Flexible power grid self-healing method, self-healing device, storage medium and program product

Abstract

The invention provides a flexible power grid self-healing method, a self-healing device, a storage medium and a program product. The method comprises the steps of obtaining target basic data; inputting the target basic data into a knowledge base model to obtain first target state data; determining a target self-healing strategy at least according to the first target state data; and executing the target self-healing strategy. The method solves the problem that the power equipment newly added into the power grid easily causes the fault of the power grid and cannot be self-healed.

Description

Technical Field

[0001] The present invention relates to the field of flexible power grid self-healing technology, and in particular to a flexible power grid self-healing method, a flexible power grid self-healing device, a computer-readable storage medium, and a computer program product. Background Art

[0002] In recent years, new equipment (power electronic devices) have been widely used in power systems. However, when new equipment is connected to the grid, the interaction between its dynamic response and other equipment will cause instability. This is because the dynamic characteristics of the equipment may not match the characteristics of other equipment in the system, which will cause oscillations in the operating state of the power grid. When new equipment is connected to the grid, it may be affected by external factors such as system load changes and voltage fluctuations. These factors will cause oscillations within the operating state of the power grid, which will lead to power grid failures and the inability to self-heal.

[0003] Currently, there is no solution to the above problem. Summary of the invention

[0004] The main purpose of the present application is to provide a flexible power grid self-healing method, a flexible power grid self-healing device, a computer-readable storage medium and a computer program product, so as to at least solve the problem that new power equipment added to the power grid is prone to cause power grid failure and cannot self-heal.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a flexible power grid self-healing method is provided, the method comprising: obtaining target basic data, the target basic data being the basic data of the power grid in a predetermined time period, the basic data comprising: a plurality of operating parameter values ​​after averaging of the first power equipment, a plurality of operating parameter values ​​after averaging of the second power equipment, a plurality of operating parameter values ​​after averaging of the grid connection point, and a meteorological data value after averaging, the first power equipment being the power equipment connected to the power grid before a predetermined time node, the second power equipment being the power equipment connected to the power grid after the predetermined time node, and the predetermined time node being prior to the starting point of the predetermined time period; inputting the target basic data into a knowledge base model to obtain first target state data, the knowledge base The model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data, status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, the first target state data is the state data of the power grid in the predetermined period; at least based on the first target state data, a target self-healing strategy is determined, the target self-healing strategy is the self-healing strategy of the power grid in the predetermined period, and the self-healing strategy is a strategy for the power grid to automatically restore normal operating status; and the target self-healing strategy is executed.

[0006] Optionally, a target self-healing strategy is determined at least based on the first target state data, including: inputting the target basic data into a power grid operation state prediction model to obtain second target state data, the power grid operation state prediction model is obtained by training a neural network using the multiple groups of first training data, and the second target state data is the state data of the power grid in the predetermined time period; determining the target self-healing strategy based on the first target state data and the second target state data.

[0007] Optionally, determining the target self-healing strategy according to the first target state data and the second target state data includes: determining a first target feature vector according to the first target state data and a predetermined mapping relationship, and determining a second target feature vector according to the second target state data and the predetermined mapping relationship, the predetermined mapping relationship being a mapping relationship between the state data and a feature vector, the feature vector including a plurality of fault state values, one of the fault state values ​​being a numerical value characterizing the severity of the fault state of the power grid, the fault state value being proportional to the severity of the fault state of the power grid, the first target feature vector being the feature vector corresponding to the first target state data in the predetermined mapping relationship, and the second target feature vector being the feature vector corresponding to the second target state data in the predetermined mapping relationship; performing weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector; inputting the third target feature vector into a self-healing means determination model to obtain the target self-healing strategy, the self-healing means determination model being obtained by training a neural network using a plurality of sets of third training data, each set of the third training data obtaining at least the feature vector and the self-healing strategy in a historical period.

[0008] Optionally, performing weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector includes: determining the third target feature vector according to the first target feature vector, the second target feature vector and E=aM+bN, where E is the third target feature vector, a is a first weight coefficient, M is the first target feature vector, b is a second weight coefficient, N is the second target feature vector, and a+b=1.

[0009] Optionally, before inputting the target basic data into the knowledge base model to obtain the first target state data, the method also includes: determining an initial knowledge inference rule based on the basic data of the historical period and the state data of the historical period, wherein the initial knowledge inference rule is a mapping relationship between the basic data and the state data; and constructing a Petri net model based on the initial knowledge inference rule to obtain the knowledge base model.

[0010] Optionally, after inputting the third target feature vector into the self-healing means determination model to obtain the target self-healing strategy, the method further includes: updating the knowledge base model based on the target basic data and the third target feature vector.

[0011] Optionally, based on the target basic data and the third target feature vector, the knowledge base model is updated, including: determining third target state data according to the third target feature vector and the predetermined mapping relationship, the third target state data being the state data corresponding to the third target feature vector in the predetermined mapping relationship; determining an update knowledge inference rule according to the target basic data and the third target state data, the update knowledge inference rule being the mapping relationship between the basic data and the state data; and reconstructing the Petri net model according to the update knowledge inference rule to obtain the knowledge base model.

[0012] According to another aspect of the present application, a flexible power grid self-healing device is provided, the device comprising: an acquisition unit, used to acquire target basic data, the target basic data being basic data of the power grid in a predetermined time period, the basic data comprising: multiple operating parameter values ​​after averaging of a first power device, multiple operating parameter values ​​after averaging of a second power device, multiple operating parameter values ​​after averaging of a grid connection point, and averaged meteorological data values, the first power device being a power device connected to the power grid before a predetermined time node, the second power device being a power device connected to the power grid after the predetermined time node, and the predetermined time node being prior to the starting point of the predetermined time period; an input unit, used to input the target basic data into a knowledge base model to obtain first target state data, the knowledge base model being based on multiple A Petri net model constructed by using a first training data set, wherein each of the first training data sets at least includes the following acquired during a historical period: the basic data and status data, wherein the status data includes: a plurality of fault states and a plurality of fault levels, wherein the fault states correspond to the fault levels one by one, and the fault levels are used to characterize the severity of the corresponding fault states, and the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid during the predetermined period; a first determining unit is used to determine a target self-healing strategy based on at least the first target status data, wherein the target self-healing strategy is the self-healing strategy of the power grid during the predetermined period, and the self-healing strategy is a strategy for the power grid to automatically restore to a normal operating state; and an executing unit is used to execute the target self-healing strategy.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the flexible power grid self-healing methods.

[0014] According to another aspect of the present application, a computer program product is provided, including a computer program / instruction, which implements any one of the flexible power grid self-healing methods when executed by a processor.

[0015] By applying the technical solution of the present application, after a new power device is added to a power grid, the present application obtains basic data, and then inputs the basic data into a knowledge base model to obtain status data, i.e., determines the fault status of the power grid, and then, based on the fault status, determines and executes a self-healing strategy to restore the power grid to normal operating status, thereby solving the problem that the power device newly added to the power grid is prone to cause power grid failures and is unable to self-heal. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a flexible power grid self-healing method provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram of a process of a flexible power grid self-healing method provided according to an embodiment of the present application is shown;

[0018] Figure 3 A structural block diagram of a flexible power grid self-healing device provided according to an embodiment of the present application is shown.

[0019] The above drawings include the following reference numerals:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background technology, electric power equipment newly added to the power grid is likely to cause the power grid to malfunction and be unable to self-heal. In order to solve the problem that electric power equipment newly added to the power grid is likely to cause the power grid to malfunction and be unable to self-heal, the embodiments of the present application provide a flexible power grid self-healing method, a flexible power grid self-healing device, a computer-readable storage medium and a computer program product.

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a mobile terminal of a flexible power grid self-healing method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a flexible power grid self-healing method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 2 is a flow chart of a flexible power grid self-healing method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0030] Step S201, obtaining target basic data;

[0031] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0032] Specifically, the types of operating parameter values ​​of power equipment (first power equipment and second power equipment) include: rated power value of power equipment, rated voltage value of power equipment, rated current value of power equipment, etc. The operating parameter values ​​of power equipment are used to help understand the performance and status of power equipment, so as to better manage and optimize the power grid. The types of meteorological data values ​​include: wind speed value, temperature value, humidity value, precipitation value, sunshine time, etc. Meteorological data values ​​are particularly important for the prediction and management of renewable energy (such as wind energy and solar energy) because they directly affect the generation of these energy sources and the stability of the power grid. The types of operating parameter values ​​of the grid connection point include: voltage value, current value, frequency value, power factor value, etc. of the grid connection point. These data are crucial to ensure that the newly added power equipment is safely and stably connected to the power grid. Averaging an operating parameter value refers to solving the average value of the operating parameter value of all time nodes in a predetermined period of time. Averaging a meteorological data value refers to solving the average value of the meteorological data value of all time nodes in a predetermined period of time.

[0033] Step S202, inputting the above target basic data into the knowledge base model to obtain first target state data;

[0034] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0035] Specifically, the types of fault conditions include: voltage fluctuation, frequency deviation, local overload, short circuit, etc., and the fault levels include: very serious, general, slightly serious, and normal.

[0036] In an optional solution, before the above step S202, the above method further includes:

[0037] Based on the above basic data of the above historical period and the above status data of the above historical period, determining an initial knowledge inference rule, wherein the above initial knowledge inference rule is a mapping relationship between the above basic data and the above status data;

[0038] Based on the above initial knowledge reasoning rules, a Petri net model is constructed to obtain the above knowledge base model.

[0039] Specifically, based on the basic data and status data obtained during the historical period, a Petri net model is constructed to obtain a knowledge base model, that is, a mapping relationship between the basic data and the status data is determined, and the target basic data is input into the knowledge base model to obtain the first target status data.

[0040] Step S203, determining a target self-healing strategy at least according to the first target state data;

[0041] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0042] In an optional solution, the above step S203 can be implemented as follows:

[0043] Step S2031, inputting the above target basic data into a power grid operation state prediction model to obtain second target state data, wherein the above power grid operation state prediction model is obtained by training a neural network using the above multiple sets of first training data, and the above second target state data is the above state data of the above power grid in the above predetermined time period;

[0044] Step S2032: determining the target self-healing strategy according to the first target state data and the second target state data.

[0045] Specifically, based on the basic data and status data obtained in the historical period, a deep learning network is trained to build a power grid operation status prediction model. The deep learning network is trained to determine the nonlinear relationship between the basic data and the status data through neural network learning, thereby improving the accuracy and generalization ability of the power grid operation status prediction model. The target basic data is input into the power grid operation status prediction model to obtain the second target status data.

[0046] In an optional solution, the above step S2032 may be implemented as follows:

[0047] Step S20321, determining a first target characteristic vector according to the first target state data and a predetermined mapping relationship, and determining a second target characteristic vector according to the second target state data and the predetermined mapping relationship, wherein the predetermined mapping relationship is a mapping relationship between the state data and the characteristic vector, wherein the characteristic vector includes a plurality of fault state values, wherein one fault state value is a numerical value characterizing the severity of the fault state of the power grid, and the fault state value is proportional to the severity of the fault state of the power grid, wherein the first target characteristic vector is the characteristic vector corresponding to the first target state data in the predetermined mapping relationship, and the second target characteristic vector is the characteristic vector corresponding to the second target state data in the predetermined mapping relationship;

[0048] Step S20322, performing weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector;

[0049] In an optional solution, the above step S20322 can be implemented as follows:

[0050] The third target feature vector is determined based on the first target feature vector, the second target feature vector and E=aM+bN, where E is the third target feature vector, a is the first weight coefficient, M is the first target feature vector, b is the second weight coefficient, N is the second target feature vector, and a+b=1.

[0051] Step S20323, input the above-mentioned third target feature vector into the self-healing means determination model to obtain the above-mentioned target self-healing strategy, and the above-mentioned self-healing means determination model is obtained by training a neural network with multiple groups of third training data, and each group of the above-mentioned third training data obtains at least the following features in a historical period: the above-mentioned feature vector and the above-mentioned self-healing strategy.

[0052] Specifically, the significance of converting the first target state data and the second target state data into feature vectors is to uniformly represent the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model as numerical features, providing a basis for subsequent fusion processing. The significance of assigning weights to the first target feature vector and the second target feature vector is to balance the contribution of the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model in the fusion process, ensuring that the importance of the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model are comprehensively considered.

[0053] In an optional solution, after the above step S20323, the above method further includes:

[0054] Based on the target basic data and the third target feature vector, the knowledge base model is updated.

[0055] In an optional solution, based on the target basic data and the third target feature vector, updating the knowledge base model may be implemented as follows:

[0056] Determine third target state data according to the third target feature vector and the predetermined mapping relationship, wherein the third target state data is the state data corresponding to the third target feature vector in the predetermined mapping relationship;

[0057] Determine an update knowledge inference rule according to the target basic data and the third target state data, wherein the update knowledge inference rule is a mapping relationship between the basic data and the state data;

[0058] According to the above updated knowledge reasoning rules, the Petri net model is reconstructed to obtain the above knowledge base model.

[0059] Specifically, by fusing the status data determined based on the knowledge base model and the status data determined based on the power grid operation status prediction model, the third target status data is obtained. By combining the target basic data and the above-mentioned third target status data to update the knowledge base model, the mapping relationship between the basic data and the status data can be more accurately captured, providing more reliable support for the formulation and implementation of self-healing measures, and improving the accuracy and timeliness of self-healing decisions.

[0060] Step S204: execute the above target self-healing strategy.

[0061] Through the above embodiments, the present application obtains basic data after a new power device is added to the power grid, and then inputs the basic data into a knowledge base model to obtain status data, that is, determines the fault status of the power grid, and then, based on the fault status, determines and executes a self-healing strategy to restore the power grid to normal operating status, thereby solving the problem that the power equipment newly added to the power grid is prone to cause power grid failures and cannot self-heal.

[0062] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0063] The embodiment of the present application also provides a flexible power grid self-healing device. It should be noted that the flexible power grid self-healing device of the embodiment of the present application can be used to execute the flexible power grid self-healing method provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0064] The following is an introduction to the flexible power grid self-healing device provided in the embodiments of the present application.

[0065] Figure 3 is a structural block diagram of a flexible power grid self-healing device according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0066] An acquisition unit 10 is used to acquire target basic data;

[0067] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0068] Specifically, the types of operating parameter values ​​of power equipment (first power equipment and second power equipment) include: rated power value of power equipment, rated voltage value of power equipment, rated current value of power equipment, etc. The operating parameter values ​​of power equipment are used to help understand the performance and status of power equipment, so as to better manage and optimize the power grid. The types of meteorological data values ​​include: wind speed value, temperature value, humidity value, precipitation value, sunshine time, etc. Meteorological data values ​​are particularly important for the prediction and management of renewable energy (such as wind energy and solar energy) because they directly affect the generation of these energy sources and the stability of the power grid. The types of operating parameter values ​​of the grid connection point include: voltage value, current value, frequency value, power factor value, etc. of the grid connection point. These data are crucial to ensure that the newly added power equipment is safely and stably connected to the power grid. Averaging an operating parameter value refers to solving the average value of the operating parameter value of all time nodes in a predetermined period of time. Averaging a meteorological data value refers to solving the average value of the meteorological data value of all time nodes in a predetermined period of time.

[0069] An input unit 20, used to input the above target basic data into the knowledge base model to obtain first target state data;

[0070] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0071] Specifically, the types of fault conditions include: voltage fluctuation, frequency deviation, local overload, short circuit, etc., and the fault levels include: very serious, general, slightly serious, and normal.

[0072] In an optional solution, the above device also includes:

[0073] A second determining unit is used to determine an initial knowledge inference rule based on the basic data of the historical period and the status data of the historical period, wherein the initial knowledge inference rule is a mapping relationship between the basic data and the status data;

[0074] The construction unit is used to construct a Petri net model based on the above initial knowledge reasoning rules to obtain the above knowledge base model.

[0075] Specifically, based on the basic data and status data obtained during the historical period, a Petri net model is constructed to obtain a knowledge base model, that is, a mapping relationship between the basic data and the status data is determined, and the target basic data is input into the knowledge base model to obtain the first target status data.

[0076] A first determining unit 30, configured to determine a target self-healing strategy based at least on the first target state data;

[0077] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0078] In an optional solution, the first determining unit includes:

[0079] An input module, used for inputting the above-mentioned target basic data into a power grid operation state prediction model to obtain second target state data, wherein the above-mentioned power grid operation state prediction model is obtained by training a neural network using the above-mentioned multiple groups of first training data, and the above-mentioned second target state data is the above-mentioned state data of the above-mentioned power grid in the above-mentioned predetermined time period;

[0080] The first determination module is used to determine the target self-healing strategy according to the first target state data and the second target state data.

[0081] Specifically, based on the basic data and status data obtained in the historical period, a deep learning network is trained to build a power grid operation status prediction model. The deep learning network is trained to determine the nonlinear relationship between the basic data and the status data through neural network learning, thereby improving the accuracy and generalization ability of the power grid operation status prediction model. The target basic data is input into the power grid operation status prediction model to obtain the second target status data.

[0082] In an optional solution, the above-mentioned determination module includes:

[0083] A first determination submodule is used to determine a first target characteristic vector according to the first target state data and a predetermined mapping relationship, and to determine a second target characteristic vector according to the second target state data and the predetermined mapping relationship, wherein the predetermined mapping relationship is a mapping relationship between the state data and the characteristic vector, wherein the characteristic vector includes a plurality of fault state values, wherein one of the fault state values ​​is a numerical value characterizing the severity of the fault state of the power grid, and the fault state value is proportional to the severity of the fault state of the power grid, wherein the first target characteristic vector is the characteristic vector corresponding to the first target state data in the predetermined mapping relationship, and wherein the second target characteristic vector is the characteristic vector corresponding to the second target state data in the predetermined mapping relationship;

[0084] A summing submodule, used for performing weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector;

[0085] In an optional solution, the above-mentioned summation submodule is used to:

[0086] The third target feature vector is determined based on the first target feature vector, the second target feature vector and E=aM+bN, where E is the third target feature vector, a is the first weight coefficient, M is the first target feature vector, b is the second weight coefficient, N is the second target feature vector, and a+b=1.

[0087] An input submodule is used to input the third target feature vector into the self-healing means determination model to obtain the target self-healing strategy. The self-healing means determination model is obtained by training a neural network using multiple sets of third training data, and each set of the third training data obtains at least the feature vector and the self-healing strategy in a historical period.

[0088] Specifically, the significance of converting the first target state data and the second target state data into feature vectors is to uniformly represent the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model as numerical features, providing a basis for subsequent fusion processing. The significance of assigning weights to the first target feature vector and the second target feature vector is to balance the contribution of the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model in the fusion process, ensuring that the importance of the state data determined based on the knowledge base model and the state data determined based on the power grid operation state prediction model are comprehensively considered.

[0089] In an optional solution, the above device also includes:

[0090] An updating unit is used to update the knowledge base model based on the target basic data and the third target feature vector.

[0091] In an optional solution, the updating unit includes:

[0092] A second determination module is used to determine third target state data according to the third target feature vector and the predetermined mapping relationship, wherein the third target state data is the state data corresponding to the third target feature vector in the predetermined mapping relationship;

[0093] A third determination module is used to determine an update knowledge inference rule according to the target basic data and the third target state data, wherein the update knowledge inference rule is a mapping relationship between the basic data and the state data;

[0094] The construction module is used to reconstruct the Petri net model according to the above updated knowledge reasoning rules to obtain the above knowledge base model.

[0095] Specifically, by fusing the status data determined based on the knowledge base model and the status data determined based on the power grid operation status prediction model, the third target status data is obtained. By combining the target basic data and the above-mentioned third target status data to update the knowledge base model, the mapping relationship between the basic data and the status data can be more accurately captured, providing more reliable support for the formulation and implementation of self-healing measures, and improving the accuracy and timeliness of self-healing decisions.

[0096] The execution unit 40 is used to execute the above target self-healing strategy.

[0097] Through the above embodiments, the present application obtains basic data after a new power device is added to the power grid, and then inputs the basic data into a knowledge base model to obtain status data, that is, determines the fault status of the power grid, and then, based on the fault status, determines and executes a self-healing strategy to restore the power grid to normal operating status, thereby solving the problem that the power equipment newly added to the power grid is prone to cause power grid failures and cannot self-heal.

[0098] The flexible power grid self-healing device includes a processor and a memory. The acquisition unit, input unit, first determination unit and execution unit are stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions. The modules are all located in the same processor; or, the modules are located in different processors in any combination.

[0099] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the problem that the power equipment newly added to the power grid is prone to cause the power grid to fail and cannot be self-healed can be solved by adjusting the kernel parameters.

[0100] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0101] An embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the flexible power grid self-healing method.

[0102] Specifically, the flexible grid self-healing method includes:

[0103] Step S201, obtaining target basic data;

[0104] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0105] Step S202, inputting the above target basic data into the knowledge base model to obtain first target state data;

[0106] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0107] Step S203, determining a target self-healing strategy at least according to the first target state data;

[0108] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0109] Step S204: execute the above target self-healing strategy.

[0110] An embodiment of the present invention provides a processor, and the processor is used to run a program, wherein the flexible power grid self-healing method is executed when the program is run.

[0111] Specifically, the flexible grid self-healing method includes:

[0112] Step S201, obtaining target basic data;

[0113] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0114] Step S202, inputting the above target basic data into the knowledge base model to obtain first target state data;

[0115] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0116] Step S203, determining a target self-healing strategy at least according to the first target state data;

[0117] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0118] Step S204: execute the above target self-healing strategy.

[0119] An embodiment of the present invention provides a device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, at least the following steps are implemented:

[0120] Step S201, obtaining target basic data;

[0121] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0122] Step S202, inputting the above target basic data into the knowledge base model to obtain first target state data;

[0123] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0124] Step S203, determining a target self-healing strategy at least according to the first target state data;

[0125] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0126] Step S204: execute the above target self-healing strategy.

[0127] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program for initializing at least the following method steps:

[0128] Step S201, obtaining target basic data;

[0129] The above target basic data are basic data of the power grid in a predetermined period of time, and the above basic data include: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values. The above first power equipment is the power equipment connected to the power grid before the predetermined time node, and the above second power equipment is the power equipment connected to the power grid after the predetermined time node. The predetermined time node is prior to the starting point of the predetermined period of time.

[0130] Step S202, inputting the above target basic data into the knowledge base model to obtain first target state data;

[0131] The knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and status data acquired in a historical period, the status data includes: multiple fault states and multiple fault levels, the fault states correspond to the fault levels one by one, the fault levels are used to characterize the severity of the corresponding fault states, the fault levels are proportional to the severity of the corresponding fault states, and the first target status data is the status data of the power grid in the predetermined period;

[0132] Step S203, determining a target self-healing strategy at least according to the first target state data;

[0133] The above-mentioned target self-healing strategy is the self-healing strategy of the above-mentioned power grid in the above-mentioned predetermined period, and the above-mentioned self-healing strategy is a strategy for the above-mentioned power grid to automatically restore the normal operating state;

[0134] Step S204: execute the above target self-healing strategy.

[0135] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0136] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0137] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0138] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0139] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0140] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0141] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0142] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0143] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0144] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0145] 1) In the flexible power grid self-healing method of the present application, after a new power device is added to the power grid, the present application obtains basic data, and then inputs the basic data into a knowledge base model to obtain status data, that is, determines the fault status of the power grid, and then, based on the fault status, determines and executes a self-healing strategy to restore the power grid to normal operating status, thereby solving the problem that the power equipment newly added to the power grid is prone to cause power grid failures and cannot self-heal.

[0146] 2) In the flexible power grid self-healing device of the present application, after the new power equipment is added to the power grid, the present application obtains basic data, and then inputs the basic data into the knowledge base model to obtain status data, that is, determines the fault state of the power grid, and then, according to the fault state, determines and executes the self-healing strategy to restore the power grid to normal operating state, thereby solving the problem that the power equipment newly added to the power grid is prone to cause power grid failures and cannot self-heal.

[0147] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A flexible power grid self-healing method, characterized in that: The method comprises: Obtaining target basic data, the target basic data is basic data of the power grid in a predetermined time period, the basic data including: averaged multiple operating parameter values ​​of the first power equipment, averaged multiple operating parameter values ​​of the second power equipment, averaged multiple operating parameter values ​​of the grid connection point, and averaged meteorological data values, the first power equipment is the power equipment connected to the power grid before a predetermined time node, the second power equipment is the power equipment connected to the power grid after the predetermined time node, and the predetermined time node is prior to the starting point of the predetermined time period; Inputting the target basic data into a knowledge base model to obtain first target state data, wherein the knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and state data acquired in a historical period, wherein the state data includes: multiple fault states and multiple fault levels, wherein the fault states correspond to the fault levels one by one, and the fault levels are used to characterize the severity of the corresponding fault states, and the fault levels are proportional to the severity of the corresponding fault states, and the first target state data is the state data of the power grid in the predetermined period; Determining a target self-healing strategy based at least on the first target state data, the target self-healing strategy being a self-healing strategy of the power grid during the predetermined period, the self-healing strategy being a strategy for the power grid to automatically restore to a normal operating state; The target self-healing strategy is executed.

2. The method according to claim 1, characterized in that: Determining a target self-healing strategy based at least on the first target state data includes: Inputting the target basic data into a power grid operation state prediction model to obtain second target state data, wherein the power grid operation state prediction model is obtained by training a neural network using the multiple sets of first training data, and the second target state data is the state data of the power grid in the predetermined time period; The target self-healing strategy is determined according to the first target state data and the second target state data.

3. The method according to claim 2, characterized in that Determining the target self-healing strategy according to the first target state data and the second target state data includes: Determine a first target feature vector according to the first target state data and a predetermined mapping relationship, and determine a second target feature vector according to the second target state data and the predetermined mapping relationship, wherein the predetermined mapping relationship is a mapping relationship between the state data and a feature vector, wherein the feature vector includes a plurality of fault state values, wherein one fault state value is a numerical value characterizing the severity of the fault state of the power grid, and the fault state value is proportional to the severity of the fault state of the power grid, wherein the first target feature vector is the feature vector corresponding to the first target state data in the predetermined mapping relationship, and wherein the second target feature vector is the feature vector corresponding to the second target state data in the predetermined mapping relationship; Performing a weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector; The third target feature vector is input into a self-healing means determination model to obtain the target self-healing strategy, wherein the self-healing means determination model is obtained by training a neural network using multiple groups of third training data, and each group of the third training data obtains at least the following from a historical period: the feature vector and the self-healing strategy.

4. The method according to claim 3, characterized in that Performing a weighted summation on the first target feature vector and the second target feature vector to obtain a third target feature vector, comprising: The third target feature vector is determined according to the first target feature vector, the second target feature vector and E=aM+bN, where E is the third target feature vector, a is the first weight coefficient, M is the first target feature vector, b is the second weight coefficient, N is the second target feature vector, and a+b=1.

5. The method according to claim 1, characterized in that Before inputting the target basic data into the knowledge base model to obtain the first target state data, the method further includes: Based on the basic data of the historical period and the status data of the historical period, determining an initial knowledge inference rule, wherein the initial knowledge inference rule is a mapping relationship between the basic data and the status data; Based on the initial knowledge reasoning rules, a Petri net model is constructed to obtain the knowledge base model.

6. The method according to claim 3, characterized in that After inputting the third target feature vector into the self-healing means determination model to obtain the target self-healing strategy, the method further includes: Based on the target basic data and the third target feature vector, the knowledge base model is updated.

7. The method according to claim 6, characterized in that Based on the target basic data and the third target feature vector, updating the knowledge base model includes: Determine third target state data according to the third target feature vector and the predetermined mapping relationship, wherein the third target state data is the state data corresponding to the third target feature vector in the predetermined mapping relationship; Determine an update knowledge inference rule according to the target basic data and the third target state data, wherein the update knowledge inference rule is a mapping relationship between the basic data and the state data; According to the updated knowledge reasoning rule, the Petri net model is reconstructed to obtain the knowledge base model.

8. A flexible power grid self-healing device, characterized in that: The device comprises: an acquisition unit, configured to acquire target basic data, wherein the target basic data is basic data of the power grid in a predetermined period of time, and the basic data includes: multiple operating parameter values ​​of the first power equipment after average processing, multiple operating parameter values ​​of the second power equipment after average processing, multiple operating parameter values ​​of the grid connection point after average processing, and meteorological data values ​​after average processing, wherein the first power equipment is a power equipment connected to the power grid before a predetermined time node, and the second power equipment is a power equipment connected to the power grid after the predetermined time node, and the predetermined time node is prior to the starting point of the predetermined period of time; An input unit, used for inputting the target basic data into a knowledge base model to obtain first target state data, wherein the knowledge base model is a Petri net model constructed based on multiple groups of first training data, each group of the first training data at least includes: the basic data and state data acquired in a historical period, wherein the state data includes: multiple fault states and multiple fault levels, wherein the fault states correspond to the fault levels one by one, and the fault levels are used to characterize the severity of the corresponding fault states, and the fault levels are proportional to the severity of the corresponding fault states, and the first target state data is the state data of the power grid in the predetermined period; A first determining unit, configured to determine a target self-healing strategy based at least on the first target state data, wherein the target self-healing strategy is a self-healing strategy of the power grid in the predetermined period, and the self-healing strategy is a strategy for the power grid to automatically restore a normal operating state; An execution unit is used to execute the target self-healing strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the flexible power grid self-healing method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the flexible power grid self-healing method described in any one of claims 1 to 7 is implemented.

Images