parameters with an importance greater than a preset importance from each unit parameter as key unit parameters of the pumped-storage unit to be analyzed; generating a target control instruction for the pumped-storage unit to be analyzed based on the target control information and the key unit parameters.

[0122] Among them, the importance prediction model refers to the network model used to determine the importance of each unit parameter, such as the XGBoost (eXtreme Gradient Boosting) model, the LightGBM (Light GradientBoosting Machine) model, etc.

[0123] The importance of each unit parameter is used to indicate the importance of each unit parameter.

[0124] The preset importance refers to a preset importance threshold, which is used to judge the importance of each unit parameter, such as 80%. It should be noted that the preset importance depends on the situation.

[0125] Among them, the key unit parameters refer to the unit parameters whose importance is greater than the preset importance.

[0126] Exemplarily, the server inputs each unit parameter into a pre-trained importance prediction model, and determines the importance of each unit parameter through the pre-trained importance prediction model; then, the server screens out unit parameters whose importance is greater than a preset importance from each unit parameter, and uses these unit parameters as key unit parameters of the pumped-storage unit to be analyzed; then, the server generates control instructions corresponding to the target control information and the key unit parameters based on the target control information and the key unit parameters of the pumped-storage unit to be analyzed, as target control instructions for the pumped-storage unit to be analyzed.

[0127] In this embodiment, by screening out key unit parameters whose importance is greater than a preset importance from multiple unit parameters, relatively minor unit parameter interference can be excluded when subsequently generating target control instructions, thereby making the generated target control instructions more targeted and helping to improve the accuracy of determining the target control instructions.

[0128] In an exemplary embodiment, Figure 2 As shown, another pumped storage unit load control method is provided, which is described by taking the application of the method to a server as an example, and includes the following steps:

[0129] Step S201, obtaining preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time.

[0130] Step S202, determine the target state information corresponding to the preset load information; preprocess the target state information and the current state information to obtain the preprocessed target state information and the preprocessed current state information; determine the target control information of the pumped-storage unit to be analyzed based on the difference between the preprocessed target state information and the preprocessed current state information.

[0131] Step S203, respectively perform feature extraction processing on the preset load information and the current state information to obtain a first feature vector corresponding to the preset load information and a second feature vector corresponding to the current state information; fuse the first feature vector and the second feature vector to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; input the fused feature vector into a pre-trained control information prediction model to obtain control information corresponding to the fused feature vector as target control information.

[0132] Step S204, determining the importance of each unit parameter through a pre-trained importance prediction model; and selecting unit parameters with importance greater than a preset importance from the various unit parameters as key unit parameters of the pumped-storage unit to be analyzed.

[0133] Step S205, generating target control instructions for the pumped-storage unit to be analyzed according to the target control information and key unit parameters.

[0134] Step S206, updating the current status information according to the target control instruction to obtain updated status information of the pumped-storage unit to be analyzed.

[0135] Step S207, according to the updated state information, control the pumped-storage unit to be analyzed to adjust the load, obtain the current load information of the pumped-storage unit to be analyzed, and when the difference between the preset load information and the current load information does not meet the preset conditions, use the updated state information as the new current state information, and jump to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then use the current load information obtained for the last time as the target load information of the pumped-storage unit to be analyzed.

[0136] In the above-mentioned load control method for pumped-storage units, in the process of load control of the pumped-storage units, after obtaining the preset load information and current state information of the pumped-storage units to be analyzed, a target control instruction is further generated to drive the pumped-storage units to adjust the load, by continuously comparing the preset load information with the actual current load information, as long as the difference between the two does not meet the preset conditions, continuous adjustment is performed to ensure that the final actual load of the unit matches the preset load as accurately as possible, thereby achieving high-precision control of the load of the pumped-storage units, which is beneficial to improving the load control accuracy of the pumped-storage units; moreover, the entire process does not require manual intervention, thereby avoiding the defects of subjective factors in the manual control method, which is prone to errors and leads to low load control accuracy of the pumped-storage units, thereby improving the load control accuracy of the pumped-storage units.

[0137] In an exemplary embodiment, in order to more clearly illustrate the pumped storage unit load control method provided in the embodiment of the present application, the pumped storage unit load control method is specifically described below with a specific embodiment. In one embodiment, Figure 3As shown, the present application also provides a pumped storage unit load control method. In the process of load control of the pumped storage unit, the preset load information and current state information of the pumped storage unit to be analyzed are first obtained, and the target control information of the pumped storage unit to be analyzed is determined according to the preset load information and the current state information. Then, according to the target control information and the unit parameters of the pumped storage unit to be analyzed, a target control instruction of the pumped storage unit to be analyzed is generated. Then, according to the target control instruction, the current state information is updated to obtain the updated state information of the pumped storage unit to be analyzed, and then, According to the updated state information, the pumped storage unit to be analyzed is controlled to adjust the load to obtain the current load information of the pumped storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset conditions, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then the current load information obtained last time is used as the target load information of the pumped storage unit to be analyzed. Specifically, it includes the following contents:

[0138] 1. The speed / load control command of the energy storage unit from the operator or the dispatching center (referred to as remote command) is sent to the monitoring system of the hydropower station through the upper computer of the power station. After being received by the software, the command is pre-judged and the corresponding pumped storage unit control program is started, such as Figure 4 Calculate whether the instruction can be executed. If it can be executed, continue to calculate. If the instruction exceeds the limit, it will not be executed and an alarm will be issued.

[0139] 2. According to the remote command and the feedback signals of the energy storage unit such as power, speed and guide vane opening, the deviation is calculated, and then the TSLG speed governor control strategy is formulated according to the deviation.

[0140] 3. Send load, speed or guide vane opening control commands to the TSLG governor according to the control strategy.

[0141] 4. The TSLG speed regulator controls the response of the energy storage unit according to the control command of the hydropower station monitoring system. At the same time, it collects the various analog quantities after the response and feeds them back to the hydropower station monitoring system to complete the closed-loop control of active power.

[0142] 5. The hydropower station monitoring system starts the shutdown process of the energy storage unit according to the shutdown command of the operator or the dispatching center, and sends a shutdown command to the speed governor at the same time.

[0143] Among them, the calculation and operation steps of the pumped storage unit control program are briefly described as follows:

[0144] (1) Store the linearized current guide vane opening value EA10308 into VN26 (R761).

[0145] (2) Store the current speed regulator load / freq value EA10307 into VN25 (R779).

[0146] (3) Store the host computer active setting value TVC17 into VN27 (i.e. VN17=VN27) (R907).

[0147] (4) Calculate the difference between VN25 and VN27 and store it in VN29 and VN30 (R910).

[0148] (5) Use VN26 as the frequency setting value and store it in VN19 and VN28 (R911).

[0149] (6) Take the absolute value of VN30 (R935).

[0150] (7) When the actual value of load / freq is greater than the active setting value, determine whether the difference between the two is greater than the guide vane action threshold (VB30 for U1 and VB25 for U2) (R936).

[0151] (8) When the actual load / freq value is less than the active power setting value, determine whether the difference between the two is greater than the guide vane action threshold value (VB30 for U1 and VB25 for U2) (R937).

[0152] (If the absolute values ​​of the above two do not meet the threshold, no action will be taken).

[0153] (9) Subtract the corresponding threshold value of the unit from VN30 (VB30 for U1 and VB25 for U2), and store it back into VN30 (R938).

[0154] (10) Subtract VBA3 from VN30 and store the result in VN31 (R385).

[0155] (11) When VN30 is less than 0 at this time, the mem values ​​of +gov and -gov are reset (R941).

[0156] (12) When VN31 is greater than 0, the +gov or -gov command is authorized (R386).

[0157] (13) When the actual load / freq value is greater than the active power setting value or the difference between the two does not reach the threshold value for opening the guide vanes, reset M662 (+gov memory) (R939).

[0158] (14) When the actual load / freq value is less than the active power setting value or the difference between the two does not reach the threshold for closing the guide vanes, reset M663 (-gov memory) (R940).

[0159] (15) When the actual value of load / freq is greater than the active setting value, and the difference between the two is greater than the threshold value (and R940=0), command SN40304 is issued to control R22 to close the guide vane (R942).

[0160] (16) When the actual value of load / freq is less than the active setting value, and the difference between the two is greater than the threshold value (and R941=0), send command SN40303 to control R21 to open the guide vane (R782).

[0161] In the above-mentioned embodiment, during the process of load control of the pumped-storage unit, after obtaining the preset load information and current state information of the pumped-storage unit to be analyzed, a target control instruction is further generated to drive the pumped-storage unit to adjust the load, by continuously comparing the preset load information with the actual current load information, as long as the difference between the two does not meet the preset conditions, the adjustment is continuously performed to ensure that the final actual load of the unit matches the preset load as accurately as possible, thereby achieving high-precision control of the load of the pumped-storage unit, which is beneficial to improving the load control accuracy of the pumped-storage unit; moreover, the entire process does not require manual intervention, thus avoiding the defect of low load control accuracy of the pumped-storage unit caused by subjective factors in the manual control method, which is prone to errors, and thus improves the load control accuracy of the pumped-storage unit.

[0162] 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 is not strictly limited in order, 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 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.

[0163] Based on the same inventive concept, the embodiment of the present application also provides a pumped storage unit load control device for implementing the pumped storage unit load control 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 embodiments of the pumped storage unit load control device provided below can refer to the limitations of the pumped storage unit load control method above, and will not be repeated here.

[0164] In an exemplary embodiment, Figure 5 As shown, a pumped storage unit load control device is provided, comprising: an information acquisition module 501, an information determination module 502, an instruction generation module 503, an information update module 504 and a load control module 505, wherein:

[0165] The information acquisition module 501 is used to obtain the preset load information and current state information of the pumped storage unit to be analyzed; the current state information at least includes the power information, speed information and guide vane opening information of the pumped storage unit to be analyzed at the current time.

[0166] The information determination module 502 is used to determine the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information.

[0167] The instruction generation module 503 is used to generate a target control instruction of the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed.

[0168] The information updating module 504 is used to update the current status information according to the target control instruction to obtain the updated status information of the pumped storage unit to be analyzed.

[0169] The load control module 505 is used to control the pumped-storage unit to be analyzed to adjust the load according to the updated state information, and obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset conditions, the updated state information is used as the new current state information, and the module jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

[0170] In an exemplary embodiment, the information acquisition module 501 is also used to obtain the target operating condition information of the pumped storage unit to be analyzed; according to the target operating condition information, the correspondence between the operating condition information and the load information is queried to obtain the load information corresponding to the target operating condition information as the preset load information.

[0171] In an exemplary embodiment, the information determination module 502 is also used to determine the target state information corresponding to the preset load information; preprocess the target state information and the current state information to obtain the preprocessed target state information and the preprocessed current state information; and determine the target control information of the pumped-storage unit to be analyzed based on the difference between the preprocessed target state information and the preprocessed current state information.

[0172] In an exemplary embodiment, the information determination module 502 is also used to perform feature extraction processing on the preset load information and the current state information respectively to obtain a first feature vector corresponding to the preset load information and a second feature vector corresponding to the current state information; to fuse the first feature vector and the second feature vector to obtain a fused feature vector corresponding to the pumped-storage unit to be analyzed; and to input the fused feature vector into a pre-trained control information prediction model to obtain control information corresponding to the fused feature vector as target control information.

[0173] In an exemplary embodiment, the pumped-storage unit load control device also includes a model training module, which is used to obtain preset sample load information and current sample state information of the sample pumped-storage unit; perform feature extraction processing on the preset sample load information and the current sample state information respectively to obtain a first sample feature vector corresponding to the preset sample load information, and a second sample feature vector corresponding to the current sample state information; perform fusion processing on the first sample feature vector and the second sample feature vector to obtain a fused sample feature vector corresponding to the sample pumped-storage unit; input the fused sample feature vector into the control information prediction model to be trained to obtain target control information corresponding to the fused sample feature vector; obtain actual control information corresponding to the fused sample feature vector, and iteratively train the control information prediction model to be trained according to the difference between the actual control information corresponding to the fused sample feature vector and the target control information to obtain a pre-trained control information prediction model.

[0174] In an exemplary embodiment, the instruction generation module 503 is also used to determine the importance of each unit parameter through a pre-trained importance prediction model; screen out unit parameters with an importance greater than a preset importance from each unit parameter as key unit parameters of the pumped-storage unit to be analyzed; and generate target control instructions for the pumped-storage unit to be analyzed based on the target control information and the key unit parameters.

[0175] Each module in the above-mentioned pumped storage unit load control device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0176] 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 preset load information and current status 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 load control method for a pumped storage unit is implemented.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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 this 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.

[0182] 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.

[0183] 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 understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations 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 method for load control of a pumped storage unit, characterized in that: The method comprises: Acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time; Determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information; generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed; According to the target control instruction, the current state information is updated to obtain updated state information of the pumped-storage unit to be analyzed; According to the updated state information, the pumped-storage unit to be analyzed is controlled to adjust its load to obtain the current load information of the pumped-storage unit to be analyzed. When the difference between the preset load information and the current load information does not meet the preset condition, the updated state information is used as the new current state information, and the process jumps to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset condition, then the current load information obtained for the last time is used as the target load information of the pumped-storage unit to be analyzed.

2. The method according to claim 1, characterized in that The obtaining of preset load information and current status information of the pumped-storage unit to be analyzed includes: Acquiring target operating condition information of the pumped-storage unit to be analyzed; According to the target operating condition information, the corresponding relationship between the operating condition information and the load information is queried to obtain the load information corresponding to the target operating condition information as the preset load information.

3. The method according to claim 1, characterized in that The step of determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information comprises: Determining target state information corresponding to the preset load information; Preprocessing the target state information and the current state information to obtain preprocessed target state information and preprocessed current state information; According to the difference between the pre-processed target state information and the pre-processed current state information, the target control information of the pumped-storage unit to be analyzed is determined.

4. The method according to claim 1, characterized in that: The step of determining target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information comprises: Performing feature extraction processing on the preset load information and the current state information respectively to obtain a first feature vector corresponding to the preset load information and a second feature vector corresponding to the current state information; Performing fusion processing on the first eigenvector and the second eigenvector to obtain a fused eigenvector corresponding to the pumped-storage unit to be analyzed; The fused feature vector is input into a pre-trained control information prediction model to obtain control information corresponding to the fused feature vector as the target control information.

5. The method according to claim 4, characterized in that The pre-trained control information prediction model is trained in the following way: Obtain preset sample load information and current sample status information of the sample pumped storage unit; Performing feature extraction processing on the preset sample load information and the current sample state information respectively to obtain a first sample feature vector corresponding to the preset sample load information and a second sample feature vector corresponding to the current sample state information; Performing fusion processing on the first sample feature vector and the second sample feature vector to obtain a fused sample feature vector corresponding to the sample pumped-storage unit; Inputting the fused sample feature vector into the control information prediction model to be trained to obtain the target control information corresponding to the fused sample feature vector; The actual control information corresponding to the fused sample feature vector is obtained, and according to the difference between the actual control information corresponding to the fused sample feature vector and the target control information, the control information prediction model to be trained is iteratively trained to obtain the pre-trained control information prediction model.

6. The method according to any one of claims 1 to 5, characterized in that: The step of generating a target control instruction for the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed comprises: Determining the importance of each of the unit parameters through a pre-trained importance prediction model; From the unit parameters, select the unit parameters whose importance is greater than the preset importance as the key unit parameters of the pumped-storage unit to be analyzed; A target control instruction of the pumped-storage unit to be analyzed is generated according to the target control information and the key unit parameters.

7. A pumped storage unit load control device, characterized in that: The device comprises: An information acquisition module, used to acquire preset load information and current state information of the pumped-storage unit to be analyzed; the current state information at least includes power information, speed information and guide vane opening information of the pumped-storage unit to be analyzed at the current time; An information determination module, used to determine the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information; An instruction generation module, used for generating a target control instruction of the pumped-storage unit to be analyzed according to the target control information and the unit parameters of the pumped-storage unit to be analyzed; An information updating module, used for updating the current state information according to the target control instruction to obtain updated state information of the pumped-storage unit to be analyzed; A load control module is used to control the pumped-storage unit to be analyzed to adjust its load according to the updated state information, obtain the current load information of the pumped-storage unit to be analyzed, and when the difference between the preset load information and the current load information does not meet the preset conditions, use the updated state information as the new current state information, and jump to the step of determining the target control information of the pumped-storage unit to be analyzed according to the preset load information and the current state information, until the difference between the preset load information and the current load information meets the preset conditions, then use the current load information obtained for the last time as the target load information of the pumped-storage unit to be analyzed.

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