Control method of virtual power plant, control device of virtual power plant, and smart grid

Abstract

The application provides a virtual power plant control method, a virtual power plant control device and a smart grid. The method comprises the following steps: obtaining target power data and a communication state of a communication line, and determining a first influence probability of the influence of the communication state on the target power data according to the communication state of the communication line and the target power data; determining whether the first influence probability is greater than a first probability threshold; in the case where the first influence probability is greater than the first probability threshold, determining that an interval of the target power data corresponding to the first influence probability is a target power interval; and controlling the virtual power plant to regulate a power system according to the target power interval. The method solves the problem that the power interval prediction of the virtual power plant in the prior art is inaccurate, which affects the operation of the virtual power plant.

Description

Technical Field

[0001] This application relates to the field of virtual power plants, and more specifically, to a control method for a virtual power plant, a control device for a virtual power plant, a computer-readable storage medium, and a smart grid. Background Technology

[0002] A Virtual Power Plant (VPP) is a system that aggregates various distributed resources, such as distributed energy sources, energy storage devices, and adjustable loads, into a "virtual" power plant. Through information and communication technologies, it enables coordinated control and optimized scheduling, further participating in power system operation and market transactions. Existing research typically assumes perfect information communication between resources within a virtual power plant, meaning there are no issues such as communication delays, packet loss, or interference. However, in practical applications, due to the complexity and instability of the internal communication network of a virtual power plant, these problems are unavoidable. Variations in communication quality affect the assessment of the virtual power plant's power adjustability, thus impacting the effectiveness of coordinated control among resources within the virtual power plant, posing challenges to its operation.

[0003] Therefore, there is an urgent need for a method to solve the problem of inaccurate power range prediction in existing technologies, which affects the operation of virtual power plants. Summary of the Invention

[0004] The main objective of this application is to provide a control method for a virtual power plant, a control device for a virtual power plant, a computer-readable storage medium, and a smart grid, so as to at least solve the problem of inaccurate power range prediction in the prior art, which affects the operation of the virtual power plant.

[0005] According to one aspect of this application, a control method for a virtual power plant is provided. The virtual power plant includes a communication line and is used to regulate a power system. The method includes: acquiring target power data and the communication status of the communication line; determining a first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data; wherein the target power data is multiple power data of the virtual power plant within a predetermined time period; the communication status includes packet loss rate, bit error rate, delay rate, and reliability of the communication line; and the influence of the communication status on the target power data includes increasing or decreasing the target power data; determining whether the first probability of influence is greater than a first probability threshold; if the first probability of influence is greater than the first probability threshold, determining the interval of the target power data corresponding to the first probability of influence as a target power interval; and controlling the virtual power plant to regulate the power system according to the target power interval.

[0006] Optionally, obtaining target power data includes: obtaining target historical power data, wherein the target historical power data includes multiple power data of the virtual power plant before the predetermined time period, part of the target historical power data is test data and the other part is training data; inputting the test data sequentially into a power prediction model to obtain multiple predicted power data, wherein the power prediction model is trained by machine learning using multiple sets of first historical data, each set of data in the multiple sets of first historical data includes: the training data of a first time period and the training data of a second time period, the start time of the second time period is after the end time of the first time period, and the predicted power data is the power data after the test data; obtaining multiple sets of random noise data and a second influence probability of the random noise data on the predicted power data, and concatenating the multiple sets of random noise data and the predicted power data at the same time to obtain concatenated data, wherein the influence of the random noise data on the predicted power data includes increasing or decreasing the predicted power data; determining whether the second influence probability is greater than a second probability threshold, and if the second influence probability threshold is greater than the second probability threshold, determining the concatenated data corresponding to the second influence probability as the target power data.

[0007] Optionally, obtaining target historical power data includes: obtaining second historical data, wherein the second historical data includes multiple power data of the virtual power plant before the predetermined time period; processing the second historical data using a dynamic time warping algorithm to obtain third historical data; obtaining meteorological parameters corresponding to the second historical data and the meteorological parameters of the third historical data, and applying the formula... Calculate the weighting coefficient w of the i-th third historical data. i Where m is the number of meteorological parameters in the third historical data, and α j x is the weighting coefficient for the j-th meteorological parameter. ij Let y be the value of the j-th meteorological parameter corresponding to the i-th third historical data. j Let j be the value of any j-th meteorological parameter of the second historical data; determine the product of the third historical data and the corresponding weighting coefficient as the target historical power data.

[0008] Optionally, acquiring multiple sets of random noise data includes: calculating the mean and variance of multiple predicted power data; and generating multiple sets of random noise data using a random number generator based on the mean and variance, wherein the random noise data follows a Gaussian distribution.

[0009] Optionally, obtaining the second probability of the influence of the random noise data on the predicted power data includes: obtaining the probability density function corresponding to each time step of the random noise data; and according to the formula... The second influence probability F is calculated to be less than or equal to q for the spliced ​​data at time j. j (q), where f j (t) is the probability density function corresponding to the j-th time step of the random noise data.

[0010] Optionally, obtaining the communication status of the communication line includes: according to the formula Calculate the packet loss rate ε of the k-th communication line. k ,in, The probability that the k-th communication line transmits m data packets at the current time and M data packets at the next time; according to the formula Calculate the bit error rate of the k-th communication line. Where r is the signal-to-noise ratio of the k-th communication line, and erfc() is the complementary error function; according to the formula Calculate the delay rate γ of the k-th communication line. k , where τ k Let τ be the end-to-end delay of the k-th communication line. kmin Let α be the minimum end-to-end delay of the k-th communication line, and let α be the coefficient of network load rate on the delay rate; according to the formula... Calculate the reliability μ of the k-th communication line. k The communication line includes multiple components, x n This refers to the operating state of the nth component, which includes a normal state and a fault state, v ki The probability that the i-th element is in the normal operating state.

[0011] Optionally, based on the communication status of the communication line and the target power data, determining a first probability of influence of the communication status on the target power data includes: according to the formula: The reliability Φ of the k-th communication line k , where ε k Let be the bit error rate of the k-th communication line. Let γ be the bit error rate of the k-th communication line. k Let μ be the delay rate of the k-th communication line. k Let a, b, c, and d be the reliability of the k-th communication line, and a, b, c, and d be the weighting coefficients of the packet loss rate, the delay rate, the bit error rate, and the reliability rate, respectively, with a + b + c + d = 1; according to the formula... Calculate the first influence probability P, Φ k p represents the reliability of the k-th communication line. k p is the target power data of the k-th communication line after being affected by the communication state, and p is the target power data of the k-th communication line before being affected by the communication state.

[0012] According to another aspect of this application, a control device for a virtual power plant is provided. The virtual power plant includes a communication line and is used to regulate a power system. The device includes: an acquisition unit, configured to acquire target power data and the communication status of the communication line, and determine a first probability of influence of the communication status on the target power data based on the communication status and the target power data. The target power data comprises multiple power data points of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate, bit error rate, latency rate, and reliability of the communication line. The influence of the communication status on the target power data includes increasing or decreasing the target power data. A determination unit, configured to determine whether the first probability of influence is greater than a first probability threshold, and if the first probability of influence is greater than the first probability threshold, determine the interval of the target power data corresponding to the first probability of influence as a target power interval. A control unit, configured to control the virtual power plant to regulate the power system according to the target power interval.

[0013] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0014] According to another aspect of this application, a smart grid is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0015] The technical solution of this application first acquires target power data and the communication status of the communication line, and determines a first probability of influence of the communication status on the target power data based on the communication status and the target power data. Then, it determines whether the first probability of influence is greater than a first probability threshold. If the first probability of influence is greater than the first probability threshold, the range of target power data corresponding to the first probability of influence is determined as the target power range. Finally, the virtual power plant is controlled to regulate the power system according to the target power range. By introducing the communication status of the communication line, including the packet loss rate, bit error rate, delay rate, and reliability rate of the communication line, the probability of influence of the communication status on the power of the virtual power plant is further determined. Based on this probability of influence, an accurate power range is determined, and precise control of the power system is achieved. This solves the problem in the prior art where inaccurate prediction of the power range of the virtual power plant leads to problems affecting the operation of the virtual power plant. Attached Figure Description

[0016] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A hardware structure block diagram of a mobile terminal for executing a control method for a virtual power plant according to an embodiment of this application is shown.

[0018] Figure 2 A flowchart illustrating a control method for a virtual power plant according to an embodiment of this application is shown.

[0019] Figure 3 A schematic diagram of predicted power data provided according to an embodiment of this application is shown;

[0020] Figure 4 A schematic diagram of predicted power data provided in an embodiment according to this application is shown;

[0021] Figure 5 A schematic diagram of a target power range provided according to an embodiment of this application is shown;

[0022] Figure 6 A structural block diagram of a control device for a virtual power plant according to an embodiment of this application is shown;

[0023] The above figures include the following reference numerals:

[0024] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] As described in the background section, the power range prediction of virtual power plants in the prior art is inaccurate, which affects the operation of virtual power plants. In order to solve the above problems, the embodiments of this application provide a control method for virtual power plants, a control device for virtual power plants, a computer-readable storage medium, and a smart grid.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a virtual power plant control method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the virtual power plant control method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] This embodiment provides a control method for a virtual power plant that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] The virtual power plant includes communication lines and is used to regulate the power system. Figure 2 This is a flowchart of a control method for a virtual power plant according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0034] Step S201: Obtain target power data and the communication status of the communication line, and determine the first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0035] Specifically, the target power data mentioned above can be predicted data obtained through various models, or historical power data. In practical applications, the complexity and instability of the communication network within the virtual power plant—namely, the changes in the communication status—affect the assessment of the virtual power plant's power adjustability, thereby impacting the collaborative control effect among resources within the virtual power plant. The packet loss rate refers to the proportion of data packets lost during transmission in network communication. A higher packet loss rate indicates poorer network transmission quality, potentially leading to incomplete or delayed data transmission. The bit error rate refers to the proportion of errors in received data in digital communication. A higher bit error rate indicates poorer data transmission reliability, potentially causing the receiver to be unable to correctly parse the data. The latency rate refers to the time delay experienced by data packets from the sender to the receiver. A higher latency rate indicates slower data transmission speed, potentially causing stuttering or delays in applications with high real-time requirements (such as video calls and online games). The reliability rate refers to the proportion of data that the receiver can correctly receive during data transmission. A higher reliability rate indicates better data transmission reliability, ensuring the receiver receives the sender's data completely.

[0036] Step S202: Determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range.

[0037] Specifically, the impact of the aforementioned communication state on the aforementioned target power data includes increasing or decreasing the aforementioned target power data. In other words, the aforementioned probability includes three cases: the probability that the aforementioned target power data after not being affected by the aforementioned communication state is higher than the aforementioned target power data after being affected by the aforementioned communication state, given the reliability of the communication line; the probability that the aforementioned target power data after not being affected by the aforementioned communication state is the same as the aforementioned target power data after being affected by the aforementioned communication state; and the probability that the aforementioned target power data after not being affected by the aforementioned communication state is lower than the aforementioned target power data after being affected by the aforementioned communication state.

[0038] Step S203: Control the virtual power plant to regulate the power system according to the target power range.

[0039] Specifically, after obtaining the target power range, the power of the virtual power plant can be set within the target power range to further achieve precise control of the power system.

[0040] This embodiment first acquires target power data and the communication status of the communication line. Based on the communication status and target power data, it determines a first probability of influence of the communication status on the target power data. Then, it determines whether the first probability of influence is greater than a first probability threshold. If the first probability of influence is greater than the first probability threshold, it determines the range of target power data corresponding to the first probability of influence as the target power range. Finally, it controls the virtual power plant to regulate the power system according to the target power range. By introducing the communication status of the communication line, including packet loss rate, bit error rate, latency rate, and reliability rate, the probability of influence of the communication status on the power of the virtual power plant is further determined. Based on this probability of influence, an accurate power range is determined, and precise control of the power system is achieved. This solves the problem in the prior art where inaccurate prediction of the power range of the virtual power plant affects its operation.

[0041] In specific implementation, step S201 can be achieved through the following steps: Step S2011, acquire target historical power data, wherein the target historical power data includes multiple power data of the virtual power plant before the predetermined time period, part of the target historical power data is test data, and the other part is training data; Step S2012, input the test data into the power prediction model in sequence to obtain multiple predicted power data, wherein the power prediction model is trained by machine learning using multiple sets of first historical data, and each set of the first historical data includes: the training data of the first time period and the training data of the second time period, wherein the start time of the second time period is the same as that of the first time period. After the end of the segment, the predicted power data is the power data following the test data; in step S2013, multiple sets of random noise data and the second influence probability of the random noise data on the predicted power data are obtained, and the multiple sets of random noise data and the predicted power data at the same time are spliced ​​together to obtain spliced ​​data, wherein the influence of the random noise data on the predicted power data includes increasing or decreasing the predicted power data; in step S2014, it is determined whether the second influence probability is greater than a second probability threshold. If the second influence probability threshold is greater than the second probability threshold, the spliced ​​data corresponding to the second influence probability is determined to be the target power data. This method can further quickly obtain the target power data.

[0042] Specifically, the power prediction model mentioned above can be an FNN-GRU model. FNN-GRU is a hybrid or ensemble model that combines a Feedforward Neural Network (FNN) and a Gated Recurrent Unit (GRU). It can be used to handle prediction or classification problems of sequence data. The basic idea of ​​FNN-GRU is to use FNN to process static features and GRU to process dynamic features, then fuse or weighted average the outputs of both to obtain the final prediction result. The structure of FNN-GRU includes an input layer, an FNN layer, a GRU layer, a fusion layer, and an output layer. The input layer receives various features of the sequence data, such as time, temperature, and humidity. The FNN layer performs linear transformations and nonlinear activations on the input data to extract static features. It consists of multiple layers, each of which is a linear transformation plus a nonlinear activation function. FNN can extract and transform features from input data to learn higher-level abstract representations; GRU layer is used to input the data from the input layer into GRU units in chronological order, and extract dynamic features using gating mechanism and memory unit; fusion layer is used to fuse or weighted average the outputs of FNN layer and GRU layer to obtain a comprehensive feature vector; output layer is used to perform linear transformation and activation function on the output of fusion layer according to the prediction or classification target to obtain the final prediction or classification result.

[0043] Furthermore, the steps to obtain the above-mentioned spliced ​​data are as follows: The predicted adjustable power of the virtual power plant is represented as a numerical sequence of length n, denoted as P = {p1, p2, ..., p...}. n}. Where p i Let N represent the predicted power data at time i. Each set of random noise data is represented as a numerical sequence of length n, denoted as N. i ={n i1 ,n i2 ,...,n in}. Where, n ij Let Q represent the noise value at time j in the i-th noise sequence. Each noise sequence is added element-wise to the virtual power plant's adjustable power prediction value to obtain a new prediction value, denoted as Q. i ={q i1 ,q i2 ,...,q in}. Where, q ij =p j +n ijThis represents the spliced ​​power data value at time j in the i-th set of new predictions. Repeat the above steps to obtain m sets of new predictions, based on the required number of new predictions (m). Each set of new predictions reflects the changes in the adjustable power baseline of the virtual power plant under different noise levels.

[0044] To further expedite the acquisition of the aforementioned target historical power data, step S2011 of this application can be implemented through the following steps: Step S20111, acquiring second historical data, wherein the second historical data includes multiple power data of the virtual power plant prior to the predetermined time period; Step S20112, processing the second historical data using a dynamic time warping algorithm to obtain third historical data; Step S20113, acquiring the meteorological parameters corresponding to the second historical data and the meteorological parameters of the third historical data, and applying the formula... Calculate the weighting coefficient w for the i-th of the aforementioned third historical data. i Where m is the number of meteorological parameters in the aforementioned third historical data, and α j Let x be the weighting coefficient for the j-th of the aforementioned meteorological parameters. ij Let y be the value of the j-th meteorological parameter corresponding to the i-th third historical data point mentioned above. j Let j be the value of any of the above-mentioned second historical data; in step S20114, determine the product of the above-mentioned third historical data and the corresponding weight coefficient as the above-mentioned target historical power data.

[0045] Specifically, Dynamic Time Warping (DTW) is a method for measuring the similarity between two time series. It can handle situations where the two series have different lengths or non-linear deformations. The basic steps of the DTW method are as follows: Construct a two-dimensional matrix, where the rows and columns correspond to the elements of the two series, and each element in the matrix represents the distance between corresponding elements in the two series. Starting from the top left corner of the matrix, find a path that minimizes the sum of all elements on the path; this path is called the optimal alignment path. Calculate the sum of all elements on the optimal alignment path as the DTW distance between the two series. The smaller the DTW distance, the more similar the two series are. The specific steps for obtaining the historical power data of the target are as follows: Take the power curves of each day (24 hours) in the historical data as a time series X = {x1, x2, ... x...} n ...x N}, the time series Y = {y1, y2...y} of the power curve for the current forecast date. m ...y MThe comparison is performed; assuming the lengths of X and Y are m and n respectively, an M×N two-dimensional matrix D is constructed, where D[i][j] represents the distance between X[i] and Y[j], which can be calculated using Euclidean distance, Manhattan distance, or other metrics; starting from the top left corner of the matrix, a path P is found such that the sum of all elements on the path is minimized. This path is called the optimal alignment path. Path P must satisfy the following conditions: the starting point of P is D[0][0], and the ending point is D[M-1][N-1]; P can only move to the right, down, or to the lower right; the sum of all elements on the optimal alignment path is calculated as the DTW distance between the two sequences, denoted as DTW(X,Y). Repeat the above steps to calculate the DTW distance between the historical data and the forecast date for each day, and select the days with the smallest distances as the target historical power data. The appropriate number of days can be selected based on the actual situation, such as 10 or 20 days. Furthermore, the aforementioned third historical power data is weighted to reflect the load characteristics of the virtual power plant in different seasons, weather conditions, and time periods, allowing the historical power data to better adapt to the load characteristics of the forecast date, thereby improving the accuracy and robustness of the forecast model.

[0046] Step S2013 above can be implemented in other ways, for example: step S20131, calculating the mean and variance of multiple predicted power data; step S20132, using a random number generator to generate multiple sets of random noise data based on the mean and variance, wherein the random noise data follows a Gaussian distribution. This method can further generate the random noise data more quickly.

[0047] Specifically, the method for randomly generating multiple sets of noise sequence data following a Gaussian distribution is as follows: based on the mean μ and variance σ of the virtual power plant's adjustable power prediction values. 2 First, determine the parameters of the Gaussian distribution. Based on the parameters of the Gaussian distribution and the length n of the predicted value, use a random number generator to generate multiple sets of random number sequences following a Gaussian distribution. Each random number sequence has n elements, and each element is a random number following a Gaussian distribution. Repeat the above steps as needed to generate the required number m noise sequences to obtain m sets of random number sequences following a Gaussian distribution. Each set of random number noise sequences represents a possible error scenario.

[0048] In some embodiments, step S2013 above can be further implemented through the following steps: step S20133, obtaining the probability density function corresponding to each time step of the random noise data; step S20134, according to the formula The calculated probability F of the second influence, where the spliced ​​data at time j is less than or equal to q, is... j (q), where fj (t) represents the probability density function corresponding to the j-th time step of the above random noise data. This method can further and quickly calculate the second influence probability mentioned above.

[0049] Specifically, in addition to using the cumulative distribution function to calculate the probability distribution, the confidence interval method can also be used to calculate the probability distribution.

[0050] In some embodiments, step S201 above can also be implemented through the following steps: Step S2015, according to the formula Calculate the packet loss rate ε of the k-th communication line mentioned above. k ,in, Given the probability that the k-th communication line transmits m data packets at the current time and M data packets at the next time; Step S2016, according to the formula Calculate the bit error rate of the k-th communication line mentioned above. Where r is the signal-to-noise ratio of the kth communication line, and erfc() is the complementary error function; Step S2017, according to the formula Calculate the delay rate γ of the k-th communication line mentioned above. k , where τ k Let τ be the end-to-end delay of the k-th communication line mentioned above. kmin Let α be the minimum end-to-end delay of the k-th communication line, and let α be the influence coefficient of network load rate on delay rate; Step S2018, according to the formula Calculate the reliability μ of the k-th communication line mentioned above. k The aforementioned communication line includes multiple components, x n This refers to the operating state of the nth of the aforementioned components, which includes a normal state and a fault state. ki This represents the probability that the i-th of the aforementioned components is in the normal operating state. This method can quickly calculate the packet loss rate, bit error rate, latency rate, and reliability rate.

[0051] Specifically, the formula for the complementary error function is as follows:

[0052] In some embodiments, step S201 above can also be implemented through the following steps: Step S2019, according to the formula The reliability Φ of the kth of the above communication lines k , where ε k Let be the bit error rate of the k-th of the above communication lines. Let γ be the bit error rate of the k-th communication line mentioned above. k Let μ be the delay rate of the k-th communication line mentioned above. kLet a, b, c, and d be the reliability of the k-th communication line, and a, b, c, and d be the weighting coefficients of the packet loss rate, latency rate, bit error rate, and reliability, respectively, with a + b + c + d = 1; Step S20110, according to the formula... Calculate the first influence probability P, Φ mentioned above. k Let p be the reliability of the k-th of the above communication lines. k Let p be the target power data of the k-th communication line after being affected by the communication state, and let p be the target power data of the k-th communication line before being affected by the communication state. This method can further quickly calculate the first influence probability.

[0053] Specifically, the steps for calculating the first influence probability are as follows: Establish a probability model of the influence of communication reliability on the power range of the virtual power plant. Integrate the communication status of each component within the virtual power plant with the influence of the adjustable power space outside the virtual power plant. k A causal relationship is established using conditional probability. First, the impact of the adjustable external power space of the virtual power plant represents the influence of the communication problem of the k-th line on the adjustable external power range of the virtual power plant: Where, p k Let represent the actual output power of line k after a communication problem occurs, and p represent the predicted output power of the virtual power plant when the network communication problem is resolved. Secondly, conditional probability is used to establish y. k With credibility Φ k The relationship between P{y k |Φ k}, where P{y k >0|Φ k} represents the probability that, under the given confidence level, the target power data after the communication state is not affected by the above communication state is higher than the target power data after the communication state is affected by the above communication state for the k-th communication line. k =0|Φ k} represents the probability that, under the given confidence level, the target power data of the k-th communication line, after being unaffected by the aforementioned communication state, is consistent with the target power data after being affected by the aforementioned communication state. P{y} k <0|Φ k Let Φ represent the probability that, under the given confidence level, the target power data after the communication state is not affected by the aforementioned communication state is lower than the target power data after the communication state is affected by the aforementioned communication state. Since the confidence level of a communication line is not constant but related to the load rate of the virtual power plant, Monte Carlo simulation can be used to conduct numerous random experiments on the communication network within the virtual power plant, simulating communication states under different scenarios, and calculating the confidence level Φ of each communication line under different load rates. kThe specific steps for determining the impact of the virtual power plant's external power characteristics are as follows: Based on the known probability table of the communication network state transition matrix, generate a large number of random numbers representing the load rate of each line and the weather conditions of the virtual power plant. For example, if the probability of each line being overloaded is 0.15, a Bernoulli distribution can be used to generate random numbers; if the random number is less than 0.15, it indicates that the line is overloaded; if the random number is greater than 0.15, it indicates that the line is not overloaded. Based on the generated random numbers, a communication state vector is obtained, representing the communication state of each node within the virtual power plant. For example, if there are n nodes in the virtual power plant, n random numbers of 0 or 1 can be generated to represent whether each line is overloaded. Based on these random numbers, a communication state vector can be obtained. Combining the conditional probability table, calculate the communication reliability of each line in the virtual power plant corresponding to the communication state vector in the virtual power plant based on historical data, and then calculate the reliability using the formula P{y k |Φ k This yields the probability distribution of the virtual power plant's external power characteristics under different communication reliability rates. Specifically, it represents the probability that the actual value of the virtual power plant's external power characteristics is higher than the predicted value, consistent with the predicted value, or lower than the predicted value under different communication states of each node. This allows us to obtain the impact of different communication states of each node on the virtual power plant's external power characteristics and their corresponding probabilities. By inputting the current network overload situation into the probability table obtained in the above steps, we can obtain the current communication reliability rate of each line and further calculate the probability of the impact of each line's communication status on the virtual power plant's external power characteristics.

[0054] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the virtual power plant control method of this application will be described in detail below with reference to specific embodiments.

[0055] This embodiment relates to a specific control method for a virtual power plant, taking a five-node virtual power plant as an example, including the following steps:

[0056] Step S1: Obtain 50 sets of historical data on the power external characteristics of a given virtual power plant, including power external characteristic data, temperature, communication status, etc.

[0057] Step S2: Using dynamic programming, select 6 days of data from 50 sets of historical data as the target historical power data. The power external characteristics are calculated in 15-minute intervals. The selected 6 sets of target historical power data are weighted, and the weights are determined based on the differences between the meteorological parameters (temperature, humidity, wind speed, etc.) corresponding to the date of the target historical power data and the meteorological parameters of the predicted date. The weights corresponding to the target historical power data are shown in the table below.

[0058] Table 1 Weighting of Historical Power Data for Targets

[0059] Weight 0.653 0.384 0.776 0.752 0.518 0.633

[0060] Step S3: Input the above target historical data into the FNN-GRN neural network to obtain the predicted power data, such as... Figure 3 As shown;

[0061] Step S4: Randomly generate multiple sets of noise sequences following a Gaussian distribution. The length of each noise sequence is the same as the predicted power data. Add each noise sequence to the predicted adjustable power value of the virtual power plant to obtain a new set of predicted values. Use the cumulative distribution function to calculate the probability distribution of the adjustable power interval at each time step to obtain the target power data, such as... Figure 4 As shown;

[0062] Step S5: Considering issues such as packet loss, bit error, delay, and unreliability in communication, establish a probabilistic model of the impact of communication reliability on the aggregated adjustable power range of the virtual power plant;

[0063] Step S6: When considering the impact of packet loss, delay, bit errors, and unreliability during communication on the virtual power plant, the formula is used. Calculate the above reliability rate, where a, b, c, and d are the weighting coefficients of packet loss rate, latency rate, bit error rate, and unreliability rate, respectively, and a = 0.25, b = 0.25, c = 0.25, and d = 0.25.

[0064] Step S7: Using Monte Carlo simulation, conduct numerous randomized experiments on the communication network within the virtual power plant to simulate communication states under different scenarios, and calculate the reliability Φ of each communication line under different weather and load conditions. k , and its impact on the power external characteristics of virtual power plants;

[0065] Step S8: Based on the known communication network state transition matrix and the virtual power plant external characteristic conditional probability table, generate a large number of random numbers to represent the load rate of each line. If the probability of each line being overloaded is 0.15, a Bernoulli distribution can be used to generate random numbers. That is, if the random number is less than 0.15, it means that the line is overloaded; if the random number is greater than 0.15, it means that the line is not overloaded.

[0066] Step S9: Calculate the communication reliability of each line in the virtual power plant corresponding to the communication state vector in the virtual power plant based on historical data, and then calculate the reliability according to the formula P{y k |Φ kThe probability distribution of the external power characteristics of the virtual power plant under different communication reliability rates is obtained. That is, the probability that the actual value of the external power characteristics of the virtual power plant is higher than the predicted value, consistent with the predicted value, and lower than the predicted value under different communication states of each node in the virtual power plant. Thus, the influence of different communication states of each node on the external power characteristics of the virtual power plant and the corresponding probability can be obtained.

[0067] Step S10: Input the current network overload status and the weather conditions of the virtual power plant into the probability distribution in step S7 to obtain the communication reliability of each line. Further calculate the probability of the impact of the communication status of each line on the external power characteristics of the virtual power plant using the formula... Obtain the probability of the overall communication state's impact on the external characteristics of the virtual power plant;

[0068] Step S11: Superimpose the probability of the impact of communication on the external power characteristics of the virtual power plant obtained above with the predicted power range obtained in step S4 to obtain a more accurate range of the external power characteristics of the virtual power plant, such as... Figure 5 As shown;

[0069] Step S12: Compare the impact of communication on the accuracy of virtual power plant power characteristic prediction, and define the prediction accuracy as: Where, ξ t P' represents the prediction accuracy at time t. t,max and P' t,min P represents the maximum predicted power at time t and the minimum predicted power at time t, respectively. t,max and P t,min Let a1 be the actual maximum power at time t and a2 be the actual minimum power at time t, respectively, and a1 be 0.5 and a2 be 0.5.

[0070] Step S13: The hourly accuracy is calculated with and without considering communication, as shown in the table below. It can be seen that considering the impact of communication reliability can improve the accuracy of the virtual power plant power external characteristic assessment.

[0071] Table 2 Comparison of Prediction Accuracy

[0072]

[0073] This application also provides a control device for a virtual power plant. It should be noted that the control device for the virtual power plant in this application can be used to execute the control method for a virtual power plant provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0074] The control device for the virtual power plant provided in the embodiments of this application will be described below.

[0075] The virtual power plant includes communication lines and is used to regulate the power system. Figure 6 This is a schematic diagram of the control device for a virtual power plant according to an embodiment of this application. Figure 6 As shown, the device includes:

[0076] The acquisition unit 10 is used to acquire target power data and the communication status of the communication line, and determine a first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0077] Specifically, the target power data mentioned above can be predicted data obtained through various models, or historical power data. In practical applications, the complexity and instability of the communication network within the virtual power plant—namely, the changes in the communication status—affect the assessment of the virtual power plant's power adjustability, thereby impacting the collaborative control effect among resources within the virtual power plant. The packet loss rate refers to the proportion of data packets lost during transmission in network communication. A higher packet loss rate indicates poorer network transmission quality, potentially leading to incomplete or delayed data transmission. The bit error rate refers to the proportion of errors in received data in digital communication. A higher bit error rate indicates poorer data transmission reliability, potentially causing the receiver to be unable to correctly parse the data. The latency rate refers to the time delay experienced by data packets from the sender to the receiver. A higher latency rate indicates slower data transmission speed, potentially causing stuttering or delays in applications with high real-time requirements (such as video calls and online games). The reliability rate refers to the proportion of data that the receiver can correctly receive during data transmission. A higher reliability rate indicates better data transmission reliability, ensuring the receiver receives the sender's data completely.

[0078] The determining unit 20 is used to determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, the range of the target power data corresponding to the first influence probability is determined as the target power range.

[0079] Specifically, the impact of the aforementioned communication state on the aforementioned target power data includes increasing or decreasing the aforementioned target power data. In other words, the aforementioned probability includes three cases: the probability that the aforementioned target power data after not being affected by the aforementioned communication state is higher than the aforementioned target power data after being affected by the aforementioned communication state, given the reliability of the communication line; the probability that the aforementioned target power data after not being affected by the aforementioned communication state is the same as the aforementioned target power data after being affected by the aforementioned communication state; and the probability that the aforementioned target power data after not being affected by the aforementioned communication state is lower than the aforementioned target power data after being affected by the aforementioned communication state.

[0080] Control unit 30 is used to control the virtual power plant to regulate the power system according to the target power range.

[0081] Specifically, after obtaining the target power range, the power of the virtual power plant can be set within the target power range to further achieve precise control of the power system.

[0082] In this embodiment, the acquisition unit acquires target power data and the communication status of the communication line, and determines a first probability of influence of the communication status on the target power data based on the communication status and the target power data. The determination unit determines whether the first probability of influence is greater than a first probability threshold. If the first probability of influence is greater than the first probability threshold, the range of target power data corresponding to the first probability of influence is determined as the target power range. The control unit controls the virtual power plant to regulate the power system according to the target power range. By introducing the communication status of the communication line, including the packet loss rate, bit error rate, latency rate, and reliability rate of the communication line, the probability of influence of the communication status on the power of the virtual power plant is further determined. Based on this probability of influence, an accurate power range is determined, and precise control of the power system is achieved. This solves the problem in the prior art where the prediction of the power range of the virtual power plant is inaccurate, which affects the operation of the virtual power plant.

[0083] In specific implementation, the aforementioned acquisition unit includes a first acquisition module, an input module, a second acquisition module, and a determination module. The first acquisition module acquires target historical power data, which includes multiple power data points of the virtual power plant prior to the predetermined time period. Part of the target historical power data is test data, and the other part is training data. The input module sequentially inputs the test data into a power prediction model to obtain multiple predicted power data points. The power prediction model is trained using multiple sets of first historical data through machine learning. Each set of first historical data includes: the training data for a first time period and the training data for a second time period, with the start time of the second time period... The predicted power data, engraved after the end of the first time period, is the power data following the test data. The second acquisition module acquires multiple sets of random noise data and a second probability of influence of the random noise data on the predicted power data. It then concatenates the multiple sets of random noise data and the predicted power data at the same time to obtain concatenated data. The influence of the random noise data on the predicted power data includes increasing or decreasing the predicted power data. The determination module determines whether the second probability is greater than a second probability threshold. If the second probability threshold is greater than the second probability threshold, the concatenated data corresponding to the second probability is determined to be the target power data. This device can further acquire the target power data quickly.

[0084] Specifically, the power prediction model mentioned above can be an FNN-GRU model. FNN-GRU is a hybrid or ensemble model that combines a Feedforward Neural Network (FNN) and a Gated Recurrent Unit (GRU). It can be used to handle prediction or classification problems of sequence data. The basic idea of ​​FNN-GRU is to use FNN to process static features and GRU to process dynamic features, then fuse or weighted average the outputs of both to obtain the final prediction result. The structure of FNN-GRU includes an input layer, an FNN layer, a GRU layer, a fusion layer, and an output layer. The input layer receives various features of the sequence data, such as time, temperature, and humidity. The FNN layer performs linear transformations and nonlinear activations on the input data to extract static features. It consists of multiple layers, each of which is a linear transformation plus a nonlinear activation function. FNN can extract and transform features from input data to learn higher-level abstract representations; GRU layer is used to input the data from the input layer into GRU units in chronological order, and extract dynamic features using gating mechanism and memory unit; fusion layer is used to fuse or weighted average the outputs of FNN layer and GRU layer to obtain a comprehensive feature vector; output layer is used to perform linear transformation and activation function on the output of fusion layer according to the prediction or classification target to obtain the final prediction or classification result.

[0085] Furthermore, the steps to obtain the above-mentioned spliced ​​data are as follows: The predicted adjustable power of the virtual power plant is represented as a numerical sequence of length n, denoted as P = {p1, p2, ..., p...}. n}. Where p i Let N represent the predicted power data at time i. Each set of random noise data is represented as a numerical sequence of length n, denoted as N. i ={n i1 ,n i2 ,...,n in}. Where, n ij Let Q represent the noise value at time j in the i-th noise sequence. Each noise sequence is added element-wise to the virtual power plant's adjustable power prediction value to obtain a new prediction value, denoted as Q. i ={q i1 ,q i2 ,...,q in}. Where, q ij =p j +n ijThis represents the spliced ​​power data value at time j in the i-th set of new predictions. Repeat the above steps to obtain m sets of new predictions, based on the required number of new predictions (m). Each set of new predictions reflects the changes in the adjustable power baseline of the virtual power plant under different noise levels.

[0086] To further and more quickly acquire the aforementioned target historical power data, the first acquisition module of this application includes a first acquisition submodule, a processing submodule, a second acquisition submodule, and a determination submodule. The first acquisition submodule acquires second historical data, which includes multiple power data points of the virtual power plant prior to the predetermined time period. The processing submodule performs dynamic time warping on the second historical data to obtain third historical data. The second acquisition submodule acquires the meteorological parameters corresponding to the second historical data and the meteorological parameters of the third historical data, and determines them according to the formula... Calculate the weighting coefficient w for the i-th of the aforementioned third historical data. i Where m is the number of meteorological parameters in the aforementioned third historical data, and α j Let x be the weighting coefficient for the j-th of the aforementioned meteorological parameters. ij Let y be the value of the j-th meteorological parameter corresponding to the i-th third historical data point mentioned above. j Let j be the value of any of the above-mentioned second historical data; the determination submodule is used to determine the product of the above-mentioned third historical data and the corresponding weight coefficient as the above-mentioned target historical power data.

[0087] Specifically, Dynamic Time Warping (DTW) is a method for measuring the similarity between two time series. It can handle situations where the two series have different lengths or non-linear deformations. The basic steps of the DTW method are as follows: Construct a two-dimensional matrix, where the rows and columns correspond to the elements of the two series, and each element in the matrix represents the distance between corresponding elements in the two series. Starting from the top left corner of the matrix, find a path that minimizes the sum of all elements on the path; this path is called the optimal alignment path. Calculate the sum of all elements on the optimal alignment path as the DTW distance between the two series. The smaller the DTW distance, the more similar the two series are. The specific steps for obtaining the historical power data of the target are as follows: Take the power curves of each day (24 hours) in the historical data as a time series X = {x1, x2, ... x...} n ...x N}, the time series Y = {y1, y2...y} of the power curve for the current forecast date. m ...y MThe comparison is performed; assuming the lengths of X and Y are m and n respectively, an M×N two-dimensional matrix D is constructed, where D[i][j] represents the distance between X[i] and Y[j], which can be calculated using Euclidean distance, Manhattan distance, or other metrics; starting from the top left corner of the matrix, a path P is found such that the sum of all elements on the path is minimized. This path is called the optimal alignment path. Path P must satisfy the following conditions: the starting point of P is D[0][0], and the ending point is D[M-1][N-1]; P can only move to the right, down, or to the lower right; the sum of all elements on the optimal alignment path is calculated as the DTW distance between the two sequences, denoted as DTW(X,Y). Repeat the above steps to calculate the DTW distance between the historical data and the forecast date for each day, and select the days with the smallest distances as the target historical power data. The appropriate number of days can be selected based on the actual situation, such as 10 or 20 days. Furthermore, the aforementioned third historical power data is weighted to reflect the load characteristics of the virtual power plant in different seasons, weather conditions, and time periods, allowing the historical power data to better adapt to the load characteristics of the forecast date, thereby improving the accuracy and robustness of the forecast model.

[0088] The second acquisition module includes a first calculation submodule and a generation submodule. The first calculation submodule is used to calculate the mean and variance of multiple predicted power data. The generation submodule is used to generate multiple sets of random noise data based on the mean and variance using a random number generator. The random noise data follows a Gaussian distribution. This method can further generate the random noise data quickly.

[0089] Specifically, the method for randomly generating multiple sets of noise sequence data following a Gaussian distribution is as follows: based on the mean μ and variance σ of the virtual power plant's adjustable power prediction values. 2 First, determine the parameters of the Gaussian distribution. Based on the parameters of the Gaussian distribution and the length n of the predicted value, use a random number generator to generate multiple sets of random number sequences following a Gaussian distribution. Each random number sequence has n elements, and each element is a random number following a Gaussian distribution. Repeat the above steps as needed to generate the required number m noise sequences to obtain m sets of random number sequences following a Gaussian distribution. Each set of random number noise sequences represents a possible error scenario.

[0090] In some embodiments, the second acquisition module further includes a third acquisition submodule and a second calculation submodule, wherein the third acquisition submodule is used to acquire the probability density function corresponding to each time step of the random noise data; the second calculation submodule is used to calculate the probability density function according to the formula... The calculated probability F of the second influence, where the spliced ​​data at time j is less than or equal to q, is... j(q), where f j (t) represents the probability density function corresponding to the j-th time step of the aforementioned random noise data. This device can further and quickly calculate the aforementioned second influence probability.

[0091] Specifically, in addition to using the cumulative distribution function to calculate the probability distribution, the confidence interval method can also be used to calculate the probability distribution.

[0092] In some embodiments, the acquisition unit includes a first calculation module, a second calculation module, a third calculation module, and a fourth calculation module, wherein the first calculation module is used to calculate according to the formula Calculate the packet loss rate ε of the k-th communication line mentioned above. k ,in, The probability that the k-th communication line transmits m data packets at the current time and M data packets at the next time; the second calculation module is used to calculate according to the formula Calculate the bit error rate of the k-th communication line mentioned above. Where r is the signal-to-noise ratio of the k-th communication line, and erfc() is the complementary error function; the third calculation module is used to calculate according to the formula Calculate the delay rate γ of the k-th communication line mentioned above. k , where τ k Let τ be the end-to-end delay of the k-th communication line mentioned above. kmin The minimum end-to-end delay for the k-th communication line is given by α, where α is the coefficient of network load rate on the delay rate. The fourth calculation module is used to calculate the delay rate according to the formula... Calculate the reliability μ of the k-th communication line mentioned above. k The aforementioned communication line includes multiple components, x n This refers to the operating state of the nth of the aforementioned components, which includes a normal state and a fault state. ki This represents the probability that the i-th of the aforementioned components is in the normal operating state. The device can quickly calculate the packet loss rate, bit error rate, latency rate, and reliability rate.

[0093] Specifically, the formula for the complementary error function is as follows:

[0094] In some embodiments, the acquisition unit includes a fifth calculation module and a sixth calculation module, wherein the fifth calculation module is used to calculate according to the formula The reliability Φ of the kth of the above communication lines k , where ε k Let be the bit error rate of the k-th of the above communication lines. Let γ be the bit error rate of the k-th communication line mentioned above. k Let μ be the delay rate of the k-th communication line mentioned above.k Let a, b, c, and d be the reliability rate of the k-th communication line, and a, b, c, and d be the weighting coefficients of the packet loss rate, latency rate, bit error rate, and reliability rate, respectively, with a + b + c + d = 1; the sixth calculation module is used to calculate according to the formula Calculate the first influence probability P, Φ mentioned above. k Let p be the reliability of the k-th of the above communication lines. k Let p be the target power data of the k-th communication line after being affected by the communication state, and let p be the target power data of the k-th communication line before being affected by the communication state. This device can further and quickly calculate the first influence probability.

[0095] Specifically, the steps for calculating the first influence probability are as follows: Establish a probability model of the influence of communication reliability on the power range of the virtual power plant. Integrate the communication status of each component within the virtual power plant with the influence of the adjustable power space outside the virtual power plant. k A causal relationship is established using conditional probability. First, the impact of the adjustable external power space of the virtual power plant represents the influence of the communication problem of the k-th line on the adjustable external power range of the virtual power plant: Where, p k Let represent the actual output power of line k after a communication problem occurs, and p represent the predicted output power of the virtual power plant when the network communication problem is resolved. Secondly, conditional probability is used to establish y. k With credibility Φ k The relationship between P{y k |Φ k}, where P{y k >0|Φ k} represents the probability that, under the given confidence level, the target power data after the communication state is not affected by the above communication state is higher than the target power data after the communication state is affected by the above communication state for the k-th communication line. k =0|Φ k} represents the probability that, under the given confidence level, the target power data of the k-th communication line, after being unaffected by the aforementioned communication state, is consistent with the target power data after being affected by the aforementioned communication state. P{y} k <0|Φ k Let Φ represent the probability that, under the given confidence level, the target power data after the communication state is not affected by the aforementioned communication state is lower than the target power data after the communication state is affected by the aforementioned communication state. Since the confidence level of a communication line is not constant but related to the load rate of the virtual power plant, Monte Carlo simulation can be used to conduct numerous random experiments on the communication network within the virtual power plant, simulating communication states under different scenarios, and calculating the confidence level Φ of each communication line under different load rates. kThe specific steps for determining the impact of the virtual power plant's external power characteristics are as follows: Based on the known probability table of the communication network state transition matrix, generate a large number of random numbers representing the load rate of each line and the weather conditions of the virtual power plant. For example, if the probability of each line being overloaded is 0.15, a Bernoulli distribution can be used to generate random numbers; if the random number is less than 0.15, it indicates that the line is overloaded; if the random number is greater than 0.15, it indicates that the line is not overloaded. Based on the generated random numbers, a communication state vector is obtained, representing the communication state of each node within the virtual power plant. For example, if there are n nodes in the virtual power plant, n random numbers of 0 or 1 can be generated to represent whether each line is overloaded. Based on these random numbers, a communication state vector can be obtained. Combining the conditional probability table, calculate the communication reliability of each line in the virtual power plant corresponding to the communication state vector in the virtual power plant based on historical data, and then calculate the reliability using the formula P{y k |Φ k This yields the probability distribution of the virtual power plant's external power characteristics under different communication reliability rates. Specifically, it represents the probability that the actual value of the virtual power plant's external power characteristics is higher than the predicted value, consistent with the predicted value, or lower than the predicted value under different communication states of each node. This allows us to obtain the impact of different communication states of each node on the virtual power plant's external power characteristics and their corresponding probabilities. By inputting the current network overload situation into the probability table obtained in the above steps, we can obtain the current communication reliability rate of each line and further calculate the probability of the impact of each line's communication status on the virtual power plant's external power characteristics.

[0096] The control device for the aforementioned virtual power plant includes a processor and a memory. The acquisition unit, determination unit, and control unit are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0097] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and the virtual power plant can be controlled by adjusting kernel parameters.

[0098] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0099] This invention provides a computer-readable storage medium that includes a stored program, wherein the program, when running, controls the device containing the computer-readable storage medium to execute the control method of the virtual power plant.

[0100] Specifically, the control methods for virtual power plants include:

[0101] Step S201: Obtain target power data and the communication status of the communication line, and determine the first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0102] Specifically, the target power data mentioned above can be predicted data obtained through various models, or historical power data. In practical applications, the complexity and instability of the communication network within the virtual power plant—namely, the changes in the communication status—affect the assessment of the virtual power plant's power adjustability, thereby impacting the collaborative control effect among resources within the virtual power plant. The packet loss rate refers to the proportion of data packets lost during transmission in network communication. A higher packet loss rate indicates poorer network transmission quality, potentially leading to incomplete or delayed data transmission. The bit error rate refers to the proportion of errors in received data in digital communication. A higher bit error rate indicates poorer data transmission reliability, potentially causing the receiver to be unable to correctly parse the data. The latency rate refers to the time delay experienced by data packets from the sender to the receiver. A higher latency rate indicates slower data transmission speed, potentially causing stuttering or delays in applications with high real-time requirements (such as video calls and online games). The reliability rate refers to the proportion of data that the receiver can correctly receive during data transmission. A higher reliability rate indicates better data transmission reliability, ensuring the receiver receives the sender's data completely.

[0103] Step S202: Determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range.

[0104] Specifically, the impact of the aforementioned communication state on the aforementioned target power data includes increasing or decreasing the aforementioned target power data. In other words, the aforementioned probability includes three cases: the probability that the aforementioned target power data after not being affected by the aforementioned communication state is higher than the aforementioned target power data after being affected by the aforementioned communication state, given the reliability of the communication line; the probability that the aforementioned target power data after not being affected by the aforementioned communication state is the same as the aforementioned target power data after being affected by the aforementioned communication state; and the probability that the aforementioned target power data after not being affected by the aforementioned communication state is lower than the aforementioned target power data after being affected by the aforementioned communication state.

[0105] Step S203: Control the virtual power plant to regulate the power system according to the target power range.

[0106] Specifically, after obtaining the target power range, the power of the virtual power plant can be set within the target power range to further achieve precise control of the power system.

[0107] This invention provides a processor for running a program, wherein the program executes the control method of the virtual power plant.

[0108] Specifically, the control methods for virtual power plants include:

[0109] Step S201: Obtain target power data and the communication status of the communication line, and determine the first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0110] Specifically, the target power data mentioned above can be predicted data obtained through various models, or historical power data. In practical applications, the complexity and instability of the communication network within the virtual power plant—namely, the changes in the communication status—affect the assessment of the virtual power plant's power adjustability, thereby impacting the collaborative control effect among resources within the virtual power plant. The packet loss rate refers to the proportion of data packets lost during transmission in network communication. A higher packet loss rate indicates poorer network transmission quality, potentially leading to incomplete or delayed data transmission. The bit error rate refers to the proportion of errors in received data in digital communication. A higher bit error rate indicates poorer data transmission reliability, potentially causing the receiver to be unable to correctly parse the data. The latency rate refers to the time delay experienced by data packets from the sender to the receiver. A higher latency rate indicates slower data transmission speed, potentially causing stuttering or delays in applications with high real-time requirements (such as video calls and online games). The reliability rate refers to the proportion of data that the receiver can correctly receive during data transmission. A higher reliability rate indicates better data transmission reliability, ensuring the receiver receives the sender's data completely.

[0111] Step S202: Determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range.

[0112] Specifically, the impact of the aforementioned communication state on the aforementioned target power data includes increasing or decreasing the aforementioned target power data. In other words, the aforementioned probability includes three cases: the probability that the aforementioned target power data after not being affected by the aforementioned communication state is higher than the aforementioned target power data after being affected by the aforementioned communication state, given the reliability of the communication line; the probability that the aforementioned target power data after not being affected by the aforementioned communication state is the same as the aforementioned target power data after being affected by the aforementioned communication state; and the probability that the aforementioned target power data after not being affected by the aforementioned communication state is lower than the aforementioned target power data after being affected by the aforementioned communication state.

[0113] Step S203: Control the virtual power plant to regulate the power system according to the target power range.

[0114] Specifically, after obtaining the target power range, the power of the virtual power plant can be set within the target power range to further achieve precise control of the power system.

[0115] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0116] Step S201: Obtain target power data and the communication status of the communication line, and determine the first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0117] Step S202: Determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range.

[0118] Step S203: Control the virtual power plant to regulate the power system according to the target power range.

[0119] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0120] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0121] Step S201: Obtain target power data and the communication status of the communication line, and determine the first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data is multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate of the communication line, the bit error rate of the communication line, the delay rate of the communication line, and the reliability rate of the communication line. The influence of the communication status on the target power data includes increasing the target power data or decreasing the target power data.

[0122] Step S202: Determine whether the first influence probability is greater than the first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range.

[0123] Step S203: Control the virtual power plant to regulate the power system according to the target power range.

[0124] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0125] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0126] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0127] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0128] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0129] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0130] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0131] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0132] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0133] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0134] 1) The virtual power plant control method of this application first acquires target power data and the communication status of the communication line, and determines a first probability of influence of the communication status on the target power data based on the communication status and the target power data; then, it determines whether the first probability of influence is greater than a first probability threshold. If the first probability of influence is greater than the first probability threshold, the range of target power data corresponding to the first probability of influence is determined as the target power range; finally, the virtual power plant is controlled to regulate the power system according to the target power range. By introducing the communication status of the communication line, including the packet loss rate, bit error rate, delay rate, and reliability rate of the communication line, the probability of influence of the communication status on the power of the virtual power plant is further determined, and an accurate power range is determined based on this probability of influence, thus achieving precise control of the power system. This solves the problem in the prior art where the prediction of the power range of the virtual power plant is inaccurate, which affects the operation of the virtual power plant.

[0135] 2) The control device for the virtual power plant of this application includes an acquisition unit that acquires target power data and the communication status of the communication line, and determines a first probability of influence of the communication status on the target power data based on the communication status and the target power data; a determination unit that determines whether the first probability of influence is greater than a first probability threshold, and if the first probability of influence is greater than the first probability threshold, determines the range of target power data corresponding to the first probability of influence as the target power range; and a control unit that controls the virtual power plant to regulate the power system according to the target power range. By introducing the communication status of the communication line, including the packet loss rate, bit error rate, delay rate, and reliability rate of the communication line, the probability of influence of the communication status on the power of the virtual power plant is further determined, and an accurate power range is determined based on this probability of influence, thus achieving precise control of the power system. This solves the problem in the prior art where the prediction of the power range of the virtual power plant is inaccurate, which affects the operation of the virtual power plant.

[0136] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for a virtual power plant, characterized in that, The virtual power plant includes communication lines and is used to regulate the power system, wherein the method includes: The system acquires target power data and the communication status of the communication line, and determines a first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data consists of multiple power data of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate, bit error rate, latency rate, and reliability rate of the communication line. The influence of the communication status on the target power data includes increasing or decreasing the target power data. Based on the communication status of the communication line and the target power data, determine a first probability of influence of the communication status on the target power data, including: According to the formula , No. Reliability of the aforementioned communication lines ,in, For the first The bit error rate of the aforementioned communication lines. For the first The bit error rate of the aforementioned communication lines. For the first The latency rate of the aforementioned communication lines. For the first The reliability of the aforementioned communication lines, These are the weighting coefficients for the packet loss rate, the latency rate, the bit error rate, and the reliability rate, respectively. ; According to the formula Calculate the first influence probability , For the first The reliability of the aforementioned communication lines. For the first k The target power data of each communication line after being affected by the communication state. For the first k The target power data of each of the communication lines that is not affected by the communication state; Determine whether the first influence probability is greater than a first probability threshold. If the first influence probability is greater than the first probability threshold, determine the range of the target power data corresponding to the first influence probability as the target power range. The virtual power plant is controlled to regulate the power system according to the target power range.

2. The method according to claim 1, characterized in that, Obtain target power data, including: Acquire target historical power data, wherein the target historical power data includes multiple power data of the virtual power plant before the predetermined time period, and part of the target historical power data is test data and the other part is training data; The test data is sequentially input into the power prediction model to obtain multiple predicted power data. The power prediction model is trained by machine learning using multiple sets of first historical data. Each set of first historical data includes: the training data of a first time period and the training data of a second time period. The start time of the second time period is after the end time of the first time period. The predicted power data is the power data after the test data. Multiple sets of random noise data and the second probability of the influence of the random noise data on the predicted power data are obtained, and the multiple sets of random noise data and the predicted power data at the same time are spliced ​​together to obtain spliced ​​data. The influence of the random noise data on the predicted power data includes increasing the predicted power data or decreasing the predicted power data. Determine whether the second influence probability is greater than the second probability threshold. If the second influence probability is greater than the second probability threshold, determine that the spliced ​​data corresponding to the second influence probability is the target power data.

3. The method according to claim 2, characterized in that, Obtain historical power data for the target, including: Acquire second historical data, wherein the second historical data includes multiple power data of the virtual power plant prior to the predetermined time period; The second historical data is processed by a dynamic time warping algorithm to obtain the third historical data; Obtain the meteorological parameters corresponding to the second historical data and the meteorological parameters of the third historical data, and then apply the formula... Calculate the first The weighting coefficient of the third historical data ,in, m The number of meteorological parameters in the third historical data. For the first j The weighting coefficients of the meteorological parameters mentioned above. For the first i The third historical data corresponding to the first j The values ​​of the aforementioned meteorological parameters For any of the second historical data, the first j The values ​​of the meteorological parameters; The product of the third historical data and the corresponding weighting coefficient is determined to be the target historical power data.

4. The method according to claim 2, characterized in that, Obtain multiple sets of random noise data, including: Calculate the mean and variance of the multiple predicted power data; Based on the mean and variance, a random number generator is used to generate multiple sets of random noise data, which follow a Gaussian distribution.

5. The method according to claim 2, characterized in that, Obtaining the second probability of influence of the random noise data on the predicted power data includes: Obtain the probability density function corresponding to each time step of the random noise data; According to the formula Calculate the first j The spliced ​​data at each moment is less than or equal to q The second influence probability ,in, For the first of the random noise data j The probability density function corresponding to each time step.

6. The method according to claim 1, characterized in that, Obtaining the communication status of the communication line includes: According to the formula Calculate the first Packet loss rate of the aforementioned communication lines ,in, For the first The current transmission of the aforementioned communication lines The data packet will be transmitted in the next moment. The probability of a data packet; According to the formula Calculate the first Bit error rate of the aforementioned communication lines ,in, For the first The signal-to-noise ratio of the aforementioned communication lines. It is a complementary error function; According to the formula Calculate the first The latency of the aforementioned communication lines ,in, For the first The end-to-end delay of the aforementioned communication line. For the first The minimum end-to-end delay of the aforementioned communication lines. This is the coefficient representing the impact of network load rate on latency rate. According to the formula Calculate the first Reliability of the aforementioned communication lines The communication line includes multiple components. For the first The operating states of the aforementioned components include normal states and fault states. For the first The probability that the operating state of each of the components is the normal state.

7. A control device for a virtual power plant, characterized in that, The virtual power plant includes communication lines and is used to regulate the power system. The device includes: An acquisition unit is configured to acquire target power data and the communication status of the communication line, and determine a first probability of influence of the communication status on the target power data based on the communication status of the communication line and the target power data. The target power data consists of multiple power data points of the virtual power plant within a predetermined time period. The communication status includes the packet loss rate, bit error rate, latency rate, and reliability of the communication line. The influence of the communication status on the target power data includes increasing or decreasing the target power data. The acquisition unit includes a fifth calculation module and a sixth calculation module, wherein the fifth calculation module is used to calculate according to the formula. , No. Reliability of the aforementioned communication lines ,in, For the first The bit error rate of the aforementioned communication lines. For the first The bit error rate of the aforementioned communication lines. For the first The latency rate of the aforementioned communication lines. For the first The reliability of the aforementioned communication lines, These are the weighting coefficients for the packet loss rate, the latency rate, the bit error rate, and the reliability rate, respectively. The sixth calculation module is used to calculate according to the formula Calculate the first influence probability , For the first The reliability of the aforementioned communication lines. For the first k The target power data of each communication line after being affected by the communication state. For the first k The target power data of each of the communication lines that is not affected by the communication state; The determining unit is used to determine whether the first influence probability is greater than a first probability threshold, and if the first influence probability is greater than the first probability threshold, to determine the range of the target power data corresponding to the first influence probability as the target power range; The control unit is used to control the virtual power plant to regulate the power system according to the target power range.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 6.

9. A smart grid, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 6.

Images