Virtual power plant power dispatching methods, systems, storage media and electronic equipment

Abstract

A power dispatching method, system, storage medium, and electronic equipment for a virtual power plant are disclosed, relating to the field of power technology. The method includes: acquiring power generation data of each energy source and electricity consumption characteristic data of each user within the virtual power plant; calculating the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user; determining the user feature vector corresponding to each user based on the time-series characteristic sequence and the fluctuation characteristic sequence of each user's load; classifying and aggregating each user according to the user feature vectors to determine the adjustable capacity of each category of user; calculating the complementarity index of power generation resources based on the power generation data of each energy source, and determining at least one power generation combination based on the complementarity index; and generating a multi-period coordinated dispatching strategy by combining the adjustable capacity and the power generation combination. Implementing the technical solution provided in this application can reduce the overall operating cost of the virtual power plant.

Description

Technical Field

[0001] This application relates to the field of power technology, specifically to a power dispatching method, system, storage medium, and electronic equipment for a virtual power plant. Background Technology

[0002] As the proportion of renewable energy generation continues to increase, the volatility and uncertainty of the power system are also increasing. Virtual power plants, as a new energy management approach, can provide power regulation services similar to traditional power plants by integrating various resources such as distributed energy, controllable loads, and energy storage, effectively improving the flexibility of the power system.

[0003] In existing technologies, virtual power plants typically manage user-side loads and generation resources separately using independent dispatching. Specifically, for the user side, load regulation commands are sent directly to users based on electricity demand; for the generation side, generation plans are determined based on predicted electricity load. However, this independent dispatching method makes it difficult to achieve economical and efficient operation of virtual power plants. For example, during peak electricity demand periods, the system may overly rely on higher-cost generation resources for regulation, failing to fully utilize the load regulation capabilities available to the user side, leading to increased overall operating costs for the virtual power plant. Summary of the Invention

[0004] This application provides a power dispatching method, system, storage medium, and electronic equipment for a virtual power plant, which can reduce the overall operating cost of the virtual power plant.

[0005] Firstly, this application provides a power dispatching method for a virtual power plant, the method comprising:

[0006] Obtain power generation data from various energy sources and electricity consumption characteristic data from each user within the virtual power plant;

[0007] Calculate the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user;

[0008] Based on the time-series characteristic sequence of each user's load and the fluctuation characteristic sequence, determine the user feature vector corresponding to each user; classify and aggregate each user according to each user feature vector to determine the adjustable capacity of each category of users;

[0009] The complementarity index of power generation resources is calculated based on the power generation data of each energy source, and at least one power generation combination is determined according to the complementarity index.

[0010] A multi-period coordinated scheduling strategy is generated by combining the adjustable capacity and the power generation combination.

[0011] By adopting the above technical solution, the power generation data of each energy source and the electricity consumption characteristic data of each user within the virtual power plant are acquired. Based on the electricity consumption characteristic data, the time-series characteristic sequence and fluctuation characteristic sequence of user load are calculated, thereby determining the user feature vector and performing classification and aggregation. This allows for accurate assessment of the adjustable capacity of each type of user. Simultaneously, based on the power generation data of each energy source, the complementarity index of power generation resources is calculated and the power generation combination is determined. Combining the adjustable capacity and the power generation combination, a multi-period collaborative scheduling strategy is generated, achieving synergistic optimization of user-side load regulation capability and power generation resources. This avoids the problem of over-reliance on high-cost power generation resources for regulation, thereby effectively reducing the overall operating cost of the virtual power plant.

[0012] A second aspect of this application provides a power dispatching system for a virtual power plant, the system comprising:

[0013] The data acquisition module is used to acquire power generation data of each energy source and electricity consumption characteristic data of each user within the virtual power plant.

[0014] The sequence acquisition module is used to calculate the time-series characteristic sequence and fluctuation characteristic sequence of the load of each user based on the electricity consumption characteristic data of each user;

[0015] The feature vector determination module is used to determine the user feature vector corresponding to each user based on the time-series feature sequence of each user's load and the fluctuation feature sequence;

[0016] The adjustable capacity determination module is used to classify and aggregate each user according to the user feature vectors and determine the adjustable capacity of each category of users.

[0017] A power generation combination determination module is used to calculate the complementarity index of power generation resources based on the power generation data of each energy source, and determine at least one power generation combination according to the complementarity index.

[0018] The scheduling strategy generation module is used to generate a multi-period coordinated scheduling strategy by combining the adjustable capacity and the power generation combination.

[0019] A third aspect of this application provides a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the method steps described above.

[0020] A fourth aspect of this application provides an electronic device, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0021] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: This application obtains the power generation data of each energy source and the electricity consumption characteristic data of each user within the virtual power plant, calculates the time-series characteristic sequence and fluctuation characteristic sequence of user load based on the electricity consumption characteristic data, and then determines the user feature vector and performs classification and aggregation, thereby accurately assessing the adjustable capacity of each type of user; at the same time, it calculates the complementarity index of power generation resources based on the power generation data of each energy source and determines the power generation combination, and generates a multi-period collaborative scheduling strategy by combining the adjustable capacity and the power generation combination, realizing the collaborative optimization of user-side load regulation capability and power generation resources, avoiding the problem of over-reliance on high-cost power generation resources for regulation, thereby effectively reducing the overall operating cost of the virtual power plant. Attached Figure Description

[0022] Figure 1 This is a schematic flowchart of a power dispatching method for a virtual power plant provided in an embodiment of this application;

[0023] Figure 2 This is a schematic diagram of a power dispatching system for a virtual power plant provided in an embodiment of this application;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0025] Explanation of reference numerals in the attached drawings: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0026] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0027] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0028] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0029] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0030] Please refer to Figure 1 This paper presents a flowchart illustrating a power dispatching method for a virtual power plant. This method can be implemented using a computer program, a microcontroller, or run on a power dispatching system for a virtual power plant. The computer program can be integrated into a computer device or run as a standalone application. Specifically, the method includes steps 10 to 60, as follows:

[0031] Step 10: Obtain the power generation data of each energy source and the electricity consumption characteristics data of each user within the virtual power plant.

[0032] In this embodiment of the application, a virtual power plant refers to an energy management system that includes multiple energy sources (such as photovoltaic power generation, wind power generation, energy storage equipment, etc.) and multiple controllable load users.

[0033] Power generation data refers to the power generation data of various energy sources during historical periods, including information such as the magnitude of power generation, the time of power generation, and the characteristics of power output changes.

[0034] Electricity consumption characteristic data refers to the electricity load data of each user in a historical period, including information such as the size of the electricity load, the time of electricity consumption, and the load adjustment range.

[0035] Specifically, this embodiment employs real-time data acquisition. The system acquires power generation data from various energy sources, including photovoltaic (PV), wind, biomass, energy storage, and distributed natural gas generator sets, through power acquisition devices. This data includes power generation data every 15 minutes over the past month, characterizing the power generation capacity and output characteristics of each type of energy, particularly the volatility and uncertainty of new energy sources such as PV and wind power. The system also acquires electricity consumption characteristic data from smart meters, including electricity load data every 15 minutes over the past month, characterizing each user's electricity consumption behavior. The system stores the acquired power generation and consumption characteristic data in the virtual power plant's database and preprocesses the data, including data cleaning, outlier handling, and data normalization. This provides a high-quality data foundation for subsequent calculations of the time-series and volatility characteristics of user loads, as well as for evaluating the complementarity index between different types of power generation resources.

[0036] Step 20: Calculate the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user.

[0037] In this embodiment, the time-series feature sequence refers to a data sequence that characterizes the pattern of user load variation over time, including time-dimensional features such as load peak-valley distribution, electricity consumption periodicity, and duration, used to depict the user's electricity consumption time-series pattern. For example, an industrial user may have a higher electricity load during weekdays from 8:00 to 17:00, while having a lower electricity load at night and on weekends. This regular load variation characteristic can be quantitatively described using a time-series feature sequence.

[0038] A fluctuation characteristic sequence refers to a data sequence that characterizes the amplitude and rate of change in a user's load, including dynamic characteristics such as the range of load fluctuations, fluctuation frequency, and ramp rate, and is used to describe a user's load adjustment capability. For example, a commercial user's air conditioning load can be quickly adjusted in a short period of time, demonstrating a large load fluctuation amplitude and a fast response rate. This dynamic adjustment characteristic can be quantitatively described using a fluctuation characteristic sequence.

[0039] Specifically, firstly, the electricity consumption data is segmented by day, and the average load for each 24-hour period is calculated as the basic data for the time-series characteristic sequence. Then, Fourier transform is used to extract the periodic characteristics of the load, resulting in a time-series characteristic sequence reflecting the peak-valley distribution, electricity consumption periodicity, and duration. Secondly, the absolute value of the load difference between adjacent moments is calculated to obtain the load change sequence, and the mean, standard deviation, and maximum value of the load change within each hour are statistically analyzed to obtain a fluctuation characteristic sequence reflecting the load fluctuation range, fluctuation frequency, and ramp rate. In this way, both the temporal distribution pattern of user load and the dynamic adjustment characteristics of the load can be characterized, providing a quantitative basis for subsequent user classification and assessment of their ability to participate in load regulation.

[0040] Based on the above embodiments, as another optional embodiment, the step of calculating the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user may also include steps 101-104: Step 101: Perform feature decomposition on the electricity consumption characteristic data to obtain the basic load characteristics, load fluctuation characteristics and instantaneous disturbance characteristics.

[0041] Specifically, in order to accurately extract load characteristics of different frequency components from electricity consumption data, this embodiment employs a multi-scale wavelet decomposition method to decompose the electricity consumption data. First, the db4 wavelet basis is selected to perform a 5-level wavelet decomposition on the electricity consumption data. The low-frequency components are reconstructed from the wavelet coefficients of the 4th and 5th levels, the mid-frequency components are reconstructed from the wavelet coefficients of the 2nd and 3rd levels, and the high-frequency components are reconstructed from the wavelet coefficients of the 1st level. This achieves hierarchical extraction of electricity consumption data in the frequency domain.

[0042] After obtaining the low-frequency components, to characterize the basic load features, the difference between the maximum and minimum values ​​of the low-frequency components every 24 hours is calculated to obtain the peak-valley difference sequence, and the duration of consecutively exceeding the threshold is counted to obtain the duration sequence. The peak-valley difference sequence and the duration sequence are normalized and combined to form the basic load characteristics, which reflect the long-term variation pattern of the load and the basic electricity consumption pattern.

[0043] For the intermediate frequency (IF) component, to capture the periodic variation characteristics of the load, the main period of the signal is first determined through autocorrelation analysis. Then, the root mean square (RMS) value of the signal is calculated within each period to obtain the amplitude variation sequence. The instantaneous phase and instantaneous amplitude of the IF component are obtained through Hilbert transform to extract the periodic fluctuation characteristics. Combining the periodic characteristics and the amplitude variation sequence forms the load fluctuation characteristics, which reflect the medium-term fluctuation pattern of the load.

[0044] Finally, time-frequency analysis was performed on the high-frequency components. The time-frequency energy spectrum was calculated using short-time Fourier transform, and the energy distribution of different frequency bands within each time window was statistically analyzed to obtain the energy density matrix. The proportion of frequency components was analyzed to obtain the frequency distribution characteristics. The energy density and frequency distribution information were combined to form the instantaneous disturbance characteristics, which reflect the rapid fluctuation and instantaneous change characteristics of the load.

[0045] This multi-level feature extraction method based on wavelet decomposition enables refined decomposition of electricity consumption characteristic data in different frequency domains. The resulting basic load characteristics, load fluctuation characteristics, and instantaneous disturbance characteristics reflect the long-term trend, medium-term fluctuation, and short-term disturbance characteristics of the load, respectively, providing a comprehensive feature representation for subsequent load characteristic analysis and user classification.

[0046] Step 102: Calculate the time series feature sequence based on the decomposition results of the basic load characteristics at multiple preset time scales and the preset weights.

[0047] Specifically, to comprehensively characterize the temporal features of user load, this embodiment analyzes the basic load characteristics and calculates the temporal feature sequence across multiple preset time scales. First, three time scales—hourly, daily, and weekly—are set, and the statistical characteristics of the basic load at each scale are calculated, including the mean, standard deviation, and peak-to-valley difference. Then, weighting coefficients are assigned to each time scale: 0.5 for the hourly scale, 0.3 for the daily scale, and 0.2 for the weekly scale. Finally, the statistical characteristics at each time scale are multiplied by their corresponding weights and summed to obtain a comprehensive temporal feature sequence. This multi-scale weighted fusion method can take into account load variation characteristics at different time scales, improving the representativeness of the temporal features.

[0048] Step 103: Calculate the fluctuation intensity index based on load fluctuation characteristics and instantaneous disturbance characteristics.

[0049] Specifically, the method first calculates the root mean square (RMS) value of the load fluctuation characteristics as the medium-term fluctuation intensity, and the RMS value of the instantaneous disturbance characteristics as the short-term fluctuation intensity. Then, a fluctuation frequency factor is introduced, and the fluctuation frequency is characterized by calculating the zero-crossing rates of the load fluctuation characteristics and the instantaneous disturbance characteristics. Finally, the fluctuation intensity is multiplied by the frequency factor to obtain a comprehensive fluctuation intensity index. This calculation method considers both the fluctuation amplitude and the fluctuation frequency, and can comprehensively reflect the dynamic characteristics of the load.

[0050] Step 104: Use the time-varying sequence of the volatility intensity index as the volatility characteristic sequence.

[0051] Specifically, to describe the time-varying pattern of load fluctuation characteristics, this embodiment employs a sliding window method to transform the fluctuation intensity index into a fluctuation characteristic sequence. The sliding window length is set to 1 hour, with a step size of 15 minutes, and the fluctuation intensity index is calculated using a sliding window method. Within each window, the mean, maximum value, and rate of change of the fluctuation intensity index are calculated to form a three-dimensional feature vector. Arranging the feature vectors of each time window in chronological order yields the fluctuation characteristic sequence characterizing the dynamic fluctuation characteristics of the load. This sliding window-based serialization method can accurately depict the time-varying pattern of load fluctuation characteristics, providing an important basis for subsequent load characteristic analysis.

[0052] Step 30: Determine the user feature vector corresponding to each user based on the time-series feature sequence and fluctuation feature sequence of each user's load.

[0053] In this embodiment of the application, the user feature vector refers to a multi-dimensional numerical sequence obtained by quantifying and representing the user's electricity consumption behavior characteristics.

[0054] Specifically, firstly, statistical analysis is performed on the time-series characteristic sequence. The ratio of the maximum to minimum load value within 24 hours is calculated to obtain the peak-valley difference rate; the ratio of actual electricity load to maximum load capacity is calculated to obtain the load utilization rate; and the cumulative duration of load exceeding the average value is calculated to obtain the electricity usage duration. Secondly, feature extraction is performed on the fluctuation characteristic sequence. The standard deviation of load changes between adjacent time points is calculated to obtain the fluctuation amplitude; the main frequency components of load fluctuations are analyzed using Fast Fourier Transform to obtain the fluctuation frequency; and the maximum load change per unit time is calculated to obtain the ramp rate. Finally, the above six characteristic values ​​are standardized using the maximum-minimum value normalization method, and user feature vectors are constructed in the order of [peak-valley difference rate, load utilization rate, electricity usage duration, fluctuation amplitude, fluctuation frequency, ramp rate]. This multi-dimensional feature extraction method preserves both the time-series distribution characteristics of user loads and includes the dynamic adjustment characteristics of the load, providing a standardized feature representation for subsequent user classification and load characteristic analysis.

[0055] Based on the above embodiments, as another optional embodiment, the step of determining the user feature vector corresponding to each user based on the time-series feature sequence and fluctuation feature sequence of each user load may also include steps 201-205: Step 201: Calculate the entropy value of the time-series feature sequence and the variance of the fluctuation feature sequence.

[0056] Specifically, firstly, the entropy value of the time-series feature sequence is calculated: the time-series feature sequence is divided into n sub-intervals according to uniform time intervals, and the sample frequency pi in each interval is counted. Then, the entropy value is calculated using the formula H = -∑(p... i ×log(p iThe entropy value H is calculated, which reflects the degree of uncertainty of the time series characteristics. Simultaneously, the variance of the fluctuation characteristic sequence is calculated: first, the mean μ of the fluctuation characteristic sequence is calculated, and then the variance is calculated according to the formula σ. 2 =∑(x i -μ) 2 The variance σ is calculated from / n. 2 The variance characterizes the degree of dispersion of the fluctuation characteristics.

[0057] Step 202: Extract the peak-to-valley difference of the time-series feature sequence and the frequency features of the fluctuation feature sequence.

[0058] Specifically, extract peak-valley differences from time-series feature sequences: within a 24-hour time window, find the maximum load P. max and minimum value P min Calculate the peak-to-valley difference ΔP = P max -P min Frequency features are extracted from the wave feature sequence: the spectrum is obtained by using Fast Fourier Transform (FFT), the amplitude and corresponding frequency of the main frequency components are statistically analyzed, and the average amplitude of the first k main frequency components is selected as the frequency feature F.

[0059] Step 203: Construct stability indices based on entropy and variance.

[0060] Specifically, the stability index S is constructed as follows: First, the entropy value H is normalized to obtain H', which has a range of [0, 1]. The variance σ is then... 2 Normalization yields σ', which ranges from [0, 1]. The stability index S = (1 - H' + 1 - σ') / 2 is calculated, representing the stability of the user load. The larger the value of this index, the more stable the user load.

[0061] Step 204: Construct a volatility index based on peak-to-valley difference and frequency characteristics.

[0062] Specifically, the volatility index V is constructed by normalizing the peak-to-trough difference ΔP to obtain ΔP', with a range of [0, 1], and normalizing the frequency characteristic F to obtain F', with a range of [0, 1]. The volatility index is then calculated.

[0063] V = (ΔP' + F') / 2. The larger this value, the stronger the fluctuation of the user load.

[0064] Step 205: Combine the stability index and volatility index to generate a user feature vector.

[0065] Specifically, the stability index S and the volatility index V are combined into a two-dimensional feature vector U = [S, V]. This feature vector contains both load stability information and reflects load volatility characteristics, comprehensively characterizing the user's electricity consumption behavior. For example, a user's feature vector is [0.85, 0.32], indicating that the user has high load stability (0.85) and low load volatility (0.32).

[0066] Step 40: Classify and aggregate users based on their feature vectors to determine the adjustable capacity of each user category.

[0067] In this embodiment of the application, adjustable capacity refers to the load capacity that users in a virtual power plant can actually participate in adjusting during power dispatching.

[0068] Specifically, to facilitate differentiated scheduling for different user types, the K-means clustering algorithm is first used to classify user feature vectors. The preset number of cluster centers, K=3, is used. All user feature vectors are taken as input, and iterative clustering is performed by calculating Euclidean distance until the sum of squared intra-cluster distances is minimized. After clustering, three user categories are obtained: high-stability users (larger S-values ​​in feature vectors), high-volatility users (larger V-values ​​in feature vectors), and intermediate users. Then, the total adjustable capacity of all users in each category is calculated to obtain the total adjustable capacity for each category. For example, the total adjustable capacity for the high-stability user category is 2000kW, for the high-volatility user category it is 1500kW, and for the intermediate user category it is 1800kW. This classification method allows the virtual power plant to formulate corresponding scheduling strategies based on the characteristics of different user categories.

[0069] Based on the above embodiments, as an optional embodiment, the step of classifying and aggregating users according to their feature vectors to determine the adjustable capacity of each category of users may further include steps 301-304:

[0070] Step 301: Calculate the Euclidean distance between user feature vectors and construct a user similarity matrix based on the Euclidean distance.

[0071] Specifically, first, calculate the Euclidean distance between any two user feature vectors: for the feature vectors U of user i and user j i =[S i V i ] and U j =[S j V j Then, according to the formula: Calculate their Euclidean distances. Fill the pairwise Euclidean distances between all users into an n×n distance matrix D, where n is the total number of users. To convert the distances to similarity, a Gaussian kernel function is used: sim(i,j)=exp(-d(i,j)). 2 / 2σ

[0072] 2), where σ is the kernel function parameter. The final result is a similarity matrix S, where each element takes values ​​in the range [0, 1], with larger values ​​indicating higher similarity between users.

[0073] Step 302: Set a classification threshold based on the similarity matrix, and divide each user into multiple categories according to the classification threshold.

[0074] Specifically, by analyzing the numerical distribution in the similarity matrix S, the 33rd and 67th quantiles of similarity were selected as classification thresholds θ1 = 0.4 and θ2 = 0.7, respectively. Based on these thresholds, users were divided into three categories: users with similarity greater than θ2 were classified as category one (highly stable users); those with similarity between θ1 and θ2 were classified as category two (intermediate users); and those with similarity less than θ1 were classified as category three (highly volatile users). This method allows users with similar characteristics to be grouped into the same category.

[0075] Step 303: Calculate the peak-valley load difference for each type of user.

[0076] Specifically, for each type of user, collect their 24-hour load curve data to determine the daily maximum load value P. max and minimum load value P min Calculate the peak-to-valley difference ΔP = P max -P min Then calculate the average peak-to-valley difference ΔP for all users in that category. avg This value reflects the overall load regulation potential of this type of user. For example, if the average peak-to-valley difference for a certain type of user is 500kW, it indicates that this type of user has a large load regulation capacity.

[0077] Step 304: Calculate the adjustable capacity for each type of user based on the peak-valley load difference.

[0078] Specifically, the adjustable capacity is calculated based on the peak-valley load difference: Considering the constraints of actual adjustment capacity, an adjustment coefficient α = 0.6 is set, indicating that 60% of the peak-valley difference can be used for actual adjustment. For each type of user, the adjustable capacity P... c The calculation formula is: P c =α×ΔP avg ×N, where N is the number of users in that category. For example, if a category has 100 users and an average peak-to-valley difference of 500kW, then the total adjustable capacity of that category is P. c=0.6×500×100=30000kW.

[0079] Step 50: Calculate the complementarity index of power generation resources based on the power generation data of each energy source, and determine at least one power generation combination based on the complementarity index.

[0080] In this embodiment, the complementarity index is a quantitative indicator used to characterize the degree of complementarity in the power generation characteristics between different types of power generation resources. It is a numerical index calculated by analyzing the complementary relationship between the output curves of different types of power generation resources (such as photovoltaic and wind power) over time. The larger the index value, the stronger the complementarity in the power generation characteristics of the two types of power generation resources. For example, when photovoltaic power generation is low (e.g., at night), wind power output may be high, reflecting the complementarity between power generation resources.

[0081] A power generation mix refers to the composition scheme of different types of distributed power generation resources within a virtual power plant, which may include, but is not limited to, capacity configuration schemes for different types of distributed energy sources such as photovoltaic power generation, wind power generation, and energy storage devices. For example, the power generation mix of a virtual power plant may include: 2000kW of photovoltaic power generation, 1500kW of wind power generation, and 800kW of energy storage devices. This power generation mix scheme determines the overall power generation capacity and regulation characteristics of the virtual power plant.

[0082] Specifically, to optimize power generation resource allocation, the historical power generation data curves of each energy source are first obtained. For any two energy sources i and j, based on their power generation sequence P... i (t) and P j (t), calculate the complementarity index IC ij First, calculate the Pearson correlation coefficient ρ. ij Then through formula IC ij =1-|ρ ij | Obtain the complementarity index. For example, the complementarity index for photovoltaic (PV) and wind power is 0.85, indicating strong complementarity between the two. Calculate the complementarity index for each pair of all energy sources to form a complementarity index matrix. Based on this matrix, energy combinations with a complementarity index greater than 0.7 are selected as candidate solutions. For example, three power generation combinations are ultimately determined: Combination 1 (PV 2000kW + Wind Power 1500kW), Combination 2 (PV 1800kW + Wind Power 1200kW + Energy Storage 600kW), and Combination 3 (PV 2200kW + Energy Storage 800kW). This complementarity-based combination method can improve the stability and reliability of power generation.

[0083] Based on the above embodiments, as another optional embodiment, the step of calculating the complementarity index of power generation resources based on the power generation data of each energy source, and determining at least one power generation combination according to the complementarity index, may further include steps 401-404:

[0084] Step 401: Calculate the autocorrelation coefficient of the power generation data of each energy source and the cross-correlation coefficient between energy sources.

[0085] Specifically, firstly, 24-hour power generation data for each energy source (such as photovoltaic, wind power, and energy storage) is obtained continuously for 30 days to form a time series. For a single energy source i, its k-th order autocorrelation coefficient r is calculated. i (k):r i (k)=Cov[P i (t),P i (t+k)] / σ i 2 , where P i (t) represents the power generation at time t, P i (t+k) represents the power generation at time t+k, where k is the time delay order, ranging from 1 to 24, and σ i Let r be the standard deviation. For any two energy sources i and j, calculate their cross-correlation coefficient r. ij (k), the specific formula is:

[0086] r ij (k)=Cov[P i (t),P j (t+k)] / (σ i ×σ j ), where σ i σ j The standard deviations of power generation for energy sources i and j are given, and the cross-correlation values ​​at 24 time lags are obtained. These correlation coefficients reflect the time-series correlation of energy generation characteristics.

[0087] Step 402: Determine the power generation stability index of each energy source based on the autocorrelation coefficient.

[0088] Specifically, calculate the power generation stability index S for each energy source. i : k is the sum of numbers from 1 to 24. The larger the index, the stronger the autocorrelation of the power generation sequence and the more stable the power generation characteristics. For example, the power generation stability index of a photovoltaic power station is 0.75, indicating that its power generation characteristics have strong time-series correlation and predictability.

[0089] Step 403: Determine the complementary coordination index between energy sources based on the cross-correlation coefficient.

[0090] Specifically, for energy pair (i, j), calculate its complementary coordination index C. ij : k is the sum of values ​​from 1 to 24. The smaller the value of this index, the stronger the complementarity of the power generation characteristics of the two energy sources. For example, the complementarity coordination index of photovoltaic and wind power is 0.3, indicating that the two have good complementarity.

[0091] Step 404: The power generation stability index and the complementary coordination index are weighted and combined to obtain the complementarity index.

[0092] Specifically, the power generation stability index and the complementary coordination index are weighted and combined. Weighting coefficients w1 = 0.4 and w2 = 0.6 are set, and the complementarity index of energy pair (i, j) is calculated as IC. ij =w1×(S i +S j ) / 2-w2×C ij S i S j These are the power generation stability indices for energy sources i and j, respectively. This index considers both the stability of individual energy sources and the complementarity between them, providing a basis for optimizing power generation combinations. For example, the complementarity index of a photovoltaic-wind power combination is 0.65, indicating that the combination has good overall performance.

[0093] Step 405: Pair energy sources according to the complementarity index to determine at least one power generation combination.

[0094] Specifically, the complementarity index IC of all energy pairs will be calculated. ij Sort the data and set a complementarity index threshold θ = 0.6. Filter out those that meet the IC (Integral Complementarity Index) requirement. ij Energy pairs with values ​​greater than θ are considered as candidate combinations. For example, the following candidate energy pairs are obtained: photovoltaic-wind power (IC). 12 =0.82), Photovoltaic-Storage (IC) 13 =0.75), Wind power-storage (IC) 23 =0.68). Then, power generation combinations are constructed based on candidate energy pairs. For two-energy combinations, energy pairs with a complementarity index greater than the threshold are directly used. For three-energy combinations, it is required that the complementarity index of any two energy pairs in the combination is greater than the threshold. Meanwhile, the following constraints are considered:

[0095] 1. Total installed capacity constraint: The sum of the installed capacity of all energy sources in the combination shall not exceed 4000kW; 2. Single energy capacity constraint: The installed capacity of any single energy source shall not exceed 60% of the total installed capacity; 3. Energy capacity constraint: Photovoltaic installed capacity ranges from 1000-2500kW, wind power installed capacity ranges from 800-2000kW, and energy storage installed capacity ranges from 400-1000kW; 4. Economic constraint: The total investment cost shall not exceed the budget limit; 5. Energy ratio constraint: Energy storage capacity shall not exceed 40% of the total installed capacity of renewable energy. Based on the above conditions, the following configuration method is adopted: Determine the main energy pair: Select the energy pair with the highest complementarity index as the basic configuration; Installed capacity allocation: Determine the specific installed capacity of each energy source based on historical load data and power generation characteristics; Supplementary energy selection: Under the premise of meeting the constraints, consider adding a third energy source to improve system stability. For example, three power generation combinations were ultimately determined: Combination 1: Photovoltaic (2000kW) + Wind power (1500kW), which has the highest complementarity index and is suitable for areas with good wind and solar resources; Combination 2: Photovoltaic (1800kW) + Wind power (1200kW) + Energy storage (600kW), which improves the system's regulation capacity by adding energy storage; Combination 3: Photovoltaic (2200kW) + Energy storage (800kW), which is suitable for areas with abundant sunshine but poor wind resources.

[0096] Step 60: Combine adjustable capacity and generation combination to generate a multi-period coordinated dispatch strategy.

[0097] In this embodiment of the application, the multi-time period coordinated scheduling strategy refers to a scheduling scheme that optimizes the allocation of the output of various types of power generation resources in different time periods based on the power generation capacity characteristics of the power generation resource combination, the electricity demand characteristics of users, and market factors such as electricity prices.

[0098] Specifically, to achieve optimal allocation of power generation resources, the adjustable capacity of each energy source in the power generation combination is first obtained, including 2000kW of adjustable photovoltaic capacity, 1500kW of adjustable wind power capacity, and 600kW of adjustable energy storage capacity. The 24-hour dispatch cycle is divided into three periods: peak, flat, and valley. Based on the electricity load forecast and electricity price level for each period, a multi-period coordinated dispatch strategy is formulated: During the peak period of 10:00-15:00 with sufficient sunlight, photovoltaic power operates at maximum output, and energy storage is charged; during the peak period of 18:00-21:00, wind power maintains 80% output, and energy storage discharges at maximum power; during the flat period of 7:00-10:00, photovoltaic and wind power adjust their output as needed, and energy storage is on standby; during the valley period of 23:00-7:00 the next day, wind power maintains 60% output, and excess electricity is used for energy storage charging. This dispatch strategy fully utilizes the adjustable characteristics of each energy source to maximize power generation efficiency.

[0099] Based on the above embodiments, as another optional embodiment, the step of generating a multi-period coordinated dispatch strategy in conjunction with adjustable capacity and power generation combination may further include steps 501-506:

[0100] Step 501: Establish an objective function with the goal of minimizing the operating cost of the virtual power plant.

[0101] Specifically: To maximize the economic benefits of the virtual power plant, a cost minimization objective function is established: Where T is the scheduling period of 24 hours, and N is the number of power generation units. Let P be the operating cost coefficient (yuan / kWh) of the i-th power generation unit in the power generation combination during time period t. i,t Power generation capacity (kW), and These are the start-up and shutdown cost coefficients (in yuan), u i,t and v i,t The state variable is either 0 or 1. This objective function comprehensively considers the power generation operating cost and equipment start-up and shutdown cost, and can effectively reflect the overall operating cost of the virtual power plant.

[0102] Step 502: Based on the adjustable capacity of each type of user, construct load-side constraints including maximum adjustable capacity, adjustment response time, and recovery time.

[0103] Specifically, load-side constraints are constructed based on the adjustable capacity of various users. First, the maximum adjustable capacity constraint is established: in The load adjustment amount for time period t. This is the maximum adjustable capacity.

[0104] Then, establish constraints on the adjustment response time: Where R l Δt represents the load regulation rate, and Δt represents the dispatch interval (usually 0.5 hours).

[0105] Finally, establish recovery time constraints: in This refers to the actual recovery time. Minimum recovery time requirements. These constraints ensure the feasibility and safety of load regulation.

[0106] Step 503: Based on the power generation combination, construct power generation-side constraints including upper and lower limits of power generation output, ramp rate, and minimum start-up and shutdown time.

[0107] Specifically, the first step is to establish upper and lower limits for power generation output constraints: in and These are the minimum and maximum output limits, respectively.

[0108] Then establish the ramp rate constraint: in and These are the descending and ascending ramp rate limits, respectively. It should be noted that the purpose of the ramp rate constraint is to protect the power generation equipment and prevent damage or unstable operation caused by rapid changes in output, because generator sets (especially thermal power units) cannot change their output instantaneously and require a gradual process.

[0109] Finally, establish the minimum start / stop time constraint: in and These are the minimum operating and downtime requirements, respectively. These constraints ensure the safe and stable operation of the power generation equipment.

[0110] Step 504: Construct balance constraints based on load-side constraints and generation-side constraints.

[0111] Specifically, balance constraints are constructed to ensure supply and demand equilibrium: Where L represents the number of adjustable loads. The load is predicted for time period t. This constraint ensures that the sum of power generation and load in each time period is equal, maintaining system power balance.

[0112] Step 505: Solve for the optimal solution of the objective function under load-side constraints, generation-side constraints, and balance constraints to obtain the multi-period coordinated scheduling strategy.

[0113] Specifically, the objective function is solved using mixed-integer linear programming. First, the problem is transformed into its standard form, with the decision variable being the power generation capacity P. i,t and start / stop state variable u i,t v i,t Then, the CPLEX solver was used, with optimization parameters set as follows: convergence accuracy of 0.1% and maximum number of iterations of 1000. The solution process employed a branch and bound algorithm, continuously updating the solution space through iterations until the optimal solution satisfying all constraints was obtained. The solution results provide the 24-hour power generation plan and start-up / shutdown plan for each power generation unit, as well as the adjustment plan for adjustable loads.

[0114] Please see Figure 2 This is a schematic diagram of a power dispatching system for a virtual power plant provided in an embodiment of this application, wherein the system includes:

[0115] The data acquisition module is used to acquire power generation data of each energy source and electricity consumption characteristic data of each user within the virtual power plant.

[0116] The sequence acquisition module is used to calculate the time-series characteristic sequence and fluctuation characteristic sequence of the load of each user based on the electricity consumption characteristic data of each user;

[0117] The feature vector determination module is used to determine the user feature vector corresponding to each user based on the time-series feature sequence of each user's load and the fluctuation feature sequence;

[0118] The adjustable capacity determination module is used to classify and aggregate each user according to the user feature vectors and determine the adjustable capacity of each category of users.

[0119] A power generation combination determination module is used to calculate the complementarity index of power generation resources based on the power generation data of each energy source, and determine at least one power generation combination according to the complementarity index.

[0120] The scheduling strategy generation module is used to generate a multi-period coordinated scheduling strategy by combining the adjustable capacity and the power generation combination.

[0121] Optionally, the sequence acquisition module is also used to perform feature decomposition on the electricity consumption characteristic data to obtain basic load characteristics, load fluctuation characteristics and instantaneous disturbance characteristics;

[0122] A time-series feature sequence is calculated based on the decomposition results of the basic load characteristics at multiple preset time scales and preset weights; a fluctuation intensity index is calculated based on the load fluctuation characteristics and the instantaneous disturbance characteristics.

[0123] The time-varying sequence of the volatility intensity index is used as the volatility characteristic sequence.

[0124] Optionally, the sequence acquisition module is also used to perform wavelet decomposition on the power consumption characteristic data to obtain high-frequency components, mid-frequency components and low-frequency components.

[0125] The peak-to-valley difference and duration of the low-frequency component are calculated to obtain the base load characteristics;

[0126] The periodic fluctuations and amplitude variations of the intermediate frequency components are extracted to obtain the load fluctuation characteristics;

[0127] By analyzing the energy density and frequency distribution of the high-frequency components, the instantaneous disturbance characteristics are obtained.

[0128] Optionally, the feature vector determination module is also used to calculate the entropy value of the time-series feature sequence and the variance of the fluctuation feature sequence;

[0129] Extract the peak-to-valley difference of the time-series feature sequence and the frequency features of the fluctuation feature sequence;

[0130] A stability index is constructed based on the entropy value and the variance.

[0131] A volatility index is constructed based on the peak-to-valley difference and frequency characteristics;

[0132] The stability index and the volatility index are combined to generate a user feature vector.

[0133] Optionally, the adjustable capacity determination module is also used to calculate the Euclidean distance between user feature vectors and construct a user similarity matrix based on the Euclidean distance;

[0134] A classification threshold is set based on the similarity matrix, and each user is divided into multiple categories according to the classification threshold;

[0135] Calculate the peak-valley load difference for each user category;

[0136] The adjustable capacity for each type of user is calculated based on the peak-valley load difference.

[0137] Optionally, the power generation combination determination module is also used to calculate the autocorrelation coefficient of the power generation data of each energy source and the cross-correlation coefficient between energy sources;

[0138] The power generation stability index of each energy source is determined based on the autocorrelation coefficient.

[0139] Based on the cross-correlation coefficient, the complementary coordination index between energy sources is determined;

[0140] The complementary index is obtained by weighting and combining the power generation stability index and the complementary coordination index.

[0141] Energy sources are paired according to the complementarity index to determine at least one power generation combination.

[0142] Optionally, the scheduling strategy generation module is also used to establish an objective function with the goal of minimizing the operating cost of the virtual power plant;

[0143] Based on the adjustable capacity of each type of user, load-side constraints are constructed, including maximum adjustable capacity, adjustment response time, and recovery time.

[0144] Based on the power generation combination, power generation side constraints are constructed, including upper and lower limits of power generation output, ramp rate, and minimum start-stop time.

[0145] Construct balance constraints based on the load-side constraints and the generator-side constraints;

[0146] By solving for the optimal solution of the objective function under the constraints of the load side, the constraints of the generation side, and the balance constraints, a multi-period coordinated scheduling strategy is obtained.

[0147] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0148] This application also provides a computer storage medium that can store multiple instructions. The instructions are adapted to be loaded by a processor and executed by a power dispatching method for a virtual power plant according to the above embodiments. For the specific execution process, please refer to the detailed description of the above embodiments, which will not be repeated here.

[0149] Please refer to Figure 3 This application also discloses an electronic device. Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0150] The communication bus 302 is used to enable communication between these components.

[0151] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0152] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0153] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array. The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and Modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0154] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a power dispatching method of a virtual power plant.

[0155] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and to acquire user input data; while the processor 301 can be used to call an application program storing a power dispatching method for a virtual power plant in the memory 305. When executed by one or more processors 301, the electronic device 300 performs one or more methods as described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0156] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0157] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0158] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0159] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0160] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0161] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will readily conceive of those skilled in the art upon consideration of the specification and the disclosure of practical truths.

[0162] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A power dispatching method for a virtual power plant, characterized in that, The method includes: Obtain power generation data from various energy sources and electricity consumption characteristic data from each user within the virtual power plant; Calculate the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user; The user feature vector corresponding to each user is determined based on the time-series feature sequence of each user's load and the fluctuation feature sequence. Based on the user feature vectors, each user is classified and aggregated to determine the adjustable capacity of each user category, including: Calculate the Euclidean distance between user feature vectors, and construct a user similarity matrix based on the Euclidean distance; A classification threshold is set based on the similarity matrix, and each user is divided into multiple categories according to the classification threshold; Calculate the peak-valley load difference for each user category; Calculate the adjustable capacity for each type of user based on the peak-valley load difference; Calculate the complementarity index of power generation resources based on the power generation data of each energy source, and determine at least one power generation combination based on the complementarity index, including: Calculate the autocorrelation coefficients of power generation data for each energy source and the cross-correlation coefficients between energy sources; The power generation stability index of each energy source is determined based on the autocorrelation coefficient. Based on the cross-correlation coefficient, the complementary coordination index between energy sources is determined; The power generation stability index and the complementary coordination index are weighted and combined to obtain the complementarity index. The complementarity index is a quantitative indicator used to characterize the degree of complementarity of power generation characteristics between different types of power generation resources. It is a numerical index calculated by analyzing the complementary relationship between the output curves of different types of power generation resources in the time dimension. Based on the complementarity index, energy sources are paired to determine at least one power generation combination; A multi-period coordinated scheduling strategy is generated by combining the adjustable capacity and the power generation combination.

2. The power dispatching method for a virtual power plant according to claim 1, characterized in that, The calculation of the time-series characteristic sequence and fluctuation characteristic sequence of each user's load based on the electricity consumption characteristic data of each user includes: The power consumption characteristic data is decomposed to obtain the base load characteristics, load fluctuation characteristics, and instantaneous disturbance characteristics; A time-series feature sequence is calculated based on the decomposition results of the basic load characteristics at multiple preset time scales and preset weights. The fluctuation intensity index is calculated based on the load fluctuation characteristics and the instantaneous disturbance characteristics; The time-varying sequence of the volatility intensity index is used as the volatility characteristic sequence.

3. The power dispatching method for a virtual power plant according to claim 2, characterized in that, The process of performing feature decomposition on the electricity consumption characteristic data to obtain base load characteristics, load fluctuation characteristics, and instantaneous disturbance characteristics includes: Wavelet decomposition was performed on the power consumption characteristic data to obtain high-frequency components, mid-frequency components, and low-frequency components; The peak-to-valley difference and duration of the low-frequency component are calculated to obtain the base load characteristics; The periodic fluctuations and amplitude variations of the intermediate frequency components are extracted to obtain the load fluctuation characteristics; By analyzing the energy density and frequency distribution of the high-frequency components, the instantaneous disturbance characteristics are obtained.

4. The power dispatching method for a virtual power plant according to claim 1, characterized in that, The determination of user feature vectors based on the time-series feature sequences and the fluctuation feature sequences of each user's load includes: Calculate the entropy value of the time-series characteristic sequence and the variance of the fluctuation characteristic sequence; Extract the peak-to-valley difference of the time-series feature sequence and the frequency features of the fluctuation feature sequence; A stability index is constructed based on the entropy value and the variance. A volatility index is constructed based on the peak-to-valley difference and frequency characteristics; The stability index and the volatility index are combined to generate a user feature vector.

5. The power dispatching method for a virtual power plant according to claim 1, characterized in that, The method of generating a multi-time-period coordinated dispatch strategy by combining the adjustable capacity and the power generation combination includes: Establish an objective function with the goal of minimizing the operating cost of the virtual power plant; Based on the adjustable capacity of each type of user, load-side constraints are constructed, including maximum adjustable capacity, adjustment response time, and recovery time. Based on the power generation combination, power generation side constraints are constructed, including upper and lower limits of power generation output, ramp rate, and minimum start-stop time. Construct balance constraints based on the load-side constraints and the generator-side constraints; By solving for the optimal solution of the objective function under the constraints of the load side, the constraints of the generation side, and the balance constraints, a multi-period coordinated scheduling strategy is obtained.

6. A power dispatching system for a virtual power plant, characterized in that, The system is used to execute the power dispatching method for the virtual power plant as described in claim 1, the system comprising: The data acquisition module is used to acquire power generation data of each energy source and electricity consumption characteristic data of each user within the virtual power plant. The sequence acquisition module is used to calculate the time-series characteristic sequence and fluctuation characteristic sequence of the load of each user based on the electricity consumption characteristic data of each user; The feature vector determination module is used to determine the user feature vector corresponding to each user based on the time-series feature sequence of each user's load and the fluctuation feature sequence; The adjustable capacity determination module is used to classify and aggregate each user according to the user feature vectors and determine the adjustable capacity of each category of users. A power generation combination determination module is used to calculate the complementarity index of power generation resources based on the power generation data of each energy source, and determine at least one power generation combination according to the complementarity index. The scheduling strategy generation module is used to generate a multi-period coordinated scheduling strategy by combining the adjustable capacity and the power generation combination.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores multiple instructions suitable for being loaded by a processor and executed as described in any one of claims 1-5.

8. An electronic device, characterized in that, It includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-5.

Images