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

Abstract

This application relates to a load transfer method, apparatus, computer equipment, storage medium, and computer program product for pumped storage units. The method includes: obtaining first updated capacity setpoints, second updated capacity setpoints, first updated load setpoints, and second updated load setpoints based on a first capacity setpoint, a second capacity setpoint, a first executed capacity setpoint, a second executed capacity setpoint, a first load setpoint, a second load setpoint, a first executed load setpoint, and a second executed load setpoint for the pumped storage unit to be analyzed; obtaining a target load transfer command corresponding to the pumped storage unit to be analyzed through a pre-trained load transfer command prediction model; and performing corresponding load transfer processing on the pumped storage unit to be analyzed according to the target load transfer command. Using this method can improve the accuracy of load transfer for pumped storage units.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for load transfer of pumped storage units. Background Technology

[0002] Currently, in order to ensure the operational stability of the power grid system where pumped storage units are located, it is crucial to accurately transfer the load on pumped storage units.

[0003] In traditional technology, manual adjustment is generally used during the load transfer process of pumped storage units. However, this manual adjustment method is subject to subjective factors and is prone to errors, resulting in low accuracy of load transfer for pumped storage units. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for transferring loads of pumped storage units that can improve the accuracy of load transfer in the aforementioned technical problems.

[0005] In a first aspect, this application provides a load transfer method for a pumped storage unit, comprising:

[0006] Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed;

[0007] A first difference is obtained based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and a second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value.

[0008] Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0009] Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0010] The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed.

[0011] According to the target load transfer command, the pumped storage unit to be analyzed is subjected to corresponding load transfer processing.

[0012] In one embodiment, the step of inputting the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed includes:

[0013] The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain multiple predicted load transfer commands corresponding to the pumped storage unit to be analyzed, as well as the prediction probability of each predicted load transfer command.

[0014] From each predicted load transfer instruction, the predicted load transfer instruction with the highest predicted probability is selected as the target load transfer instruction.

[0015] In one embodiment, obtaining the first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value includes:

[0016] The first capacity setting value and the second capacity setting value are weighted to obtain a weighted capacity setting value, and the first capacity execution value and the second capacity execution value are weighted to obtain a weighted capacity execution value;

[0017] The first difference value is obtained by subtracting the weighted capacity setting value and the weighted capacity execution value.

[0018] The step of obtaining the second difference based on the first load setpoint, the second load setpoint, the first load execution value, and the second load execution value includes:

[0019] The first load setting value and the second load setting value are weighted to obtain a weighted load setting value, and the first load execution value and the second load execution value are weighted to obtain a weighted load execution value;

[0020] The difference between the weighted load setting value and the weighted load execution value is calculated to obtain the second difference value.

[0021] In one embodiment, after obtaining a first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value, and obtaining a second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value, the method further includes:

[0022] Obtain the capacity setpoint tolerance rate and load setpoint tolerance rate of the pumped storage unit to be analyzed;

[0023] The step of updating the first capacity setpoint and the second capacity setpoint based on the first difference to obtain the first updated capacity setpoint and the second updated capacity setpoint of the pumped storage unit to be analyzed includes:

[0024] If the first difference is less than the capacity setting value error rate, the first capacity setting value and the second capacity setting value are updated according to the first difference to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0025] The step of updating the first load setpoint and the second load setpoint based on the second difference to obtain the first updated load setpoint and the second updated load setpoint of the pumped storage unit to be analyzed includes:

[0026] If the second difference is less than the load setting value tolerance rate, the first load setting value and the second load setting value are updated according to the second difference to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0027] In one embodiment, after obtaining the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed, the method further includes:

[0028] The first load setting value, the first capacity setting value, the second load setting value, and the second capacity setting value are verified to obtain the verification result;

[0029] If the verification result meets the preset conditions, an early warning message is generated for the pumped storage unit to be analyzed.

[0030] The warning information is sent to the target terminal associated with the pumped storage unit to be analyzed.

[0031] In one embodiment, the pre-trained load transfer instruction prediction model is trained in the following manner:

[0032] Obtain the first sample load setpoint, the first sample capacity setpoint, the second sample load setpoint, the second sample capacity setpoint, the first sample load execution value, the first sample capacity execution value, the second sample load execution value, and the second sample capacity execution value of the sample pumped storage unit;

[0033] A first sample difference is obtained based on the first sample capacity setting value, the second sample capacity setting value, the first sample capacity execution value, and the second sample capacity execution value; and a second sample difference is obtained based on the first sample load setting value, the second sample load setting value, the first sample load execution value, and the second sample load execution value.

[0034] Based on the first sample difference, the first sample capacity setting value and the second sample capacity setting value are updated respectively to obtain the first updated sample capacity setting value and the second updated sample capacity setting value of the sample pumped storage unit.

[0035] Based on the second sample difference, the first sample load setting value and the second sample load setting value are updated respectively to obtain the first updated sample load setting value and the second updated sample load setting value of the sample pumped storage unit.

[0036] The first updated sample capacity setting value, the second updated sample capacity setting value, the first updated sample load setting value, and the second updated sample load setting value are input into the load transfer command prediction model to be trained to obtain the predicted load transfer command corresponding to the sample pumped storage unit.

[0037] Obtain the actual load transfer command corresponding to the sample pumped storage unit, and iteratively train the load transfer command prediction model to be trained based on the difference between the predicted load transfer command and the actual load transfer command to obtain the pre-trained load transfer command prediction model.

[0038] Secondly, this application also provides a load transfer device for a pumped storage unit, comprising:

[0039] The data acquisition module is used to acquire the first load setpoint, the first capacity setpoint, the second load setpoint, the second capacity setpoint, the first load execution value, the first capacity execution value, the second load execution value, and the second capacity execution value of the pumped storage unit to be analyzed.

[0040] The difference determination module is used to obtain a first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value, and to obtain a second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value;

[0041] The first update module is used to update the first capacity setting value and the second capacity setting value according to the first difference, respectively, to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0042] The second update module is used to update the first load setting value and the second load setting value according to the second difference, respectively, to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0043] The instruction prediction module is used to input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value and the second updated load setting value into a pre-trained load transfer instruction prediction model to obtain the target load transfer instruction corresponding to the pumped storage unit to be analyzed.

[0044] The load transfer module is used to perform corresponding load transfer processing on the pumped storage unit to be analyzed according to the target load transfer command.

[0045] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0046] Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed;

[0047] A first difference is obtained based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and a second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value.

[0048] Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0049] Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0050] The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed.

[0051] According to the target load transfer command, the pumped storage unit to be analyzed is subjected to corresponding load transfer processing.

[0052] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0053] Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed;

[0054] A first difference is obtained based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and a second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value.

[0055] Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0056] Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0057] The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed.

[0058] According to the target load transfer command, the pumped storage unit to be analyzed is subjected to corresponding load transfer processing.

[0059] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0060] Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed;

[0061] A first difference is obtained based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and a second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value.

[0062] Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0063] Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0064] The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed.

[0065] According to the target load transfer command, the pumped storage unit to be analyzed is subjected to corresponding load transfer processing.

[0066] The aforementioned pumped-storage unit load transfer method, apparatus, computer equipment, storage medium, and computer program product first acquire the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped-storage unit to be analyzed. Based on these values, a first difference is obtained, and a second difference is obtained. Finally, based on the first difference, the first capacity setpoint and second capacity setpoint are updated accordingly. The process involves obtaining the first and second updated capacity setpoints of the pumped storage unit to be analyzed. Then, based on the second difference, the first and second load setpoints are updated to obtain the first and second updated load setpoints of the pumped storage unit to be analyzed. Next, the first and second updated capacity setpoints, the first and second updated load setpoints, and the second updated load setpoints are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed. Finally, based on the target load transfer command, the corresponding load transfer processing is performed on the pumped storage unit to be analyzed. In this way, during the load transfer process of pumped storage units, by acquiring multi-dimensional data related to different aspects of the pumped storage unit under analysis, and through a series of processes such as difference processing, update processing, and model processing, the judgment is not based on a single data point. This allows for a more accurate load transfer instruction to be obtained for the pumped storage unit under analysis, and thus more precise load transfer processing can be performed on the pumped storage unit under analysis, which is beneficial to improving the load transfer accuracy of the pumped storage unit. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur when using manual adjustments, which leads to low load transfer accuracy of the pumped storage unit, thereby improving the load transfer accuracy of the pumped storage unit. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart illustrating a load transfer method for a pumped storage unit in one embodiment;

[0069] Figure 2This is a flowchart illustrating the steps for obtaining the target load transfer command corresponding to the pumped storage unit to be analyzed in one embodiment.

[0070] Figure 3 This is a flowchart illustrating the load transfer method for a pumped storage unit in another embodiment;

[0071] Figure 4 This is a flowchart illustrating the load transfer method for a pumped storage unit in yet another embodiment;

[0072] Figure 5 This is a structural block diagram of a pumped storage unit load transfer device in one embodiment;

[0073] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0075] 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, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0076] Currently, pumped-storage units are managed and controlled by dispatching systems A and B. These two systems adjust the load and capacity of the pumped-storage units according to their respective grid load demands. Therefore, load transfer functions are frequently used between the two dispatching systems to transfer loads to the pumped-storage units, thereby achieving load balancing in their respective grids. Due to limitations in the communication protocol, there is a deviation of 0.01 to 0.02 in the various analog setpoints issued by dispatching systems A and B. The load transfer module in the original host computer control program did not consider the slight errors caused by data format conversion during communication, which may lead to discrepancies between its result and the calculation result of the subsequent execution value assignment module. The possible consequences are as follows: When scheduling load transfer, the capacity and load setpoints of one party's scheduling might pass the judgment of the load transfer module and be sent to the subsequent execution value assignment module for execution, while the setpoints of the other party's scheduling might fail to pass the judgment of the subsequent execution value assignment module and remain unchanged from the pre-transfer setpoints. This could result in the actual scheduled capacity and load being greater or less than the scheduling setpoints, potentially leading to additional start-ups or shutdowns of the units. The most serious consequence could be a complete shutdown of pumped storage units, resulting in a significant load deficit for the power grid. To ensure the operational stability of the power grid system where pumped storage units are located, accurate load transfer for these units is crucial. However, load transfer for pumped storage units typically involves manual adjustments; however, this manual adjustment method is subject to subjective factors and prone to errors, leading to low accuracy in load transfer. Therefore, this application provides a load transfer method for pumped storage units that can solve the problem of low load transfer accuracy and improve the overall accuracy of load transfer for pumped storage units.

[0077] In one exemplary embodiment, such as Figure 1 As shown, a load transfer method for pumped storage units is provided. This embodiment illustrates the application of this method to a server. It is understood that this method can also be applied to terminals, and further to systems including terminals and servers, and is implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, and tablets; the servers can be independent servers or server clusters composed of multiple servers. In this embodiment, the method includes the following steps:

[0078] Step S101: Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed.

[0079] Among them, the pumped storage units to be analyzed refer to pumped storage units that require load transfer processing.

[0080] The first load setpoint refers to the load setpoint of the pumped storage unit to be analyzed set by the dispatching system A.

[0081] The first capacity setting value refers to the capacity setting value of the pumped storage unit to be analyzed set by the dispatching system A.

[0082] The second load setpoint refers to the load setpoint of the pumped storage unit to be analyzed, set by the dispatching system B.

[0083] The second capacity setting value refers to the capacity setting value of the pumped storage unit to be analyzed set by the dispatching system B.

[0084] The first load execution value refers to the load execution value of the pumped storage unit to be analyzed set by the dispatching system A.

[0085] The first capacity execution value refers to the capacity execution value of the pumped storage unit to be analyzed set by the scheduling system A.

[0086] The second load execution value refers to the load execution value of the pumped storage unit to be analyzed, set by the dispatching system B.

[0087] The second capacity execution value refers to the capacity execution value of the pumped storage unit to be analyzed, set by the scheduling system B.

[0088] For example, the server determines the candidate scheduling system corresponding to the pumped storage unit to be analyzed from multiple candidate scheduling systems, and uses it as the target scheduling system (such as scheduling system A and scheduling system B); then, the server obtains the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value and second capacity execution value of the pumped storage unit to be analyzed through the target scheduling system.

[0089] Step S102: Obtain a first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and obtain a second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value.

[0090] The first difference is used to represent the difference between the capacity setpoint and the capacity execution value of the pumped storage unit to be analyzed.

[0091] The second difference is used to represent the difference between the load setpoint and the load execution value of the pumped storage unit to be analyzed.

[0092] For example, the server constructs a first correspondence between a first capacity setting value, a second capacity setting value, a first capacity execution value, a second capacity execution value, and a first difference, and constructs a correspondence between a first load setting value, a second load setting value, a first load execution value, a second load execution value, and a second difference; then, the server queries the first correspondence based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value to obtain the first difference; then, the server queries the second correspondence based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value to obtain the second difference.

[0093] Step S103: Based on the first difference, update the first capacity setting value and the second capacity setting value respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0094] The first updated capacity setting value is used to represent the adjusted first capacity setting value of the pumped storage unit to be analyzed.

[0095] The second updated capacity setting value is used to represent the adjusted second capacity setting value of the pumped storage unit to be analyzed.

[0096] For example, the server updates the first capacity setting value based on the first difference to obtain the first updated capacity setting value of the pumped storage unit to be analyzed; then, the server updates the second capacity setting value based on the first difference to obtain the second updated capacity setting value of the pumped storage unit to be analyzed.

[0097] For example, the server can obtain the first updated capacity setting using the following formula:

[0098] QCOG ' = QCOG + DIFF1*QCOG / (QCOG-QCOC), formula (1)

[0099] Where QCOG' refers to the first updated capacity setting, QCOG refers to the first capacity setting, QCOC refers to the second capacity setting, and DIFF1 refers to the first difference.

[0100] For example, the server can obtain the second updated capacity setting using the following formula:

[0101] QCOC ' = QCOC + DIFF1* QCOC / (QCOG-QCOC), formula (2)

[0102] QCOC' refers to the second updated capacity setting.

[0103] Step S104: Based on the second difference, update the first load setting value and the second load setting value respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0104] The first updated load setting value is used to represent the adjusted first load setting value of the pumped storage unit to be analyzed.

[0105] The second updated load setting value is used to represent the adjusted second load setting value of the pumped storage unit to be analyzed.

[0106] For example, the server updates the first load setting value based on the second difference to obtain the first updated load setting value of the pumped storage unit to be analyzed; then, the server updates the second load setting value based on the second difference to obtain the second updated load setting value of the pumped storage unit to be analyzed.

[0107] For example, the server can obtain the load setting value after the first update using the following formula:

[0108] QLOG ' = QLOG + DIFF2*QLOG / (QLOG-QLOC), equation (3)

[0109] Where QLOG' refers to the first updated load setting value, QLOG refers to the first load setting value, QLOC refers to the second load setting value, and DIFF2 refers to the second difference value.

[0110] For example, the server can obtain the second updated load setting value using the following formula:

[0111] QLOC ' = QLOC + DIFF2*QLOC / (QLOG-QLOC), equation (4)

[0112] Here, QLOC' refers to the load setting value after the second update.

[0113] Step S105: Input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into the pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed.

[0114] Among them, the load transfer command prediction model refers to a network model that can obtain the target load transfer command corresponding to the pumped storage unit to be analyzed by using the first updated capacity setpoint, the second updated capacity setpoint, the first updated load setpoint, and the second updated load setpoint. For example, a long short-term memory network model.

[0115] Among them, the target load transfer instruction refers to the instruction information for load transfer processing of the pumped storage unit to be analyzed.

[0116] For example, the server preprocesses the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value to obtain the first preprocessed capacity setting value, the second preprocessed capacity setting value, the first preprocessed load setting value, and the second preprocessed load setting value of the pumped storage unit to be analyzed. Then, the server inputs the first preprocessed capacity setting value, the second preprocessed capacity setting value, the first preprocessed load setting value, and the second preprocessed load setting value into a pre-trained load transfer instruction prediction model to obtain the target load transfer instruction corresponding to the pumped storage unit to be analyzed.

[0117] Step S106: According to the target load transfer instruction, perform the corresponding load transfer processing on the pumped storage unit to be analyzed.

[0118] For example, the server performs integrity verification on the target load transfer instruction and obtains the verification result corresponding to the target load transfer instruction; if the verification result indicates that the target load transfer instruction is passed, the server performs the corresponding load transfer processing on the pumped storage unit to be analyzed according to the target load transfer instruction.

[0119] In the aforementioned load transfer method for pumped storage units, the following steps are first taken: obtaining the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed. Then, based on these values, a first difference is obtained, and a second difference is also obtained. Finally, based on the first difference, the first and second capacity setpoints are updated to obtain the pumped storage unit to be analyzed. The unit has a first updated capacity setting value and a second updated capacity setting value. Then, based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed. Then, the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value and the second updated load setting value are input into the pre-trained load transfer instruction prediction model to obtain the target load transfer instruction corresponding to the pumped storage unit to be analyzed. Finally, based on the target load transfer instruction, the pumped storage unit to be analyzed is subjected to the corresponding load transfer processing. In this way, during the load transfer process of pumped storage units, by acquiring multi-dimensional data related to different aspects of the pumped storage unit under analysis, and through a series of processes such as difference processing, update processing, and model processing, the judgment is not based on a single data point. This allows for a more accurate load transfer instruction to be obtained for the pumped storage unit under analysis, and thus more precise load transfer processing can be performed on the pumped storage unit under analysis, which is beneficial to improving the load transfer accuracy of the pumped storage unit. Moreover, the entire process does not require manual intervention, avoiding the subjective factors and errors that are prone to occur when using manual adjustments, which leads to low load transfer accuracy of the pumped storage unit, thereby improving the load transfer accuracy of the pumped storage unit.

[0120] In an exemplary embodiment, step S105 above, which involves inputting the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed, specifically includes the following steps:

[0121] Step S201: Input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into the pre-trained load transfer command prediction model to obtain multiple predicted load transfer commands corresponding to the pumped storage unit to be analyzed, as well as the prediction probability of each predicted load transfer command.

[0122] Step S202: From each predicted load transfer instruction, select the predicted load transfer instruction with the highest predicted probability as the target load transfer instruction.

[0123] Among them, the predicted load transfer instruction is used to represent the predicted instruction corresponding to the load transfer processing of the pumped storage unit to be analyzed.

[0124] The prediction probability is used to represent the likelihood that the load transfer command prediction model determines that the predicted load transfer command is correct.

[0125] For example, the server uses the first updated capacity setting as primary data and the second updated capacity setting, the first updated load setting, and the second updated load setting as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the first updated capacity setting. Next, the server uses the second updated capacity setting as primary data and the first updated capacity setting, the first updated load setting, and the second updated load setting as auxiliary data, inputting them into the feature extraction model for feature extraction processing to obtain a second feature vector corresponding to the second updated capacity setting. Then, the server uses the first updated load setting as primary data and the first updated capacity setting, the second updated capacity setting, and the second updated load setting as auxiliary data, inputting them into the feature extraction model for feature extraction processing to obtain a first feature vector. The server first updates the load setpoint, then uses the second updated load setpoint as the primary data and the first updated capacity setpoint, the second updated capacity setpoint, and the first updated load setpoint as auxiliary data. This data is then input into a feature extraction model to extract the fourth feature vector corresponding to the second updated load setpoint. Next, the server inputs the first, second, third, and fourth feature vectors into a pre-trained load transfer instruction prediction model. This model generates multiple predicted load transfer instructions for the pumped storage unit to be analyzed, along with the prediction probability of each instruction. Finally, the server selects the predicted load transfer instruction with the highest prediction probability from these instructions and uses this instruction as the target load transfer instruction.

[0126] In this embodiment, by selecting the predicted load transfer instruction with the highest prediction probability as the target load transfer instruction, it can be ensured that the selected instruction is highly consistent with the actual situation of the unit at present, thereby making the unit perform load transfer operations more smoothly and efficiently, and avoiding problems such as equipment wear and unstable operation caused by unreasonable instructions.

[0127] In an exemplary embodiment, step S102 above, which obtains a first difference based on a first capacity setting value, a second capacity setting value, a first capacity execution value, and a second capacity execution value, specifically includes the following: weighting the first capacity setting value and the second capacity setting value to obtain a weighted capacity setting value, and weighting the first capacity execution value and the second capacity execution value to obtain a weighted capacity execution value; and subtracting the weighted capacity setting value and the weighted capacity execution value to obtain the first difference.

[0128] The second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value. Specifically, the second difference is obtained by weighting the first load setting value and the second load setting value to obtain the weighted load setting value, and by weighting the first load execution value and the second load execution value to obtain the weighted load execution value; and by subtracting the weighted load setting value and the weighted load execution value to obtain the second difference.

[0129] The weighted capacity setting value refers to the capacity setting value obtained by weighting the first capacity setting value and the second capacity setting value.

[0130] The weighted capacity execution value refers to the capacity execution value obtained by weighting the first capacity execution value and the second capacity execution value.

[0131] The weighted load setting value refers to the load setting value obtained by weighting the first load setting value and the second load setting value.

[0132] The weighted load execution value refers to the load execution value obtained by weighting the first load execution value and the second load execution value.

[0133] For example, the server performs weighted processing on the first capacity setting value and the second capacity setting value to obtain a weighted capacity setting value, which is used as the weighted capacity setting value; and performs weighted processing on the first capacity execution value and the second capacity execution value to obtain a weighted capacity execution value, which is used as the weighted capacity execution value; then, the server performs subtraction processing on the weighted capacity setting value and the weighted capacity execution value to obtain the difference between the weighted capacity setting value and the weighted capacity execution value, which is used as the first difference value; then, the server performs weighted processing on the first load setting value and the second load setting value to obtain a weighted load setting value, which is used as the weighted load setting value; and performs weighted processing on the first load execution value and the second load execution value to obtain a weighted load execution value, which is used as the weighted load execution value; finally, the server performs subtraction processing on the weighted load setting value and the weighted load execution value to obtain the difference between the weighted load setting value and the weighted load execution value, which is used as the second difference value.

[0134] For example, the server can obtain the weighted capacity setting value using the following formula:

[0135] CAPAO = QCOG + QCOC, Equation (5)

[0136] CAPAO refers to the weighted capacity setting.

[0137] For example, the server can obtain the weighted capacity execution value using the following formula:

[0138] CAPAE = QCEG + QCEC, Equation (6)

[0139] In this context, CAPAE refers to the weighted capacity execution value, QCEG refers to the first capacity execution value, and QCEC refers to the second capacity execution value.

[0140] For example, the server can obtain the first difference using the following formula:

[0141] DIFF1=CAPAE – CAPAO, equation (7)

[0142] For example, the server can obtain the weighted load setting value using the following formula:

[0143] LOADO = QLOG + QLOC, Equation (8)

[0144] LOADO refers to the weighted load setting.

[0145] For example, the server can obtain the weighted load execution value using the following formula:

[0146] LOADE = QLEG + QLEC, Equation (9)

[0147] Where LOADE refers to the weighted load execution value, QLEG refers to the first load execution value, and QLEC refers to the second load execution value.

[0148] For example, the server can obtain the second difference using the following formula:

[0149] DIFF2=LOADO – LOADE, formula (10)

[0150] In this embodiment, the first difference and the second difference can be obtained quickly and directly by using multiple data associated with the pumped storage unit to be analyzed. The entire process does not require manual intervention, which avoids the time and manpower consumption that is easy to spend on manual calculation, and helps to improve the efficiency of determining the first difference and the second difference.

[0151] In an exemplary embodiment, after obtaining the first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value, and obtaining the second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value, step S102 specifically includes the following: obtaining the capacity setting value tolerance rate and the load setting value tolerance rate of the pumped storage unit to be analyzed.

[0152] Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed. Specifically, this includes the following: when the first difference is less than the capacity setting value error tolerance rate, the first capacity setting value and the second capacity setting value are updated respectively based on the first difference to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0153] Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed. Specifically, this includes the following: when the second difference is less than the load setting value fault tolerance rate, the first load setting value and the second load setting value are updated respectively based on the second difference to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0154] Among them, the capacity setting tolerance rate is used to represent the proportion of the range in which the capacity setting value may have an error.

[0155] Among them, the load setpoint tolerance rate is used to represent the proportion of the range in which the load setpoint may have errors.

[0156] For example, the server determines the capacity setpoint tolerance rate and load setpoint tolerance rate of the pumped storage unit to be analyzed based on manually set tolerance rate parameters. Then, the server judges a first difference based on the capacity setpoint tolerance rate. If the first difference is less than the capacity setpoint tolerance rate, the server updates the first capacity setpoint based on the first difference to obtain a first updated capacity setpoint for the pumped storage unit to be analyzed, and updates the second capacity setpoint based on the first difference to obtain a second updated capacity setpoint for the pumped storage unit to be analyzed. If the first difference is greater than or equal to the capacity setpoint tolerance rate, the server generates an early warning message for the pumped storage unit to be analyzed and... The warning information is sent to the target terminal associated with the pumped storage unit to be analyzed. Then, the server judges the second difference based on the load setpoint tolerance rate. If the second difference is less than the load setpoint tolerance rate, the server updates the first load setpoint based on the second difference to obtain the first updated load setpoint of the pumped storage unit to be analyzed, and updates the second load setpoint based on the second difference to obtain the second updated load setpoint of the pumped storage unit to be analyzed. If the second difference is greater than or equal to the load setpoint tolerance rate, the server generates a warning information for the pumped storage unit to be analyzed and sends the warning information to the target terminal associated with the pumped storage unit to be analyzed.

[0157] In this embodiment, by obtaining the capacity setpoint error rate and the load setpoint error rate, a reasonable allowable error range is set for the capacity and load parameters of the pumped storage unit during operation. This avoids frequent and unnecessary changes to the setpoints due to excessive sensitivity to minor deviations, thereby ensuring that the pumped storage unit can operate continuously in a relatively stable state.

[0158] In an exemplary embodiment, step S101, after obtaining the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed, specifically includes the following: performing verification processing on the first load setpoint, first capacity setpoint, second load setpoint, and second capacity setpoint to obtain verification results; generating early warning information for the pumped storage unit to be analyzed if the verification results meet preset conditions; and sending the early warning information to the target terminal associated with the pumped storage unit to be analyzed.

[0159] The verification result is used to indicate the verification status corresponding to the first load setting value, the first capacity setting value, the second load setting value, and the second capacity setting value.

[0160] The preset conditions refer to pre-defined judgment conditions used to judge the verification results. For example, the absolute value of the first load setting is less than or equal to the absolute value of the first capacity setting, or the absolute value of the second load setting is less than or equal to the absolute value of the second capacity setting, or the first load setting and the first capacity setting have opposite signs, or the second load setting and the second capacity setting have opposite signs. It should be noted that the preset conditions depend on the specific circumstances.

[0161] Among them, the early warning information is used to indicate that the pumped storage unit to be analyzed is abnormal.

[0162] The target terminal refers to the terminal associated with the pumped storage unit to be analyzed.

[0163] For example, the server verifies the first load setting, the first capacity setting, the second load setting, and the second capacity setting based on their respective absolute values ​​and signs, and obtains a verification result. If the verification result meets preset conditions, the server generates an early warning message for the pumped storage unit to be analyzed based on the unit identifier. Then, the server identifies the target terminal associated with the pumped storage unit to be analyzed and sends the early warning message to the target terminal through the network path between the server and the target terminal.

[0164] In this embodiment, by verifying key parameters such as the first load setting value, the first capacity setting value, the second load setting value, and the second capacity setting value, the rationality and accuracy of the pumped storage unit's load and capacity settings can be comprehensively checked, thereby enabling the pumped storage unit to maintain a stable and reliable operating state.

[0165] In an exemplary embodiment, the pumped storage unit load transfer method provided in this application further includes a training step of a pre-trained load transfer command prediction model, specifically including the following: obtaining a first sample load setpoint, a first sample capacity setpoint, a second sample load setpoint, a second sample capacity setpoint, a first sample load execution value, a first sample capacity execution value, a second sample load execution value, and a second sample capacity execution value for the sample pumped storage unit; obtaining a first sample difference based on the first sample capacity setpoint, the second sample capacity setpoint, the first sample capacity execution value, and the second sample capacity execution value; and obtaining a second sample difference based on the first sample load setpoint, the second sample load setpoint, the first sample load execution value, and the second sample load execution value; and updating the first sample capacity setpoint and the second sample capacity setpoint based on the first sample difference. The process involves obtaining the first and second updated sample capacity settings for the sample pumped storage units. Based on the second sample difference, the first and second sample load settings are updated to obtain the first and second updated sample load settings for the sample pumped storage units. These updated values ​​are then input into the load transfer command prediction model to be trained, yielding the predicted load transfer command for each sample pumped storage unit. Finally, the actual load transfer command for each sample pumped storage unit is obtained, and based on the difference between the predicted and actual load transfer commands, the load transfer command prediction model to be trained is iteratively trained to obtain a pre-trained load transfer command prediction model.

[0166] Among them, the sample pumped storage unit refers to the pumped storage unit trained on the load transfer command prediction model.

[0167] The first sample load setpoint refers to the load setpoint of the sample pumped storage unit set by the dispatching system A.

[0168] The first sample capacity setting value refers to the capacity setting value of the sample pumped storage unit set by the scheduling system A.

[0169] The second sample load setting value refers to the load setting value of the sample pumped storage unit set by the dispatching system B.

[0170] The second sample capacity setting value refers to the capacity setting value of the sample pumped storage unit set by the scheduling system B.

[0171] The first sample load execution value refers to the sample pumped storage unit load execution value set by the dispatching system A.

[0172] The first sample capacity execution value refers to the capacity execution value of the sample pumped storage unit set by the scheduling system A.

[0173] The second sample load execution value refers to the load execution value of the sample pumped storage unit set by the dispatching system B.

[0174] The second sample capacity execution value refers to the capacity execution value of the sample pumped storage unit set by the scheduling system B.

[0175] The first sample difference is used to represent the difference between the capacity setpoint and the capacity execution value of the sample pumped storage unit.

[0176] The second sample difference is used to represent the difference between the load setpoint and the load execution value of the sample pumped storage unit.

[0177] The first updated sample capacity setting value is used to represent the first capacity setting value of the sample pumped storage unit after adjustment.

[0178] The second updated sample capacity setting value is used to represent the adjusted second capacity setting value of the sample pumped storage unit.

[0179] The first updated sample load setting value is used to represent the first load setting value of the sample pumped storage unit after adjustment.

[0180] The second updated sample load setting value is used to represent the adjusted second load setting value of the sample pumped storage unit.

[0181] Among them, the predicted load transfer instruction corresponding to the sample pumped storage unit is used to represent the predicted instruction corresponding to the load transfer processing of the sample pumped storage unit.

[0182] Among them, the actual load transfer command corresponding to the sample pumped storage unit is used to represent the actual command corresponding to the load transfer processing of the sample pumped storage unit.

[0183] For example, in response to a model training instruction for a load transfer command prediction model to be trained, the server retrieves from the database a first sample load setpoint, a first sample capacity setpoint, a second sample load setpoint, a second sample capacity setpoint, a first sample load execution value, a first sample capacity execution value, a second sample load execution value, and a second sample capacity execution value for sample pumped storage units. Then, the server obtains a first sample difference based on the first sample capacity setpoint, the second sample capacity setpoint, the first sample capacity execution value, and the second sample capacity execution value, and obtains a second sample difference based on the first sample load setpoint, the second sample load setpoint, the first sample load execution value, and the second sample load execution value. Next, the server updates the first sample capacity setpoint and the second sample capacity setpoint based on the first sample difference, respectively, to obtain a first updated sample capacity setpoint and a second updated sample capacity setpoint for the sample pumped storage units. Finally, the server updates the first sample load setpoint and the second sample capacity setpoint based on the second sample difference, respectively. The two sample load setpoints are updated to obtain the first and second updated sample load setpoints for the sample pumped storage units. Then, the server inputs these values ​​into the load transfer command prediction model to be trained, obtaining the predicted load transfer command for the sample pumped storage units. Next, the server obtains the actual load transfer command for the sample pumped storage units and calculates the loss value based on the difference between the predicted and actual load transfer commands. Then, the server adjusts the model parameters of the load transfer command prediction model to be trained based on the loss value. Finally, the server retrains the load transfer command prediction model with adjusted parameters until the loss value obtained by the trained model is less than a loss value threshold. Training then stops, and this trained model is used as the pre-trained load transfer command prediction model.

[0184] In this embodiment, by pre-training the load transfer command prediction model, it is convenient to predict the target load transfer command corresponding to the pumped storage unit to be analyzed after obtaining the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value in practical applications. Moreover, the load transfer command prediction model receives new data in each iteration, and performs internal model improvement and optimization, which facilitates more effective prediction and helps to improve the prediction accuracy of the load transfer command prediction model.

[0185] In one exemplary embodiment, such as Figure 3As shown, another method for load transfer of pumped storage units is provided. Taking the application of this method to a server as an example, the method includes the following steps:

[0186] Step S301: Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed.

[0187] Step S302: Weight the first capacity setting value and the second capacity setting value to obtain a weighted capacity setting value, and weight the first capacity execution value and the second capacity execution value to obtain a weighted capacity execution value.

[0188] Step S303: Subtract the weighted capacity setting value and the weighted capacity execution value to obtain the first difference value.

[0189] Step S304: Weight the first load setting value and the second load setting value to obtain a weighted load setting value, and weight the first load execution value and the second load execution value to obtain a weighted load execution value.

[0190] Step S305: Subtract the weighted load setpoint and the weighted load execution value to obtain the second difference value.

[0191] Step S306: Obtain the capacity setpoint tolerance rate and load setpoint tolerance rate of the pumped storage unit to be analyzed.

[0192] Step S307: If the first difference is less than the capacity setting value error rate, update the first capacity setting value and the second capacity setting value according to the first difference to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0193] Step S308: If the second difference is less than the load setting value fault rate, update the first load setting value and the second load setting value according to the second difference to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0194] Step S309: Input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into the pre-trained load transfer command prediction model to obtain multiple predicted load transfer commands corresponding to the pumped storage unit to be analyzed, as well as the prediction probability of each predicted load transfer command.

[0195] Step S310: Select the predicted load transfer instruction with the highest prediction probability from each predicted load transfer instruction and use it as the target load transfer instruction.

[0196] Step S311: Based on the target load transfer instruction, perform corresponding load transfer processing on the pumped storage unit to be analyzed.

[0197] In the aforementioned load transfer method for pumped storage units, during the load transfer process, multi-dimensional data related to different aspects of the pumped storage unit under analysis is acquired. Through a series of processes such as difference processing, update processing, and model processing, the method avoids relying solely on single data points for judgment. This allows for more accurate load transfer instructions to be obtained, leading to more precise load transfer processing and improved load transfer accuracy. Furthermore, the entire process requires no manual intervention, avoiding the subjective factors and errors inherent in manual adjustments that can result in low load transfer accuracy. This further enhances the overall accuracy of load transfer for pumped storage units.

[0198] In an exemplary embodiment, to more clearly illustrate the pumped storage unit load transfer method provided in this application, the following specific embodiment will be used to describe the pumped storage unit load transfer method in detail. In one embodiment, as... Figure 4 As shown, this application also provides a control method for a pumped-storage unit. During load transfer of the pumped-storage unit, the method first acquires a first load setpoint, a first capacity setpoint, a second load setpoint, a second capacity setpoint, a first load execution value, a first capacity execution value, a second load execution value, and a second capacity execution value for the pumped-storage unit to be analyzed. Based on these values, a first difference is obtained, and a second difference is obtained. Then, based on the first difference, the first capacity setpoint and the second capacity setpoint are adjusted accordingly. The process involves updating the capacity setpoints of the pumped storage unit to be analyzed, obtaining the first and second updated capacity setpoints. Then, based on the second difference, the first and second load setpoints are updated to obtain the first and second updated load setpoints for the pumped storage unit. These updated capacity setpoints, load setpoints, and load setpoints are then input into a pre-trained load transfer command prediction model to obtain the target load transfer command for the pumped storage unit. Finally, based on the target load transfer command, the corresponding load transfer process is performed on the pumped storage unit. Specifically, this includes the following:

[0199] The pumped storage units in this scheme are managed and controlled by dispatching system A and dispatching system B. The two dispatching systems will increase or decrease the load and capacity of the pumped storage units according to their respective grid load demands. Therefore, the load transfer function will be frequently used between the two dispatching systems. The specific steps are as follows:

[0200] M1, Load Transfer Mode Startup Module: The load transfer mode is started by dispatching system A or dispatching system B, and the load setpoints and capacity setpoints before and after the transfer are set.

[0201] After the transfer: QLOG, QCOG, QLOC, QCOC.

[0202] Before the transfer: QLEG, QCEG, QLEC, QCEC.

[0203] M2, Dispatch Setpoint Analysis and Judgment Module: Judges the setpoint of the dispatch settings. If one of the following conditions is met, it exits the load transfer mode and issues an alarm. The duty officer can then re-perform the load transfer operation.

[0204] (1) The absolute value of the load setting value QLOG of the dispatching system A is greater than the absolute value of the capacity setting value QCOG of the dispatching system A, or the load setting value and capacity setting value of the dispatching system A have opposite signs.

[0205] (2) The absolute value of the load setting value QLOC of the dispatching system B is greater than the absolute value of the capacity setting value QCOC of the dispatching system B, or the load setting value and the capacity setting value of the dispatching system B have opposite signs.

[0206] Otherwise, continue with the load transfer.

[0207] M3, the module for calculating setpoints, execution values, and fault tolerance: calculates the sum of the setpoints for two scheduled loads and the sum of the execution values ​​for two scheduled loads and the values ​​before load transfer.

[0208] The sum of the two scheduling capacity settings: CAPAO = QCOG + QCOC, Equation (5)

[0209] The sum of the two scheduled capacity execution values: CAPAE = QCEG + QCEC, Equation (6)

[0210] The sum of the two dispatch load setpoints: LOADO = QLOG + QLOC, Equation (8)

[0211] The sum of the execution values ​​of the two scheduled loads: LOADE = QLEG + QLEC, Equation (9)

[0212] Among them, the capacity setting fault tolerance rate is: CAPA10 = DIFSTM / 100; the load setting fault tolerance rate is: LOAD10 = DIFSTM / 100. DIFSTM is the fault tolerance rate parameter manually set in the system screen.

[0213] M4, Fault Tolerance Analysis and Judgment Module: Calculates whether the difference between the sum of the load and capacity setpoints of the two scheduling systems and the sum of the executed values ​​is greater than the fault tolerance rate. If the difference is greater than the fault tolerance rate, the load transfer mode is exited and an alarm is triggered. The load and capacity setpoints of the two scheduling systems remain at the values ​​before the transfer, and the duty officer can perform the load transfer operation again.

[0214] If the difference is less than the fault tolerance rate, i.e. within the fault tolerance range, continue the load transfer mode and calculate the difference.

[0215] The difference between the capacity setting value and the executed value: DIFF1 = CAPAE – CAPAO, Equation (7)

[0216] The difference between the load setpoint and the executed value: DIFF2 = LOADO – LOADE, Equation (10)

[0217] M5, the setpoint calculation module after load transfer: calculates the load and capacity setpoints of the two schedulers after load transfer.

[0218] QCOG ' = QCOG + DIFF1*QCOG / (QCOG-QCOC), formula (1)

[0219] QCOC ' = QCOC + DIFF1*QCOC / (QCOG-QCOC), formula (2)

[0220] QLOG ' = QLOG + DIFF2*QLOG / (QLOG-QLOC), equation (3)

[0221] QLOC ' = QLOC + DIFF2*QLOC / (QLOG-QLOC), equation (4)

[0222] M6, load transfer calculation setpoint analysis and judgment module: judges the load and capacity setpoints of the two dispatches calculated by the load transfer program. If one of the following conditions is met, the load transfer mode is exited and an alarm is issued. The load and capacity setpoints of the two dispatches are maintained at the values ​​before the transfer, and the duty officer can re-perform the load transfer operation.

[0223] (1) The absolute value of the load setting value QLOG' of dispatching system A is greater than the absolute value of the capacity setting value QCOG' of dispatching system A, or the load and capacity setting values ​​of dispatching system A have opposite signs.

[0224] (2) The absolute value of the load setting value QLOC' of the dispatching system B is greater than the absolute value of the capacity setting value QCOC' of the dispatching system B, or the load and capacity setting values ​​of the dispatching system B have opposite signs.

[0225] Otherwise, continue with the load transfer.

[0226] M7, Load Transfer Mode End Module: After calculating the required set value according to the load transfer program, the host computer monitoring system allows the load transfer mode to end.

[0227] M8, Execute Load Transfer Calculation Result Module: Determine whether the load setpoint calculated by the load transfer is greater than the capacity setpoint. If it is greater, do not execute; if it is less than or equal to, write the load and capacity setpoints to the load and capacity execution values ​​for execution.

[0228] In the above embodiments, during the load transfer process of pumped storage units, multi-dimensional data related to different aspects of the pumped storage unit under analysis is acquired. Through a series of processes such as difference processing, update processing, and model processing, the judgment is avoided by relying solely on a single data point. This allows for a more accurate load transfer instruction to be obtained for the pumped storage unit under analysis, enabling more precise load transfer processing and improving the accuracy of load transfer. Moreover, the entire process requires no manual intervention, avoiding the subjective factors and errors inherent in manual adjustments that can lead to low load transfer accuracy. This further improves the accuracy of load transfer for pumped storage units.

[0229] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0230] Based on the same inventive concept, this application also provides a pumped storage unit load transfer device for implementing the above-mentioned pumped storage unit load transfer method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more pumped storage unit load transfer device embodiments provided below can be found in the limitations of the pumped storage unit load transfer method above, and will not be repeated here.

[0231] In one exemplary embodiment, such as Figure 5 As shown, a load transfer device for a pumped storage unit is provided, comprising: a data acquisition module 501, a difference determination module 502, a first update module 503, a second update module 504, an instruction prediction module 505, and a load transfer module 506, wherein:

[0232] The data acquisition module 501 is used to acquire the first load setpoint, the first capacity setpoint, the second load setpoint, the second capacity setpoint, the first load execution value, the first capacity execution value, the second load execution value, and the second capacity execution value of the pumped storage unit to be analyzed.

[0233] The difference determination module 502 is used to obtain a first difference based on a first capacity setting value, a second capacity setting value, a first capacity execution value, and a second capacity execution value, and to obtain a second difference based on a first load setting value, a second load setting value, a first load execution value, and a second load execution value.

[0234] The first update module 503 is used to update the first capacity setting value and the second capacity setting value according to the first difference, so as to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed.

[0235] The second update module 504 is used to update the first load setting value and the second load setting value according to the second difference, respectively, to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0236] The instruction prediction module 505 is used to input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into a pre-trained load transfer instruction prediction model to obtain the target load transfer instruction corresponding to the pumped storage unit to be analyzed.

[0237] The load transfer module 506 is used to perform corresponding load transfer processing on the pumped storage unit to be analyzed according to the target load transfer command.

[0238] In an exemplary embodiment, the instruction prediction module 505 is further configured to input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into a pre-trained load transfer instruction prediction model to obtain multiple predicted load transfer instructions corresponding to the pumped storage unit to be analyzed, as well as the prediction probability of each predicted load transfer instruction; and select the predicted load transfer instruction with the highest prediction probability from each predicted load transfer instruction as the target load transfer instruction.

[0239] In an exemplary embodiment, the difference determination module 502 is further configured to perform weighted processing on the first capacity setting value and the second capacity setting value to obtain a weighted capacity setting value, and to perform weighted processing on the first capacity execution value and the second capacity execution value to obtain a weighted capacity execution value; to perform subtraction processing on the weighted capacity setting value and the weighted capacity execution value to obtain a first difference value; to perform weighted processing on the first load setting value and the second load setting value to obtain a weighted load setting value, and to perform weighted processing on the first load execution value and the second load execution value to obtain a weighted load execution value; and to perform subtraction processing on the weighted load setting value and the weighted load execution value to obtain a second difference value.

[0240] In an exemplary embodiment, the pumped storage unit load transfer device further includes a fault tolerance rate acquisition module for acquiring the capacity setting fault tolerance rate and load setting fault tolerance rate of the pumped storage unit to be analyzed; the first update module 503 is further configured to update the first capacity setting value and the second capacity setting value according to the first difference when the first difference is less than the capacity setting fault tolerance rate, to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed; the second update module 504 is further configured to update the first load setting value and the second load setting value according to the second difference when the second difference is less than the load setting fault tolerance rate, to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

[0241] In an exemplary embodiment, the pumped storage unit load transfer device further includes an information transmission module, which is used to perform verification processing on the first load setting value, the first capacity setting value, the second load setting value, and the second capacity setting value to obtain a verification result; if the verification result meets the preset conditions, generate early warning information for the pumped storage unit to be analyzed; and send the early warning information to the target terminal associated with the pumped storage unit to be analyzed.

[0242] In an exemplary embodiment, the pumped storage unit load transfer device further includes a model training module, used to acquire a first sample load setpoint, a first sample capacity setpoint, a second sample load setpoint, a second sample capacity setpoint, a first sample load execution value, a first sample capacity execution value, a second sample load execution value, and a second sample capacity execution value of the sample pumped storage unit; to obtain a first sample difference based on the first sample capacity setpoint, the second sample capacity setpoint, the first sample capacity execution value, and the second sample capacity execution value; and to obtain a second sample difference based on the first sample load setpoint, the second sample load setpoint, the first sample load execution value, and the second sample load execution value; and to update the first sample capacity setpoint and the second sample capacity setpoint based on the first sample difference to obtain the sample pumped storage unit. The first updated sample capacity setting value and the second updated sample capacity setting value are used. Based on the second sample difference, the first sample load setting value and the second sample load setting value are updated respectively to obtain the first updated sample load setting value and the second updated sample load setting value of the sample pumped storage unit. The first updated sample capacity setting value, the second updated sample capacity setting value, the first updated sample load setting value and the second updated sample load setting value are input into the load transfer command prediction model to be trained to obtain the predicted load transfer command corresponding to the sample pumped storage unit. The actual load transfer command corresponding to the sample pumped storage unit is obtained, and the load transfer command prediction model to be trained is iteratively trained according to the difference between the predicted load transfer command and the actual load transfer command to obtain the pre-trained load transfer command prediction model.

[0243] Each module in the aforementioned pumped storage unit load transfer device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0244] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data such as load setpoints and capacity setpoints. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a load transfer method for a pumped-storage unit.

[0245] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0246] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0247] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0248] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0249] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0250] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0251] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A load transfer method for a pumped storage unit, characterized in that, The method includes: Obtain the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed; A first difference is obtained based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value; and a second difference is obtained based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value. Based on the first difference, the first capacity setting value and the second capacity setting value are updated respectively to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed. Based on the second difference, the first load setting value and the second load setting value are updated respectively to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed. The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed. According to the target load transfer command, the pumped storage unit to be analyzed is subjected to corresponding load transfer processing.

2. The method according to claim 1, characterized in that, The step of inputting the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value into a pre-trained load transfer command prediction model to obtain the target load transfer command corresponding to the pumped storage unit to be analyzed includes: The first updated capacity setting value, the second updated capacity setting value, the first updated load setting value, and the second updated load setting value are input into a pre-trained load transfer command prediction model to obtain multiple predicted load transfer commands corresponding to the pumped storage unit to be analyzed, as well as the prediction probability of each predicted load transfer command. From each predicted load transfer instruction, the predicted load transfer instruction with the highest predicted probability is selected as the target load transfer instruction.

3. The method according to claim 1, characterized in that, The step of obtaining the first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value includes: The first capacity setting value and the second capacity setting value are weighted to obtain a weighted capacity setting value, and the first capacity execution value and the second capacity execution value are weighted to obtain a weighted capacity execution value; The first difference value is obtained by subtracting the weighted capacity setting value and the weighted capacity execution value. The step of obtaining the second difference based on the first load setpoint, the second load setpoint, the first load execution value, and the second load execution value includes: The first load setting value and the second load setting value are weighted to obtain a weighted load setting value, and the first load execution value and the second load execution value are weighted to obtain a weighted load execution value; The difference between the weighted load setting value and the weighted load execution value is calculated to obtain the second difference value.

4. The method according to claim 1, characterized in that, After obtaining a first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value, and obtaining a second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value, the process further includes: Obtain the capacity setpoint tolerance rate and load setpoint tolerance rate of the pumped storage unit to be analyzed; The step of updating the first capacity setpoint and the second capacity setpoint based on the first difference to obtain the first updated capacity setpoint and the second updated capacity setpoint of the pumped storage unit to be analyzed includes: If the first difference is less than the capacity setting value error rate, the first capacity setting value and the second capacity setting value are updated according to the first difference to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed. The step of updating the first load setpoint and the second load setpoint based on the second difference to obtain the first updated load setpoint and the second updated load setpoint of the pumped storage unit to be analyzed includes: If the second difference is less than the load setting value tolerance rate, the first load setting value and the second load setting value are updated according to the second difference to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed.

5. The method according to claim 1, characterized in that, After obtaining the first load setpoint, first capacity setpoint, second load setpoint, second capacity setpoint, first load execution value, first capacity execution value, second load execution value, and second capacity execution value of the pumped storage unit to be analyzed, the following is also included: The first load setting value, the first capacity setting value, the second load setting value, and the second capacity setting value are verified to obtain the verification result; If the verification result meets the preset conditions, an early warning message is generated for the pumped storage unit to be analyzed. The warning information is sent to the target terminal associated with the pumped storage unit to be analyzed.

6. The method according to any one of claims 1 to 5, characterized in that, The pre-trained load transfer command prediction model is trained in the following manner: Obtain the first sample load setpoint, the first sample capacity setpoint, the second sample load setpoint, the second sample capacity setpoint, the first sample load execution value, the first sample capacity execution value, the second sample load execution value, and the second sample capacity execution value of the sample pumped storage unit; A first sample difference is obtained based on the first sample capacity setting value, the second sample capacity setting value, the first sample capacity execution value, and the second sample capacity execution value; and a second sample difference is obtained based on the first sample load setting value, the second sample load setting value, the first sample load execution value, and the second sample load execution value. Based on the first sample difference, the first sample capacity setting value and the second sample capacity setting value are updated respectively to obtain the first updated sample capacity setting value and the second updated sample capacity setting value of the sample pumped storage unit. Based on the second sample difference, the first sample load setting value and the second sample load setting value are updated respectively to obtain the first updated sample load setting value and the second updated sample load setting value of the sample pumped storage unit. The first updated sample capacity setting value, the second updated sample capacity setting value, the first updated sample load setting value, and the second updated sample load setting value are input into the load transfer command prediction model to be trained to obtain the predicted load transfer command corresponding to the sample pumped storage unit. Obtain the actual load transfer command corresponding to the sample pumped storage unit, and iteratively train the load transfer command prediction model to be trained based on the difference between the predicted load transfer command and the actual load transfer command to obtain the pre-trained load transfer command prediction model.

7. A load transfer device for a pumped storage unit, characterized in that, The device includes: The data acquisition module is used to acquire the first load setpoint, the first capacity setpoint, the second load setpoint, the second capacity setpoint, the first load execution value, the first capacity execution value, the second load execution value, and the second capacity execution value of the pumped storage unit to be analyzed. The difference determination module is used to obtain a first difference based on the first capacity setting value, the second capacity setting value, the first capacity execution value, and the second capacity execution value, and to obtain a second difference based on the first load setting value, the second load setting value, the first load execution value, and the second load execution value; The first update module is used to update the first capacity setting value and the second capacity setting value according to the first difference, respectively, to obtain the first updated capacity setting value and the second updated capacity setting value of the pumped storage unit to be analyzed. The second update module is used to update the first load setting value and the second load setting value according to the second difference, respectively, to obtain the first updated load setting value and the second updated load setting value of the pumped storage unit to be analyzed. The instruction prediction module is used to input the first updated capacity setting value, the second updated capacity setting value, the first updated load setting value and the second updated load setting value into a pre-trained load transfer instruction prediction model to obtain the target load transfer instruction corresponding to the pumped storage unit to be analyzed. The load transfer module is used to perform corresponding load transfer processing on the pumped storage unit to be analyzed according to the target load transfer command.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

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

Images