Power plant elastic polymerization method and device considering standby margin, equipment and medium

Abstract

The invention discloses a power plant elastic aggregation method, device, equipment and medium considering a standby margin, relates to the technical field of power system optimization scheduling, and aims to solve the problem of lack of a flexible adjustment elastic aggregation method in the prior art. The method comprises the following steps: through a QR-Siamese LSTM model constructed by quantile regression and twinborn long and short term memory, obtaining a QR-Siamese LSTM model; predicting a flexible resource adjustment potential probability interval; performing aggregation modeling of the flexible resources of the virtual power plant according to the flexible resource adjustment potential probability interval; and solving the aggregation modeling of the flexible resources of the virtual power plant based on error propagation to obtain a standby adjustment margin elastic interval of the virtual power plant. According to the method, the flexible resource adjustment potential probability interval is predicted, and then the adjustment margin elastic interval is obtained through aggregation.

Description

Technical Field

[0001] The present invention relates to the technical field of power system optimization and dispatching, and in particular to a QR-Siamese LSTM-based power plant elastic aggregation method, device, equipment and medium considering reserve margin. Background Art

[0002] Flexible resources are those capable of flexibly adjusting to maintain a dynamic balance between supply and demand. With the increasing availability of flexible resources, renewable energy is also rapidly developing. Currently, how to efficiently integrate these diverse resources, flexibly respond to emergency regulation needs in the power system, and improve the overall economic efficiency of the power system has become a pressing issue.

[0003] Virtual power plants (VPPs) are an innovative energy management solution that leverages advanced information technology and control strategies to aggregate vast amounts of flexible resources into a coordinated, reliable power resource cluster, enabling them to participate in grid demand response control. However, current research on VPPs focuses primarily on analyzing trading mechanisms for VPPs in various markets and studying VPP market bidding strategies. There is limited research on VPPs for grid demand response control.

[0004] Existing research on virtual power plant aggregation technology fails to fully consider the correlation between the power system's reserve regulation margin requirements and the probability and potential range of flexible resources. Instead, it sets a reserve margin range based on a fixed maximum load forecast and the required reserve margin ratio, and then aggregates flexible resources based on this. This virtual power plant aggregation technology increases system reserve regulation costs and reduces system operational economics. Therefore, a flexible and adaptable aggregation method is needed. Summary of the Invention

[0005] In order to overcome the shortcomings of the existing technology, one of the objectives of the present invention is to provide a power plant elastic aggregation method considering the reserve margin, which constructs a QR-SiameseLSTM model to obtain a more accurate and reliable probability prediction interval of flexible resource regulation potential, and then obtains the regulation margin elasticity interval through elastic aggregation.

[0006] One of the purposes of the present invention is achieved by the following technical solution: A power plant resilience aggregation method considering reserve margin includes the following steps: The QR-SiameseLSTM model constructed by quantile regression and twin long short-term memory is used to predict the probability interval of flexible resource adjustment potential; Performing aggregation modeling of flexible resources of the virtual power plant according to the probability interval of the flexible resource regulation potential; The aggregation modeling of the flexible resources of the virtual power plant is solved based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

[0007] Furthermore, in order to fully demonstrate the ability to capture the temporal coupling and nonlinear characteristics of flexible resources, the QR-SiameseLSTM model includes a first LSTM neural network, a second LSTM neural network and a quantile regression layer; The first LSTM neural network is used to output the encoded load elasticity characteristics based on the demand side load sequence data, time-of-use electricity prices, weather parameters, and time information; The second LSTM neural network is used to output an elasticity vector according to the encoded load elasticity feature; The quantile regression layer is used to output the confidence interval of the load forecast; The probability interval of flexible resource adjustment potential is calculated based on the confidence interval, which satisfies: , , in, and are the updated upper and lower bounds of confidence, and They are / 2 quantile level upper and lower boundary prediction deviations, is the probability interval of flexible resource adjustment potential, and are the quantile levels in / 2 and / 2 corresponding predicted value.

[0008] Furthermore, in order to obtain the overall required reserve capacity of the power system, after the calculation of the probability interval of the flexible resource regulation potential, the following is also included: calculating the reserve regulation set capacity interval to meet the following requirements: ,in, represents the occurrence probability conversion function, represents the confidence level of the probability interval of flexible resources, represents the center value of the probability interval, Indicates The quantile level of the prediction interval at time .

[0009] Furthermore, based on the flexible resource adjustment potential probability interval, aggregation modeling of the flexible resources of the virtual power plant is performed, including: According to the number of flexible resources involved in regulation and the number of equipment of each type of resources in the virtual power plant, the algebraic sum of the regulation capacity of the virtual power plant is calculated; The adjustable potential interval characteristics of flexible resources are mapped to the aggregated external adjustable characteristics of the virtual power plant for aggregation calculation to meet the following requirements: , in, Before optimization The forecast load capacity at the time, for Flexible aggregation capacity at all times, Indicates the upper and lower limits of adjustable potential.

[0010] Furthermore, the constraints of the aggregate calculation include technical constraints combining linear network constraints and flexible resource models, and constraints on the aggregate regulation potential of virtual power plants; The technical constraints are satisfied: , , , in, For decision variables The vector of time, , represents the set of technical constraints, , Represents the matrix and vector form of the network constraint set, represents the output power trajectory of the virtual power plant, , Respectively represent the matrix and vector forms of the output power constant coefficient matrix; The virtual power plant aggregate regulation potential constraint satisfy: ,in, and are the quantile levels in / 2 and / 2 corresponding to the predicted value, Indicates the center value.

[0011] Furthermore, based on error propagation, the aggregation modeling of the flexible resources of the virtual power plant is solved to obtain the elastic range of the reserve regulation margin of the virtual power plant, including: The active power flexibility of the virtual power plant is modeled as a multi-faceted projection, and its expression satisfies: ,in, and Calculation parameters representing the active power flexibility range of the virtual power plant Optimize and model the constraints of aggregate computing, eliminate coupling constraints through robust optimization algorithms, and transform uncertain parameters in the constraints into deterministic problems; According to the multi-faceted projection and the optimized constraint conditions, an optimized aggregation calculation formula is constructed, and the aggregation calculation formula is: ,in, represents the occurrence probability conversion function, represents the affine value of the active output power of the virtual power plant, represents the affine value of the virtual battery active output power, represents the affine value of the active output power of the virtual generator, represents the aggregate elastic range of the virtual battery, represents the aggregation scope of the virtual generator, represents the aggregation scope of the virtual power plant; The aggregation calculation formula is solved to obtain the virtual power plant reserve margin elasticity range.

[0012] Furthermore, solving the aggregation calculation formula includes: The aggregation calculation is described by error interval propagation, and an aggregation formula that is convenient for solution is obtained: ,in, represents the interface contraction equation of the polyhedron projection, Representing variables The noise source, 、 Indicates the interval center value and interval radius variables; The elastic range of the virtual power plant reserve margin is obtained by solving the problem.

[0013] A second object of the present invention is to provide a power plant elastic aggregation device that takes into account the backup margin.

[0014] The second object of the present invention is achieved by adopting the following technical solutions: A power plant elastic aggregation device considering reserve margin, comprising: The potential prediction module is used to predict the probability interval of flexible resource adjustment potential through quantile regression and the QR-Siamese LSTM model constructed by twin long short-term memory; an aggregation module, configured to perform aggregation modeling of flexible resources of a virtual power plant according to the probability interval of the flexible resource adjustment potential; A solution module is used to solve the aggregation modeling of the flexible resources of the virtual power plant based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

[0015] The third object of the present invention is to provide an electronic device for performing one of the objects of the invention, which includes a processor, a storage medium and a computer program, wherein the computer program is stored in the storage medium, and when the computer program is executed by the processor, it implements the above-mentioned power plant elastic aggregation method considering the backup margin.

[0016] A fourth object of the present invention is to provide a computer-readable storage medium for storing one of the objects of the invention, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned power plant elastic aggregation method considering the backup margin is implemented.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes a quantitative evaluation of the elasticity interval and elastic aggregation strategy of virtual power plants that considers the reserve regulation margin and flexible resources. By constructing a QR-SiameseLSTM model, an accurate and reliable probability prediction interval of the flexible resource regulation potential is obtained to predict the overall reserve capacity required by the power system. Based on the prediction results, the aggregation calculation of flexible resources is then performed to complete the dynamic evaluation of the overall regulation potential after the aggregation of reserve capacity and flexible resources, thereby improving resource utilization efficiency and saving the system reserve regulation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a flow chart of power plant elastic aggregation considering reserve margin in embodiment 1; Figure 2 1 is a schematic diagram of the wind power regulation potential probability interval prediction result of Example 1; Figure 3 2 is a schematic diagram of the flexible load demand probability interval prediction result of Example 1; Figure 4 This is a schematic diagram of the ordered aggregation results of the virtual power plant in Example 1; Figure 5 Schematic diagram of the optimization result of Example 1; Figure 6 This is a structural block diagram of a power plant elastic aggregation device considering a reserve margin according to a second embodiment; Figure 7 It is a structural block diagram of an electronic device of embodiment 3. DETAILED DESCRIPTION

[0019] The present invention will be described in more detail below with reference to the accompanying drawings. It should be noted that the following description of the present invention with reference to the accompanying drawings is merely illustrative and non-limiting. Various embodiments may be combined with each other to form other embodiments not shown in the following description.

[0020] Example 1 Example 1 provides a power plant elasticity aggregation method considering the reserve margin, which aims to predict the elasticity interval of the flexible resource regulation potential and realize the orderly aggregation of virtual power plants based on the central value of the probability interval of each type of flexible resource. Finally, the interval analysis method is used to consider the dynamic relationship between the flexible resource output probability and the reserve regulation margin probability interval to solve the elastic space of the virtual power plant.

[0021] It should be emphasized that the power plant described in this embodiment and the present invention is specifically a virtual power plant.

[0022] The power system usually needs to consider a certain reserve regulation margin to ensure that the system can still operate safely and stably when encountering peak load or impact disturbance. The reserve regulation margin is a part of the extra capacity reserved by the power system to ensure that it can maintain safe and stable operation under peak load, sudden failure or disturbance. The reserve regulation margin of the power system is usually 25% to 30% of the maximum load forecast value of the day before, including load reserve capacity, accident reserve capacity and maintenance reserve capacity, which are used to deal with load shocks, generator unit accident shutdown and maintenance plans respectively. For example: when the maximum load forecast value of the day before is 100, the reserve regulation margin range is [100 25%, 100 30%]. However, the day-ahead maximum load does not persist for long periods of time and may not reach the predicted value. Planning the reserve regulation margin based on the predicted maximum load value will increase the system's reserve regulation costs and reduce the system's economic efficiency.

[0023] In fact, the reserve regulation margin can be dynamically adjusted according to the changes in load demand. The reserve condition margin demand is different from the conventional load demand. The reserve regulation margin demand has greater flexibility. The elasticity of the reserve regulation margin can be determined by the probability of load occurrence, the possible load range, and the proportion of the reserve regulation margin demand. Specifically, the load demand can be described in the form of a probability interval forecast, for example: the load forecast value has a 68% probability of being within [90, 120] or a 90% probability of being within [80, 125]; correspondingly, the reserve regulation margin has a 68% probability of being within [90 25%, 120 30%], there is a 90% probability of being in [80 25%, 125 30%]. In addition, the proportion of standby regulation margin demand (normally 25-30%) will also be adjusted accordingly according to the probability of load occurrence. Therefore, calculating the probability interval prediction can provide the probability of occurrence of uncertain things and the uncertainty interval in which they are located, and can achieve the characterization and description of the elasticity of the standby regulation margin. Therefore, this embodiment proposes a virtual power plant standby regulation margin quantification and elastic aggregation method based on the QR-SiameseLSTM neural network. This method no longer uses a fixed maximum load forecast value as the base value to set the standby regulation margin interval, but takes into account the probability of load demand occurrence, possible intervals, the required standby regulation margin ratio, and the probability interval prediction results of flexible resources for setting. Under the premise of ensuring system safety, the elastic aggregation of virtual power plants is achieved.

[0024] This example uses a QR-Siamese LSTM model for forecasting because deep learning technology demonstrates strong capabilities in time series forecasting and probabilistic modeling, and offers significant advantages in processing uncertain data and performing correlation analysis. The QR-Siamese LSTM model can learn the probability distribution of load demand based on historical data, thereby generating probabilistic interval forecasts of load demand. The Siamese LSTM neural network excels at capturing similarities between different data points and is suitable for probabilistic interval forecasting and aggregate analysis of flexible resources.

[0025] Based on the above principles, this embodiment proposes a power plant elasticity aggregation method that considers the reserve margin and combines probability interval prediction and its aggregate projection to achieve probability interval prediction of the regulation potential of various types of flexible resources, and realizes orderly aggregation of virtual power plants based on the central value of the probability interval of each type of flexible resource. Finally, an interval analysis method is used to consider the dynamic relationship between the flexible resource output probability and the reserve regulation margin probability interval to solve the virtual power plant elasticity space.

[0026] Please refer to Figure 1 As shown, a power plant resilience aggregation method considering reserve margin includes the following steps: S1. The QR-SiameseLSTM model constructed by quantile regression and twin long short-term memory is used to predict the probability interval of flexible resource adjustment potential; Step S1 is based on the QR-SiameseLSTM neural network model to achieve probability interval prediction of flexible resource regulation potential. First, the Long Short Term Memory (LSTM) neural network is suitable for solving the long-term dependency problem in the training process. The LSTM network contains multiple cell units to process sequence information, and each cell unit contains a forget gate, input gate, and output gate structure. This structure can effectively memorize the time-varying dynamic behavior of data and fully demonstrates the ability to capture the temporal coupling and nonlinear characteristics of flexible resources. SiameseLSTM is a special neural network evolved on the basis of the LSTM network unit. It consists of two LSTM neural networks with the same structure and shared weights ( and ).

[0027] The above QR-SiameseLSTM model includes the first LSTM neural network, the second LSTM neural network and the quantile regression layer; The first LSTM neural network is used to output the encoded load elasticity characteristics based on the demand side load sequence data, time-of-use electricity prices, weather parameters, and time information; The second LSTM neural network is used to output an elasticity vector according to the encoded load elasticity feature; Among them, the first LSTM neural network , the second LSTM neural network The hidden state of each cell 、 They can be expressed as: , , in and They are and The input data, and are the weight parameters of the two neural networks respectively.

[0028] The similarity between two hidden state sequences is calculated using the cosine similarity function: .

[0029] In summary, the Siamese twin neural network structure of this embodiment includes two identical sub-networks that share weights and architecture and capture load elasticity characteristics through a dual-channel LSTM structure.

[0030] Specifically, the first neural network It is used to encode the load elasticity characteristics and analyze the reserve adjustment margin of the virtual power plant's multiple flexible resources, such as wind power generation, photovoltaic power generation, and controllable loads, in the face of the scenario of reduced grid operation flexibility. The input data includes demand-side load series data, time-of-use electricity prices, weather parameters, and time information. The second neural network It is used to estimate the elastic vector that changes with time and reflects the impact of time-varying cumulative error on prediction accuracy. A new density layer, the Sigmoid function, is introduced to transform The encoding vector is converted into an elastic vector : ,in, represents the Sigmoid activation function, represents the weight matrix, Represents the bias vector.

[0031] The output elastic vector can be used to measure the similarity between the predicted value and the observed value at each time step. It is then used as the memory information of the LSTM network in the form of prediction error and is input into the parameter update of the next recurrent unit. This is designed to achieve real-time rolling parameter optimization in multi-step prediction. By using the dual-channel structure of the Siamese neural network to measure the similarity between the predicted value and the observed value, rolling optimization parameters in multi-step prediction can be achieved to reduce prediction error. The specific formula is as follows: ,in, is the learning rate, is the loss function, which takes into account the impact of prediction error and elastic vector, express The model parameters at time t, express The above model structure can significantly improve the prediction accuracy of elastic interval.

[0032] The quantile regression layer is used to output the confidence interval of the load forecast; Specifically, for each training set output result, quantile regression is used to estimate the upper and lower boundaries of the prediction interval. The confidence level of the new output observation value belonging to the prediction interval is set to 1- i, when the input distribution is , output At the quantile Conditional quantile regression function under It can be expressed as: , is the input sample set, To contribute The probability distribution function of , its probability density can be estimated from the conditional quantile regression function corresponding to all training data sets. At this time, the output probability interval length is 1- , output probability interval It can be determined by the predicted values ​​corresponding to the upper and lower quantiles, as shown in the following formula: , in, and are the quantile levels in / 2 and / 2 corresponds to the predicted value. For different input values, the interval width can be dynamically adjusted to effectively adapt to the elastic variation characteristics of the reserve adjustment margin. At the / 2 quantile level, the upper and lower bounds of the original sequence and the new sequence deviate. These deviations can be regarded as and the actual interval The approximate error is calculated as follows: , in, represents the new upper boundary sequence, for exist / 2 prediction deviation value at the quantile level; Indicates the calculation of the sequence quantile level Quantile function under / 2.

[0033] The probability interval of flexible resource adjustment potential is calculated based on the confidence interval. Specifically, the predicted deviation value is superimposed on the original output interval, and the deviation of the original elastic probability interval is corrected to obtain the elastic probability interval corresponding to the set confidence level. The calculation satisfies: , , in, and are the updated upper and lower bounds of confidence, and They are / 2 quantile level upper and lower boundary prediction deviations, is the probability interval of flexible resource adjustment potential, and are the quantile levels in / 2 and / 2 corresponding predicted value.

[0034] The prediction results of the above process can be referred to Figure 2 and Figure 3 As shown, Figure 2 The wind power regulation potential probability interval prediction results are shown. Figure 3 The flexible load demand probability interval forecast results are shown.

[0035] In summary, this embodiment considers the correlation between the standby adjustment margin and the elasticity of flexible resources, dynamically adjusts the standby adjustment margin requirement ratio based on the occurrence probability of flexible resources, and sets the standby adjustment margin interval based on the probability interval prediction result of flexible resources.

[0036] In order to obtain a more specific overall required reserve capacity of the power system, based on the prediction results of the flexible controllable load probability interval, the present invention will adopt a dynamic adjustment strategy for the proportion of reserve regulation margin demand. At this moment, the confidence level of the prediction interval is 1- , the load demand forecast value is the central value of the probability interval, that is, ,in and Respectively Therefore, after calculating the probability interval of flexible resource adjustment potential, the following is also included: calculating the reserve adjustment set capacity interval to meet the following requirements: ,in, The probability conversion function is an empirical formula that is expressed as a nonlinear function based on the quantiles of the standard normal distribution. The key parameters are fitted using historical data. represents the confidence level of the probability interval of flexible resources, represents the center value of the probability interval, Indicates The quantile level of the prediction interval at time , The reserve adjustment margin is set at the current time step based on the probability of occurrence of flexible resources. The higher the probability of occurrence, the higher the proportion of reserve adjustment margin demand.

[0037] S2. performing aggregation modeling of flexible resources of a virtual power plant according to the probability interval of the flexible resource adjustment potential; Step S2 realizes the orderly aggregation of flexible resources of the virtual power plant based on the probability interval characteristics of flexible resources, such as the aforementioned central value. In response to the grid's backup regulation needs, the virtual power plant can provide upward power support to the system immediately. As an equivalent power plant, the backup regulation capability of the virtual power plant follows the definition of power source, that is, it provides additional power to cope with frequency reduction by reducing its load or the discharge of energy storage equipment. The power regulation capability of the virtual power plant is composed of the regulation capabilities of each distributed energy resource within it, and can be reflected in two ways: it can allow multiple distributed power sources to participate in power regulation at the same time. This synchronous regulation can quickly respond to changes in grid demand; secondly, the virtual power plant can also arrange distributed power sources to participate in regulation in a certain order. This sequential regulation allows the virtual power plant to gradually adjust power output at different time points according to changes in grid conditions. In S2, the aggregation modeling of the flexible resources of the virtual power plant is carried out according to the probability interval of the flexible resource regulation potential, including: According to the number of flexible resources involved in regulation and the number of equipment of each type of resources in the virtual power plant, the algebraic sum of the regulation capacity of the virtual power plant is calculated; This embodiment ignores the coupling factor in time sequence and obtains the algebraic sum of the regulation capacity of the virtual power plant as follows:

[0038] Where, and They are the number of flexible resources involved in regulation in the virtual power plant and the number of devices of each type of resources. For the Class resources The maximum upward adjustment margin that a device can provide under the constraints of the scheduling instructions and its own conditions. Indicates the starting time, Indicates the time span, Indicates upward adjustment direction, Indicates The total regulation capacity of the virtual power plant at all times.

[0039] In virtual power plants, various resources are distributed over a wide area, and individual regulation margins are limited. Therefore, a certain scale of flexible resources needs to be aggregated and collectively regulated to optimize the elasticity of the power system, achieving more efficient resource utilization and more stable grid operation. This embodiment proposes a new method for evaluating the aggregate elasticity interval of virtual power plants. This method models the aggregate elasticity interval evaluation problem as a high-dimensional polyhedron projection problem. A dimensionality-reducing polyhedron of a specific shape is used to approximate the aggregate elastic power interval of the virtual power plant.

[0040] In this embodiment, the adjustable potential of each type of flexible resource is mapped as a central value to the aggregated external adjustable characteristics of the virtual power plant, participating in the elastic optimization of the virtual power plant and transforming the uncertainty optimization model into a deterministic optimization model. Specifically, the adjustable potential interval characteristics of the flexible resource are mapped to the aggregated external adjustable characteristics of the virtual power plant for aggregation calculation to meet the following requirements: , in, Before optimization The predicted load capacity at each moment can be obtained by traditional time series forecasting methods, that is, the capacity of the optimization period is predicted based on the trend of historical load data. for The moment-to-moment elastic aggregation capacity, i.e. the regulation potential predicted by S1, Indicates the upper and lower limits of adjustable potential. Figure 4 The diagram below shows the results of the ordered aggregation of virtual power plants. Based on the daily load probability forecast, the flexible aggregation capacity of virtual power plants is determined across 24 time periods with the goal of smoothing the daily load curve. This aggregation scheme, based on the center value of the flexible resource probability interval, can achieve the ordered aggregation of virtual power plants and optimize resource allocation.

[0041] The externally adjustable feature mentioned above refers to aggregating the results of S1 based on the central value, and roughly obtaining the capacity of the virtual power plant regulation.

[0042] The constraints of aggregate calculation include technical constraints combining linear network constraints with flexible resource models, and constraints on the aggregate regulation potential of virtual power plants; The linear network constraints and the flexible resource model are combined to form the technical constraints of the virtual power plant, which meet the following requirements: , , , in, For decision variables The decision variables refer to the adjustment potential of various flexible resources. , The matrix and vector forms of the technical constraint set, , Represents the matrix and vector form of the network constraint set, represents the output power trajectory of the virtual power plant, , Represent the matrix and vector form of the output power constant coefficient matrix; Based on the flexible resource output probability model, the central value of the virtual power plant aggregation regulation potential is calculated, so the virtual power plant aggregation regulation potential constraint satisfy: ,in, and are the quantile levels in / 2 and / 2 corresponding to the predicted value, Indicates the center value.

[0043] S3. Solve the aggregation modeling of the flexible resources of the virtual power plant based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

[0044] Based on the aggregation goal of virtual power plants, S3 models the aggregation problem of multi-type, heterogeneous distributed resources as a high-dimensional polyhedron projection problem, and solves the multi-probability interval superposition quantification problem based on the error propagation law to solve the elastic space of virtual power plants.

[0045] Specifically, the aggregation modeling of the flexible resources of the virtual power plant is solved based on error propagation to obtain the elastic range of the reserve regulation margin of the virtual power plant, including: In a single time period, the active power flexibility of the virtual power plant can be expressed as a polyhedron in the feasible domain. The active power flexibility of the virtual power plant is modeled as a polyhedron projection, and its expression satisfies: ,in, and The calculation parameters of the active power elasticity range of the virtual power plant are represented by: is the projective polyhedron in Period expression, Contains VPP calculation parameters such as the equipment's active and reactive power levels, ramp rate, etc. The constant term on the right side defines the maximum output power of the VPP after considering various technical constraints.

[0046] Considering the dynamic relationship between the reserve regulation margin and flexible resources, it is necessary to flexibly adjust the aggregation range of the virtual power plant and map the external adjustable characteristics of the virtual power plant into a more flexible elastic space. Based on this, this embodiment classifies the flexible resource cluster according to its technical constraints, and uses two approximate models, virtual generators and virtual batteries, to achieve elastic aggregation of virtual power plants. When the probability of flexible resource regulation potential is low, the virtual battery model is often used to participate in the aggregation; when the probability of flexible resource regulation potential is high, it is necessary to increase reliable power sources to improve the safety and stability of the power system, and the virtual generator model is often used to participate in the aggregation.

[0047] Optimize and model the constraints of aggregate computing, eliminate coupling constraints through robust optimization algorithms, and transform uncertain parameters in the constraints into deterministic problems; Specifically, homogeneous clusters composed of homogeneous resources share similar technical constraints and can be modeled using the same approach. Robust optimization algorithms can be used to eliminate the coupling constraints between the two resource types. Specifically, by introducing balance constraints and corresponding auxiliary variables, constraints originally containing uncertain parameters can be transformed into clear linear or quadratic constraints. These transformed problems can then be solved using conventional optimization techniques.

[0048] In order to simplify the model, the decision variables Decomposed into three sub-variables, namely the active power of the virtual generator , the active power of the virtual battery , and the reactive power of all distributed resources , the specific formula is as follows: ,in, and Respectively The constraint matrix and constraint vector at time t.

[0049] First, As the uncertainty parameter in robust optimization, and separating the constraints related to it, the above formula can be rearranged as follows: , Through the robust equivalence method, the robust optimization problem can be transformed into a deterministic problem that is easy to handle. The specific formula is as follows: , , in, 、 、 、 Represent different types of constraint matrices after the total constraint conditions are separated. 、 Represent different types of constraint vectors respectively.

[0050] Finally, the decoupled network constraints of the virtual generators in each period can be simplified as follows: ,in, represents the time-decoupled network constraint matrix, represents the virtual generator output power, represents the time-decoupled network constraint vector.

[0051] With similar calculation steps, the decoupling network constraints of the virtual battery can be expressed as: ,in, Decoupling network constraint matrix and constraint vector representing the virtual battery.

[0052] This completes the construction of decoupling network constraints for two types of homogeneous distributed power sources.

[0053] Consider all the technical constraints of the virtual generator: ,in, represents the constraint matrix, represents the constraint vector.

[0054] The active output power of the virtual generator is expressed as the following affine form: ,in, represents the active output power trajectory, represents the active power conversion matrix, Represents the active power bias vector.

[0055] Thus the origin polyhedron and the corresponding projected polyhedron are: , , in, represents the feasible region of the virtual generator output power, represents the feasible domain of the output power of the virtual generator after dimensionality reduction projection, represents the virtual generator output power, represents the constraint matrix of the projective polyhedron, Represents the constraint vector of the projected polyhedron.

[0056] This embodiment uses an inscribed polyhedron with a similar shape to the target polyhedron to approximate quantization to simplify the complex calculation process and gradually optimizes the polyhedron boundary using the interface shrinkage technique. The advantage of this method is that it can retain the key features of the generator model, such as the Its elastic characteristics can be described by other key parameters, including the ramp limit in each time period ( and ) and the upper and lower limits of power output ( and In this way, the aggregation scope of the virtual generator can be described and analyzed more effectively. The specific formula is as follows: , Further simplified to compact form: , Here is a constant matrix, Define the parameter vector for the key. The specific formula is as follows:

[0057] , , Then, a similar method can be used to solve the aggregation elastic range of the virtual battery , Including energy constraints for each time period ( and ) and power upper and lower bounds ( and ) The formula is as follows: , Further simplified to compact form: , Here is a constant matrix, Define the parameter vector for the key. The specific formula is as follows:

[0058] , .

[0059] In summary, based on the time period and the optimized constraint conditions, an optimized aggregation calculation formula is constructed, and the aggregation calculation formula is: ,in, represents the occurrence probability conversion function, represents the affine value of the virtual power plant output power, represents the affine value of the virtual battery output power, represents the affine value of the active output power of the virtual generator, represents the aggregate elastic range of the virtual battery, represents the aggregation scope of the virtual generator, represents the aggregation scope of the virtual power plant; The aggregation calculation formula is solved to obtain the virtual power plant reserve margin elasticity range.

[0060] Based on the probabilistic prediction results of flexible resources, the variables in the above elastic space are all described in the form of intervals. The deterministic aggregation problem of flexible resources is transformed into a probability interval superposition problem. This embodiment solves the above model based on the error propagation law. Since the output probability prediction of flexible resources has an error interval, its elastic space mapping also contains an error interval. This phenomenon can be explained by the error propagation law. If the prediction error is defined as , define the function error as , the error propagation law is: , Where, is the transfer function from prediction error to function error, 、 represent observed values ​​and predicted values, respectively.

[0061] Assume that the confidence interval of the output forecast of flexible resources is ,According to the interval analysis method, it can be expressed in affine form as: ,in, and Indicates the center value and radius of the interval.

[0062] in, ; Indicates independent variables The noise source, in this embodiment .

[0063] In this embodiment, the power variable is represented by combining two variables, the interval center value and the interval radius, in the elastic space mapping to solve the model. The superposition problem of the probability interval of flexible resources can be simplified and decomposed into two core steps: the first step is to use the interval center value as the main body to participate in the elastic optimization of the virtual power plant to meet the rigid load demand in the day-ahead forecast; the second step is to solve the elastic interval of the standby adjustment margin, and consider the error propagation effect caused by the potential uncertainty within the interval radius. The interval analysis method based on the error propagation law adopted by the present invention can effectively solve the interval expansibility problem and is suitable for analyzing the result interval in the interval aggregation problem. The central value variable of the flexible resource output forecast is used Participate in solving the feasible domain model of virtual power plant aggregation and obtain the set confidence level 1- The center value of the spare adjustable margin under .

[0064] In summary, solving the aggregation calculation formula includes: The aggregation calculation is described by error interval propagation, and an aggregation formula that is convenient for solution is obtained: ,in, The interface contraction equation of the polyhedron projection is a quantitative description of the boundary after the dimensionality reduction projection of the high-dimensional aggregation range, that is, the feasible domain of the variable. express The derivative of , which represents the rate at which the polyhedron projection interface changes with the variable, represents the noise element of the variable, 、 represents the center value variable and radius variable of the virtual power plant; The elastic range of the virtual power plant reserve margin is obtained by solving the problem.

[0065] Based on the ordered aggregation results of the central value variables of the flexible resource output model in step S2, the rigid load capacity after power system elasticity optimization and the reserve regulation margin capacity set considering the probability of flexible resource occurrence can be obtained. Due to the interval characteristics of flexible load, this embodiment uses an interval analysis method to characterize the elasticity of the reserve regulation margin. Based on the probability of occurrence and possible interval of flexible resources, and taking into account the cost-investment benefit of power system reserve regulation, the lower bound of the reserve regulation margin interval is determined using the possible interval with a lower output probability (e.g., 90%). Taking into account the safety and stability of the power system, the upper bound of the reserve regulation margin interval is determined using the possible interval with a higher output probability (e.g., 95%), i.e., a more abundant interval value. By solving the dynamic relationship between flexible resources and the probability interval of the reserve regulation margin, the elastic space of the virtual power plant is solved, achieving more accurate and efficient elastic optimization scheduling.

[0066] Please refer to Figure 5 The schematic diagram of the optimization results shown is the probability interval of the virtual power plant obtained based on the confidence level set at 90% and 95%.

[0067] Example 2 Example 2 discloses a device corresponding to the power plant elastic aggregation method considering the reserve margin corresponding to the above embodiment, which is a virtual device structure of the above embodiment, please refer to Figure 6 As shown, including: Potential prediction module 210, used to predict the probability interval of flexible resource adjustment potential through quantile regression and QR-Siamese LSTM model constructed by twin long short-term memory; an aggregation module 220 for performing aggregation modeling of flexible resources of a virtual power plant according to the flexible resource adjustment potential probability interval; The solving module 230 is used to solve the aggregation modeling of the flexible resources of the virtual power plant based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

[0068] Preferably, the QR-SiameseLSTM model includes a first LSTM neural network, a second LSTM neural network and a quantile regression layer; The first LSTM neural network is used to output the encoded load elasticity characteristics based on the demand side load sequence data, time-of-use electricity prices, weather parameters, and time information; The second LSTM neural network is used to output an elasticity vector according to the encoded load elasticity feature; The quantile regression layer is used to output the confidence interval of the load forecast; The probability interval of flexible resource adjustment potential is calculated based on the confidence interval, which satisfies: , , in, and are the updated upper and lower bounds of confidence, and They are / 2 quantile level upper and lower boundary prediction deviations, is the probability interval of flexible resource adjustment potential, and are the quantile levels in / 2 and / 2 corresponding predicted value.

[0069] Preferably, after calculating the probability interval of the flexible resource adjustment potential, the method further includes: calculating the reserve adjustment set capacity interval to meet the following requirements: ,in, represents the occurrence probability conversion function, represents the confidence level of the probability interval of flexible resources, represents the center value of the probability interval, Indicates The quantile level of the prediction interval at time .

[0070] Preferably, the aggregation modeling of the flexible resources of the virtual power plant is performed according to the flexible resource adjustment potential probability interval, including: According to the number of flexible resources involved in regulation and the number of equipment of each type of resources in the virtual power plant, the algebraic sum of the regulation capacity of the virtual power plant is calculated; The adjustable potential interval characteristics of flexible resources are mapped to the aggregated external adjustable characteristics of the virtual power plant for aggregation calculation to meet the following requirements: , in, Before optimization The forecast load capacity at the time, for Flexible aggregation capacity at all times, Indicates the upper and lower limits of adjustable potential.

[0071] Preferably, the constraints of the aggregate calculation include technical constraints combining linear network constraints and flexible resource models, and constraints on the aggregate regulation potential of virtual power plants; The technical constraints are satisfied: , , , in, For decision variables The vector of time, , The matrix and vector forms of the technical constraint set, , Represents the matrix and vector form of the network constraint set, represents the output power trajectory of the virtual power plant, , Represent the matrix and vector form of the output power constant coefficient matrix; The virtual power plant aggregate regulation potential constraint satisfy: ,in, and are the quantile levels in / 2 and / 2 corresponding to the predicted value, Indicates the center value.

[0072] Preferably, the aggregation modeling of the flexible resources of the virtual power plant is solved based on error propagation to obtain the elastic range of the reserve regulation margin of the virtual power plant, including: The active power flexibility of the virtual power plant is modeled as a multi-faceted projection, and its expression satisfies: ,in, and Calculation parameters representing the active power flexibility range of the virtual power plant Optimize and model the constraints of aggregate computing, eliminate coupling constraints through robust optimization algorithms, and transform uncertain parameters in the constraints into deterministic problems; According to the multi-faceted projection and the optimized constraint conditions, an optimized aggregation calculation formula is constructed, and the aggregation calculation formula is: ,in, represents the occurrence probability conversion function, represents the affine value of the active output power of the virtual power plant, represents the affine value of the virtual battery active output power, represents the affine value of the active output power of the virtual generator, represents the aggregate elastic range of the virtual battery, represents the aggregation scope of the virtual generator, represents the aggregation scope of the virtual power plant; The aggregation calculation formula is solved to obtain the virtual power plant reserve margin elasticity range.

[0073] Preferably, solving the aggregation calculation formula includes: The aggregation calculation is described by error interval propagation, and an aggregation formula that is convenient for solution is obtained: ,in, The interface contraction equation representing the polyhedron projection is a quantitative description of the boundary after the dimensionality reduction projection of the high-dimensional aggregation range. Representing variables The noise source, 、 Indicates the interval center value and interval radius variables; The elastic range of the virtual power plant reserve margin is obtained by solving the problem.

[0074] Example 3 Figure 7 This is a structural diagram of an electronic device provided in the third embodiment of the present invention, such as Figure 7 As shown, the electronic device includes a processor 310, a memory 320, an input device 330 and an output device 340; the number of processors 310 in the computer device can be one or more. Figure 7 In the figure, a processor 310 is used as an example; the processor 310, memory 320, input device 330 and output device 340 in the electronic device can be connected via a bus or other means. Figure 7 The bus connection is taken as an example.

[0075] Memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the method for resilient aggregation of power plants considering reserve margins in the embodiments of the present invention. Processor 310 executes the software programs, instructions, and modules stored in memory 320 to execute various functional applications and data processing of the electronic device, thereby implementing the method for resilient aggregation of power plants considering reserve margins in the first embodiment described above.

[0076] The memory 320 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the terminal, etc. Furthermore, the memory 320 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include a memory remotely located relative to the processor 310, and these remote memories may be connected to the electronic device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0077] The input device 330 may be used to receive input user identity information, virtual power plant data, etc. The output device 340 may include a display device such as a display screen.

[0078] Example 4 A fourth embodiment of the present invention further provides a storage medium containing computer-executable instructions, which can be used by a computer to execute a method for elastic aggregation of power plants considering reserve margins, the method comprising: The QR-SiameseLSTM model constructed by quantile regression and twin long short-term memory is used to predict the probability interval of flexible resource adjustment potential; Performing aggregation modeling of flexible resources of the virtual power plant according to the probability interval of the flexible resource regulation potential; The aggregation modeling of the flexible resources of the virtual power plant is solved based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

[0079] Of course, the storage medium containing computer-executable instructions provided in an embodiment of the present invention is not limited to the method operations described above, and can also execute related operations in the power plant elastic aggregation method based on consideration of the backup margin provided in any embodiment of the present invention.

[0080] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware. Of course, it can also be implemented with hardware, but in many cases the former is a more preferred embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the existing technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., and includes a number of instructions for enabling an electronic device (such as a mobile phone, personal computer, server, or network device) to execute the methods described in various embodiments of the present invention.

[0081] It is worth noting that in the above-mentioned embodiment of the power plant elastic aggregation method device based on consideration of the backup margin, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0082] Those skilled in the art can make various other corresponding changes and deformations based on the technical solutions and concepts described above, and all of these changes and deformations should fall within the scope of protection of the claims of the present invention.

Claims

1. A power plant elastic aggregation method considering reserve margin, characterized in that: The following steps are involved: The QR-SiameseLSTM model constructed by quantile regression and twin long short-term memory is used to predict the probability interval of flexible resource adjustment potential; Performing aggregation modeling of flexible resources of the virtual power plant according to the probability interval of the flexible resource regulation potential; The aggregation modeling of the flexible resources of the virtual power plant is solved based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

2. The power plant elastic aggregation method considering reserve margin according to claim 1, characterized in that: The QR-SiameseLSTM model includes a first LSTM neural network, a second LSTM neural network and a quantile regression layer; The first LSTM neural network is used to output the encoded load elasticity characteristics based on the demand side load sequence data, time-of-use electricity prices, weather parameters, and time information; The second LSTM neural network is used to output an elasticity vector according to the encoded load elasticity feature; The quantile regression layer is used to output the confidence interval of the load forecast; The probability interval of flexible resource adjustment potential is calculated based on the confidence interval, which satisfies: ， ， in, and are the updated upper and lower bounds of confidence, and They are / 2 quantile level upper and lower boundary prediction deviations, is the probability interval of flexible resource adjustment potential, and are the quantile levels in / 2 and / 2 corresponding predicted value.

3. The power plant elastic aggregation method considering reserve margin according to claim 2, characterized in that: After calculating the probability interval of flexible resource adjustment potential, the following is also included: calculating the reserve adjustment set capacity interval to meet the following requirements: ,in, represents the occurrence probability conversion function, represents the confidence level of the probability interval of flexible resources, represents the center value of the probability interval, Indicates The quantile level of the prediction interval at time t.

4. The power plant elastic aggregation method considering reserve margin according to claim 1, characterized in that: Based on the probability interval of the flexible resource regulation potential, aggregate modeling of the flexible resources of the virtual power plant is performed, including: According to the number of flexible resources involved in regulation and the number of equipment of each type of resources in the virtual power plant, the algebraic sum of the regulation capacity of the virtual power plant is calculated; The adjustable potential interval characteristics of flexible resources are mapped to the aggregated external adjustable characteristics of the virtual power plant for aggregation calculation to meet the following requirements: ， in, Before optimization The forecast load capacity at the time, for Flexible aggregation capacity at all times, Indicates the upper and lower limits of adjustable potential.

5. The power plant elastic aggregation method considering reserve margin according to claim 4, characterized in that: The constraints of the aggregate calculation include technical constraints combining linear network constraints and flexible resource models, and constraints on the aggregate regulation potential of virtual power plants; The technical constraints satisfy: ， ， ， in, For decision variables The vector of time, , The matrix and vector forms of the technical constraint set, , Represents the matrix and vector form of the network constraint set, represents the output power trajectory of the virtual power plant, , Represent the matrix and vector form of the output power constant coefficient matrix; The virtual power plant aggregate regulation potential constraint satisfy: ,in, and are the quantile levels in / 2 and / 2 corresponding to the predicted value, Indicates the center value.

6. The power plant elastic aggregation method considering reserve margin according to claim 5, characterized in that: Based on error propagation, the aggregation modeling of the flexible resources of the virtual power plant is solved to obtain the elastic range of the reserve regulation margin of the virtual power plant, including: The active power flexibility of the virtual power plant is modeled as a multi-faceted projection, and its expression satisfies: ,in, and Calculation parameters representing the active power flexibility range of the virtual power plant; Optimize and model the constraints of aggregate computing, eliminate coupling constraints through robust optimization algorithms, and transform uncertain parameters in the constraints into deterministic problems; According to the multi-faceted projection and the optimized constraint conditions, an optimized aggregation calculation formula is constructed, and the aggregation calculation formula is: ,in, represents the occurrence probability conversion function, represents the affine value of the active output power of the virtual power plant, represents the affine value of the virtual battery active output power, represents the affine value of the active output power of the virtual generator, represents the aggregate elastic range of the virtual battery, represents the aggregation scope of the virtual generator, represents the aggregation scope of the virtual power plant; The aggregation calculation formula is solved to obtain the virtual power plant reserve margin elasticity range.

7. The power plant elastic aggregation method considering reserve margin according to claim 6, characterized in that: Solving the aggregation calculation formula includes: The aggregation calculation is described by error interval propagation, and an aggregation formula that is convenient for solution is obtained: ,in, represents the interface contraction equation of the polyhedron projection, Representing variables The noise source, 、 Indicates the interval center value and interval radius variables; The elastic range of the virtual power plant reserve margin is obtained by solving the problem.

8. A power plant elastic aggregation device considering reserve margin, characterized in that: It includes: The potential prediction module is used to predict the probability interval of flexible resource adjustment potential through quantile regression and the QR-Siamese LSTM model constructed by twin long short-term memory; an aggregation module, configured to perform aggregation modeling of flexible resources of a virtual power plant according to the probability interval of the flexible resource adjustment potential; A solution module is used to solve the aggregation modeling of the flexible resources of the virtual power plant based on error propagation to obtain the elastic range of the standby regulation margin of the virtual power plant.

9. An electronic device comprising a processor, a storage medium, and a computer program, wherein the computer program is stored in the storage medium, When the computer program is executed by a processor, the method for power plant resilience aggregation considering reserve margin as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for power plant resilience aggregation considering reserve margin as described in any one of claims 1 to 7 is implemented.

Images