Control method, device, equipment, storage medium and program product of virtual power plant

Abstract

The present application discloses a control method, device, equipment, storage medium and program product for a virtual power plant. The method predicts the predicted power error at the next moment of the current moment through the power deviation sequence of the previous time window at the current moment, and adjusts the control influence factor of the cumulative power error at the next moment through the relationship between the cumulative power error and the error threshold of the current time window to which the current moment belongs. The control power of the virtual power plant is determined based on the control influence factor, the cumulative power error and the predicted power error, and the operation of the virtual power plant at the next moment is controlled based on the control power. The method predicts external disturbances and performs feedforward compensation, and at the same time performs feedback correction based on the real-time response results of the system, thereby realizing the coordinated optimization and regulation of multiple distributed energy resources in the virtual power plant.

Description

Technical Field

[0001] The present disclosure generally relates to the field of control, and in particular to a control method, computer equipment, computer-readable storage medium, and computer program product for a virtual power plant. Background Art

[0002] A virtual power plant (VPP) is not a traditional physical power plant. Instead, it uses advanced information and communication technology (ICT) and intelligent algorithms to aggregate distributed energy resources (such as photovoltaics, wind power, energy storage, electric vehicles, and adjustable loads) to form a "virtualized" power system that can be centrally dispatched and operated in a coordinated manner. While it does not rely on physical power plants, it can participate in electricity market transactions and grid dispatch just like traditional power plants. The efficient operation of a VPP depends on its three core components: distributed energy resources, energy storage systems, and intelligent control systems. These components work together to form the "intelligent brain" of the VPP.

[0003] At present, open-loop control methods are mostly used in actual virtual power plant control at home and abroad. That is, target power is allocated according to the preset target power curve and the adjustment capabilities of each aggregated adjustable resource. However, for distributed resources with weak control rights such as electric vehicle charging loads, the errors caused by open-loop control will be uncontrollable. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desired to provide a control method, computer equipment, computer-readable storage medium and computer program product for a virtual power plant, which can improve the control accuracy of the virtual power plant.

[0005] A first aspect provides a control method for a virtual power plant, the method comprising:

[0006] Get the power deviation sequence of the previous time window at the current moment;

[0007] Predicting a predicted power error at the next moment of the current moment according to the power deviation sequence of the previous time window;

[0008] Obtaining a cumulative power error of a current time window to which the current moment belongs, and adjusting a control influence factor of the cumulative power error at a next moment according to a magnitude relationship between the cumulative power error and an error threshold;

[0009] The control power of the virtual power plant is determined according to the control influencing factor, the accumulated power error and the predicted power error, and the operation of the virtual power plant at the next moment is controlled based on the control power.

[0010] The control method of the virtual power plant provided by the present application takes into account that the existing open-loop control method will produce uncontrollable errors in the control of the virtual power plant. The present application predicts the predicted power error at the next moment of the current moment through the power deviation sequence of the previous time window at the current moment, and adjusts the control influence factor of the cumulative power error at the next moment through the relationship between the cumulative power error and the error threshold of the current time window to which the current moment belongs, and determines the control power of the virtual power plant based on the control influence factor, the cumulative power error and the predicted power error, and controls the operation of the virtual power plant at the next moment based on the control power. The method predicts the external disturbance and performs feedforward compensation, and at the same time performs feedback correction based on the real-time response results of the system, thereby realizing the coordinated optimization and control of multiple distributed energy resources in the virtual power plant. The method has both rapid response capability and robustness, can improve the response speed and control accuracy of the virtual power plant, and is suitable for real-time control scenarios under high uncertainty environments.

[0011] A second aspect provides a control device for a virtual power plant, the device comprising:

[0012] An acquisition module is used to obtain the power deviation sequence of the previous time window at the current moment;

[0013] A prediction module, configured to predict a predicted power error at a next moment after the current moment based on the power deviation sequence of the previous time window;

[0014] an acquisition and adjustment module, configured to acquire a cumulative power error of a current time window to which the current moment belongs, and adjust a control influence factor of the cumulative power error at the next moment according to a magnitude relationship between the cumulative power error and an error threshold;

[0015] A determination module is used to determine the control power of the virtual power plant according to the control influencing factor, the accumulated power error and the predicted power error, and control the operation of the virtual power plant at the next time based on the control power.

[0016] A third aspect provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the control method of the virtual power plant of the first aspect when executing the computer program.

[0017] A third aspect provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the control method for the virtual power plant of the first aspect.

[0018] A fourth aspect provides a computer program product, comprising a computer program, which, when executed by a processor, implements the control method of the virtual power plant of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other features, objects and advantages of the present application will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0020] Figure 1 A flowchart of the steps of a control method for a virtual power plant provided in this application;

[0021] Figure 2 A flowchart of another virtual power plant control method provided in this application;

[0022] Figure 3 A flowchart of another virtual power plant control method provided in this application;

[0023] Figure 4 A flowchart of another virtual power plant control method provided in this application;

[0024] Figure 5 A flowchart of another virtual power plant control method provided in this application;

[0025] Figure 6 A schematic structural diagram of a control device for a virtual power plant provided in this application. DETAILED DESCRIPTION

[0026] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0027] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0028] At present, in terms of closed-loop control methods of virtual power plants, they can be divided into energy management strategies based on Markov decision processes, control strategies based on robust optimization, and control strategies based on model predictive control; among them, the Markov decision process method relies on a large amount of historical data for training, while the actual control data of virtual power plants is very small and has the characteristics of privacy, complexity and high confidentiality, which is obviously not suitable for actual promotion and application; robust optimization methods tend to provide conservative solutions, which puts high demands on the accuracy of virtual power plant regulation capacity assessment, which is obviously not suitable in practical applications; model predictive control can perform rolling optimization based on the real-time information of the virtual power plant, which is more suitable for real-time optimization control of virtual power plants, while the current conventional model predictive control method requires modeling the internal resources of the virtual power plant, and then solving it online according to the set optimization objectives, which will obviously cause the method to have control lag in practical applications.

[0029] To address the above problems, this application performs online correction on the control power that needs to be issued based on the predicted errors that may occur in the future and the current real-time accumulated errors, so that the output power of the virtual power plant is consistent with the target power, thereby improving the control accuracy.

[0030] The following combination Figure 1 For an explanation of the control method of the virtual power plant provided in this application, please refer to Figure 1 , Figure 1 A flowchart of a control method for a virtual power plant provided in an exemplary embodiment of the present application includes the following steps:

[0031] Step S20, obtaining the power deviation sequence of the previous time window at the current moment;

[0032] The current moment refers to the real-time point in time when the "get" operation occurs, which can be any time during virtual power plant control. The time window is a fixed-length time interval that is preset in advance, such as 30 minutes, 1 hour, or 50 minutes. The previous time window refers to the fixed-length time interval immediately before the current moment.

[0033] A power deviation sequence is a set of data points arranged in chronological order, representing the value of the control power deviation. This application can extract all "control power deviation" values ​​obtained within the "previous time window" from stored historical data and arrange these values ​​in chronological order to obtain the power deviation sequence for the previous time window at the current moment.

[0034] For example, assuming the time window length is 1 second, then at the current time t, the previous time window refers to the interval from t-1 seconds to t seconds. We need to obtain the 10 control power deviations recorded in this interval and sort them in time sequence to obtain a power deviation sequence.

[0035] Optionally, the present application may obtain the above power deviation sequence by the following method:

[0036] Collect the first operating power at each moment in the previous time window;

[0037] Subtracting each first operating power from the issued power to obtain a plurality of first power deviations;

[0038] Arrange the multiple first power deviations in chronological order to obtain a power deviation sequence.

[0039] It's important to note that the delivered power is a set value that ideally allows the virtual power plant to operate at that power level. However, due to other factors, the actual operating power of a virtual power plant often deviates from the delivered power. Therefore, it's important to capture this deviation and use it to optimize subsequent control of the virtual power plant.

[0040] Step S30, predicting the predicted power error at the next moment of the current moment based on the power deviation sequence of the previous time window;

[0041] After obtaining the power deviation sequence of the previous time window according to the above method, the control power deviation of the virtual power plant at the next moment can be predicted in advance based on this sequence. In other words, based on the historical power deviation, the future control power deviation is predicted, and the passive response is converted into active pre-control, achieving the technical effect of compensating for the prediction deviation in advance and reducing the fluctuation of the actual operating power. In addition, the application adjusts the control strategy before the disturbance, which can improve the resilience of the control system.

[0042] This application can use the power deviation sequence of the previous time window as the model input, organize the data through a sliding time window structure to capture the temporal dependence and fluctuation pattern of the power deviation sequence, and then use a time series prediction algorithm to analyze the evolution trend of the power deviation sequence and output the predicted power error at the next moment. For example, this application can implement the above operations using an LSTM model.

[0043] Step S40, obtaining the cumulative power error of the current time window to which the current moment belongs, and adjusting the control influence factor of the cumulative power error at the next moment according to the relationship between the cumulative power error and the error threshold;

[0044] Based on the above explanation of the previous time window, the current time window and the previous time window have the same time length. The current time window is a time interval of a fixed length adjacent to the previous time window, and the current moment belongs to this time interval.

[0045] The cumulative power error is the sum of the control power errors at all times in the current time window. The error threshold is a preset critical value used to determine whether the cumulative power error exceeds the allowable range.

[0046] The control influence factor is a proportional coefficient of the cumulative power error when it plays a control role on the virtual power plant, and is used to adjust the control influence of the cumulative power error on the virtual power plant.

[0047] The magnitude relationship between the cumulative power error and the error threshold includes two types: the cumulative power error is greater than or equal to the error threshold and the cumulative power error is less than the error threshold. The present application may increase the control influence factor in order to more aggressively eliminate the cumulative deviation of the power when the cumulative power error is greater than or equal to the error threshold; in addition, the control influence factor may be reduced in order to avoid over-adjustment and oscillation. Of course, the present application may also not adjust the control influence factor in order to maintain the current control strength when the cumulative power error is less than the error threshold.

[0048] Exemplarily, the present application includes a relationship information table, which includes the correspondence between the size relationship between the cumulative power error and the error threshold and the control influence factor. After the size relationship between the cumulative power error and the error threshold is determined, the control influence factor can be directly read from the relationship information table, and then the control influence factor of the cumulative power error at the next moment can be adjusted to the corresponding value.

[0049] Exemplarily, the present application may also adjust the control impact factor of the accumulated power error at the next moment by the following formula:

[0050] ,

[0051] Among them, a next To control the impact factor, k1 is the first adjustment coefficient (such as 0.6~0.8), k2 is the second adjustment coefficient (such as 1.2~1.5), a curret is the baseline impact factor, which is a preset value, for example, 1; E cum is the error threshold, E th is the accumulated power error.

[0052] Optionally, the present application may obtain the accumulated power error according to the following steps:

[0053] Collect the second operating power at each moment in the current time window;

[0054] Subtracting each second operating power from the issued power to obtain a plurality of second power deviations;

[0055] The plurality of second power deviations are summed to obtain a cumulative power error.

[0056] The sending power is as explained above, and the calculation method of the control power deviation is the same and will not be repeated here.

[0057] Step S50 , determining the control power of the virtual power plant according to the control influencing factor, the accumulated power error and the predicted power error, and controlling the operation of the virtual power plant at the next moment based on the control power.

[0058] The control impact factor determines the degree to which the cumulative power error and predicted power error influence the control command for the target power at the next moment. The cumulative power error reflects the direction of the system's control deviation, while the predicted power error quantifies an uncertain expected deviation. Combining these three factors, the prediction of external disturbances introduced through forward-looking input processing (predicted power error) and closed-loop feedback correction (cumulative power error) enables dynamic optimized coordinated control of multi-source heterogeneous resources, effectively enhancing system stability and improving the response speed and control accuracy of the virtual power plant.

[0059] For example, the present application may determine the control power of the virtual power plant according to the following formula:

[0060] ,

[0061] Where P is the control power of the virtual power plant, P1 is the preset reference power; a next To control the impact factor, E cum is the error threshold, E th is the accumulated power error.

[0062] In an optional embodiment, if Figure 2 As shown, Figure 2 An optional method embodiment for determining a predicted power error provided by an exemplary embodiment of the present application includes the following steps:

[0063] Step S201, decomposing the high-frequency part and the low-frequency part in the power deviation sequence to obtain a high-frequency component and a low-frequency component;

[0064] The high-frequency portion of the power deviation sequence reflects the instantaneous fluctuations in the controlled power deviation and requires rapid response and adjustment. The low-frequency portion of the power deviation sequence reflects the long-term trend of the controlled power deviation and corresponds to the steady-state regulation requirements of the control system.

[0065] The present application may, for example, decompose the high-frequency part and the low-frequency part in the power deviation sequence according to discrete wavelet transform, inverse wavelet transform, Fourier filtering, VMD algorithm, etc. to obtain high-frequency components and low-frequency components.

[0066] Step S202: synthesize the predicted power error based on the high-frequency component and the low-frequency component.

[0067] Among them, after the present application separates the high-frequency component and the low-frequency component according to the above steps, they can be synthesized according to the following formula to obtain the predicted power error.

[0068] ,

[0069] Among them, E pred is the predicted power error, E L is the low-frequency component, E H is the high frequency component.

[0070] The present application predicts power error by frequency division, which can improve the accuracy of prediction and reduce control error.

[0071] In another optional embodiment, the present application may be based on Figure 3 The method steps shown synthesize the predicted power error:

[0072] Step S301, performing filtering and estimation processing on the high frequency component to obtain a corrected high frequency component;

[0073] Among them, the core purpose of filtering and estimating high-frequency components is to retain effective fluctuation characteristics and suppress noise interference, thereby improving prediction and control accuracy.

[0074] The present application can be to obtain high-frequency components through, for example, wavelet decomposition technology, distinguish effective fluctuations and interference noise in the high-frequency components through Kalman filtering, threshold filtering or frequency domain bandpass filtering technology, and then perform inverse transform reconstruction through wavelet reconstruction, IFFT and other technologies to obtain pure corrected high-frequency components.

[0075] By processing the high-frequency components, high-frequency noise can be eliminated and the true fluctuation characteristics can be retained, thereby achieving the technical effects of suppressing high-frequency noise, preventing control system oscillation, and reducing harmonic resonance.

[0076] Step S302: capturing the evolution law of the low-frequency component, predicting the low-frequency component according to the evolution law, and obtaining a corrected low-frequency component;

[0077] Among them, the core logic of low-frequency component correction is: by mining the regular patterns in historical data and building a prediction model to actively compensate for system deviations.

[0078] The present application may be to separate the low-frequency components through STL decomposition, Hodrick-Prescott filtering and other technologies, and then identify the deterministic evolution laws such as periodicity and trend implicit in the low-frequency components, so as to predict the low-frequency components according to the evolution laws to obtain the corrected low-frequency components.

[0079] For example, the present application may utilize Fourier series fitting techniques to obtain the periodic evolution patterns implicit in low-frequency components. Furthermore, a polynomial regression / Prophet model may be used to obtain the trend evolution patterns implicit in low-frequency components. Furthermore, the periodic evolution patterns and trend evolution patterns may be input into an LSTM neural network to output a corrected low-frequency component.

[0080] Optionally, the present application may also input the low-frequency component into the LightGBM model and obtain the corrected low-frequency component according to the prediction of the model.

[0081] Step S303: synthesize the predicted power error according to the corrected high-frequency component and the corrected low-frequency component.

[0082] For example, the present invention can be synthesized according to the following formula:

[0083] ,

[0084] ΔP low-corrected is the corrected low-frequency component; ΔP high-filtered is the corrected high-frequency component; R residual is the preset residual compensation term; α, β, γ are dynamic weight coefficients, for example, α = 0.7, β = 0.25, γ = 0.05.

[0085] In another optional embodiment, the present application may be based on Figure 4 The method steps shown synthesize the predicted power error:

[0086] Step S401, sorting the corrected high-frequency components and the corrected low-frequency components according to a preset order to obtain a component sequence, wherein the preset order is that the corrected low-frequency components are in front and the corrected high-frequency components are sorted in reverse order of decomposition levels;

[0087] This application places the corrected low-frequency components at the beginning of the sequence and arranges the corrected high-frequency components in reverse order of the original decomposition hierarchy to obtain a component sequence, ensuring strict correspondence between the high-frequency and low-frequency components. Furthermore, this prioritizes preserving the main trend characteristics, and the reverse order of the high-frequency components conforms to the physical logic of signal reconstruction.

[0088] Step S402 : By linearly combining wavelet basis functions, the time-frequency domain information of the high-frequency part and the low-frequency part in the component sequence are fused into a complete time-domain signal to obtain a predicted power error.

[0089] Among them, the core process of using wavelet transform to achieve signal reconstruction is essentially to fuse multi-scale components into time domain signals through orthogonal projection.

[0090] Exemplarily, the present application may be implemented by the following formula:

[0091] ,

[0092] △Perror(t) is the predicted power error, ϕ j,k (t) is the corrected low-frequency component; ψ j,k (t) is the corrected high-frequency component; c L,k is the preset low-frequency component coefficient; d j,k It is the preset high frequency component coefficient.

[0093] In an optional embodiment, the present application may adjust and control the impact factor through the following steps. The method embodiment includes the following steps:

[0094] If the magnitude relationship is that the accumulated power error is less than the error threshold, the control influence factor is reduced according to the preset adjustment integral gain;

[0095] If the magnitude relationship is that the accumulated power error is greater than or equal to the error threshold, the preset adjustment integral gain is used as the control influencing factor.

[0096] The above description can be expressed by the following formula:

[0097] ,

[0098] To control the impact factor, is the error threshold, is the preset adjustment integral gain, and e(t-1) is the accumulated power error.

[0099] In an optional embodiment, if Figure 5 As shown, Figure 5 An optional method embodiment for determining the control power of a virtual power plant provided in an exemplary embodiment of the present application includes the following steps:

[0100] Step S501, updating the cumulative power error according to the control influence factor to obtain a target cumulative power error;

[0101] Step S502: determining the control power according to the target accumulated power error and the predicted power error.

[0102] The updating of the accumulated power error according to the control influence factor is, for example, taking the product of the control influence factor and the accumulated power error as the target accumulated power error.

[0103] Determining the control power based on the target cumulative power error and the predicted power error may, for example, be to use the sum of the target cumulative power error and the predicted power error as the control power, and control the operation of the virtual power plant at the next moment through the control power.

[0104] The formula is as follows:

[0105] ,

[0106] in, is the target cumulative power error, To control the impact factor, is the predicted power error.

[0107] It should be noted here that the above-mentioned control method can be executed in a loop within a control time window, that is, after determining the control power of the virtual power plant at the next moment and controlling the operation of the virtual power plant according to the control power, before the control time window ends, it is necessary to continue to obtain the power deviation sequence of the previous time window at the current moment, but the current moment is replaced by the next moment, that is, the next moment is used as the current moment, and the operation of determining the control power of the virtual power plant at the next moment is executed in a loop until the control time window ends.

[0108] It should be noted that although the operations of the present invention are described in a particular order in the accompanying drawings, this does not require or imply that these operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flowchart can be performed in a different order.

[0109] Further references Figure 6 ,like Figure 6 As shown, Figure 6 A control device for a virtual power plant is provided for this application. The control device includes an acquisition module 601 , a prediction module 602 , an acquisition adjustment module 603 and a determination module 604 .

[0110] An acquisition module 601 is configured to acquire a power deviation sequence of a previous time window at a current moment;

[0111] Prediction module 602, configured to predict the predicted power error at the next moment after the current moment based on the power deviation sequence of the previous time window;

[0112] An acquisition and adjustment module 603 is configured to acquire the cumulative power error of the current time window to which the current moment belongs, and adjust the control influence factor of the cumulative power error at the next moment according to the relationship between the cumulative power error and the error threshold;

[0113] The determination module 604 is used to determine the control power of the virtual power plant according to the control influencing factor, the accumulated power error and the predicted power error, and control the operation of the virtual power plant at the next moment based on the control power.

[0114] In an optional embodiment, the prediction module 602 is specifically configured to decompose the high-frequency part and the low-frequency part in the power deviation sequence to obtain a high-frequency component and a low-frequency component;

[0115] The predicted power error is synthesized based on the high-frequency component and the low-frequency component.

[0116] In an optional embodiment, the prediction module 602 is further configured to perform filtering and estimation processing on the high-frequency component to obtain a corrected high-frequency component;

[0117] Capture the evolution law of the low-frequency component, predict the low-frequency component according to the evolution law, and obtain the corrected low-frequency component;

[0118] The predicted power error is synthesized according to the corrected high-frequency component and the corrected low-frequency component.

[0119] In an optional embodiment, the prediction module 602 is further configured to sort the corrected high-frequency components and the corrected low-frequency components according to a preset order to obtain a component sequence, wherein the preset order is that the corrected low-frequency components are in front and the corrected high-frequency components are arranged in reverse order of the decomposition level.

[0120] Through the linear combination of wavelet basis functions, the time-frequency domain information of the high-frequency part and the low-frequency part in the component sequence are fused into a complete time domain signal to obtain the predicted power error.

[0121] In an optional embodiment, the acquisition adjustment module 603 is specifically configured to reduce the control influence factor according to a preset adjustment integral gain if the magnitude relationship is that the accumulated power error is less than the error threshold;

[0122] If the magnitude relationship is that the accumulated power error is greater than or equal to the error threshold, the preset adjustment integral gain is used as the control influencing factor.

[0123] In an optional embodiment, the determination module 604 is specifically configured to update the cumulative power error according to the control influence factor to obtain a target cumulative power error;

[0124] The control power is determined according to the target accumulated power error and the predicted power error.

[0125] Each module in the above-mentioned control device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The units or modules involved in the embodiments described in this application may be implemented by software or hardware. The units or modules described may also be provided in a processor. For example, it may be described as follows: a processor includes unit XX, unit YY, and unit ZZ. The names of these units or modules do not, in certain circumstances, constitute limitations on the units or modules themselves. For example, unit XX may also be described as a "unit for XX."

[0128] As another aspect, the present application further provides a computer-readable storage medium, which may be included in the apparatus described in the above embodiments, or may be a separate computer-readable storage medium not incorporated into the apparatus. The computer-readable storage medium stores one or more programs, which are used by one or more processors to execute the virtual power plant control method described in the present application.

[0129] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention herein is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features having similar functions disclosed in this application.

Claims

1. A control method for a virtual power plant, characterized in that: The method comprises: Get the power deviation sequence of the previous time window at the current moment; Predicting a predicted power error at the next moment of the current moment according to the power deviation sequence of the previous time window; Obtaining a cumulative power error of a current time window to which the current moment belongs, and adjusting a control influence factor of the cumulative power error at a next moment according to a magnitude relationship between the cumulative power error and an error threshold; determining a control power of the virtual power plant according to the control influencing factor, the accumulated power error, and the predicted power error, and controlling the operation of the virtual power plant at a next moment based on the control power; The step of adjusting the control influence factor of the accumulated power error at the next moment according to the magnitude relationship between the accumulated power error and the error threshold includes: If the magnitude relationship is that the accumulated power error is less than the error threshold, the control influence factor is reduced according to a preset adjustment integral gain; If the magnitude relationship is that the accumulated power error is greater than or equal to the error threshold, the preset adjustment integral gain is used as the control influencing factor, and the adjustment formula is as follows: To control the impact factor, is the error threshold, is the preset adjustment integral gain, and e(t-1) is the accumulated power error.

2. The control method according to claim 1, characterized in that: The predicting the predicted power error at the next moment of the current moment according to the power deviation sequence of the previous time window includes: Decomposing the high-frequency part and the low-frequency part in the power deviation sequence to obtain a high-frequency component and a low-frequency component; The predicted power error is synthesized based on the high frequency component and the low frequency component.

3. The control method according to claim 2, characterized in that: The synthesizing the predicted power error based on the high-frequency component and the low-frequency component includes: Performing filtering and estimation processing on the high-frequency component to obtain a corrected high-frequency component; capturing the evolution law of the low-frequency component, predicting the low-frequency component according to the evolution law, and obtaining a corrected low-frequency component; The predicted power error is synthesized according to the corrected high-frequency component and the corrected low-frequency component.

4. The control method according to claim 3, characterized in that: The synthesizing the predicted power error according to the corrected high-frequency component and the corrected low-frequency component includes: Sorting the corrected high-frequency components and the corrected low-frequency components according to a preset order to obtain a component sequence, wherein the preset order is that the corrected low-frequency components are in front and the corrected high-frequency components are arranged in reverse order of decomposition levels; The predicted power error is obtained by fusion of the time-frequency domain information of the high-frequency part and the low-frequency part in the component sequence into a complete time-domain signal through the linear combination of wavelet basis functions.

5. The control method according to claim 1, characterized in that: The determining the control power of the virtual power plant according to the control influencing factor, the accumulated power error, and the predicted power error includes: Updating the cumulative power error according to the control influencing factor to obtain a target cumulative power error; The control power is determined according to the target accumulated power error and the predicted power error.

6. A control device for a virtual power plant, characterized in that: The device comprises: An acquisition module is used to obtain the power deviation sequence of the previous time window at the current moment; A prediction module, configured to predict a predicted power error at a next moment after the current moment based on the power deviation sequence of the previous time window; an acquisition and adjustment module, configured to acquire a cumulative power error of a current time window to which the current moment belongs, and adjust a control influence factor of the cumulative power error at the next moment according to a magnitude relationship between the cumulative power error and an error threshold; a determination module, configured to determine a control power of the virtual power plant according to the control influencing factor, the accumulated power error, and the predicted power error, and control the operation of the virtual power plant at a next moment based on the control power; The acquisition and adjustment module is specifically configured to reduce the control influence factor according to a preset adjustment integral gain if the magnitude relationship is that the accumulated power error is less than the error threshold; If the magnitude relationship is that the accumulated power error is greater than or equal to the error threshold, the preset adjustment integral gain is used as the control influencing factor, and the adjustment formula is as follows: To control the impact factor, is the error threshold, is the preset adjustment integral gain, and e(t-1) is the accumulated power error.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images