A wind storage collaborative prediction error compensation method based on grid-connected examination risk and related device

Abstract

The application provides a wind storage collaborative prediction error compensation method based on grid-connected examination risk and related devices, and belongs to the technical field of wind storage collaborative prediction error compensation. According to the size relationship between the out-of-bound risk and the preset risk threshold, it is judged whether to generate a candidate instruction; if the out-of-bound risk reaches the preset risk threshold, the candidate instruction is generated based on the prediction error type, the out-of-bound occurrence direction, the third data, the fourth data and the fifth data; the safety of the candidate instruction is checked based on the second data, the fourth data, the fifth data, the sixth data and the seventh data, a safety checking result is obtained, whether the candidate instruction meets the comprehensive operation constraint is judged based on the safety checking result; if the candidate instruction meets the comprehensive operation constraint, the candidate instruction is issued; if the candidate instruction does not meet the comprehensive operation constraint, the candidate instruction is degraded. The application solves the problems of insufficient safety and economy of the operation of wind storage collaborative prediction compensation action.

Description

Technical Field

[0001] This invention belongs to the field of wind-storage collaborative prediction error compensation technology, specifically involving a wind-storage collaborative prediction error compensation method and related device based on grid connection assessment risk. Background Technology

[0002] With the continuous expansion of wind power installed capacity, the randomness, volatility, and uncertainty of wind power output have had a significant impact on grid dispatch, grid connection assessment, and the economic operation of new energy power plants. Although wind power forecasting can provide a basis for dispatching plans and power plant control, significant deviations may still occur between the predicted power and the actual grid-connected power under circumstances such as sudden wind speed changes, unit power limitations, changes in AGC (Automatic Generation Control) targets, communication anomalies, or changes in equipment status. If not compensated in a timely and reasonable manner, the power at the grid connection point may exceed the assessment boundary, leading to problems such as power deviation assessment, exceeding ramp limits, or inconsistencies in dispatching and tracking.

[0003] Existing wind and energy storage joint control methods typically convert prediction deviations directly into energy storage charging and discharging commands. They fail to adequately distinguish between different error formation mechanisms, such as amplitude-type, phase-type, ramp-type, dispatch command-type, and abnormal data-type errors. This can easily lead to frequent energy storage actions, overcompensation, SOC (State of Charge) exceeding limits, or conflicts with AGC control objectives.

[0004] Meanwhile, most existing methods use fixed error thresholds as compensation trigger conditions, making it difficult to comprehensively consider dynamic constraints such as grid connection assessment allowable deviations, AGC target power, power station ramping limits, grid connection point power limits, and the status of energy storage SOC / SOH (State of Health), PCS (Power Conversion System) / BMS (Battery Management System), leading to insufficient necessity and safety of compensation actions. Furthermore, if energy storage is treated as the sole compensation target, ignoring the active power release, active power suppression, and power station ramping capabilities, it will increase energy storage lifespan loss and reduce system economics.

[0005] Therefore, it is necessary to propose a prediction error compensation method that can identify prediction error types, dynamically assess grid connection assessment risks, coordinate the use of wind turbine and energy storage regulation capabilities, and perform safety verification before the instruction is issued. Summary of the Invention

[0006] The purpose of this invention is to provide a wind-storage collaborative prediction error compensation method and related device based on grid connection assessment risk, which can solve the problems of insufficient safety and economy in the operation of wind-storage collaborative prediction compensation in the prior art.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a wind-storage collaborative prediction error compensation method based on grid connection assessment risk, comprising the following steps: The wind farm operation data is obtained, including historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints, and quality evaluation data, which are respectively denoted as the first data, the second data, the third data, the fourth data, the fifth data, the sixth data, and the seventh data. Based on the first data, an error fingerprint vector and a conditional historical error distribution are constructed, and the prediction error type is obtained based on the error fingerprint vector. Based on the first, second, fifth, and sixth data, a dynamic assessment corridor is constructed within the future control window; Based on the conditional historical error distribution and the error fingerprint vector, the uncompensated predicted trajectory within the future control window is obtained; based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor, the boundary crossing risk and the direction of boundary crossing within the future control window are obtained. Based on the relationship between the boundary risk and the preset risk threshold, it is determined whether to generate a candidate instruction; if the boundary risk reaches the preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Based on the seventh data, the candidate instructions are subjected to security verification to obtain the security verification result. Based on the security verification result, it is determined whether the candidate instructions meet the comprehensive operation constraints. If a candidate instruction meets the comprehensive operation constraints, the candidate instruction is issued; if a candidate instruction does not meet the comprehensive operation constraints, the candidate instruction is downgraded.

[0008] A further improvement of this invention is that the formula for calculating the error fingerprint vector is:

[0009] in, For the error fingerprint vector, This represents the deviation between historical predicted power and actual grid-connected power. This is the deviation sign function, used to characterize the direction of the deviation. The duration of the current deviation; The rate of change of deviation To predict the offset between the peak and valley times and the measured peak and valley times. This represents the deviation of the actual grid-connected power from the AGC target power. This serves as a consistency flag for scheduling instructions. This serves as a marker of data validity.

[0010] A further improvement of this invention is that the formula for calculating the risk of boundary crossing is:

[0011] in, To avoid the risk of crossing the boundary, This represents the current error fingerprint vector based on historical similar error distributions. and data validity indicators The constructed probability estimate.

[0012] A further improvement of the present invention is that the candidate instructions include candidate wind turbine active power control instructions and candidate energy storage charging and discharging instructions.

[0013] A further improvement of the present invention is that, if the boundary risk reaches a preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Specifically, if the boundary risk reaches a preset risk threshold, the wind turbine-side adjustable capability, the energy storage-side adjustable capability, and the energy storage lifetime budget constraint are obtained based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Candidate instructions are generated based on the adjustable capabilities of the wind turbine side, the adjustable capabilities of the energy storage side, and the energy storage lifetime budget constraints.

[0014] A further improvement of the present invention is that the comprehensive operational constraints include energy storage status constraints, energy storage device status constraints, grid-connected operation constraints, and scheduling and tracking constraints.

[0015] A further improvement of the present invention is that the degradation processing includes amplitude limiting, delay, segmented ramping, conservative substitution, and rejection processing.

[0016] Secondly, the present invention provides a wind-storage collaborative prediction error compensation system based on grid connection assessment risk, comprising: The data acquisition module is used to acquire wind farm operation data, which includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints and quality evaluation data, respectively denoted as first data, second data, third data, fourth data, fifth data, sixth data and seventh data; The prediction error type determination module is used to construct an error fingerprint vector based on the first data, and to obtain the prediction error type based on the error fingerprint vector. The assessment corridor construction module is used to construct a dynamic assessment corridor within the future control window based on the first, second, fourth, and sixth data. The boundary crossing state determination module is used to construct a conditional historical error distribution based on historical power, obtain the uncompensated predicted trajectory within the future control window based on the conditional historical error distribution and the error fingerprint vector, and obtain the boundary crossing risk and boundary crossing direction within the future control window based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor. The candidate instruction generation module is used to determine whether to generate a candidate instruction based on the relationship between the boundary risk and the preset risk threshold; if the boundary risk reaches the preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. The security verification module is used to perform security verification on candidate instructions based on the second data, the fourth data, the fifth data, the sixth data, and the seventh data, obtain the security verification result, and determine whether the candidate instructions meet the comprehensive operation constraints based on the security verification result. The judgment module is used to issue candidate instructions if they meet the comprehensive operation constraints, and to downgrade candidate instructions if they do not meet the comprehensive operation constraints.

[0017] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk described above.

[0018] Fourthly, the present invention provides a storage medium storing a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk described above.

[0019] Compared with the prior art, the present invention has the following beneficial effects: The wind-storage coordinated prediction error compensation method proposed in this invention, based on grid connection assessment risk, constructs an error fingerprint vector based on first data, and obtains the prediction error type based on the error fingerprint vector. This operation avoids miscompensation or overcompensation caused by directly controlling energy storage charging and discharging based solely on prediction deviation. Furthermore, based on the relationship between the uncompensated prediction trajectory within the future control window and the dynamic assessment corridor, the method obtains the boundary risk and direction of boundary violation within the future control window. This operation transforms the compensation action from being triggered by a fixed deviation threshold to being triggered by grid connection assessment risk. Moreover, this invention performs safety verification on candidate commands based on second, fourth, fifth, sixth, and seventh data, obtaining safety verification results. Based on the safety verification results, it determines whether the candidate commands meet comprehensive operational constraints. This operation effectively avoids problems such as equipment exceeding limits, grid connection power exceeding limits, and site ramping exceeding limits that occur after candidate commands are issued, comprehensively improving the operational safety of wind-storage coordinated compensation actions. Simultaneously, this invention constructs a dynamic assessment corridor within the future control window based on first, second, fourth, and sixth data. This operation not only reduces unnecessary reserves and losses but also reduces human error and avoids boundary violations. Attached Figure Description

[0020] Figure 1 This is a flowchart of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk according to the present invention; Figure 2 This is a schematic diagram of the wind-storage collaborative prediction error compensation system based on grid connection assessment risk according to the present invention; Figure 3 This is a flowchart of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk in Embodiment 4 of the present invention; Figure 4 This is a flowchart of the error fingerprint vector construction and dynamic assessment corridor construction in Embodiment 4 of the present invention; Figure 5 This is a flowchart of the wind turbine-energy storage (hereinafter referred to as wind storage) collaborative compensation and candidate command security verification in Embodiment 4 of the present invention; Figure 6 This is a schematic diagram of the structure of the electronic device of the present invention. Detailed Implementation

[0021] To further understand the content of this invention, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments are merely illustrative and not limiting of the invention.

[0022] Example 1: The flowchart of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk of this invention is as follows: Figure 1 As shown, the wind-storage collaborative prediction error compensation method based on grid connection assessment risk of the present invention includes the following steps: S1. Obtain wind farm operation data, which includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints and quality evaluation data, respectively denoted as first data, second data, third data, fourth data, fifth data, sixth data and seventh data; S2. Based on the first data, construct an error fingerprint vector, and based on the error fingerprint vector, obtain the prediction error type; S3. Based on the first data, the second data, the fourth data, and the sixth data, construct a dynamic assessment corridor within the future control window; S4. Based on historical power, construct a conditional historical error distribution. Based on the conditional historical error distribution and the error fingerprint vector, obtain the uncompensated predicted trajectory within the future control window. Based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor, obtain the boundary crossing risk and the direction of boundary crossing within the future control window. S5. Based on the relationship between the boundary risk and the preset risk threshold, determine whether to generate a candidate instruction; if the boundary risk reaches the preset risk threshold, generate a candidate instruction based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data; S6. Based on the second data, the fourth data, the fifth data, the sixth data, and the seventh data, perform security verification on the candidate instructions to obtain security verification results, and determine whether the candidate instructions meet the comprehensive operation constraints based on the security verification results; S7. If the candidate instruction meets the comprehensive operation constraints, issue the candidate instruction; if the candidate instruction does not meet the comprehensive operation constraints, downgrade the candidate instruction.

[0023] Example 2: A schematic diagram of the wind-storage collaborative prediction error compensation system based on grid connection assessment risk of this invention is shown below. Figure 2 As shown, the wind-storage collaborative prediction error compensation system based on grid connection assessment risk of this invention includes: The data acquisition module is used to acquire wind farm operation data, which includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints and quality evaluation data, respectively denoted as first data, second data, third data, fourth data, fifth data, sixth data and seventh data; The prediction error type determination module is used to construct an error fingerprint vector based on the first data, and to obtain the prediction error type based on the error fingerprint vector. The assessment corridor construction module is used to construct a dynamic assessment corridor within the future control window based on the first, second, fourth, and sixth data. The boundary crossing state determination module is used to construct a conditional historical error distribution based on historical power, obtain the uncompensated predicted trajectory within the future control window based on the conditional historical error distribution and the error fingerprint vector, and obtain the boundary crossing risk and boundary crossing direction within the future control window based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor. The candidate instruction generation module is used to determine whether to generate a candidate instruction based on the relationship between the boundary risk and the preset risk threshold; if the boundary risk reaches the preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. The security verification module is used to perform security verification on candidate instructions based on the second data, the fourth data, the fifth data, the sixth data, and the seventh data, obtain the security verification result, and determine whether the candidate instructions meet the comprehensive operation constraints based on the security verification result. The judgment module is used to issue candidate instructions if they meet the comprehensive operation constraints, and to downgrade candidate instructions if they do not meet the comprehensive operation constraints.

[0024] Example 3: The wind-storage coordinated prediction error compensation method based on grid connection assessment risk of this invention includes the following steps: S1. Obtain wind farm operation data.

[0025] The wind farm operation data in this step includes current power and historical power, dispatch constraints, wind turbine status, energy storage status, energy storage equipment status, grid connection operation constraints, and quality evaluation data, which are respectively recorded as the first data, the second data, the third data, the fourth data, the fifth data, the sixth data, and the seventh data.

[0026] S2. Based on the first data, construct an error fingerprint vector, and based on the error fingerprint vector, obtain the prediction error type.

[0027] The formula for calculating the error fingerprint vector in this step is:

[0028] in, For the error fingerprint vector, This represents the deviation between historical predicted power and actual grid-connected power. This is the deviation sign function, used to characterize the direction of the deviation. The duration of the current deviation; The rate of change of deviation To predict the offset between the peak and valley times and the measured peak and valley times. This represents the deviation of the actual grid-connected power from the AGC target power. This serves as a consistency flag for scheduling instructions. This serves as a marker for evaluating the validity of data.

[0029] S3. Based on the first data, the second data, the fourth data, and the sixth data, construct a dynamic assessment corridor within the future control window.

[0030] S4. Based on historical power, construct a conditional historical error distribution. Based on the conditional historical error distribution and the error fingerprint vector, obtain the uncompensated predicted trajectory within the future control window. Based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor, obtain the boundary crossing risk and the direction of boundary crossing within the future control window.

[0031] The formula for calculating the risk of crossing the boundary in this step is:

[0032] in, To avoid the risk of crossing the boundary, This represents the current error fingerprint vector based on historical similar error distributions. and data validity indicators The constructed probability estimate.

[0033] S5. Based on the relationship between the boundary risk and the preset risk threshold, determine whether to generate a candidate instruction; if the boundary risk reaches the preset risk threshold, generate a candidate instruction based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data.

[0034] The candidate commands in this step include candidate wind turbine active power control commands and candidate energy storage charging and discharging commands.

[0035] In this step, if the boundary crossing risk reaches a preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary crossing direction, the third data, the fourth data, and the fifth data. Specifically, if the boundary crossing risk reaches a preset risk threshold, the wind turbine-side adjustable capability, the energy storage-side adjustable capability, and the energy storage lifetime budget constraint are obtained based on the prediction error type, the boundary crossing direction, the third data, the fourth data, and the fifth data. Based on the adjustable capability of the wind turbine side, the adjustable capability of the energy storage side, and the energy storage lifetime budget constraint, candidate indicators are generated. S6. Based on the second, fourth, fifth, sixth, and seventh data, perform security verification on the candidate instructions to obtain security verification results, and determine whether the candidate instructions meet the comprehensive operation constraints based on the security verification results.

[0036] The comprehensive operational constraints in this step include energy storage status constraints, energy storage device status constraints, grid connection operation constraints, and scheduling and tracking constraints.

[0037] S7. If the candidate instruction meets the comprehensive operation constraints, issue the candidate instruction; if the candidate instruction does not meet the comprehensive operation constraints, downgrade the candidate instruction.

[0038] The degradation process in this step includes limiting, delaying, segmented ramping, conservative substitution, and rejection of distribution.

[0039] Example 4: The method of the present invention will be described in detail below. The flowchart of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk of the present invention is as follows: Figure 3 As shown, the flowchart for constructing the error fingerprint vector and the dynamic assessment corridor in this invention is as follows: Figure 4 As shown, the flowchart of the wind turbine-energy storage (hereinafter referred to as wind storage) collaborative compensation and candidate instruction security verification of the present invention is as follows: Figure 5 As shown, the wind-storage collaborative prediction error compensation method based on grid connection assessment risk of the present invention includes the following steps: Step 1: Data Acquisition and Preprocessing Obtain wind farm operation data, which includes current power data and historical power data (also known as current power and historical power), scheduling constraint data (also known as scheduling constraints), wind turbine status data (also known as wind turbine status), energy storage status data (also known as energy storage status), energy storage device status data (also known as energy storage device status), grid connection operation constraint data (also known as grid connection operation constraints), and quality data (also known as quality evaluation data).

[0040] Dispatch constraint data includes AGC target power. Wind turbine status data includes wind turbine operating status. Energy storage status data includes energy storage SOC and energy storage SOH. Energy storage device status data includes PCS operating status and BMS status. Grid connection operation constraint data includes substation ramp limits, transformer capacity, and grid connection point power constraints. Quality data includes data validity flags and abnormal data flags.

[0041] By performing unified time-scale alignment, validity verification, and anomaly marking on wind farm operation data, the basic data for subsequent error identification, risk calculation, and collaborative compensation control are obtained.

[0042] Step 2: Error fingerprint construction and error type identification Based on current and historical power data, the prediction deviation and corresponding change characteristics between the current and historical predicted power and the actual grid-connected power are obtained. Based on the prediction deviation and corresponding change characteristics between the current and historical predicted power and the actual grid-connected power, an error fingerprint vector is constructed. Based on the error fingerprint vector, the prediction error type is obtained.

[0043] Error fingerprint vectors are used to characterize the magnitude, direction, duration, trend, peak-to-valley time offset, degree of deviation from scheduling constraints, and data validity of prediction errors. Prediction error types include magnitude errors, phase errors, ramp-up errors, scheduling command errors, and outlier data errors.

[0044] Amplitude-type errors correspond to situations where the predicted trend matches the actual trend, but the deviation amplitude consistently exceeds the limit. Phase-type errors correspond to situations where the predicted peak and valley times are earlier or later than the actual peak and valley times. Climbing-type errors correspond to situations where the rate of change of actual grid-connected power or the rate of change of prediction error exceeds the preset climbing threshold. Dispatch command-type errors correspond to situations where dispatch constraint data causes the actual grid-connected power to deviate from the predicted power. Abnormal data-type errors correspond to situations where the data validity flag does not meet the compensation control requirements.

[0045] Step 3: Dynamic Assessment of Corridor Construction and Boundary Risk Calculation Based on historical power data, scheduling constraint data, grid connection operation constraint data, and energy storage status data, a dynamic assessment corridor is constructed within the future control window.

[0046] Based on historical power data, a conditional historical error distribution is obtained. Based on the conditional historical error distribution and the error fingerprint vector, the uncompensated predicted trajectory within the future control window is obtained.

[0047] Based on the relationship between the uncompensated predicted trajectory and the dynamic assessment corridor within the future control window, the risk of exceeding the boundary and the direction of the boundary exceedance within the future control window are obtained.

[0048] The dynamic assessment corridor represents the boundary range of the grid-connected point's permissible power within the future control window. Out-of-bounds directions include exceeding the upper limit, exceeding the lower limit, and not exceeding the limit.

[0049] The dynamic assessment corridor must meet the following constraints:

[0050] in, and Each of the future The lower and upper limits of the dynamic assessment corridor corresponding to each control step size. This represents the predicted active power at the grid connection point.

[0051] Among them, the lower limit of the dynamic assessment corridor and the upper limit of the dynamic assessment corridor represent the lower and upper boundaries of the power allowed to operate at the grid connection point within the future control window, respectively.

[0052] The formula for calculating the risk of boundary crossing is:

[0053] in, To avoid the risk of crossing the boundary, This represents the current error fingerprint vector based on historical similar error distributions. and data validity indicators The constructed probability estimate, when When the preset risk threshold is reached, the wind energy storage collaborative compensation instruction in step 4 is triggered.

[0054] Step 4: Generating wind-storage collaborative compensation instructions Based on the relationship between the boundary risk and the preset risk threshold, it is determined whether to generate candidate instructions. When the boundary risk is lower than the preset risk threshold, energy storage compensation actions are suppressed or only grid-connected power smoothing actions are executed. When the boundary risk reaches the preset risk threshold, based on the prediction error type, boundary occurrence direction, wind turbine status data, energy storage status data, and energy storage device status data, the adjustable capacity of the wind turbine side, the adjustable capacity of the energy storage side, and the energy storage lifetime budget constraints are obtained. Based on the adjustable capacity of the wind turbine side, the adjustable capacity of the energy storage side, and the energy storage lifetime budget constraints, candidate wind turbine active power control instructions and candidate energy storage charging and discharging instructions (candidate instructions) are generated.

[0055] Specifically, the adjustable capability of the wind turbine is obtained based on wind turbine status data, and includes at least the wind turbine's ability to release functional capacity, the wind turbine's ability to suppress functional capacity, and the wind turbine's adjustable ramping capability.

[0056] The adjustable capability of the energy storage side is obtained based on energy storage status data and energy storage device status data, including at least the energy storage rechargeable capability, energy storage dischargeable capability, PCS available power, and BMS allowable charge and discharge status.

[0057] When generating candidate wind turbine active power control commands and candidate energy storage charging and discharging commands, the adjustable capacity on the wind turbine side and the adjustable capacity on the energy storage side are allocated according to the direction of the boundary violation and the type of prediction error.

[0058] The energy storage lifespan budget constraint is determined based on energy storage status data. When the energy storage SOC is close to the operating boundary or the energy storage SOH does not meet the preset requirements, the proportion of adjustable capacity on the energy storage side is reduced, and the proportion of adjustable capacity on the wind turbine side is increased or a safety degradation process is implemented. When the energy storage lifespan budget constraint meets the requirements, energy storage is allowed to participate in the generation of wind-storage collaborative compensation instructions.

[0059] This invention relies on the energy storage lifespan budget constraint to regulate the adjustable capacity range of the energy storage side. By optimizing the coordinated allocation strategy of wind turbine and energy storage regulation resources, it effectively reduces the lifespan loss caused by frequent and excessive energy storage operations. This method can reduce various operating costs caused by grid connection deviation assessment, energy storage lifespan loss and unreasonable compensation, and significantly improve the overall operating economy of wind-storage joint stations.

[0060] Step 5: Security Verification of Candidate Instructions Based on the active power control commands of candidate wind turbines and the charging and discharging commands of candidate energy storage, the predicted operating state after candidate compensation is obtained.

[0061] Based on the predicted operating status, energy storage status data, energy storage device status data, scheduling constraint data, grid connection operation constraint data, and quality data after candidate compensation, a security verification based on virtual execution is performed on the candidate instructions to obtain the security verification results. Based on the security verification results, it is determined whether the candidate instructions meet the energy storage status constraints, energy storage device status constraints, grid connection operation constraints, and scheduling tracking constraints.

[0062] Candidate instruction security verification (safety verification of candidate instructions based on virtual execution) is used to perform safety verification of candidate wind turbine active power control instructions and candidate energy storage charging and discharging instructions based on virtual execution before the compensation instructions are actually issued.

[0063] Energy storage state constraints include ensuring that the energy storage SOC and SOH meet operational requirements. Energy storage device state constraints include ensuring that the PCS operating status and BMS status meet execution requirements. Grid connection operation constraints include ensuring that the transformer capacity, substation ramping limits, and grid connection point power constraints meet operational requirements.

[0064] Step 6: Issuance of Compensation Instructions and Conservative Processing If the candidate command meets the equipment safety constraints, grid connection operation constraints, and dispatch tracking constraints, the candidate wind turbine active power control command and the candidate energy storage charging and discharging command are issued; if the candidate command does not meet the equipment safety constraints, grid connection operation constraints, and dispatch tracking constraints, the candidate wind turbine active power control command and the candidate energy storage charging and discharging command are downgraded (limited, delayed, segmented ramping, conservative substitution, and rejected issuance) to avoid equipment exceeding limits, grid connection power exceeding limits, or site ramping exceeding limits due to compensation actions.

[0065] Step 7: Recording Compensation Results and Updating Parameters Record the compensation execution results, boundary crossing risks, direction of boundary crossing, prediction error type, wind turbine-side action amount, energy storage-side action amount, energy storage life budget constraint satisfaction status, safety verification results, and safety degradation processing results; Based on the recorded results, the correspondence between the error fingerprint vector and the prediction error type, the distribution of conditional historical errors, the dynamic assessment corridor, the preset risk threshold, the energy storage lifetime budget constraint, and the wind-storage collaborative compensation allocation relationship are updated for subsequent error identification, risk calculation, and collaborative compensation control.

[0066] Example 5: Please see Figure 6As shown, the present invention also provides an electronic device 100 for a wind-storage collaborative prediction error compensation method based on grid connection assessment risk; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and capable of running on the at least one processor 102, and at least one communication bus 104.

[0067] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk described in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0068] The at least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0069] The memory 101 in the electronic device 100 stores multiple instructions to implement a wind-storage collaborative prediction error compensation method based on grid connection assessment risk, and the processor 102 can execute the multiple instructions to achieve the following: The wind farm operation data includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints, and quality evaluation data, which are respectively denoted as the first data, the second data, the third data, the fourth data, the fifth data, the sixth data, and the seventh data. Based on the first data, an error fingerprint vector is constructed, and based on the error fingerprint vector, the prediction error type is obtained; Based on the first, second, fourth, and sixth data, a dynamic assessment corridor is constructed within the future control window; Based on historical power, a conditional historical error distribution is constructed. Based on the conditional historical error distribution and the error fingerprint vector, the uncompensated predicted trajectory within the future control window is obtained. Based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor, the boundary crossing risk and the direction of boundary crossing within the future control window are obtained. Based on the relationship between the boundary risk and the preset risk threshold, it is determined whether to generate a candidate instruction; if the boundary risk reaches the preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Based on the second, fourth, fifth, sixth, and seventh data, the candidate instructions are subjected to security verification to obtain security verification results. Based on the security verification results, it is determined whether the candidate instructions meet the comprehensive operation constraints. If a candidate instruction meets the comprehensive operational constraints, the candidate instruction is issued; if a candidate instruction does not meet the comprehensive operational constraints, the candidate instruction is downgraded.

[0070] Example 6: If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0071] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention 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.

[0072] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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 illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0073] 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.

[0074] 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.

[0075] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A wind-storage collaborative prediction error compensation method based on grid connection assessment risk, characterized in that, Includes the following steps: The wind farm operation data includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints, and quality evaluation data, which are respectively denoted as the first data, the second data, the third data, the fourth data, the fifth data, the sixth data, and the seventh data. Based on the first data, an error fingerprint vector is constructed, and based on the error fingerprint vector, the prediction error type is obtained; Based on the first, second, fourth, and sixth data, a dynamic assessment corridor is constructed within the future control window; Based on historical power, a conditional historical error distribution is constructed. Based on the conditional historical error distribution and the error fingerprint vector, the uncompensated predicted trajectory within the future control window is obtained. Based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor, the boundary crossing risk and the direction of boundary crossing within the future control window are obtained. Based on the relationship between the boundary risk and the preset risk threshold, determine whether to generate a candidate instruction; If the risk of crossing the boundary reaches a preset risk threshold, a candidate instruction is generated based on the prediction error type, the direction of the boundary crossing, the third data, the fourth data, and the fifth data. Based on the second, fourth, fifth, sixth, and seventh data, the candidate instructions are subjected to security verification to obtain security verification results. Based on the security verification results, it is determined whether the candidate instructions meet the comprehensive operation constraints. If a candidate instruction meets the comprehensive operational constraints, the candidate instruction is issued; if a candidate instruction does not meet the comprehensive operational constraints, the candidate instruction is downgraded.

2. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk as described in claim 1, characterized in that, The formula for calculating the error fingerprint vector is as follows: in, For the error fingerprint vector, This represents the deviation between historical predicted power and actual grid-connected power. This is the deviation sign function, used to characterize the direction of the deviation. The duration of the current deviation; The rate of change of deviation To predict the offset between the peak and valley times and the measured peak and valley times. This represents the deviation of the actual grid-connected power from the AGC target power. This serves as a consistency flag for scheduling instructions. This serves as a marker of data validity.

3. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk as described in claim 1, characterized in that, The formula for calculating the risk of boundary crossing is: in, To avoid the risk of crossing the boundary, This represents the current error fingerprint vector based on historical similar error distributions. and data validity indicators The constructed probability estimate.

4. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk as described in claim 1, characterized in that, The candidate commands include candidate wind turbine active power control commands and candidate energy storage charging and discharging commands.

5. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk according to claim 1, characterized in that, If the boundary risk reaches a preset risk threshold, a candidate instruction is generated based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Specifically, if the boundary risk reaches a preset risk threshold, the wind turbine-side adjustable capability, the energy storage-side adjustable capability, and the energy storage lifetime budget constraint are obtained based on the prediction error type, the boundary occurrence direction, the third data, the fourth data, and the fifth data. Candidate instructions are generated based on the adjustable capabilities of the wind turbine side, the adjustable capabilities of the energy storage side, and the energy storage lifetime budget constraints.

6. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk according to claim 1, characterized in that, The comprehensive operational constraints include energy storage status constraints, energy storage device status constraints, grid connection operation constraints, and scheduling and tracking constraints.

7. The wind-storage coordinated prediction error compensation method based on grid connection assessment risk according to claim 1, characterized in that, The degradation process includes amplitude limiting, delay, segmented ramping, conservative substitution, and rejection of distribution.

8. A wind-storage collaborative prediction error compensation system based on grid connection assessment risk, characterized in that, include: The data acquisition module is used to acquire wind farm operation data, which includes current power and historical power, scheduling constraints, wind turbine status, energy storage status, energy storage device status, grid connection operation constraints and quality evaluation data, respectively denoted as first data, second data, third data, fourth data, fifth data, sixth data and seventh data; The prediction error type determination module is used to construct an error fingerprint vector based on the first data, and to obtain the prediction error type based on the error fingerprint vector. The assessment corridor construction module is used to construct a dynamic assessment corridor within the future control window based on the first, second, fourth, and sixth data. The boundary crossing state determination module is used to construct a conditional historical error distribution based on historical power, obtain the uncompensated predicted trajectory within the future control window based on the conditional historical error distribution and the error fingerprint vector, and obtain the boundary crossing risk and boundary crossing direction within the future control window based on the relationship between the uncompensated predicted trajectory within the future control window and the dynamic assessment corridor. The candidate instruction generation module is used to determine whether to generate a candidate instruction based on the relationship between the boundary risk and the preset risk threshold. If the risk of crossing the boundary reaches a preset risk threshold, a candidate instruction is generated based on the prediction error type, the direction of the boundary crossing, the third data, the fourth data, and the fifth data. The security verification module is used to perform security verification on candidate instructions based on the second data, the fourth data, the fifth data, the sixth data, and the seventh data, obtain the security verification result, and determine whether the candidate instructions meet the comprehensive operation constraints based on the security verification result. The judgment module is used to issue candidate instructions if they meet the comprehensive operation constraints, and to downgrade candidate instructions if they do not meet the comprehensive operation constraints.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk as described in any one of claims 1 to 7.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the wind-storage collaborative prediction error compensation method based on grid connection assessment risk as described in any one of claims 1 to 7.

Images