New energy base multi-energy complementary scheduling operation inversion correction method, device and system

Abstract

The invention discloses a new energy base multi-energy complementary scheduling operation inversion correction method, device and system, and the method comprises the steps: generating a plurality of historical working condition case sections based on the historical related data of a new energy base; performing feature recognition and extraction on each historical working condition case section to obtain corresponding historical features; generating a case library based on the historical working condition case sections and the corresponding historical features; generating a real-time working condition case section based on the real-time related data of the new energy base; performing feature recognition and extraction on the real-time working condition case section to obtain real-time features; based on the real-time features, finding out similar historical working condition case sections from a case library; and performing inversion correction based on the real-time working condition case section and the found similar historical working condition case section to obtain a final instruction value of equipment in the new energy base system. According to the method, the operation risk caused by the fact that an existing power grid dispatching operation mechanism cannot deal with instability of high-proportion new energy can be solved.

Description

Technical Field

[0001] This invention belongs to the field of power system optimization and dispatching technology, specifically relating to a method, device, and system for inversion correction of multi-energy complementary dispatching operation in new energy bases. Background Technology

[0002] To comprehensively promote the green and low-carbon development and transformation of energy, maximize the consumption of new energy sources, explore safe and stable control methods for power grids without conventional power sources, break the dependence of traditional AC power grids on conventional synchronous generator units, and study engineering and technical solutions for increasing system strength through resource allocation, coordinating and controlling grid faults, disturbances exceeding 100 milliseconds, and mutual interference between controllers using multi-timescale coordinated control technology, achieve optimized control on long time scales, friendly coordination and interaction with the main grid under the condition of high proportion of new energy bases connected to the grid, and safe and stable operation under off-grid conditions, this research has a good demonstration effect and significant practical significance for the construction of new energy systems and the innovative exploration of green and low-carbon transformation and development of power grids.

[0003] Traditional power grids rely on Automatic Generation Control (AGC), primary and secondary frequency regulation of generators to handle small fluctuations, and three lines of defense to cope with various large disturbances. However, for new power systems primarily based on renewable energy sources, the existing grid dispatching and operation mechanisms are insufficient to address the operational risks posed by the instability of high-proportion renewable energy sources. The high-proportion renewable energy base coordination and control system adopts a hierarchical architecture, achieving a combination of unified optimization, centralized coordination control, and local decentralized control. It balances control performance optimization and reliability, leveraging the flexible and rapid control characteristics of power electronic devices to achieve deep coordination, multi-directional interaction, unified coordination, and effective integration of local control. This fully utilizes the regulatory role of multiple types and objects of resources, enabling high-proportion renewable energy bases to achieve harmonious interaction with the main grid and stable operation of isolated grids. Furthermore, it can rationally utilize the ratio of internal generation to main grid power supply, achieving relatively optimized overall power supply and consumption costs, effectively solving the problem of simultaneously achieving economic efficiency, stability, and environmental friendliness in high-proportion renewable energy base projects. Summary of the Invention

[0004] To address the aforementioned issues, this invention proposes a method, device, and system for inversion correction of multi-energy complementary scheduling operation in new energy bases, which can solve the operational risks caused by the instability of high-proportion new energy sources that cannot be addressed by existing power grid scheduling operation mechanisms.

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

[0006] In a first aspect, the present invention provides a method for inversion and correction of multi-energy complementary scheduling and operation in new energy bases, comprising:

[0007] Based on historical data from the new energy base system, several historical operating condition case sections are generated.

[0008] Feature identification and extraction are performed on cross sections of each historical working condition case to obtain the corresponding historical features;

[0009] A case library is generated based on historical working condition case sections and their corresponding historical features;

[0010] Based on real-time relevant data from the new energy base system, generate real-time operating condition case sections;

[0011] Feature recognition and extraction are performed on the cross-section of the real-time operating condition case to obtain real-time features;

[0012] Based on the real-time features, similar historical working condition case sections are found from the case library;

[0013] Based on the real-time operating condition case profile and the found similar historical operating condition case profiles, inversion correction is performed to obtain the final instruction value of the equipment in the new energy base system.

[0014] In conjunction with the first aspect, optionally, based on historical relevant data from the new energy base system, several historical operating condition case sections are generated, including:

[0015] Based on historical data from the new energy base system, several historical operation sections of the new energy bases are generated.

[0016] Based on the power grid topology model of the new energy base system, the historical operation sections of each new energy base are mapped to the corresponding historical operating condition case sections.

[0017] Based on the real-time relevant data of the new energy base system, several real-time operating condition case sections are generated, including:

[0018] Based on the real-time relevant data of the new energy base system, several real-time operation sections of the new energy base are generated.

[0019] Based on the power grid topology model of the new energy base system, the real-time operation sections of each new energy base are mapped to corresponding real-time operating condition case sections.

[0020] In conjunction with the first aspect, optionally, the historical relevant data includes: historical operating data of conventional generator sets, historical operating data of new energy sources, historical operating data of energy storage systems, and historical power generation plans and power generation control instructions issued by the superior dispatch system;

[0021] The real-time relevant data includes: real-time operating data of conventional generator sets, real-time operating data of new energy sources, real-time operating data of energy storage systems, and real-time power generation plans and power control instructions issued by the superior dispatch system.

[0022] In conjunction with the first aspect, optionally, the time interval between the generation of each historical working condition case section is a predetermined number of minutes, and the data of each historical working condition case section is stored in a time series manner.

[0023] In conjunction with the first aspect, optionally, the methods for identifying and extracting the historical features and real-time features are the same, including:

[0024] Based on historical or real-time operating condition case cross-sections, the preset index values ​​are calculated.

[0025] All preset index values ​​are used as the corresponding historical or real-time characteristics of the historical or real-time working condition case section.

[0026] In conjunction with the first aspect, optionally, the preset indicators include the comprehensive power generation cost indicator of the energy base, the new energy consumption indicator, and / or environmental protection and carbon emission indicators.

[0027] In conjunction with the first aspect, optionally, the inversion correction based on the real-time operating condition case profile and the identified similar historical operating condition case profiles includes:

[0028] If the pre-constructed inversion correction objective function is determined to be invalid based on real-time operating condition case cross-sections, it indicates that the new energy base system is in a state of dynamic mismatch.

[0029] Based on the aforementioned similar historical operating condition case cross-sections, the final dynamic parameter correction amount of the equipment in the new energy base system is calculated using the adjoint method. The formula for calculating the final dynamic parameter correction amount of the equipment is as follows:

[0030] ,

[0031] In the formula, The final dynamic parameter correction amount of the equipment is obtained by minimizing the sum of squared errors between the real-time cross-sectional data and the model output; Let argmin represent the optimization variable, indicating the dynamic parameter adjustment of the device at time point r. The optimization process, argmin, finds the value that minimizes the objective function. The value is ; This represents a time index variable, indicating the time point for summation, with a value range from... arrive That is, covering multiple moments within a time window; This indicates the current time, and this indicates the end time of the time window for summation. This indicates the historical offset length of the time window, i.e., the number of historical data points used for inversion correction; This represents the real-time cross-sectional data at time point r, and the real-time measurement output data of the new energy base system. This represents the model output value at time point r, indicating the model prediction output based on cross-sections of similar historical operating conditions. This model prediction output depends on the equipment command value at time point r. and the corrected dynamic parameters ; The device instruction value at time point r represents the control instruction sent to the device by the scheduling or control system. This represents the original dynamic parameters of the device, and the initial parameter values ​​of the model before correction.

[0032] Based on the dynamic parameter correction amount of the equipment, combined with the original dynamic parameters of the equipment, the new dynamic parameters of the equipment are obtained. The calculation formula for the new dynamic parameters of the equipment is as follows:

[0033] ,

[0034] In the formula, Indicates the new dynamic parameters of the device;

[0035] The new dynamic parameters of the equipment are input into the pre-constructed inversion correction objective function to obtain the final command value of the equipment. The formula for calculating the final command value of the equipment is as follows:

[0036] ,

[0037] In the formula, This represents the real-time cross-sectional data at time point i, and represents the real-time measurement output data of the new energy base system. Represents the final instruction value based on the device. and new dynamic parameters of the equipment The model predicts the output; Q is the output error weight matrix, used to assign different weights to the errors of different output variables; The square of the weighted Euclidean norm; T represents the optimization time range, and the number of future time steps considered; This represents the time retrieval index, with values ​​ranging from 1 to T. R is the regularization coefficient, used to balance the weights between the fitting error and the control cost; R is the control cost weight matrix, used to assign different weights to the adjustment costs of different control variables. The rated command value or reference command value of the equipment; This is the regularization coefficient, which is the magnitude of the user-controlled parameter adjustment to prevent over-adjustment. A penalty term for parameter drift to prevent over-correction.

[0038] In conjunction with the first aspect, optionally, after identifying and extracting historical or real-time features, the multi-energy complementary scheduling and operation inversion correction method for new energy bases further includes:

[0039] Based on the extracted historical or real-time features, the historical or real-time working condition case sections are corrected and marked.

[0040] The corrected and marked historical or real-time operating condition case sections, along with their corresponding historical and real-time features, are stored in the case library.

[0041] Secondly, the present invention provides a multi-energy complementary scheduling and operation inversion correction device for a new energy base, comprising:

[0042] The historical operating condition case section generation module is used to generate several historical operating condition case sections based on historical relevant data of the new energy base system.

[0043] The historical feature extraction module is used to identify and extract features from cross-sections of various historical working conditions to obtain the corresponding historical features.

[0044] The case library generation module is used to generate a case library based on historical working condition case sections and their corresponding historical features;

[0045] The real-time operating condition case section generation module is used to generate real-time operating condition case sections based on real-time relevant data of the new energy base system.

[0046] The real-time feature extraction module is used to identify and extract features from the cross-section of the real-time working condition case to obtain real-time features.

[0047] The module for finding similar historical working condition case sections is used to find similar historical working condition case sections from the case library based on the real-time features.

[0048] The feedback correction module is used to perform inversion correction based on the real-time operating condition case section and the found similar historical operating condition case sections to obtain the final instruction value of the equipment in the new energy base system.

[0049] Thirdly, the present invention provides a multi-energy complementary scheduling and operation inversion correction system for a new energy base, including a storage medium and a processor;

[0050] The storage medium is used to store instructions;

[0051] The processor is configured to operate according to the instructions to perform the method according to any one of the first aspects.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0053] This invention generates several historical operating condition case sections based on historical data from new energy bases; it identifies and extracts features from each historical operating condition case section to obtain corresponding historical features; it generates a case library based on the historical operating condition case sections and their corresponding historical features; it generates real-time operating condition case sections based on real-time data from the new energy bases; it identifies and extracts features from the real-time operating condition case sections to obtain real-time features; it finds similar historical operating condition case sections from the case library based on the real-time operating condition case sections and the found similar historical operating condition case sections; it performs inversion correction based on the real-time operating condition case sections and the found similar historical operating condition case sections to obtain the final instructions of the equipment in the new energy base system. This invention enables case section management, feature scenario inversion, multi-source coordinated control, and target case operation guidance functions, effectively improving the operator's scheduling and operation level and addressing the operational risks caused by the instability of high-proportion new energy sources, which cannot be adequately addressed by existing power grid scheduling and operation mechanisms. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0055] Figure 1 This is a schematic diagram of the process of inversion correction for multi-energy complementary scheduling operation of a new energy base according to an embodiment of the present invention;

[0056] Figure 2 This is a schematic diagram illustrating the application of inversion correction in the multi-energy complementary scheduling operation of a new energy base according to an embodiment of the present invention. Detailed Implementation

[0057] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0058] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0059] Example 1

[0060] This invention provides a method for inversion and correction of multi-energy complementary scheduling and operation in new energy bases, comprising the following steps:

[0061] (1) Based on the historical data of the new energy base system, generate several historical operating condition case sections. The operating condition case sections include the power grid topology and dynamic operation data of the energy base system.

[0062] (2) Feature identification and extraction are performed on the cross sections of each historical working condition case to obtain the corresponding historical features;

[0063] (3) Generate a case library based on historical working condition case sections and their corresponding historical features;

[0064] (4) Generate real-time operating condition case sections based on real-time relevant data of the new energy base system;

[0065] (5) Perform feature recognition and extraction on the cross-section of the real-time working condition case to obtain real-time features;

[0066] (6) Based on the real-time features, find similar historical working condition case sections from the case library;

[0067] (7) Based on the real-time operating condition case section and the found similar historical operating condition case section, perform inversion correction to obtain the final instruction value of the equipment in the new energy base system.

[0068] In the above scheme, several historical operating condition case sections are generated based on historical relevant data of the new energy base; feature identification and extraction are performed on each historical operating condition case section to obtain corresponding historical features; a case library is generated based on the historical operating condition case sections and their corresponding historical features; real-time operating condition case sections are generated based on real-time relevant data of the new energy base; feature identification and extraction are performed on the real-time operating condition case sections to obtain real-time features; similar historical operating condition case sections are found from the case library based on the real-time features; inversion correction is performed based on the real-time operating condition case sections and the found similar historical operating condition case sections to obtain the final instructions of the equipment in the new energy base system. This scheme can realize case section management, feature scenario inversion, multi-source coordinated control, and target case operation guidance functions, effectively improve the operator's scheduling and operation level, and solve the operational risks caused by the instability of high proportion of new energy sources that the existing power grid scheduling and operation mechanism cannot cope with.

[0069] like Figure 1 As shown, the new energy base system includes conventional generator sets, new energy sources, energy storage systems, and a dispatching system. The multi-energy complementary dispatching operation inversion and correction method for the new energy base in this embodiment of the invention may specifically include: combining conventional generator sets, new energy sources, energy storage systems, and the dispatching system to collect and store data; generating historical operating condition cases; identifying case cross-sectional features; correcting and updating source cases; and case inversion and correction steps.

[0070] In one specific embodiment of the present invention, the generation of several historical operating condition case sections based on historical relevant data of the new energy base system includes:

[0071] Based on historical data from the new energy base system, several historical operation sections of the new energy bases are generated.

[0072] Based on the power grid topology model of the new energy base system, the historical operation sections of each new energy base are mapped to the corresponding historical operating condition case sections.

[0073] Based on the real-time relevant data of the new energy base system, several real-time operating condition case sections are generated, including:

[0074] Based on the real-time relevant data of the new energy base system, several real-time operation sections of the new energy base are generated.

[0075] Based on the power grid topology model of the new energy base system, the real-time operation sections of each new energy base are mapped to corresponding real-time operating condition case sections.

[0076] The historical data includes: historical operating data of conventional generator sets, historical operating data of new energy sources, historical operating data of energy storage systems, and historical power generation plans and power control instructions (i.e., power instructions for each power generation device) issued by the superior dispatch system.

[0077] The real-time relevant data includes: real-time operating data of conventional generator sets, real-time operating data of new energy sources, real-time operating data of energy storage systems, and real-time power generation plans and power control instructions issued by the superior dispatch system.

[0078] In the above scheme, the conventional generator sets specifically include thermal power units and / or hydropower units and / or nuclear power units, and the new energy generator sets specifically include wind power generator sets and / or solar power generator sets. Historical and real-time operating data include analog quantities (active power, reactive power, etc.) and switch quantities; the energy storage system includes electrochemical energy storage, molten salt energy storage, pumped hydro storage, and flywheel energy storage. The new energy sources include wind power, photovoltaic power, etc.

[0079] In one specific embodiment of the present invention, the time interval between the generation of each historical working condition case section is a predetermined number of minutes, and the data of each historical working condition case section is stored in a time series manner.

[0080] In the above scheme, during implementation, each historical operating condition case section is specially marked based on the feature identification and extraction results. This mark is then used to screen for similar historical operating condition case sections. Correlation analysis is generally used for screening similar historical operating condition case sections. In practice, the time interval for generating historical operating condition cases is 15 minutes, and the data for each historical operating condition case section is stored in a time-series format with a storage period of 1 minute.

[0081] In one specific embodiment of the present invention, the methods for identifying and extracting the historical features and real-time features are the same, both including:

[0082] Based on historical or real-time operating condition case cross-sections, the preset index values ​​are calculated.

[0083] All preset index values ​​are used as the corresponding historical or real-time characteristics of the historical or real-time working condition case section.

[0084] In the above scheme, by identifying and extracting features from the cross-section of the working condition case, it is convenient to effectively screen the cross-section of similar historical working condition cases in the later stage.

[0085] In one specific embodiment of the present invention, the preset indicators include the comprehensive power generation cost indicator of the energy base, the new energy consumption indicator, and / or environmental protection and carbon emission indicators. In specific implementation, the indicators can also be other indicators, and can be set according to actual needs. Preferably, the indicators are those that can effectively distinguish different operating conditions and case sections.

[0086] In one specific embodiment of the present invention, the inversion correction based on the real-time operating condition case profile and the identified similar historical operating condition case profiles includes:

[0087] If the pre-constructed inversion correction objective function is determined to be invalid based on real-time operating condition case cross-sections, it indicates that the new energy base system is in a state of dynamic mismatch.

[0088] Based on the aforementioned similar historical operating condition case cross-sections, the final dynamic parameter correction amount of the equipment in the new energy base system is calculated using the adjoint method. The formula for calculating the final dynamic parameter correction amount of the equipment is as follows:

[0089] ,

[0090] In the formula, The final dynamic parameter correction amount of the equipment is obtained by minimizing the sum of squared errors between the real-time cross-sectional data and the model output; Let argmin represent the optimization variable, indicating the dynamic parameter adjustment of the device at time point r. The optimization process, argmin, finds the value that minimizes the objective function. The value is ; This represents a time index variable, indicating the time point for summation, with a value range from... arrive That is, covering multiple moments within a time window; This indicates the current time, and this indicates the end time of the time window for summation. This indicates the historical offset length of the time window, i.e., the number of historical data points used for inversion correction; This represents the real-time cross-sectional data at time point r, and the real-time measurement output data of the new energy base system. This represents the model output value at time point r, indicating the model prediction output based on cross-sections of similar historical operating conditions. This model prediction output depends on the equipment command value at time point r. and the corrected dynamic parameters ; The device instruction value at time point r represents the control instruction sent to the device by the scheduling or control system. This represents the original dynamic parameters of the equipment (such as inertia time constant, damping coefficient, etc.), and the initial parameter values ​​of the model before correction.

[0091] Based on the final dynamic parameter correction of the equipment, combined with the original dynamic parameters of the equipment, the new dynamic parameters of the equipment are obtained. The formula for calculating the new dynamic parameters of the equipment is as follows:

[0092] ,

[0093] In the formula, Indicates the new dynamic parameters of the device;

[0094] The new dynamic parameters of the equipment are input into the pre-constructed inversion correction objective function to obtain the final command value of the equipment. The formula for calculating the final command value of the equipment is as follows:

[0095]

[0096] In the formula, Indicates a point in time The real-time cross-sectional data represents the real-time measurement output data of the new energy base system. Represents the final instruction value based on the device. (Including several adjustable parameters, such as the maximum output setting value of new energy (wind / solar), the threshold value of energy storage charging and discharging power, etc.) and new dynamic parameters of the equipment. The model predicts the output; Q is the output error weight matrix, used to assign different weights to the errors of different output variables; The square of the weighted Euclidean norm; T represents the optimization time range, and the number of future time steps considered; This represents the time retrieval index, with values ​​ranging from 1 to T. R is the regularization coefficient, used to balance the weights between the fitting error and the control cost; R is the control cost weight matrix, used to assign different weights to the adjustment costs of different control variables. The rated command value or reference command value of the equipment; This is the regularization coefficient, which is the magnitude of the user-controlled parameter adjustment to prevent over-adjustment. A penalty term for parameter drift to prevent over-correction.

[0097] The inversion correction objective function takes into account the requirements of accuracy, stability and reliability.

[0098] In one specific embodiment of the present invention, after historical or real-time feature identification and extraction, the multi-energy complementary scheduling operation inversion correction method for new energy bases further includes:

[0099] Based on the extracted historical or real-time features, the historical or real-time working condition case sections are corrected and marked.

[0100] The corrected and marked historical or real-time operating condition case sections, along with their corresponding historical and real-time features, are stored in the case library.

[0101] In the above scheme, the correction can be based on the integrity check results to modify the working condition case profile (such as correcting abnormal data and states), ultimately forming a new usable working condition case profile. By continuously adding real-time working condition case profiles to the case library, real-time updates of the case library can be achieved.

[0102] like Figure 2 As shown, the multi-energy complementary scheduling operation inversion correction method of the new energy base in this embodiment of the invention is applied to the parallel scheduling system to achieve inversion correction.

[0103] The inversion correction process includes the following steps:

[0104] (1) Based on the power transmission network topology of the new energy base, the electrical topology relationship, equipment status and measurement data in the power transmission network are saved into a working condition case section file and marked according to time;

[0105] (2) The storage time interval for the working case section is 15 minutes. The specific storage content includes the planned value and actual value of the bundled transmission line; the pipeline pressure and flow rate of heat transmission; the planned value, actual value, predicted value and maximum theoretical output of wind power generation and photovoltaic power generation;

[0106] (3) The power generation output dispatch command value, actual value, start-up and shutdown status of thermal power units; the status and measurement data of power equipment at substations and collection stations in the power grid;

[0107] (4) Collect the data required for the working condition case section from thermal power SIS (existing technology) and new energy centralized control (existing technology), generate historical working condition case section files, and, based on the historical working conditions selected by the user, combine the established or manually adjusted system parameters, unit parameters, etc., call the inversion correction objective function to perform the inversion calculation of the power generation plan, and output the inversion power generation plan of each resource of wind, solar and thermal power.

[0108] (5) Compare and analyze the inversion results with the actual historical data, and calculate key indicators, such as deviation indicators and economic indicators errors;

[0109] (6) Deviation index: Calculate the power deviation and energy deviation between the inverted power generation plan and the actual power generation curve, and evaluate the rationality and effectiveness of the optimized scheduling model through the inversion results;

[0110] (7) Economic indicators: Evaluate the economic benefits of the inverted power generation plan, such as the new energy absorption rate and power generation cost, and compare them with the actual situation;

[0111] (8) Combine key indicator evaluation and analysis with current power generation equipment status, fuel supply, grid demand and other factors to provide a basis and suggestions for the optimization and adjustment of power generation plans, such as unit deep adjustment stage adjustment, load distribution adjustment and so on.

[0112] Based on the above explanation, it can be seen that by tracing back the deviation between historical operation data and scheduling instructions, and through the autonomous operation of the parallel scheduling simulation system, a closed-loop feedback correction of "forward scheduling - reverse verification - rolling optimization" is formed.

[0113] Example 2

[0114] Based on the same inventive concept as Embodiment 1, this embodiment of the invention provides a multi-energy complementary scheduling and operation inversion correction device for a new energy base, comprising:

[0115] The historical operating condition case section generation module is used to generate several historical operating condition case sections based on historical relevant data of the new energy base system.

[0116] The historical feature extraction module is used to identify and extract features from cross-sections of various historical working conditions to obtain the corresponding historical features.

[0117] The case library generation module is used to generate a case library based on historical working condition case sections and their corresponding historical features;

[0118] The real-time operating condition case section generation module is used to generate real-time operating condition case sections based on real-time relevant data of the new energy base system.

[0119] The real-time feature extraction module is used to identify and extract features from the cross-section of the real-time working condition case to obtain real-time features.

[0120] The module for finding similar historical working condition case sections is used to find similar historical working condition case sections from the case library based on the real-time features.

[0121] The feedback correction module is used to perform inversion correction based on the real-time operating condition case section and the found similar historical operating condition case sections to obtain the final instruction value of the equipment in the new energy base system.

[0122] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0123] Example 3

[0124] This invention provides a multi-energy complementary scheduling and operation inversion correction system for a new energy base, including a storage medium and a processor;

[0125] The storage medium is used to store instructions;

[0126] The processor is configured to operate according to the instructions to execute the method according to any one of Embodiment 1.

[0127] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

[0132] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for inversion correction of multi-energy complementary scheduling and operation in a new energy base, characterized in that, include: Based on historical data from the new energy base system, several historical operating condition case sections are generated. Feature identification and extraction are performed on cross sections of each historical working condition case to obtain the corresponding historical features; A case library is generated based on historical working condition case sections and their corresponding historical features; Based on real-time relevant data from the new energy base system, generate real-time operating condition case sections; Feature recognition and extraction are performed on the cross-section of the real-time operating condition case to obtain real-time features; Based on the real-time features, similar historical working condition case sections are found from the case library; Based on the real-time operating condition case profile and the found similar historical operating condition case profiles, inversion correction is performed to obtain the final instruction value of the equipment in the new energy base system.

2. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 1, characterized in that: Based on historical data from the new energy base system, several historical operating condition case sections are generated, including: Based on historical data from the new energy base system, several historical operation sections of the new energy bases are generated. Based on the power grid topology model of the new energy base system, the historical operation sections of each new energy base are mapped to the corresponding historical operating condition case sections. Based on the real-time relevant data of the new energy base system, several real-time operating condition case sections are generated, including: Based on the real-time relevant data of the new energy base system, several real-time operation sections of the new energy base are generated. Based on the power grid topology model of the new energy base system, the real-time operation sections of each new energy base are mapped to corresponding real-time operating condition case sections.

3. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 1 or 2, characterized in that, The historical data includes: historical operating data of conventional generator sets, historical operating data of new energy sources, historical operating data of energy storage systems, and historical power generation plans and power generation control instructions issued by the superior dispatch system. The real-time relevant data includes: real-time operating data of conventional generator sets, real-time operating data of new energy sources, real-time operating data of energy storage systems, and real-time power generation plans and power control instructions issued by the superior dispatch system.

4. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 1, characterized in that: The time interval for generating each historical working condition case section is a predetermined number of minutes, and the data of each historical working condition case section is stored in a time series manner.

5. The method for inversion correction of multi-energy complementary scheduling operation in a new energy base according to claim 1, characterized in that: The methods for identifying and extracting the historical features and real-time features are the same, including: Based on historical or real-time operating condition case cross-sections, the preset index values ​​are calculated. All preset index values ​​are used as the corresponding historical or real-time characteristics of the historical or real-time working condition case section.

6. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 5, characterized in that: The preset indicators include the comprehensive power generation cost of the energy base, the renewable energy consumption indicator, and / or environmental protection and carbon emission indicators.

7. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 1, characterized in that: The inversion correction based on the real-time operating condition case cross-section and the found similar historical operating condition case cross-sections includes: If the pre-constructed inversion correction objective function is determined to be invalid based on real-time operating condition case cross-sections, it indicates that the new energy base system is in a state of dynamic mismatch. Based on the aforementioned similar historical operating condition case cross-sections, the final dynamic parameter correction amount of the equipment in the new energy base system is calculated using the adjoint method. The formula for calculating the final dynamic parameter correction amount of the equipment is as follows: ， In the formula, The final dynamic parameter correction amount of the equipment is obtained by minimizing the sum of squared errors between the real-time cross-sectional data and the model output; Let argmin represent the optimization variable, indicating the dynamic parameter adjustment of the device at time point r. The optimization process, argmin, finds the value that minimizes the objective function. The value is ; This represents a time index variable, indicating the time point for summation, with a value range from... arrive That is, covering multiple moments within a time window; This indicates the current time, and this indicates the end time of the time window for summation. This indicates the historical offset length of the time window, i.e., the number of historical data points used for inversion correction; This represents the real-time cross-sectional data at time point r, and the real-time measurement output data of the new energy base system. This represents the model output value at time point r, indicating the model prediction output based on cross-sections of similar historical operating conditions. This model prediction output depends on the equipment command value at time point r. and the corrected dynamic parameters ; The device instruction value at time point r represents the control instruction sent to the device by the scheduling or control system. This represents the original dynamic parameters of the device, and the initial parameter values ​​of the model before correction. Based on the dynamic parameter correction amount of the equipment, combined with the original dynamic parameters of the equipment, the new dynamic parameters of the equipment are obtained. The calculation formula for the new dynamic parameters of the equipment is as follows: ， In the formula, Indicates the new dynamic parameters of the device; The new dynamic parameters of the equipment are input into the pre-constructed inversion correction objective function to obtain the final command value of the equipment. The formula for calculating the final command value of the equipment is as follows: ， In the formula, This represents the real-time cross-sectional data at time point i, and represents the real-time measurement output data of the new energy base system. Represents the final instruction value based on the device. and new dynamic parameters of the equipment The model predicts the output; Q is the output error weight matrix, used to assign different weights to the errors of different output variables; The square of the weighted Euclidean norm; T represents the optimization time range, and the number of future time steps considered; This represents the time retrieval index, with values ​​ranging from 1 to T. R is the regularization coefficient, used to balance the weights between the fitting error and the control cost; R is the control cost weight matrix, used to assign different weights to the adjustment costs of different control variables. The rated command value or reference command value of the equipment; This is the regularization coefficient, which is the magnitude of the user-controlled parameter adjustment to prevent over-adjustment. A penalty term for parameter drift to prevent over-correction.

8. The method for inversion correction of multi-energy complementary scheduling operation of a new energy base according to claim 1, characterized in that: After identifying and extracting historical or real-time features, the multi-energy complementary scheduling and operation inversion correction method for new energy bases also includes: Based on the extracted historical or real-time features, the historical or real-time working condition case sections are corrected and marked. The corrected and marked historical or real-time operating condition case sections, along with their corresponding historical and real-time features, are stored in the case library.

9. A multi-energy complementary scheduling and operation inversion correction device for a new energy base, characterized in that, include: The historical operating condition case section generation module is used to generate several historical operating condition case sections based on historical relevant data of the new energy base system. The historical feature extraction module is used to identify and extract features from cross-sections of various historical working conditions to obtain the corresponding historical features. The case library generation module is used to generate a case library based on historical working condition case sections and their corresponding historical features; The real-time operating condition case section generation module is used to generate real-time operating condition case sections based on real-time relevant data of the new energy base system. The real-time feature extraction module is used to identify and extract features from the cross-section of the real-time working condition case to obtain real-time features. The module for finding similar historical working condition case sections is used to find similar historical working condition case sections from the case library based on the real-time features. The feedback correction module is used to perform inversion correction based on the real-time operating condition case section and the found similar historical operating condition case sections to obtain the final instruction value of the equipment in the new energy base system.

10. A multi-energy complementary scheduling and operation inversion correction system for a new energy base, characterized in that, Including storage media and processor; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to perform the method according to any one of claims 1-8.

Images