Power dispatching strategy determination method and device in unstable state of power system, equipment, readable storage medium and program product

Abstract

The invention relates to a power dispatching strategy determination method and device in an unstable state of a power system, equipment, a readable storage medium and a program product. The method comprises the steps that under the condition that a target power system is affected by a fire, the renewable energy generating capacity of the target power system at the current moment is acquired, and the renewable energy generating capacity is the electric quantity generated by renewable energy power generation equipment with the power generation stability affected by the fire; determining an economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy generating capacity, wherein the economic maximization power dispatching strategy comprises income information and dispatching information; the income information is used for representing the income of the target power system at the next moment, and the scheduling information is used for representing the number of thermal power generation equipment needing to execute power generation tasks of the target power system at the next moment. By adopting the method provided by the invention, the economic maximization power dispatching strategy can be determined under the condition that the power system is influenced by the fire.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for determining a power dispatching strategy in an unstable state of a power system. Background Art

[0002] As the world pays more attention to and utilizes more renewable energy, the renewable energy power generation equipment (such as wind power generation, solar power generation, etc.) in the power system is becoming more and more important.

[0003] In traditional technologies, most of them use historical data and normal operating modes to determine the economically maximized power dispatch strategy. However, this method does not take into account that the power generation stability of renewable energy equipment is often affected by many external factors, especially when natural disasters (such as fires) occur, their power generation capacity may be severely suppressed.

[0004] Therefore, there is an urgent need for a method that can determine the economically maximizing power dispatch strategy when the power system is affected by fire. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining a power dispatching strategy under an unstable power system state in response to the above-mentioned technical problems, which can determine an economically maximizing power dispatching strategy when the power system is affected by a fire.

[0006] In a first aspect, the present application provides a method for determining a power dispatching strategy in an unstable power system state, comprising:

[0007] When the target power system is affected by the fire, obtaining the renewable energy power generation of the target power system at the current moment, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0008] Determine an economic maximization power dispatching strategy for the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0009] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0010] In one of the embodiments, the economic maximization power dispatching strategy of the target power system at the next moment is determined based on the renewable energy power generation, including: determining the renewable energy load probability density information based on the renewable energy power generation and a pre-trained load probability density information prediction model, the renewable energy load probability density information is used to characterize the renewable energy power generation of the target power system at the next moment and the corresponding probability value predicted by the load probability density information prediction model; determining the economic maximization power dispatching strategy of the target power system at the next moment based on the renewable energy load probability density information.

[0011] In one embodiment, the load probability density information prediction model includes multiple sub-models trained based on multiple different quantile loss functions, and the renewable energy load probability density information is determined based on the renewable energy power generation and the pre-trained load probability density information prediction model, including: inputting the renewable energy power generation into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; and determining the renewable energy load probability density information based on the multiple coverage probability density curves.

[0012] In one of the embodiments, the renewable energy load probability density information is determined based on the multiple coverage probability density curves, including: fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; and determining the renewable energy load probability density information based on the target load probability density curve.

[0013] In one of the embodiments, the economic maximization power dispatching strategy of the target power system at the next moment is determined based on the renewable energy load probability density information, including: inputting the renewable energy load probability density information into a pre-trained power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the power dispatching determination model.

[0014] In one of the embodiments, the training method of the load probability density information prediction model includes: obtaining a training data set, which is historical power generation data collected when the target power system is affected by a fire; and training an initial load probability density information prediction model based on the training data set to obtain the load probability density information prediction model.

[0015] In a second aspect, the present application also provides a device for determining a power dispatching strategy in an unstable power system state, comprising:

[0016] an acquisition module, for acquiring the renewable energy power generation of the target power system at a current moment when the target power system is affected by a fire, the renewable energy power generation being the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0017] A determination module, used to determine the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0018] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0019] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the method described in any embodiment of the first aspect when executing the computer program.

[0020] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any one of the embodiments of the first aspect above.

[0021] In a fifth aspect, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any embodiment of the first aspect above.

[0022] The above-mentioned method, device, computer equipment, computer-readable storage medium and computer program product for determining the power dispatching strategy in an unstable power system state, when the target power system is affected by a fire, obtains the renewable energy power generation of the target power system at the current moment, and the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire; determines the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation, and the economic maximization power dispatching strategy includes revenue information and dispatching information; wherein the revenue information is used to characterize the revenue of the target power system at the next moment, and the dispatching information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks at the next moment of the target power system. The method for determining the power dispatching strategy in an unstable power system provided by the present application takes into account that the power generation stability of the renewable energy equipment is affected by the fire, causing the renewable energy power generation to become uncontrollable, and then determines the economic maximization power dispatching strategy at the next moment by the renewable energy power generation at the current moment, thereby realizing the determination of the economic maximization power dispatching strategy when the power system is affected by the fire. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0024] Figure 1 A schematic diagram of a flow chart of a method for determining a power dispatching strategy in an unstable power system state in one embodiment;

[0025] Figure 2 A flow chart of a method for determining an economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation in one embodiment;

[0026] Figure 3 A flowchart of a method for determining renewable energy load probability density information based on the renewable energy power generation and a pre-trained load probability density information prediction model in one embodiment;

[0027] Figure 4 It is a flowchart of a method for determining the renewable energy load probability density information according to the multiple coverage probability density curves in one embodiment;

[0028] Figure 5 A schematic diagram of a flow chart of a method for training a load probability density information prediction model in one embodiment;

[0029] Figure 6 A schematic flow chart of a method for determining a power dispatching strategy in an unstable power system state in another embodiment;

[0030] Figure 7 A structural block diagram of a device for determining a power dispatching strategy in an unstable power system state in one embodiment;

[0031] Figure 8 is an internal structure diagram of a computer device in one embodiment;

[0032] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] As the world pays more attention to renewable energy and the proportion of its utilization continues to increase, the renewable energy generation equipment (such as wind power generation, solar power generation, etc.) in the power system is becoming more and more important. In traditional technologies, most of them determine the economically maximized power dispatch strategy through historical data and normal operating modes. However, this method does not take into account that the power generation stability of renewable energy equipment is often affected by many external factors, especially when natural disasters (such as fires) occur, its power generation capacity may be severely suppressed.

[0035] For example, the total power generation of the power system is fixed, and the total power generation is composed of the renewable energy power generation of renewable energy power generation equipment and the thermal power generation of traditional thermal power generation equipment. Under normal circumstances, the power generation stability of renewable energy power generation equipment is relatively stable. Therefore, it is possible to determine how many traditional thermal power generation equipment are needed to work according to the renewable energy power generation to generate sufficient thermal power. However, when the power system is affected by a fire, the power generation stability of the renewable energy power generation equipment is unstable. Therefore, it is necessary to predict the renewable energy power generation of the renewable energy power generation equipment, and determine how many traditional thermal power generation equipment are needed to work after the prediction to achieve an economically maximized power dispatching strategy. In other words, there is an urgent need for a method that can determine an economically maximized power dispatching strategy when the power system is affected by a fire.

[0036] In view of this, the present application provides a method for determining a power dispatching strategy in an unstable power system state, which can determine an economically maximizing power dispatching strategy when the power system is affected by a fire.

[0037] The method for determining the power dispatch strategy under an unstable power system state provided in the present application can be executed by a computer device, which can be a terminal or a server.

[0038] In an exemplary embodiment, Figure 1 As shown, a method for determining a power dispatching strategy in an unstable state of a power system is provided, the method comprising the following steps:

[0039] Step 101: When a target power system is affected by a fire, obtain the renewable energy power generation of the target power system at a current moment.

[0040] Among them, the renewable energy power generation refers to the amount of electricity generated by renewable energy power generation equipment whose power generation stability is affected by the fire.

[0041] The power system refers to a power network composed of multiple interconnected components for generating, transmitting and distributing electric energy. The target power system refers to the power system for which the power dispatch strategy is to be determined.

[0042] Exemplarily, the target power system may include power generation equipment, substations, power transmission lines, distribution networks, control systems, and users. The power generation equipment is responsible for converting other forms of energy (such as mechanical energy, chemical energy, solar energy, wind energy, etc.) into electrical energy. The power generation equipment may include thermal power generation equipment and renewable energy power generation equipment, and the renewable energy power generation equipment may include hydropower generation equipment, wind power generation equipment, and solar power generation equipment. The substation is used to transmit the high voltage generated by the power generation equipment to users far away from the power generation site, and the voltage can also be reduced for user use. The power transmission line transmits electrical energy from the power generation equipment to the high-voltage cable or overhead line of the substation and the end user. The distribution network is used to distribute electrical energy from the substation to the end user. The control system is used to monitor and manage the operating status of the target power system, including real-time data acquisition, load scheduling, frequency control, and fault detection. The user is also the end user of the power system, including households, enterprises, industrial facilities, and public institutions.

[0043] In one possible implementation, when a target power system is affected by a fire, a computer device may obtain the renewable energy power generation of the target power system at the current moment through a control system of the target power system.

[0044] Optionally, the measurement of the above time can be set according to actual needs, and a time can be one hour, one day, or one week.

[0045] It should be noted that although the present application specifies in detail that the opportunity to obtain the renewable energy power generation of the target power system at the current moment is when the target power system is affected by a fire, in actual applications, there may also be other situations that may affect the power generation stability of the renewable energy power generation equipment in the power system.

[0046] Step 102: Determine the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation.

[0047] Among them, the economic maximization power dispatching strategy includes revenue information and dispatching information; the revenue information is used to characterize the revenue of the target power system at the next moment, and the dispatching information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0048] As mentioned above, when the target power system is affected by a fire, the power generation stability of the renewable energy power generation equipment in the target power system is poor. Therefore, it is necessary to first predict the renewable energy power generation of the renewable energy power generation equipment at the next moment to determine how many thermal power generation equipment should be in working condition at the next moment to generate electricity and make up for the renewable energy power generation to meet the electricity consumption required by users in the target power system.

[0049] In one possible implementation, the renewable energy power generation can be input into a pre-trained economic maximization power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the economic maximization power dispatching strategy determination model.

[0050] Furthermore, the maximum profit of the target power system at the next moment can be determined based on the profit information in the economic maximization power dispatching strategy, and the thermal power generation equipment in the target power system is dispatched according to the dispatching information in the economic maximization power dispatching strategy, and the corresponding thermal power generation equipment is controlled to enter the working state according to the quantity indicated by the dispatching information to perform the power generation task.

[0051] The above-mentioned method for determining the power dispatching strategy in an unstable power system state, when the target power system is affected by a fire, obtains the renewable energy power generation of the target power system at the current moment, the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire; determines the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation, the economic maximization power dispatching strategy includes revenue information and dispatching information; wherein the revenue information is used to characterize the revenue of the target power system at the next moment, and the dispatching information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks at the next moment of the target power system. The power dispatching strategy determination method provided in the present application takes into account that the power generation stability of the renewable energy equipment is affected by the fire, causing the renewable energy power generation to become uncontrollable, and then determines the economic maximization power dispatching strategy at the next moment according to the renewable energy power generation at the current moment, thereby realizing the determination of the economic maximization power dispatching strategy when the power system is affected by the fire.

[0052] In an exemplary embodiment, Figure 2 As shown, the economic maximization power dispatching strategy of the target power system at the next moment is determined according to the renewable energy power generation, including the following steps:

[0053] Step 201: Determine renewable energy load probability density information based on the renewable energy power generation and a pre-trained load probability density information prediction model.

[0054] The renewable energy load probability density information is used to characterize the renewable energy power generation of the target power system at the next moment and the corresponding probability value predicted by the load probability density information prediction model.

[0055] Optionally, the load probability density information prediction model can be a CNNs-LSTM-Attention hybrid model. Among them, CNNs can be used to extract features of the renewable energy power generation, effectively capturing the changing trend of the power generation stability of the renewable energy equipment, that is, the changing trend of the renewable energy power generation. The LSTM-Attention is used to predict the renewable energy power generation of the renewable energy equipment at the next moment, that is, the renewable energy load probability density information.

[0056] In one possible implementation, after the computer device obtains the renewable energy power generation of the target power system at the current moment, the renewable energy power generation can be input into a pre-trained load probability density information prediction model to obtain the renewable energy load probability density information output by the load probability density information prediction model.

[0057] Step 202: Determine the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy load probability density information.

[0058] In one possible implementation method, after the computer device determines the renewable energy load probability density information, the renewable energy load probability density information can be input into a pre-trained economic maximization power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the economic maximization power dispatching strategy determination model.

[0059] In an exemplary embodiment, Figure 3 As shown, the load probability density information prediction model includes multiple sub-models trained based on multiple different quantile loss functions, and the load probability density information of renewable energy is determined based on the renewable energy power generation and the pre-trained load probability density information prediction model, including the following steps:

[0060] Step 301: input the renewable energy power generation into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models.

[0061] Optionally, as described above, the multiple sub-models are trained based on multiple different quantile loss functions, so the quantiles of the multiple sub-models are not the same. That is, through the multiple sub-models, the probability value corresponding to the value of each renewable energy power generation at the next moment can be obtained, that is, the load probability density curve. For example, the value of renewable energy power generation at the next moment corresponds to three values ​​of A, B, and C, then the corresponding probability values ​​can be A1, B1, and C1, that is, the probability value of renewable energy power generation at the next moment is A1, the probability value of renewable energy power generation at the next moment is B1, and the probability value of renewable energy power generation at the next moment is C1.

[0062] In one possible implementation, after obtaining the renewable energy power generation, the computer device may input the renewable energy power generation into the multiple sub-models respectively to obtain multiple load probability density curves output by the multiple sub-models.

[0063] Step 302: Determine the renewable energy load probability density information according to the multiple coverage probability density curves.

[0064] In one possible implementation, after the computer device determines the multiple load probability density curves output by the multiple sub-models, that is, after the computing device determines the probability value corresponding to the value of each renewable energy power generation at the next moment, the coverage probability density curve can be input into a pre-trained renewable energy load probability density information determination model to obtain the renewable energy load probability density information output by the renewable energy load probability density information determination model.

[0065] In an exemplary embodiment, Figure 4 As shown, determining the renewable energy load probability density information according to the multiple coverage probability density curves includes the following steps:

[0066] Step 401: Fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve;

[0067] Step 402: Determine the renewable energy load probability density information according to the target load probability density curve.

[0068] In one possible implementation, after a computer device determines multiple load probability density curves, the multiple load probability density curves can be fitted based on a kernel density estimation algorithm to obtain a target load probability density curve. The target load probability density curve is a curve that fits the values ​​of each renewable energy power generation and the corresponding probability values.

[0069] Furthermore, the renewable energy load probability density information is determined based on the target load probability density curve. That is, the renewable energy power generation corresponding to the vertex of the target load probability density curve is determined as the renewable energy load probability density information, that is, the renewable energy power generation with the maximum probability value at the next moment.

[0070] In an exemplary embodiment, the economic maximization power dispatching strategy of the target power system at the next moment is determined based on the renewable energy load probability density information, including: inputting the renewable energy load probability density information into a pre-trained power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the power dispatching determination model.

[0071] Optionally, the power dispatch strategy determination model may be a CNNs-LSTM-Attention hybrid model.

[0072] In one possible implementation, after the computer device determines the renewable energy load probability density information, the renewable energy load probability density information can be input into a pre-trained power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the power dispatching determination model.

[0073] Furthermore, the revenue of the target power system at the next moment and the number of thermal power generation equipment required to perform power generation tasks of the target power system at the next moment are determined according to the economic maximization power dispatching strategy.

[0074] In an exemplary embodiment, Figure 5 As shown, the training method of the load probability density information prediction model includes the following steps:

[0075] Step 501: Obtain a training data set.

[0076] The training data set is historical power generation data collected when the target power system is affected by a fire;

[0077] Step 502: Train the initial load probability density information prediction model based on the training data set to obtain the load probability density information prediction model.

[0078] In an optional embodiment of the present application, in the process of training the initial load probability density information prediction model based on the training data set, a pre-constructed loss function is used to continuously optimize the model to improve the accuracy of the load probability density information prediction model obtained through training.

[0079] In an exemplary embodiment, Figure 6As shown, another method for determining a power dispatch strategy in an unstable power system state is provided, the method comprising the following steps:

[0080] Step 601: when a target power system is affected by a fire, obtain the renewable energy power generation of the target power system at the current moment, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0081] Step 602: inputting the renewable energy power generation into a plurality of sub-models trained based on a plurality of different quantile loss functions included in the load probability density information prediction model to obtain a plurality of load probability density curves output by the plurality of sub-models;

[0082] Step 603: Fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; determining the renewable energy load probability density information according to the target load probability density curve; the renewable energy load probability density information is used to characterize the renewable energy power generation of the target power system at the next moment predicted by the load probability density information prediction model and the corresponding probability value;

[0083] Step 604: input the renewable energy load probability density information into a pre-trained power dispatching strategy determination model to obtain the economic maximization power dispatching strategy of the target power system at the next moment output by the power dispatching determination model; the economic maximization power dispatching strategy includes revenue information and dispatching information; the revenue information is used to characterize the revenue of the target power system at the next moment, and the dispatching information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0084] It should be noted that the inventor of the present application has compared and analyzed the method for determining the power dispatch strategy under the unstable state of the power system provided by the present application with the traditional method. In the comparison and analysis, two indicators are used to evaluate the dispatch effectiveness and computational complexity, namely: dispatch cost loss (the difference between the cost of the power dispatch strategy and the cost of the optimal power dispatch strategy ($ / MWh)) and calculation time (iteration time of running the method once (s / iteration)). The specific experimental results can be shown in Table 1.

[0085] Table 1

[0086]

[0087] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0088] Based on the same inventive concept, the embodiment of the present application also provides a power dispatch strategy determination device for implementing the power dispatch strategy determination method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power dispatch strategy determination device embodiments provided below can refer to the limitations of the power dispatch strategy determination method above, and will not be repeated here.

[0089] In an exemplary embodiment, Figure 7 As shown, a device 700 for determining a power dispatching strategy in an unstable power system is provided, comprising: an acquisition module 701 and a determination module 702, wherein:

[0090] The acquisition module 701 is used to acquire the renewable energy power generation of the target power system at the current moment when the target power system is affected by the fire, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0091] A determination module 702 is used to determine an economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation, where the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0092] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0093] In one embodiment, the determination module 702 is specifically used to determine the renewable energy load probability density information based on the renewable energy power generation and a pre-trained load probability density information prediction model, and the renewable energy load probability density information is used to characterize the renewable energy power generation and the corresponding probability value of the target power system at the next moment predicted by the load probability density information prediction model; determine the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy load probability density information.

[0094] In one embodiment, the load probability density information prediction model includes multiple sub-models trained based on multiple different quantile loss functions, and the determination module 702 is specifically used to input the renewable energy power generation into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; and determine the renewable energy load probability density information based on the multiple coverage probability density curves.

[0095] In one embodiment, the determination module 702 is specifically used to fit the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; and determine the renewable energy load probability density information according to the target load probability density curve.

[0096] In one embodiment, the determination module 702 is specifically used to input the renewable energy load probability density information into a pre-trained power dispatch strategy determination model to obtain the economic maximization power dispatch strategy of the target power system at the next moment output by the power dispatch determination model.

[0097] In one embodiment, the acquisition module 701 is further used to acquire a training data set, where the training data set is historical power generation data collected when the target power system is affected by a fire;

[0098] The initial load probability density information prediction model is trained based on the training data set to obtain the load probability density information prediction model.

[0099] Each module in the above-mentioned device for determining the power dispatching strategy in an unstable power system state can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0100] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 8As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining a power dispatching strategy in an unstable state of a power system is implemented.

[0101] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for determining a power dispatch strategy in an unstable state of a power system is implemented.

[0102] Those skilled in the art will understand that Figure 8 or Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0103] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0104] When the target power system is affected by the fire, obtaining the renewable energy power generation of the target power system at the current moment, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0105] Determine an economic maximization power dispatching strategy for the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0106] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0107] In one embodiment, when the processor executes the computer program, the following steps are also implemented: based on the renewable energy power generation and a pre-trained load probability density information prediction model, the renewable energy load probability density information is determined, and the renewable energy load probability density information is used to characterize the renewable energy power generation and the corresponding probability value of the target power system at the next moment predicted by the load probability density information prediction model; according to the renewable energy load probability density information, the economic maximization power dispatching strategy of the target power system at the next moment is determined.

[0108] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the renewable energy power generation is input into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; and the renewable energy load probability density information is determined based on the multiple coverage probability density curves.

[0109] In one embodiment, when the processor executes the computer program, the following steps are also implemented: fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; and determining the renewable energy load probability density information based on the target load probability density curve.

[0110] In one embodiment, when the processor executes the computer program, the following steps are also implemented: the renewable energy load probability density information is input into a pre-trained power dispatch strategy determination model to obtain the economic maximization power dispatch strategy of the target power system at the next moment output by the power dispatch determination model.

[0111] In one embodiment, when the processor executes the computer program, the following steps are also implemented: obtaining a training data set, which is historical power generation data collected when the target power system is affected by a fire; and training an initial load probability density information prediction model based on the training data set to obtain the load probability density information prediction model.

[0112] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0113] When the target power system is affected by the fire, obtaining the renewable energy power generation of the target power system at the current moment, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0114] Determine an economic maximization power dispatching strategy for the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0115] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0116] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: based on the renewable energy power generation and a pre-trained load probability density information prediction model, the renewable energy load probability density information is determined, and the renewable energy load probability density information is used to characterize the renewable energy power generation and the corresponding probability value of the target power system at the next moment predicted by the load probability density information prediction model; based on the renewable energy load probability density information, the economic maximization power dispatching strategy of the target power system at the next moment is determined.

[0117] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: the renewable energy power generation is input into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; and the renewable energy load probability density information is determined based on the multiple coverage probability density curves.

[0118] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; and determining the renewable energy load probability density information based on the target load probability density curve.

[0119] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the renewable energy load probability density information is input into a pre-trained power dispatch strategy determination model to obtain the economic maximization power dispatch strategy of the target power system at the next moment output by the power dispatch determination model.

[0120] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: obtaining a training data set, which is historical power generation data collected when the target power system is affected by a fire; and training an initial load probability density information prediction model based on the training data set to obtain the load probability density information prediction model.

[0121] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0122] When the target power system is affected by the fire, obtaining the renewable energy power generation of the target power system at the current moment, where the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire;

[0123] Determine an economic maximization power dispatching strategy for the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information;

[0124] The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

[0125] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: based on the renewable energy power generation and a pre-trained load probability density information prediction model, the renewable energy load probability density information is determined, and the renewable energy load probability density information is used to characterize the renewable energy power generation and the corresponding probability value of the target power system at the next moment predicted by the load probability density information prediction model; based on the renewable energy load probability density information, the economic maximization power dispatching strategy of the target power system at the next moment is determined.

[0126] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: the renewable energy power generation is input into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; and the renewable energy load probability density information is determined based on the multiple coverage probability density curves.

[0127] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; and determining the renewable energy load probability density information based on the target load probability density curve.

[0128] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: the renewable energy load probability density information is input into a pre-trained power dispatch strategy determination model to obtain the economic maximization power dispatch strategy of the target power system at the next moment output by the power dispatch determination model.

[0129] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented: obtaining a training data set, which is historical power generation data collected when the target power system is affected by a fire; and training an initial load probability density information prediction model based on the training data set to obtain the load probability density information prediction model.

[0130] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0131] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0132] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a power dispatching strategy in an unstable power system, characterized in that: The method comprises: When the target power system is affected by the fire, obtaining the renewable energy power generation of the target power system at the current moment, wherein the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire; Determine the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information; The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

2. The method according to claim 1, characterized in that The step of determining the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy power generation includes: Determine the renewable energy load probability density information based on the renewable energy power generation and a pre-trained load probability density information prediction model, wherein the renewable energy load probability density information is used to characterize the renewable energy power generation of the target power system at the next moment predicted by the load probability density information prediction model and the corresponding probability value; An economic maximization power dispatching strategy for the target power system at the next moment is determined according to the renewable energy load probability density information.

3. The method according to claim 2, characterized in that The load probability density information prediction model includes a plurality of sub-models trained based on a plurality of different quantile loss functions, and the renewable energy load probability density information is determined based on the renewable energy power generation and the pre-trained load probability density information prediction model, including: Inputting the renewable energy power generation into the multiple sub-models to obtain multiple load probability density curves output by the multiple sub-models; The renewable energy load probability density information is determined according to the multiple coverage probability density curves.

4. The method according to claim 3, characterized in that The determining the renewable energy load probability density information according to the multiple coverage probability density curves includes: Fitting the multiple load probability density curves based on a kernel density estimation algorithm to obtain a target load probability density curve; The renewable energy load probability density information is determined according to the target load probability density curve.

5. The method according to claim 2, characterized in that: The step of determining the economic maximization power dispatching strategy of the target power system at the next moment according to the renewable energy load probability density information includes: The renewable energy load probability density information is input into a pre-trained power dispatch strategy determination model to obtain the economic maximization power dispatch strategy of the target power system at the next moment output by the power dispatch determination model.

6. The method according to claim 2, characterized in that The training method of the load probability density information prediction model includes: Acquire a training data set, wherein the training data set is historical power generation data collected when the target power system is affected by a fire; The initial load probability density information prediction model is trained based on the training data set to obtain the load probability density information prediction model.

7. A device for determining a power dispatching strategy in an unstable power system, characterized in that: The device comprises: an acquisition module, for acquiring the renewable energy power generation of the target power system at a current moment when the target power system is affected by a fire, wherein the renewable energy power generation is the amount of electricity generated by the renewable energy power generation equipment whose power generation stability is affected by the fire; A determination module, configured to determine an economic maximization power dispatching strategy of the target power system at a next moment according to the renewable energy power generation, wherein the economic maximization power dispatching strategy includes revenue information and dispatching information; The revenue information is used to characterize the revenue of the target power system at the next moment, and the scheduling information is used to characterize the number of thermal power generation equipment that needs to perform power generation tasks in the target power system at the next moment.

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

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

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

Images