Online emergency control strategy adjustment method, device and system adaptive to power grid changes

Abstract

The application discloses an online emergency control strategy adjustment method, device and system suitable for power grid changes, and the method comprises the following steps: acquiring a power angle stability margin calculation model; in response to a signal that the amplitude of power flow change of the power grid is less than or equal to a set threshold or the topology structure of the power grid is unchanged, calculating a first power angle stability margin by using the power angle stability margin calculation model; in response to a signal that the amplitude of power flow change of the power grid is greater than the set threshold or the topology structure of the power grid is changed, calculating a second power angle stability margin by using the power angle stability margin calculation model; based on the first power angle stability margin and the second power angle stability margin, calculating a power angle stability margin difference; based on the power angle stability margin difference, modifying an emergency control amount, and performing emergency control amount checking. The application can solve the problem that the strategy table is not suitable due to the great change of the topology structure or the key injection space amount associated with the control strategy mode in the period from the decision time to the fault occurrence, and improve the accuracy and reliability of online emergency control.

Description

Technical Field

[0001] This invention belongs to the field of power system safety and stability control, and specifically relates to an online emergency control strategy adjustment method, device and system that adapts to changes in the power grid. Background Technology

[0002] Upon detecting a fault, the emergency control device for power system safety and stability executes corresponding control measures based on the emergency control strategy table, matching the grid operating mode and the fault, to ensure the safe and stable operation of the grid after a severe fault. Currently, there are two types of emergency control strategies: offline and online. Offline emergency control strategies, however, pose risks of over-control leading to uneconomical results and under-control resulting in failure to guarantee grid safety due to differences between typical offline methods and actual operating conditions. Online emergency control strategies, on the other hand, make pre-decision decisions based on the actual online operating mode, effectively improving the adaptability of the control strategy to the grid operating mode.

[0003] However, since online emergency control strategies make pre-decision decisions before a fault occurs, there is a risk of mismatch if the grid topology or key injection space quantities associated with the control strategy change significantly between the decision-making time and the fault occurrence. Simultaneously, the calculation of online stability strategies takes minutes; if a fault occurs during the period between strategy mismatch and strategy recalculation, it will cause grid safety and stability problems. Therefore, traditional online calculation methods cannot meet real-time requirements. Especially with the large-scale integration of new energy sources, the impact of strong uncertainties on grid safety and stability control is increasingly significant. Summary of the Invention

[0004] To address the aforementioned problems, this invention proposes an online emergency control strategy adjustment method, device, and system that adapts to changes in the power grid. This method can solve the problem of strategy table mismatch caused by significant changes in the power grid topology or key injection space quantities associated with the control strategy mode from the decision-making time to the fault occurrence period, thereby improving the accuracy and reliability of online emergency control.

[0005] To achieve the above-mentioned technical objectives and effects, the present invention is implemented through the following technical solution:

[0006] In a first aspect, the present invention provides an online emergency control strategy adjustment method to adapt to changes in the power grid, comprising:

[0007] Obtain the power angle stability margin calculation model;

[0008] In response to a power flow change amplitude less than or equal to a set threshold or a signal indicating no change in topology, the first power angle stability margin under the fault set is calculated using the power angle stability margin calculation model.

[0009] In response to a power flow change amplitude exceeding a set threshold or a topology change signal in the power grid, the second power angle stability margin under a preset fault set is calculated using the power angle stability margin calculation model.

[0010] The difference in power angle stability margin is calculated based on the first power angle stability margin and the second power angle stability margin.

[0011] Based on the power angle stability margin difference, modify the emergency control quantity corresponding to the second power angle stability margin, perform emergency control quantity verification, and save the emergency control quantity that can ensure the stability of the power grid.

[0012] Optionally, the input parameters of the power angle stability margin calculation model include: preset key injection space quantity, grid topology, anticipated fault set and emergency control measures quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin.

[0013] Optionally, the method for obtaining the power angle stability margin calculation model includes the following steps:

[0014] Based on the historical variation patterns of preset key injection space quantities, power grid topology, and anticipated fault sets, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0015] Online real-time data is constructed based on online data of preset key injection space quantities, power grid topology, and anticipated fault sets. Simulation analysis is then performed to derive the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0016] A neural network is constructed with preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output.

[0017] A neural network is trained using a training sample library to obtain a power angle stability margin calculation model.

[0018] Optionally, training a neural network using a training sample library to obtain a power angle stability margin calculation model includes the following steps:

[0019] Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, and the weights and thresholds of each layer;

[0020] The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

[0021] Optionally, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0022] If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity.

[0023] Repeat the verification steps until an emergency control quantity that can ensure the stability of the power grid is obtained;

[0024] The verification steps include:

[0025] Perform simulation verification on the modified emergency control values;

[0026] Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

[0027] Optionally, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0028] If the difference in power angle stability margin between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin will be used as the emergency control quantity corresponding to the second power angle stability margin.

[0029] Optionally, the online emergency control strategy adjustment method for adapting to power grid changes further includes:

[0030] Based on the obtained emergency control quantities and second power angle stability margin that enable the power grid to remain stable, the power angle stability margin calculation model is retrained.

[0031] Secondly, the present invention provides an online emergency control strategy adjustment device for adapting to changes in the power grid, comprising:

[0032] The acquisition module is used to acquire the power angle stability margin calculation model;

[0033] The first calculation module is used to calculate the first power angle stability margin under the fault set in response to a power flow change amplitude of less than or equal to a set threshold or a signal that the topology has not changed.

[0034] The second calculation module is used to calculate the second power angle stability margin under the preset fault set in response to the power flow change amplitude exceeding the set threshold or the topology change signal of the power grid.

[0035] The third calculation module is used to calculate the difference in power angle stability margin based on the first power angle stability margin and the second power angle stability margin.

[0036] The strategy adjustment module is used to modify the emergency control quantity corresponding to the second power angle stability margin based on the power angle stability margin difference, and to perform emergency control quantity verification and save the emergency control quantity that can ensure the stability of the power grid.

[0037] Optionally, the input parameters of the power angle stability margin calculation model include: preset key injection space quantity, grid topology, anticipated fault set and emergency control measures quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin.

[0038] Optionally, the method for obtaining the power angle stability margin calculation model includes the following steps:

[0039] Based on the historical variation patterns of preset key injection space quantities, power grid topology, and anticipated fault sets, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0040] Online real-time data is constructed based on online data of preset key injection space quantities, power grid topology, and anticipated fault sets. Simulation analysis is then performed to derive the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0041] A neural network is constructed with preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output.

[0042] A neural network is trained using a training sample library to obtain a power angle stability margin calculation model.

[0043] Optionally, training a neural network using a training sample library to obtain a power angle stability margin calculation model includes the following steps:

[0044] Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, and the weights and thresholds of each layer;

[0045] The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

[0046] Optionally, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0047] If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity.

[0048] Repeat the verification steps until an emergency control quantity that can ensure the stability of the power grid is obtained;

[0049] The verification steps include:

[0050] Perform simulation verification on the modified emergency control values;

[0051] Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

[0052] Optionally, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0053] If the difference in power angle stability margin between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin will be used as the emergency control quantity corresponding to the second power angle stability margin.

[0054] Optionally, the online emergency control strategy adjustment device further includes:

[0055] The model update module is used to retrain the power angle stability margin calculation model based on the obtained emergency control quantities and second power angle stability margin that enable the power grid to remain stable.

[0056] Thirdly, the present invention provides an online emergency control strategy adjustment system that adapts to changes in the power grid, including a processor and a storage medium;

[0057] The storage medium is used to store instructions;

[0058] The processor is configured to operate according to the instructions to perform the steps of the method according to any one of the first aspects.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0060] In existing technologies, when a sudden change occurs in the power grid, a complete online calculation process involving re-estimation of the grid state, generation of mode data, and search for stability strategies is performed, taking approximately 5 minutes. Therefore, there are instances where the power grid's safety and stability control strategies become inapplicable for at least several minutes. To address this, this invention employs a data-driven method to construct a rapid generation model for the power grid's transient power angle stability margin. Using key injection space quantities, emergency control measure quantities, grid topology, and anticipated fault sets as inputs, the model generates and verifies strategies within a short time, significantly reducing the time when power grid control strategies become inapplicable and greatly improving power grid safety and stability. Attached Figure Description

[0061] To make the content of this invention easier to understand, the invention will be further described in detail below with reference to specific embodiments and accompanying drawings, wherein:

[0062] Figure 1 This is a schematic flowchart of an online emergency control strategy adjustment method for adapting to changes in the power grid, according to an embodiment of the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the scope of protection of the invention.

[0064] The application principle of the present invention will be described in detail below with reference to the accompanying drawings.

[0065] Since online emergency control strategies make pre-decision decisions before a fault occurs, there is a risk of strategy mismatch if the grid topology or key injection space quantities associated with the control strategy change significantly between the decision-making time and the fault occurrence period. Simultaneously, the calculation of online stability strategies takes minutes; if a fault occurs during the period between strategy mismatch and strategy recalculation, it will cause grid safety and stability problems. Therefore, traditional online calculation methods cannot meet real-time requirements. Especially with the large-scale integration of new energy sources, the impact of strong uncertainties on grid safety and stability control is increasingly significant. To address this, this invention proposes an online emergency control strategy adjustment method, device, and system adapted to grid changes. This solves the problem of strategy mismatch caused by significant changes in the grid topology or key injection space quantities associated with the control strategy between the decision-making time and the fault occurrence period, improving the accuracy and reliability of online emergency control.

[0066] Example 1

[0067] This invention provides a method for adjusting an online emergency control strategy to adapt to changes in the power grid, comprising the following steps:

[0068] Step (1) Obtain the power angle stability margin calculation model;

[0069] Step (2) In response to a power flow change amplitude of less than or equal to a set threshold or a signal that the topology has not changed, the first power angle stability margin under the fault set is calculated using the power angle stability margin calculation model.

[0070] Step (3) In response to a power flow change amplitude greater than a set threshold or a topology change signal in the power grid, the second power angle stability margin under the preset fault set is calculated using the power angle stability margin calculation model.

[0071] Step (4) Calculate the power angle stability margin difference based on the first power angle stability margin and the second power angle stability margin;

[0072] Step (5) Based on the power angle stability margin difference, modify the emergency control quantity corresponding to the second power angle stability margin, and perform emergency control quantity verification, saving the emergency control quantity that ensures the stability of the power grid. In practical applications, the emergency control quantity that ensures the stability of the power grid will be sent to the control execution device;

[0073] Step (6) Based on the obtained emergency control quantity and second power angle stability margin that can keep the power grid stable, retrain the power angle stability margin calculation model.

[0074] Repeat the above steps continuously to complete the adjustment of the online emergency control strategy to adapt to changes in the power grid.

[0075] In one specific embodiment of the present invention, the input parameters of the power angle stability margin calculation model include: a preset critical injection space quantity, a grid topology, a set of anticipated faults, and an emergency control measure quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin; the method for obtaining the power angle stability margin calculation model includes the following steps:

[0076] (1.1) Based on the historical variation of the preset key injection space quantity, the power grid topology, and the set of anticipated faults, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0077] (1.2) Based on the online data of the preset key injection space quantity, the power grid topology, and the set of anticipated faults, online real-time data is constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library;

[0078] (1.3) A neural network is constructed with the preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output.

[0079] (1.4) Train the neural network using the training sample library to obtain the power angle stability margin calculation model.

[0080] The step of training a neural network using a training sample library to obtain a power angle stability margin calculation model specifically includes the following steps:

[0081] Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, the weights and thresholds of each layer; in specific implementation, the neural network can be a BP neural network, and its activation function is the tanh function;

[0082] The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

[0083] In one specific embodiment of the present invention, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0084] (5.1) If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity.

[0085] Repeat the verification steps until an emergency control quantity that can ensure the stability of the power grid is obtained;

[0086] The verification steps include:

[0087] Perform simulation verification on the modified emergency control values;

[0088] Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

[0089] (5.2) If the difference between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin is used as the emergency control quantity corresponding to the second power angle stability margin.

[0090] The following is combined Figure 1 The present invention will be described in detail with reference to a specific embodiment.

[0091] Typical scenario data constructed offline and real-time online data are used as training sample sets. The training sample sets are normalized, and the training parameters of the BP neural network are initialized. BP neural network training is then carried out, specifically:

[0092] Based on the variation law of the preset key injection space quantity in the corresponding security control deployment area, the power grid topology, and the expected fault set, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then included in the training sample library.

[0093] The existing online preset key injection space quantity, power grid topology, and expected fault set generated every 5 minutes are used to construct online real-time data, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then included in the training sample library.

[0094] A BP neural network is established using preset key injection space quantities, emergency control measure quantities, power grid topology, and anticipated fault sets as inputs, and the post-fault power angle stability margin as the output. The initial training parameters of the neural network include the number of hidden layers, the number of neurons in each hidden layer, the number of training iterations, the learning rate, the weights and thresholds of each layer, and the tanh function as the activation function. The emergency control measure quantities refer to the control quantities required after a power grid fault to ensure the safe and stable operation of the power grid. The power grid topology refers to the network structure of power stations, lines, etc., and is a known quantity.

[0095] Based on the calculation results of the initial training parameters, the error gradient descent method is used to sequentially correct the weights and thresholds of the output layer and the weights and thresholds of each hidden layer, so that the final output of the modified network can approach the expected value, and the BP neural network with final iterative optimization is obtained, which is the power angle stability margin calculation model.

[0096] When the power flow or topology of the power grid undergoes significant changes, the impact of these changes on the transient power angle stability margin of the power grid under each fault in the preset fault set is calculated, specifically including:

[0097] (A) The grid status is sensed through the Scada / PMU system. When the preset key injection space fluctuation amount > a (the value of a is set separately according to different regions) or the topology changes, the changed preset key injection space amount, grid topology, expected fault set, and emergency control amount calculated based on the cross section of the previous time when the change occurs are used as neural network inputs to calculate the corresponding grid power angle stability margin η′.

[0098] (B) Compare η' with the power angle stability margin η of the grid calculated by simulation before a significant change in the preset key injection space or topology. If the decrease value η-η'>e, where η is the power angle stability margin of the grid before the change and e is the reference value of the change (set separately according to different regions), modify the emergency control quantity. The step size of the emergency control quantity is set according to the dispatching operation experience, and the corresponding empirical value is set for each set of stability. Otherwise, the emergency control quantity calculated by the previous time segment is used. The emergency control strategy in general power systems is to disconnect the generator or load. Increasing the emergency control strategy quantity mainly refers to disconnecting the power value of the generator or load. The increase value is generally set according to experience.

[0099] (C) Perform simulation verification on the modified emergency control quantity. If the emergency control quantity can ensure the safe and stable operation of the power grid after a fault occurs, output the emergency control quantity and send it to the execution device. At the same time, add the current power grid operation status and emergency control quantity as training samples to the training samples for model training. Otherwise, proceed to step D.

[0100] (D) If the simulation verification fails, further increase the amount of security control measures and return to step C.

[0101] Example 2

[0102] Based on the same inventive concept as Embodiment 1, this embodiment of the invention provides an online emergency control strategy adjustment device that adapts to power grid changes, comprising:

[0103] The acquisition module is used to acquire the power angle stability margin calculation model;

[0104] The first calculation module is used to calculate the first power angle stability margin under the fault set in response to a power flow change amplitude of less than or equal to a set threshold or a signal that the topology has not changed.

[0105] The second calculation module is used to calculate the second power angle stability margin under the preset fault set in response to the power flow change amplitude exceeding the set threshold or the topology change signal of the power grid.

[0106] The third calculation module is used to calculate the difference in power angle stability margin based on the first power angle stability margin and the second power angle stability margin.

[0107] The strategy adjustment module is used to modify the emergency control quantity corresponding to the second power angle stability margin based on the power angle stability margin difference, and to perform emergency control quantity verification and save the emergency control quantity that can ensure the stability of the power grid.

[0108] In one specific embodiment of the present invention, the online emergency control strategy adjustment device further includes:

[0109] The model update module is used to retrain the power angle stability margin calculation model based on the obtained emergency control quantities and second power angle stability margin that enable the power grid to remain stable.

[0110] In one specific embodiment of the present invention, the input parameters of the power angle stability margin calculation model include: a preset critical injection space quantity, a grid topology, a set of anticipated faults, and an emergency control measure quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin; the method for obtaining the power angle stability margin calculation model includes the following steps:

[0111] (1.1) Based on the historical variation of the preset key injection space quantity, the power grid topology, and the set of anticipated faults, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library.

[0112] (1.2) Based on the online data of the preset key injection space quantity, the power grid topology, and the set of anticipated faults, online real-time data is constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library;

[0113] (1.3) A neural network is constructed with the preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output.

[0114] (1.4) Train the neural network using the training sample library to obtain the power angle stability margin calculation model.

[0115] The step of training a neural network using a training sample library to obtain a power angle stability margin calculation model specifically includes the following steps:

[0116] Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, the weights and thresholds of each layer; in specific implementation, the neural network can be a BP neural network, and its activation function is the tanh function;

[0117] The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

[0118] In one specific embodiment of the present invention, the method for obtaining the emergency control quantity that enables the power grid to remain stable includes:

[0119] (5.1) If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity.

[0120] Repeat the verification steps until an emergency control quantity that can ensure the stability of the power grid is obtained;

[0121] The verification steps include:

[0122] Perform simulation verification on the modified emergency control values;

[0123] Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

[0124] (5.2) If the difference between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin is used as the emergency control quantity corresponding to the second power angle stability margin.

[0125] The following is combined Figure 1 The working process of the device in the embodiments of the present invention will be described in detail below with a specific implementation method.

[0126] Typical scenario data constructed offline and real-time online data are used as training sample sets. The training sample sets are normalized, and the training parameters of the BP neural network are initialized. BP neural network training is then carried out, specifically:

[0127] Based on the variation law of the preset key injection space quantity in the corresponding security control deployment area, the power grid topology, and the expected fault set, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then included in the training sample library.

[0128] The existing online preset key injection space quantity, power grid topology, and expected fault set generated every 5 minutes are used to construct online real-time data, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then included in the training sample library.

[0129] A BP neural network is established using preset key injection space quantities, emergency control measure quantities, power grid topology, and anticipated fault sets as inputs, and the post-fault power angle stability margin as the output. The initial training parameters of the neural network include the number of hidden layers, the number of neurons in each hidden layer, the number of training iterations, the learning rate, the weights and thresholds of each layer, and the tanh function as the activation function. The emergency control measure quantities refer to the control quantities required after a power grid fault to ensure the safe and stable operation of the power grid. The power grid topology refers to the network structure of power stations, lines, etc., and is a known quantity.

[0130] Based on the calculation results of the initial training parameters, the error gradient descent method is used to sequentially correct the weights and thresholds of the output layer and the weights and thresholds of each hidden layer, so that the final output of the modified network can approach the expected value, and the BP neural network with final iterative optimization is obtained, which is the power angle stability margin calculation model.

[0131] When the power flow or topology of the power grid undergoes significant changes, the impact of these changes on the transient power angle stability margin of the power grid under each fault in the preset fault set is calculated, specifically including:

[0132] (A) The grid status is sensed through the Scada / PMU system. When the preset key injection space fluctuation amount > a (the value of a is set separately according to different regions) or the topology changes, the changed preset key injection space amount, grid topology, expected fault set, and emergency control amount calculated based on the cross section of the previous time when the change occurs are used as neural network inputs to calculate the corresponding grid power angle stability margin η′.

[0133] (B) Compare η' with the power angle stability margin η of the grid calculated by simulation before a significant change in the preset key injection space or topology. If the decrease value η-η'>e, where η is the power angle stability margin of the grid before the change and e is the reference value of the change (set separately according to different regions), modify the emergency control quantity. The step size of the emergency control quantity is set according to the dispatching operation experience, and the corresponding empirical value is set for each set of stability. Otherwise, the emergency control quantity calculated by the previous time segment is used. The emergency control strategy in general power systems is to disconnect the generator or load. Increasing the emergency control strategy quantity mainly refers to disconnecting the power value of the generator or load. The increase value is generally set according to experience.

[0134] (C) Perform simulation verification on the modified emergency control quantity. If the emergency control quantity can ensure the safe and stable operation of the power grid after a fault occurs, output the emergency control quantity and send it to the execution device. At the same time, add the current power grid operation status and emergency control quantity as training samples to the training samples for model training. Otherwise, proceed to step D.

[0135] (D) If the simulation verification fails, further increase the amount of security control measures and return to step C.

[0136] Example 3

[0137] Based on the same inventive concept as in Embodiment 1, this embodiment of the invention provides an online emergency control strategy adjustment system that adapts to changes in the power grid, including a processor and a storage medium;

[0138] The storage medium is used to store instructions;

[0139] The processor is configured to operate according to the instructions to perform the steps of the method according to any one of Embodiment 1.

[0140] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0142] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0143] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0144] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

[0145] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for adjusting an online emergency control strategy to adapt to changes in the power grid, characterized in that, include: Obtain the power angle stability margin calculation model; In response to a power flow change amplitude less than or equal to a set threshold or a signal indicating no change in topology, the first power angle stability margin under the fault set is calculated using the power angle stability margin calculation model. In response to a power flow change amplitude exceeding a set threshold or a topology change signal in the power grid, the second power angle stability margin under a preset fault set is calculated using the power angle stability margin calculation model. The difference in power angle stability margin is calculated based on the first power angle stability margin and the second power angle stability margin. Based on the power angle stability margin difference, modify the emergency control quantity corresponding to the second power angle stability margin, and perform emergency control quantity verification to save the emergency control quantity that can keep the power grid stable. The method for obtaining the power angle stability margin calculation model includes the following steps: Based on the historical variation patterns of preset key injection space quantities, power grid topology, and anticipated fault sets, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library. Online real-time data is constructed based on online data of preset key injection space quantities, power grid topology, and anticipated fault sets. Simulation analysis is then performed to derive the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library. A neural network is constructed with preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output. A neural network is trained using a training sample library to obtain a power angle stability margin calculation model.

2. The method for adjusting an online emergency control strategy to adapt to changes in the power grid according to claim 1, characterized in that, The input parameters of the power angle stability margin calculation model include: preset key injection space quantity, grid topology, anticipated fault set, and emergency control measures quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin.

3. The method for adjusting an online emergency control strategy to adapt to changes in the power grid according to claim 1, characterized in that: The process of training a neural network using a training sample library to obtain a power angle stability margin calculation model includes the following steps: Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, and the weights and thresholds of each layer; The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

4. The method for adjusting an online emergency control strategy to adapt to changes in the power grid according to claim 1, characterized in that, The method for obtaining emergency control quantities that enable the power grid to remain stable includes: If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity. Repeat the verification steps until an emergency control quantity that can keep the power grid stable is obtained; The verification steps include: Perform simulation verification on the modified emergency control values; Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

5. A method for adjusting an online emergency control strategy to adapt to changes in the power grid, as described in claim 1 or 4, characterized in that: The method for obtaining emergency control quantities that enable the power grid to remain stable includes: If the difference in power angle stability margin between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin will be used as the emergency control quantity corresponding to the second power angle stability margin.

6. The method for adjusting an online emergency control strategy to adapt to changes in the power grid according to claim 1, characterized in that: The online emergency control strategy adjustment method for adapting to power grid changes also includes: Based on the obtained emergency control quantities and second power angle stability margin that enable the power grid to remain stable, the power angle stability margin calculation model is retrained.

7. An online emergency control strategy adjustment device adapting to power grid changes, characterized in that, include: The acquisition module is used to acquire the power angle stability margin calculation model; The first calculation module is used to calculate the first power angle stability margin under the fault set in response to a power flow change amplitude of less than or equal to a set threshold or a signal that the topology has not changed. The second calculation module is used to calculate the second power angle stability margin under the preset fault set in response to the power flow change amplitude exceeding the set threshold or the topology change signal of the power grid. The third calculation module is used to calculate the difference in power angle stability margin based on the first power angle stability margin and the second power angle stability margin. The strategy adjustment module is used to modify the emergency control quantity corresponding to the second power angle stability margin based on the power angle stability margin difference, and to perform emergency control quantity verification and save the emergency control quantity that can keep the power grid stable. The method for obtaining the power angle stability margin calculation model includes the following steps: Based on the historical variation patterns of preset key injection space quantities, power grid topology, and anticipated fault sets, typical scenario data are constructed, and simulation analysis is performed to obtain the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library. Online real-time data is constructed based on online data of preset key injection space quantities, power grid topology, and anticipated fault sets. Simulation analysis is then performed to derive the corresponding power angle stability margin and emergency control measures, which are then incorporated into the training sample library. A neural network is constructed with preset key injection space quantity, emergency control measure quantity, power grid topology, and expected fault set as inputs and the power angle stability margin of the power grid after the fault as output. A neural network is trained using a training sample library to obtain a power angle stability margin calculation model.

8. The online emergency control strategy adjustment device for adapting to power grid changes according to claim 7, characterized in that, The input parameters of the power angle stability margin calculation model include: preset key injection space quantity, grid topology, anticipated fault set, and emergency control measures quantity; the output parameter of the power angle stability margin calculation model is the power angle stability margin.

9. The online emergency control strategy adjustment device for adapting to power grid changes according to claim 7, characterized in that, The process of training a neural network using a training sample library to obtain a power angle stability margin calculation model includes the following steps: Initialize the training parameters of the neural network, including the number of hidden layers, the number of neurons in the hidden layers, the number of training iterations, the learning rate, and the weights and thresholds of each layer; The error gradient descent method is used to sequentially modify the weights and thresholds of the output layer and the weights and thresholds of each hidden layer of the neural network, so that the final output value of the modified neural network is close to the expected value, thus obtaining the power angle stability margin calculation model.

10. The online emergency control strategy adjustment device for adapting to power grid changes according to claim 7, characterized in that, The method for obtaining emergency control quantities that enable the power grid to remain stable includes: If the difference between the first power angle stability margin and the second power angle stability margin is greater than the set threshold, then the emergency control quantity corresponding to the second power angle stability margin is modified to obtain the modified emergency control quantity. Repeat the verification steps until an emergency control quantity that can keep the power grid stable is obtained; The verification steps include: Perform simulation verification on the modified emergency control values; Confirm whether the power grid is in a stable state. If the power grid is in an unstable state, continue to modify the emergency control quantity.

11. An online emergency control strategy adjustment device for adapting to power grid changes according to claim 8 or 10, characterized in that, The method for obtaining emergency control quantities that enable the power grid to remain stable includes: If the difference in power angle stability margin between the first power angle stability margin and the second power angle stability margin is less than a set threshold, then the emergency control quantity corresponding to the first power angle stability margin will be used as the emergency control quantity corresponding to the second power angle stability margin.

12. The online emergency control strategy adjustment device for adapting to power grid changes according to claim 11, characterized in that, The online emergency control strategy adjustment device also includes: The model update module is used to retrain the power angle stability margin calculation model based on the obtained emergency control quantities and second power angle stability margin that enable the power grid to remain stable.

13. An online emergency control strategy adjustment system adapting to changes in the power grid, characterized in that, Including processor and storage media; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the steps of the method according to any one of claims 1-6.

Images