Electric power cooperative reasoning scheduling method and system of electric power intelligent center platform

Abstract

The embodiment of the invention provides an electric power cooperative reasoning scheduling method and system of an electric power smart center platform, and belongs to the technical field of electric power reasoning scheduling. The electric power collaborative reasoning scheduling method comprises the following steps: acquiring electric power equipment of a transformer substation; constructing a digital twinborn model of the transformer substation according to the power equipment of the transformer substation, and synchronizing the real-time data of the power equipment of the current transformer substation to the digital twinborn model; a digital twin model of a transformer substation is constructed according to power equipment of the transformer substation, real-time simulation operation can be carried out on the power equipment of the transformer substation, meanwhile, a power collaborative reasoning scheduling model is constructed, and real-time operation data is input into the power collaborative reasoning scheduling model to obtain an optimal solution of power scheduling. And then inputting into the digital twinborn model for simulation operation, so that the feasibility and effect of the optimal scheduling scheme can be effectively verified.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power reasoning and scheduling, and specifically to an electric power collaborative reasoning and scheduling method and system for an electric power intelligent central platform. Background Art

[0002] In today's era of growing energy demand and increasingly complex power networks, the power dispatching and control center, as a core component of the smart grid, plays a role in ensuring the safe and reliable operation of the power system. It is not only the central brain for information aggregation and decision output in the power system, but also the key to achieving optimal allocation of power resources and ensuring safe and stable operation of the power grid.

[0003] At present, power inference dispatch, also known as power forecasting, is mostly carried out by training models. However, limited data means that the power dispatch model still has certain errors, which leads to low power forecasting accuracy and low reliability of power dispatching.

[0004] The inventors of the present application discovered during the process of implementing the present invention that the above-mentioned solution in the prior art has the defect of poor reliability of power dispatching. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for collaborative reasoning and scheduling of electric power for an electric power intelligent central platform, which has the function of high reliability of electric power scheduling.

[0006] In order to achieve the above objectives, an embodiment of the present invention provides a power collaborative reasoning and scheduling method for a power intelligence central platform, comprising:

[0007] Obtaining power equipment from substations;

[0008] Building a digital twin model of the substation according to the power equipment of the substation, and synchronizing the real-time data of the power equipment of the substation into the digital twin model;

[0009] Obtaining the power collaborative reasoning scheduling model;

[0010] Obtaining real-time operating data of the digital twin model;

[0011] Obtaining an optimal solution for power dispatching according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatching model;

[0012] The optimal solution for power dispatching is input into the digital twin model.

[0013] Optionally, obtaining the power collaborative reasoning scheduling model includes:

[0014] Acquiring historical data of power equipment of the substation;

[0015] Construct a power collaborative reasoning dispatch model;

[0016] The historical data is used to train the power collaborative reasoning scheduling model.

[0017] Optionally, the historical data includes power output type, date and output power.

[0018] Optionally, the power output types include household electricity and industrial electricity.

[0019] Optionally, obtaining the optimal solution for power dispatch according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatch model includes:

[0020] Inputting the real-time operation data of the digital twin model into the power collaborative reasoning scheduling model;

[0021] Obtaining a predicted value of domestic electricity consumption and a predicted value of industrial electricity consumption of the substation;

[0022] According to formula (1), the power forecast value of the substation is obtained.

[0023] P z =P1+P2, (1)

[0024] Among them, P z is the predicted value of power consumption of the substation, P1 is the predicted value of domestic power consumption of the substation, and P2 is the predicted value of industrial power consumption of the substation;

[0025] According to formula (2), the predicted peak value of the power of the substation is obtained.

[0026] P max =τ1·P1+τ2·P2, (2)

[0027] Among them, P max is the predicted peak value of electricity consumption, τ1 is the threshold coefficient of the predicted value of domestic electricity consumption of the substation, and τ2 is the threshold coefficient of the predicted value of industrial electricity consumption of the substation;

[0028] The power output is distributed according to the power forecast value and the power forecast peak value of the substation.

[0029] Optionally, allocating power output according to the power forecast value and power forecast peak value of the substation includes:

[0030] Determine whether the predicted peak value of the power of the substation is greater than the total power value;

[0031] In the case where it is determined that the predicted peak value of the power of the substation is greater than the total power value, determining whether the predicted value of the power of the substation is less than or equal to the total power value;

[0032] When it is determined that the power forecast value of the substation is less than or equal to the total power value, the domestic power and industrial power of the substation are allocated, and a power risk warning is issued;

[0033] When it is determined that the power forecast value of the substation is greater than the total power value, a power shortage warning is issued;

[0034] When it is determined that the predicted peak power of the substation is less than or equal to the total power value, the domestic power and industrial power of the substation are allocated.

[0035] Optionally, obtaining the optimal solution for power dispatch according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatch model further includes:

[0036] Obtain the maximum and minimum values ​​of the domestic electricity consumption and industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year;

[0037] Obtain the average of the domestic electricity consumption and industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year;

[0038] Obtain threshold coefficients for predicted values ​​of domestic electricity consumption and threshold coefficients for predicted values ​​of industrial electricity consumption.

[0039] Optionally, the threshold coefficients for obtaining the predicted value of household electricity consumption and the threshold coefficients for obtaining the predicted value of industrial electricity consumption include:

[0040] According to formula (3), the threshold coefficient of the predicted value of the life electricity consumption of the substation is obtained.

[0041]

[0042] Among them, p max1 、p min1 The maximum and minimum values ​​of the household electricity consumption of the substation in the previous year for the preset number of days before and after the current day, The average value of the household electricity consumption of the substation for a preset number of days before and after the current day in the previous year;

[0043] According to formula (4), the threshold coefficient of the industrial power consumption prediction value of the substation is obtained.

[0044]

[0045] Among them, p max2 、p min2 is the maximum and minimum industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year, It is the average industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year.

[0046] Optionally, allocating domestic electricity and industrial electricity of the substation includes allocating in proportion.

[0047] On the other hand, the present invention also provides a power collaborative reasoning and dispatching system for a power intelligence central platform, comprising:

[0048] Digital twin module, used to build and simulate the operation of power equipment in substations;

[0049] The model training module is communicatively connected to the digital twin module and is used to call the real-time data of the digital twin module and make predictions.

[0050] Through the above-mentioned technical scheme, the power collaborative reasoning and scheduling method and system of the power intelligent central platform provided by the present invention can construct a digital twin model of the substation according to the power equipment of the substation, so as to perform real-time simulation operation of the power equipment of the substation, and at the same time construct a power collaborative reasoning and scheduling model, and input the real-time operation data into the power collaborative reasoning and scheduling model to obtain the optimal solution for power scheduling, and then input it into the digital twin model for simulation operation, so as to effectively verify the feasibility and effect of the optimal scheduling scheme; the combination of the digital twin model and the power collaborative reasoning and scheduling model can effectively improve the reliability and regulation effect of power scheduling.

[0051] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0053] Figure 1 It is a flow chart of a power collaborative reasoning and scheduling method of a power intelligence central platform according to one embodiment of the present invention;

[0054] Figure 2 It is a flowchart of training a power collaborative reasoning scheduling model in a power collaborative reasoning scheduling method of a power intelligent central platform according to one embodiment of the present invention;

[0055] Figure 3 It is a flowchart of obtaining power forecast value and power forecast peak value in the power collaborative reasoning and dispatching method of the power intelligent central platform according to one embodiment of the present invention;

[0056] Figure 4It is a flowchart of obtaining the optimal solution for power dispatching in the power collaborative reasoning dispatching method of the power intelligent central platform according to one embodiment of the present invention;

[0057] Figure 5 It is a flowchart of obtaining a threshold coefficient in a power collaborative reasoning and scheduling method of a power intelligence central platform according to one embodiment of the present invention;

[0058] Figure 6 It is a structural block diagram of the power collaborative reasoning and dispatching system of the power intelligent central platform according to one embodiment of the present invention. DETAILED DESCRIPTION

[0059] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0060] Figure 1 This is a flow chart of a method for collaborative reasoning and dispatching of electric power by an electric power intelligence hub platform according to one embodiment of the present invention. Figure 1 In the embodiment of the present invention, the power collaborative reasoning scheduling method may include:

[0061] In step S10, the power equipment of the substation is obtained. The power equipment includes transformers, circuit breakers, etc. Specifically, in one embodiment of the present invention, considering the overall topological structure characteristics of the substation, the transformer can include not only 220V, 380V, etc., but also a single substation can be used as a node to construct a substation topology model of the power grid system.

[0062] In step S11, a digital twin model of the substation is constructed based on the power equipment of the substation, and the real-time data of the power equipment of the current substation is synchronized to the digital twin model. The construction of the digital twin model of the substation may include modeling, data synchronization, real-time monitoring feedback by video, etc., which are known to those skilled in the art.

[0063] In step S12, a power collaborative reasoning scheduling model is obtained.

[0064] In step S13, real-time operation data of the digital twin model is obtained, wherein the real-time operation data may include date, power output type, and output power, etc.

[0065] In step S14, the optimal solution for power dispatch is obtained based on the real-time operation data of the digital twin model and the power collaborative reasoning dispatch model. The real-time operation data is transmitted to the power collaborative reasoning dispatch model and used as the input of the model. The model is a trained model, so the optimal solution for power dispatch can be obtained. Specifically, the optimal solution for power dispatch is also the power dispatch plan for each node / device, that is, the specific power value of each node / device.

[0066] In step S15, the optimal solution for power dispatch is input into the digital twin model. The optimal solution for power dispatch is input into the digital twin model, and the digital twin model can perform simulation operation according to the optimal solution to verify the validity of the optimal solution.

[0067] In step S10 to step S15, a digital twin model of the substation is first constructed according to the power equipment of the substation, and the real-time data simulation is run synchronously. Then, the power collaborative reasoning scheduling model is constructed and trained, and the real-time operation data of the digital twin model is input into the trained power collaborative reasoning scheduling model to obtain the predicted optimal solution for power scheduling. The predicted optimal solution for power scheduling is input into the digital twin model for simulation and operation to verify whether the predicted optimal solution is effective and reliable. At the same time, the digital twin model inputs the real-time data into the power collaborative reasoning scheduling model, so as to continuously iterate and continuously train the power collaborative reasoning scheduling model, thereby further improving the prediction accuracy of the power collaborative reasoning scheduling model.

[0068] Traditional power inference scheduling is mostly carried out by training models. However, limited data still causes certain errors in the power dispatch model, which leads to low power prediction accuracy and low reliability of power dispatch. In this embodiment of the present invention, the digital twin model is used in conjunction with the power collaborative inference scheduling model to effectively improve the reliability and regulation effect of power dispatch.

[0069] In this embodiment of the present invention, for the power collaborative reasoning scheduling model, historical power data needs to be used for training. The specific training steps can be as follows: Figure 2 Specifically, Figure 2 In the embodiment, the power collaborative reasoning scheduling method may further include:

[0070] In step S20, historical data of the power equipment of the substation is obtained. Among them, the historical data can be pre-processed as known in the art, including but not limited to Gaussian filtering, interpolation processing, etc. Specifically, the historical data may include power output type, date, and output power. Specifically, for the convenience of expression, and in order to correspond to the types of different transformers in the substation, that is, in order to directly classify the outputs of different transformers, the present invention simply divides the power output type into domestic electricity and industrial electricity. In practice, the power output type may also include commercial electricity and agricultural electricity. Further, from the perspective of the topological structure of the power system, the power output type may include the power output of each node substation.

[0071] In step S21, a power collaborative reasoning scheduling model is constructed.

[0072] In step S22, historical data is used to train the power collaborative reasoning scheduling model.

[0073] In this embodiment of the present invention, after obtaining the trained power collaborative reasoning scheduling model, it is also necessary to input the real-time operation data of the digital twin model into the power collaborative reasoning scheduling model to obtain the optimal solution for power scheduling. The specific acquisition method can be as follows: Figure 3 Specifically, Figure 3 In the embodiment, the power collaborative reasoning scheduling method may further include:

[0074] In step S30, the real-time operation data of the digital twin model is input into the power collaborative reasoning scheduling model.

[0075] In step S31, the predicted value of domestic power consumption and the predicted value of industrial power consumption of the substation are obtained. The power collaborative reasoning scheduling model may also include a domestic power consumption prediction model and an industrial power consumption prediction model.

[0076] In step S32, the power forecast value of the substation is obtained according to formula (1):

[0077] P z =P1+P2, (1)

[0078] Among them, P z P1 is the predicted value of power consumption of the substation, P2 is the predicted value of industrial power consumption of the substation. Specifically, the predicted value of power consumption may include but is not limited to the power consumption of the next day or month.

[0079] In step S33, the predicted peak power of the substation is obtained according to formula (2):

[0080] P max =τ1·P1+τ2·P2, (2)

[0081] Among them, P max is the predicted peak value of electricity consumption, τ1 is the threshold coefficient of the predicted value of domestic electricity consumption of the substation, and τ2 is the threshold coefficient of the predicted value of industrial electricity consumption of the substation.

[0082] In step S34, the power output is allocated according to the power forecast value and the power forecast peak value of the substation.

[0083] In step S30 to step S34, after the real-time operation data of the digital twin model is input into the power collaborative reasoning scheduling model, the predicted value of domestic electricity consumption and the predicted value of industrial electricity consumption can be obtained. According to the predicted values ​​of the two, the power prediction value and the predicted peak value of the substation are obtained respectively. Specifically, the power prediction value is the sum of the predicted value of domestic electricity consumption and the predicted value of industrial electricity consumption, while the predicted peak value of power consumption fully considers the power fluctuation and pre-stores the power threshold, thereby effectively ensuring the reliability of the substation operation.

[0084] In this embodiment of the present invention, after obtaining the power forecast value and the power forecast peak value, it is necessary to compare the two with the total power value. The specific comparison step can be as follows: Figure 4 Specifically, Figure 4 In the embodiment, the power collaborative reasoning scheduling method may further include:

[0085] In step S40, it is determined whether the predicted peak power of the substation is greater than the total power value. In the substation digital twin model, the total power value may include the total power delivered to the substation, and in the power system digital twin model, the total power value may include the total power generation of the power system, etc.

[0086] In step S41, when it is determined that the predicted power peak value of the substation is greater than the total power value, it is determined whether the predicted power value of the substation is less than or equal to the total power value. If the predicted power peak value is greater than the total power value, it means that the current total power value cannot meet the reliable power dispatching. The specific dispatching strategy to be adopted also needs to compare the predicted power value with the total power value.

[0087] In step S42, when it is determined that the predicted power value of the substation is less than or equal to the total power value, the domestic power and industrial power of the substation are allocated, and a power risk warning is issued. If the predicted power value of the substation is less than or equal to the total power value, it means that the power value is barely meeting the power output demand, and the power output of the substation can be allocated according to the existing total power value. At the same time, considering the possible abnormality, a power risk warning can be issued. Specifically, after the warning is issued, the possibility of risk occurrence can be further evaluated, and then it can be determined whether the total power value of the substation needs to be increased.

[0088] In step S43, when it is determined that the power forecast value of the substation is greater than the total power value, a power shortage warning is issued. If the power forecast value is greater than the total power value, it means that the total power value of the substation does not meet the power supply demand, and additional scheduling is required to increase the total power value of the substation, so a power shortage warning can be issued.

[0089] In step S44, when it is determined that the predicted peak power of the substation is less than or equal to the total power value, the substation's domestic power and industrial power are allocated. If the predicted peak power is less than or equal to the total power value, it means that the power is sufficient and reliable power supply can be provided.

[0090] In step S40 to step S44, the predicted peak value of the power of the substation is first compared with the total power value. If the predicted peak value of the power is greater than the total power value, the predicted value of the power is further compared with the total power value to ensure the reliability of the power supply of the substation. If the predicted value of the power is less than or equal to the total power value, the domestic power and industrial power of the substation can be allocated first, otherwise an early warning of power shortage is issued. Specifically, the allocation of domestic power and industrial power of the substation can include but is not limited to a proportional allocation method.

[0091] In this embodiment of the present invention, in the process of obtaining the power forecast peak value, the threshold coefficient of the predicted value of domestic power consumption and the threshold coefficient of the predicted value of industrial power consumption are taken into consideration, and the acquisition of the two threshold coefficients can be calculated in combination with the power consumption data of previous years. The specific calculation steps can be as follows: Figure 5 Specifically, Figure 5 In the embodiment, the power collaborative reasoning scheduling method may further include:

[0092] In step S50, the maximum and minimum values ​​of the household electricity consumption and industrial electricity consumption of the substation in the preset number of days before and after the current day of the previous year are obtained. The preset number of days before and after the current day of the previous year is the same period of previous years. If the prediction unit is days, the adjacent days of the same period can be used as reference. If the prediction unit is months / time periods, the maximum and minimum values ​​within the month / time period can be used as reference.

[0093] In step S51, the average values ​​of the domestic electricity consumption and industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year are obtained.

[0094] In step S52, the threshold coefficient of the predicted value of household electricity consumption and the threshold coefficient of the predicted value of industrial electricity consumption are obtained. The calculation of the threshold coefficient of the predicted value of household electricity consumption may include:

[0095] According to formula (3), the threshold coefficient of the predicted value of the substation's domestic electricity consumption is obtained:

[0096]

[0097] Among them, p max1 、p min1 The maximum and minimum values ​​of the daily electricity consumption of the substation for the preset number of days before and after the current day in the previous year. It is the average of the residential electricity consumption of the substation for a preset number of days before and after the current day in the previous year.

[0098] The calculation of the threshold coefficient for the industrial electricity forecast value may include:

[0099] According to formula (4), the threshold coefficient of the industrial power consumption forecast value of the substation is obtained:

[0100]

[0101] Among them, p max2 、p min2 The maximum and minimum values ​​of industrial electricity consumption of the substation for the preset number of days before and after the current day in the previous year. It is the average industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year.

[0102] In step S50 to step S52, the data of the substation in the same period of previous years are first obtained, and then the threshold coefficients of the predicted value of household electricity consumption and the threshold coefficients of the predicted value of industrial electricity consumption are obtained based on the data of the same period of previous years. Specifically, in calculating the threshold coefficients of the two predicted values ​​of electricity consumption, the fluctuation range of electricity consumption in the same period of previous years is fully considered, thereby effectively improving the reliability of power dispatching of the substation.

[0103] On the other hand, the present invention also provides a power collaborative reasoning and dispatching system for a power intelligence central platform. Figure 6 As shown, the power collaborative reasoning and dispatching system may include a digital twin module and a model training module. Specifically, the module training module is Figure 6 Artificial intelligence platform in.

[0104] The digital twin module is used to build and simulate the operation of power equipment in the substation. The model training module is connected to the digital twin module to call the real-time data of the digital twin module and make predictions.

[0105] The artificial intelligence platform is responsible for providing data-driven models with simulation and analysis capabilities, which helps improve the stability and reliability of the power system. The artificial intelligence platform uses the sample library to collect structured power grid operation data and unstructured power grid data, and builds data-driven models for each digital twin based on the artificial intelligence platform training voucher, and pushes the model to the artificial intelligence reasoning platform for the digital twin model to call on demand.

[0106] The artificial intelligence platform calls the external interface of the digital twin / model (RESTful, web service, etc.) and gives the corresponding input parameters and parameter configurations of each digital twin. The digital twin starts to run the simulation, and the data acquisition unit in the artificial intelligence platform / server collects the running data of the digital twin and saves it in the database. The artificial intelligence platform extracts the running data from the database and inputs it into the data-driven model (that is, the deep neural network model), automatically evaluates the output of the deep neural network model and gives new input values ​​to the digital twin. This process is continuously iterated to train a deep neural network model.

[0107] Through the above-mentioned technical scheme, the power collaborative reasoning and scheduling method and system of the power intelligent central platform provided by the present invention can construct a digital twin model of the substation according to the power equipment of the substation, so as to perform real-time simulation operation of the power equipment of the substation, and at the same time construct a power collaborative reasoning and scheduling model, and input the real-time operation data into the power collaborative reasoning and scheduling model to obtain the optimal solution for power scheduling, and then input it into the digital twin model for simulation operation, so as to effectively verify the feasibility and effect of the optimal scheduling scheme; the combination of the digital twin model and the power collaborative reasoning and scheduling model can effectively improve the reliability and regulation effect of power scheduling.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0113] 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.

[0114] 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 tape 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.

[0115] 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.

[0116] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for coordinated power reasoning and dispatching of a power intelligence central platform, characterized in that: include: Obtaining power equipment from substations; Building a digital twin model of the substation according to the power equipment of the substation, and synchronizing the real-time data of the power equipment of the substation into the digital twin model; Obtaining the power collaborative reasoning scheduling model; Obtaining real-time operating data of the digital twin model; Obtaining an optimal solution for power dispatching according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatching model; The optimal solution for power dispatching is input into the digital twin model.

2. The power collaborative reasoning scheduling method according to claim 1 is characterized in that: Acquiring the power collaborative reasoning scheduling model includes: Acquiring historical data of power equipment of the substation; Construct a power collaborative reasoning dispatch model; The historical data is used to train the power collaborative reasoning scheduling model.

3. The power collaborative reasoning scheduling method according to claim 2 is characterized in that: The historical data includes power output type, date, and output power.

4. The power collaborative reasoning scheduling method according to claim 3 is characterized in that: The power output types include household electricity and industrial electricity.

5. The power collaborative reasoning scheduling method according to claim 4 is characterized in that: Obtaining the optimal solution for power dispatch according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatch model includes: Inputting the real-time operation data of the digital twin model into the power collaborative reasoning scheduling model; Obtaining a predicted value of domestic electricity consumption and a predicted value of industrial electricity consumption of the substation; According to formula (1), the power forecast value of the substation is obtained. P z =P1+P2, (1) Among them, P z is the predicted value of power consumption of the substation, P1 is the predicted value of domestic power consumption of the substation, and P2 is the predicted value of industrial power consumption of the substation; According to formula (2), the predicted peak value of the power of the substation is obtained. P max =τ1·P1+τ2·P2, (2) Among them, P max is the predicted peak value of electricity consumption, τ1 is the threshold coefficient of the predicted value of domestic electricity consumption of the substation, and τ2 is the threshold coefficient of the predicted value of industrial electricity consumption of the substation; The power output is distributed according to the power forecast value and the power forecast peak value of the substation.

6. The power collaborative reasoning scheduling method according to claim 5 is characterized in that: The power output is distributed according to the power forecast value and power forecast peak value of the substation, including: Determine whether the predicted peak value of the power of the substation is greater than the total power value; In the case where it is determined that the predicted peak value of the power of the substation is greater than the total power value, determining whether the predicted value of the power of the substation is less than or equal to the total power value; When it is determined that the power forecast value of the substation is less than or equal to the total power value, the domestic power and industrial power of the substation are allocated, and a power risk warning is issued; When it is determined that the power forecast value of the substation is greater than the total power value, a power shortage warning is issued; When it is determined that the predicted peak power of the substation is less than or equal to the total power value, the domestic power and industrial power of the substation are allocated.

7. The power collaborative reasoning and scheduling method according to claim 5, characterized in that: Obtaining the optimal solution for power dispatch according to the real-time operation data of the digital twin model and the power collaborative reasoning dispatch model also includes: Obtain the maximum and minimum values ​​of the domestic electricity consumption and industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year; Obtain the average of the domestic electricity consumption and industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year; Obtain threshold coefficients for predicted values ​​of domestic electricity consumption and threshold coefficients for predicted values ​​of industrial electricity consumption.

8. The power collaborative reasoning scheduling method according to claim 7 is characterized in that: The threshold coefficients for obtaining the predicted value of household electricity consumption and the threshold coefficients for obtaining the predicted value of industrial electricity consumption include: According to formula (3), the threshold coefficient of the predicted value of the life electricity consumption of the substation is obtained. Among them, p max1 、p min1 The maximum and minimum values ​​of the household electricity consumption of the substation in the previous year for the preset number of days before and after the current day, The average value of the household electricity consumption of the substation for a preset number of days before and after the current day in the previous year; According to formula (4), the threshold coefficient of the industrial power consumption prediction value of the substation is obtained. Among them, p max2 、p min2 is the maximum and minimum industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year, It is the average industrial electricity consumption of the substation for a preset number of days before and after the current day in the previous year.

9. The power collaborative reasoning scheduling method according to claim 6 is characterized in that: Allocating domestic electricity and industrial electricity of the substation includes allocating in proportion.

10. A system using the power collaborative reasoning and dispatching method according to any one of claims 1 to 9, characterized in that: include: Digital twin module, used to build and simulate the operation of power equipment in substations; The model training module is communicatively connected to the digital twin module and is used to call the real-time data of the digital twin module and make predictions.

Images