Operation mode division method and system for high-proportion distributed new energy power grid

Abstract

The invention discloses an operation mode division method and system for a high-proportion distributed new energy power grid, and the method comprises the steps: obtaining the operation data of a power grid, carrying out the preprocessing, carrying out the overall planning of elements affecting the operation mode of a power system, and obtaining the characteristics of each element through logic analysis; defining a characteristic quantity expression corresponding to each element characteristic, and calculating to obtain each element characteristic quantity and normalizing the element characteristic quantity; according to the normalized characteristic quantity of each element, clustering each element to obtain a plurality of element typical scenes, and extracting a typical curve of each element typical scene; in combination with permutation and combination of typical curves of typical scenes of various elements in actual daily operation, obtaining a normalized operation mode set of elements actually existing in the power grid; clustering the normalized operation modes of the elements according to the weighted feature vectors to obtain a power grid operation mode rough set, and obtaining a final power grid operation mode set through combination, calibration and supplement.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for dividing operating modes for a high-proportion distributed new energy power grid. Background Art

[0002] The power system operation mode describes the typical operation state of the power grid, which can not only provide a reference boundary for the safe and stable operation of the power system, but also serve as an important theoretical support for dispatchers to evaluate the current operation state of the power grid. In the traditional power system with thermal power and hydropower as the main power sources, the operation mode is mainly affected by the load and seasonal hydropower output, which can often rely on manual selection and division into simple and fixed methods such as "large in winter and small in winter, large in summer and small in summer, and high water and low water".

[0003] At present, the construction of a new power system with new energy as the main body is constantly being promoted. Compared with the traditional power system, the new power system has access to new energy represented by wind power and photovoltaics on a large scale, which has unprecedentedly increased the scale and complexity of the power grid and made the operation mode more diverse. Furthermore, the volatility, randomness and intermittency of the output of new energy sources connected to the new power system make the operation mode of the new power system complex. As a result, the traditional power system operation mode division method based mainly on experience is difficult to achieve an effective division of the operation mode of the new power system. In order to achieve accurate and efficient division of the new power system, it is necessary to comprehensively consider more influencing factors and fully explore the actual operation data. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for dividing the operation mode of a high-proportion distributed renewable energy power grid to overcome the defects of the prior art. The present invention is based on the idea of ​​dividing the operation mode of the traditional power system, further comprehensively considers the new energy elements, and combines the k-means clustering algorithm to propose a method for dividing the operation mode that is both practical and explainable, and further realizes the problem orientation of the operation mode based on the division logic.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme: The method for dividing the operation modes of a high-proportion distributed renewable energy power grid includes the following steps: Acquire power grid operation data and pre-process the power grid operation data; Based on the pre-processed grid operation data, the factors affecting the operation mode of the power system are comprehensively analyzed, and the characteristics of each factor are obtained through logical analysis; Define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; According to the normalized feature quantity of each element, each element is clustered to obtain several typical scenes of the elements, and the typical curve of the typical scene of each element is extracted; Combining the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, the combination mode of typical curves of typical scenarios of elements in reality is obtained as the normalized operation mode set of elements actually existing in the power grid; Establish a weighted feature vector of the operation mode, cluster the normalized operation modes of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; The operation modes in the rough set of power grid operation modes are merged, the special power grid operation modes are calibrated, and the potential power grid operation modes are supplemented to obtain the final power grid operation mode set.

[0006] Furthermore, the power grid operation data includes power grid load, photovoltaic, wind power, thermal power, hydropower, nuclear energy and external power operation data; the preprocessing includes cleaning and denoising.

[0007] Furthermore, the denoising is specifically as follows: using wavelet transform to decompose the noise-contaminated power grid operation data, and obtaining the noise-removed power grid operation data through reconstructing the processed wavelet coefficients.

[0008] Furthermore, the factors include photovoltaic, wind power, thermal power, hydropower, nuclear energy, external electricity and load, and the characteristics of each factor include the power generation, volatility, and correlation between output and load changes of photovoltaic and wind power, the daily power generation of thermal power, hydropower, nuclear energy and external electricity, as well as the daily power consumption of load and the daily maximum load utilization time.

[0009] Furthermore, the feature quantity expression corresponding to the feature of each element specifically includes: 1) Calculate the daily power generation of all power sources or the daily power consumption of loads:

[0010] in, is the number of power supply daily data collection, is the sampling period, Indicates the daily power generation of the power source or the daily power consumption of the load. Indicates the daily sampling point number, Indicates the electricity consumption or generation data at the sampling time; 2) Define wind power fluctuation quantity:

[0011] in, For the Maximum daily wind power output, For the Minimum daily wind power output; 3) Define wind power peak offset:

[0012] in, For the The serial number of the sampling point for the corresponding wind power output on the day; 4) Perform Fourier decomposition on the normalized photovoltaic output to obtain the various frequency intensities after decomposition. Sum the various frequency intensities of the day to obtain the photovoltaic daily fluctuation, which is specifically expressed as follows:

[0013]

[0014] in, Indicates the frequency domain sampling point number of Fourier transform, represents the frequency domain intensity, The photovoltaic power generation per day is The amount of effort at any given moment, Indicates the daily fluctuation of photovoltaic power; 5) Define photovoltaic output and load related quantities:

[0015] in, Indicates photovoltaic The amount of electricity generated at the time of day, Represents the quantity related to photovoltaic and load, Indicates load Electricity consumption at different times of the day; 6) Define the maximum load utilization time of the load day:

[0016] in, Indicates the maximum load utilization time, Indicates the daily power consumption of the load.

[0017] Furthermore, the calculation obtains the characteristic quantity of each element and normalizes the characteristic quantity of each element, specifically: Substitute the preprocessed grid operation data into the characteristic quantity expression for calculation, and then normalize the result to obtain the normalized element characteristic quantity: wind power daily power generation series 、Wind power daily fluctuation quantity series , Wind power daily peak offset sequence , Photovoltaic daily power generation series , Photovoltaic daily fluctuation quantity series , Photovoltaic daily load related quantity series 、Daily power generation series of thermal power , Hydropower daily power generation series 、Nuclear power daily power generation series 、External power daily quantity series , Load daily power consumption sequence , Load day maximum load utilization time series .

[0018] Furthermore, according to the normalized feature quantity of each element, each element is clustered to obtain several typical scenes of the elements, and a typical curve of the typical scene of each element is extracted, specifically: Based on the normalized feature quantities of each element, a daily feature vector is formed. , photovoltaic day feature vector , wind power daily feature vector , load day characteristic vector ; Based on the k-means clustering algorithm, the Elbow Method and Silhouette Coefficient are used for comprehensive judgment. The combined results are then clustered to obtain typical scenarios of each element, including typical photovoltaic scenario categories. , Typical wind power scenario categories , Typical scenario categories of traditional power supply combination And load typical scenario categories ; The mean curve of typical scenarios of the same type of elements is taken as the typical curve of the typical scenario to obtain the mean of the daily data series:

[0019] in, For a certain element Typical daily scenes of the day data points, For the The number of days the class runs.

[0020] Furthermore, the normalized operating mode set of elements is expressed as:

[0021] in, Represents a set of normalized operation modes of elements. Indicates the number of operating modes.

[0022] Furthermore, the weighted feature vector of the operation mode is established, and the normalized operation mode of each element is clustered according to the weighted feature vector to obtain a rough set of power grid operation modes, which is specifically: Normalized operation mode set of actual elements in the power grid , based on the element characteristic quantity, solve the characteristic vector under different operation modes:

[0023] in, is the operating mode characteristic vector, grid The superscripts are abbreviated and represent solar Photovoltaic, wind Wind power, thermal Thermal power, water Hydropower, nuclear nuclear power, external External calls and load load, j Represents the sample number in each type of operation mode, For the The number of sample curves for the class operation mode; Based on the operating mode feature vector, the further weighted definition of the operating mode weighted feature vector is as follows:

[0024] in, is the experience weight sequence, Weighted feature vector for operation mode; Weighted feature vector sequence for operation mode Perform k-means cluster analysis again to obtain a rough set of power grid operation modes ,in, represents the samples in the rough set of running modes, Indicates the number of samples in the rough set of running modes.

[0025] The operation mode classification system for high-proportion distributed renewable energy power grids includes: Data acquisition and processing module: used to acquire power grid operation data and pre-process the power grid operation data; Data analysis module: used to coordinate the factors affecting the operation mode of the power system based on the pre-processed power grid operation data, and obtain the characteristics of each factor through logical analysis; Normalization module: used to define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; The first clustering module is used to cluster each element according to the normalized feature quantity of each element, obtain several typical scenes of the elements, and extract the typical curve of the typical scene of each element; Combination module: used to combine the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, and obtain the combination mode of typical curves of typical scenarios of elements in reality, as the normalized operation mode set of elements actually existing in the power grid; The second clustering module is used to establish a weighted feature vector of the operation mode, cluster the normalized operation mode of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; Merging processing module: used to merge the operation modes in the rough set of power grid operation modes, calibrate the special operation modes of the power grid, and supplement the potential operation modes of the power grid to obtain the final set of power grid operation modes.

[0026] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for dividing the operation mode for a high-proportion distributed new energy power grid when executing the computer program.

[0027] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for dividing the operation mode of a high-proportion distributed new energy power grid.

[0028] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention comprehensively considers the factors that affect the power grid mode and analyzes the relevant characteristics, achieving a more comprehensive and accurate division of the operation mode. The present invention first performs a logical analysis of the factors that affect the operation mode of the power grid, and obtains the factors that affect the operation mode; then, by constructing the characteristic quantity of the factors and performing a clustering on them, the typical scene of the factors is obtained, and then the typical curve of the typical scene is obtained; then, according to the actual operation data, the typical curves of the typical scenes of different factors are combined to obtain the normalized operation mode set of the factors actually existing in the power grid, and then the weighted characteristic vector of the operation mode is constructed, and a secondary clustering is performed to obtain the operation mode set of the power grid. This method achieves a significant reduction in the complexity of clustering data through the constructed characteristic quantity of the factors, improves the calculation efficiency and clustering effect, and can realize the visualization of cluster points due to the reduction of data dimension.

[0029] In addition, the present invention performs secondary clustering by setting empirical weights, thereby achieving efficient merging of operation modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings in the specification are used to provide further understanding of the present invention and constitute a part of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 It is a flow chart of the method for dividing the operation modes of the high-proportion distributed new energy power grid according to the present invention; Figure 2A schematic diagram of the system structure for dividing the operation mode of the high-proportion distributed new energy power grid of the present invention; Figure 3 It is the cluster scatter plot of load characteristic quantity; Figure 4 It is a typical curve of each element in a certain operation scenario. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1 See also Figure 1 The present invention provides a method for dividing the operation modes of a high-proportion distributed new energy power grid, comprising the following steps: Acquire power grid operation data and pre-process the power grid operation data; Based on the pre-processed grid operation data, the factors affecting the operation mode of the power system are comprehensively analyzed, and the characteristics of each factor are obtained through logical analysis; Define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; According to the normalized feature quantity of each element, each element is clustered to obtain several typical scenes of the elements, and the typical curve of the typical scene of each element is extracted; Combining the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, the combination mode of typical curves of typical scenarios of elements in reality is obtained as the normalized operation mode set of elements actually existing in the power grid; Establish a weighted feature vector of the operation mode, cluster the normalized operation modes of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; The operation modes in the rough set of power grid operation modes are merged, the special power grid operation modes are calibrated, and the potential power grid operation modes are supplemented to obtain the final power grid operation mode set.

[0035] The present invention comprehensively considers the factors that affect the power grid mode and analyzes the relevant characteristics, achieving a more comprehensive and accurate division of the operation mode. The feature quantity of the elements constructed by the present invention greatly reduces the complexity of clustering data, improves the operation efficiency and clustering effect, and realizes the visualization of cluster points due to the reduction of data dimension.

[0036] Embodiment 2 Based on the traditional idea of ​​power system operation mode division, the present invention further comprehensively considers new energy elements, and proposes an operation mode division method that is both practical and explainable in combination with the k-means clustering algorithm, and further realizes the problem orientation of the operation mode based on the division logic.

[0037] The specific steps include: Step 1: Obtain power grid operation data, and pre-process the power grid operation data by cleaning and denoising; First, obtain the grid operation data including grid load, photovoltaic, wind power, thermal power, hydropower, nuclear energy and external electricity.

[0038] Since the sources of power grid operation data are diverse and sensors are prone to data loss and delayed transmission during the collection process, it is necessary to eliminate dates with more missing data points. For dates with fewer missing data points, the missing data points are filled by linear interpolation and the abnormal data are cleaned.

[0039] Due to the noise pollution generated by the data measurement and transmission process, is the real data of the element running on a certain day, and the noisy data contaminated by noise is expressed as: (1) in, is the length of the element data for the day, For noise.

[0040] In order to convert the original signal that is not contaminated by noise From the signal contaminated by noise After being recovered, the wavelet transform can be used to decompose the signal contaminated by noise: (2) in, represents the part containing noise, and the detailed part is represented by , the similar part is expressed as , , the signal after noise elimination It can be obtained by reconstructing the wavelet coefficients.

[0041] After data preprocessing, we get Photovoltaic intraday series 、Wind power intraday sequence 、 Thermal power intraday sequence 、Hydropower intraday series 、Nuclear power daily sequence 、Incoming call intraday sequence 、Load intraday series .

[0042] Step 2: Based on the pre-processed grid operation data, coordinate the factors that affect the operation mode of the power system, and then obtain the characteristics of each factor through logical analysis; The division of power system operation modes needs to take into account relevant factors, namely the operating scenarios of various types of power sources and loads. For general regional power grids, power sources can be divided into new energy and traditional power sources. Adding the factor of load, the power grid operation is considered from three aspects, namely new energy, traditional power sources, and loads.

[0043] Renewable energy mainly includes photovoltaic and wind power. Compared with traditional power sources, daily power generation varies greatly with natural conditions, and the output is volatile. In recent years, with the increase in the number of new energy grid connections, the consumption of new energy has become an increasingly serious problem. Therefore, the analysis of new energy issues also needs to consider the correlation between load and new energy output. Therefore, the analysis of new energy needs to consider the power generation, i.e. large and small generation, volatility, and the correlation between new energy output and load changes.

[0044] Traditional power sources include thermal power, hydropower, nuclear power and external power. Thermal power technology is mature and flexible, and is the main component of traditional power sources. Hydropower has obvious seasonality, and should be consumed first in the flood season. Safety is the main consideration in the operation of nuclear power, and it is generally not involved in daily regulation as a base load. External power can supplement local power and effectively ensure regional energy security and grid stability. Therefore, for traditional power sources, the main consideration is daily power generation.

[0045] Load changes are significantly correlated with workday and holiday schedules, and the daily routines of ordinary people. Generally, the intraday change trends are obviously similar, but on special dates, the intraday trends of loads will change significantly, generally showing a decrease in power consumption and a decrease in the peak-to-valley ratio of loads. Therefore, for loads, it is necessary to consider the intraday power consumption and the maximum load utilization time of the day.

[0046] The above logical analysis is summarized in the following table:

[0047] If each characteristic of each element is regarded as a dimension, there are 12 dimensions in total, and these 12 dimensions form the steady-state operation space of the power grid.

[0048] Step 3: Define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the result; Calculate the daily power generation of all power sources or the daily power consumption of loads. This characteristic quantity is as follows: (3) in, is the length of the element data for the day, is the sampling period, Indicates the daily power generation of the power source or the daily power consumption of the load. Indicates the daily sampling point number, Indicates the electricity consumption or generation data at the sampling time.

[0049] Define wind power fluctuation quantity: (4) in, For the Maximum daily wind power output, For the Minimum daily wind power output.

[0050] Define wind power peak offset: (5) in, For the The serial number of the sampling point corresponding to the daily wind power output.

[0051] Although photovoltaic output is affected by natural conditions and has randomness and volatility, the light intensity within a day is still regular, so the photovoltaic output after normalization of the daily output is subjected to Fourier decomposition: (6) in, Indicates the frequency domain sampling point number of Fourier transform, represents the frequency domain intensity, The photovoltaic power generation per day is The amount of effort at all times.

[0052] The intensity of each frequency component after decomposition is calculated, and the various frequency intensities of the day are summed up to obtain the photovoltaic daily fluctuation: (7) Define PV output and load related quantities: (8) Define the maximum load utilization time of the load day: (9) in, Indicates the maximum load utilization time, Indicates the daily power consumption of the load.

[0053] Furthermore, the preprocessed grid operation data is substituted into the characteristic quantity expression for calculation, and then the result is normalized to obtain the normalized element characteristic quantity: wind power daily power generation series 、Wind power daily fluctuation quantity series , Wind power daily peak offset sequence , Photovoltaic daily power generation series , Photovoltaic daily fluctuation quantity series , Photovoltaic daily load related quantity series 、Daily power generation series of thermal power , Hydropower daily power generation series 、Nuclear power daily power generation series 、External power daily quantity series , Load daily power consumption sequence , Load day maximum load utilization time series .

[0054] Step 4: Cluster each element based on the normalized feature quantity of each element to obtain the typical scene of the element or element combination, and extract the typical curve of the typical scene of each element; Based on the above defined element characteristics, the daily characteristic vectors are formed for the traditional power supply combination. , photovoltaic day feature vector , wind power daily feature vector , load day characteristic vector .

[0055] Since the time series data has been preprocessed and the characteristic quantities of each element have been defined, a simple and efficient k-means algorithm is used.

[0056] The k-means clustering algorithm is a partition-based clustering algorithm that uses distance as a measure of similarity between data. Represents the number of clusters, and the within-cluster sum of squared errors (SSE) between the mass points of each cluster and the sample points within the cluster is called the distortion degree expression as follows: (10) in, It is kind, yes The sample points in the class, yes The centroid of the class ( The mean of all samples in .

[0057] K-means takes minimizing the square error between samples and points as the objective function, while the number of clusters in cluster analysis is The determination of is crucial to the quality of clustering. For a cluster, the lower the degree of distortion, the tighter the structure within the cluster, and the higher the degree of distortion, the looser the structure within the cluster. The degree of distortion will decrease with the increase of categories, but for data with a certain degree of discrimination, the degree of distortion will be greatly improved when it reaches a certain critical point, and then slowly decrease. This critical point can be considered as a point with better clustering performance, that is, Elbow Method. Silhouette Coefficient is an evaluation index of the density and dispersion of the class, as shown in the following formula: (11) in, is the mean distance between samples in the same cluster, is the mean distance between the sample and the nearest sample in the cluster other than the cluster where the sample belongs, and the Silhouette Coefficient is , the value is [-1,1], the closer to 1, the The more reasonable the value.

[0058] Furthermore, the Elbow Method and Silhouette Coefficient were used to make a comprehensive judgment. The values ​​are then clustered to obtain the typical scenes of each element.

[0059] After clustering, typical photovoltaic scene categories are obtained. , Typical wind power scenario categories , Typical scenario categories of traditional power supply combination And load typical scenario categories .

[0060] Furthermore, the mean curve of typical scenarios of the same type of elements is obtained as the characteristic curve of the typical scenario to obtain the mean of the daily data series: (12) in, For a certain element Typical daily scenes of the day data points, For the The number of days the class runs.

[0061] Step 5: Combining the typical curves of typical scenes of various elements in actual daily operation, the combination mode of typical curves of typical scenes of elements in actual operation is obtained, that is, the normalized operation mode set of elements actually existing in the power grid; Specifically, combined with the arrangement and combination of typical scenarios of various elements in actual daily operation, that is, the set of normalized operation modes of elements ,in, Represents a set of normalized operation modes of elements. Indicates the number of operating modes.

[0062] Step 6: Establish a weighted feature vector of the operation mode, and cluster each normalized operation mode based on it to obtain a rough set of power grid operation modes; For the actual operation mode set of the power grid , based on the element characteristic quantity, solve the characteristic vector under different operation modes: (13) in, is the operating mode characteristic vector, grid The superscripts are abbreviated and represent solar Photovoltaic, wind Wind power, thermal Thermal power, water Hydropower, nuclear nuclear power, external External calls and load load, j Represents the sample number in each type of operation mode, For the The number of sample curves for the class operation mode.

[0063] The weighted feature vector of the operating mode is defined as follows: (14) in, is the empirical weight sequence, determined by experience, The weighted operating mode feature vector.

[0064] For the operating mode feature vector sequence Perform k-means cluster analysis again to obtain a rough set of power grid operation modes ,in, represents the samples in the rough set of running modes, Indicates the number of samples in the rough set of running modes.

[0065] Step 7: Manually merge the operation modes in the rough set of power grid operation modes, calibrate the special operation modes of the power grid, and supplement the potential operation modes of the power grid, and finally obtain the set of power grid operation modes.

[0066] According to the staff's experience, the operation modes in the rough set of power grid operation modes are manually merged, the special operation modes of the power grid are calibrated, and the potential operation modes of the power grid are supplemented to obtain the supplemented operation modes. .

[0067] Embodiment 3 The actual operation data of the power grid in a certain region is selected for case analysis.

[0068] Actual operation case of a regional power grid: The actual operation data of the regional power grid for two years was obtained, including power grid load, photovoltaic power, wind power, thermal power, hydropower, nuclear power and external power elements. After preliminary comparison, the maximum output of nuclear power and hydropower is far less than the maximum load, so it has no obvious impact on the classification of power grid operation mode. The load characteristic quantity clustering is obtained as follows Figure 2 , Figure 2 The characteristic value clustering result of the load element is shown in Figure 2, and the load output curve is divided into 7 categories. The empirical weights are all set to 1, and the typical curves of each element under a certain operation mode are obtained as follows: Figure 3 As shown, Figure 3 It represents the output curve of load, photovoltaic power, wind power, thermal power and external power under a certain operating mode.

[0069] Embodiment 4 See also Figure 2 The present invention provides an operation mode classification system for a high-proportion distributed new energy power grid, comprising: Data acquisition and processing module: used to acquire power grid operation data and pre-process the power grid operation data; Data analysis module: used to coordinate the factors affecting the operation mode of the power system based on the pre-processed power grid operation data, and obtain the characteristics of each factor through logical analysis; Normalization module: used to define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; The first clustering module is used to cluster each element according to the normalized feature quantity of each element, obtain several typical scenes of the elements, and extract the typical curve of the typical scene of each element; Combination module: used to combine the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, and obtain the combination mode of typical curves of typical scenarios of elements in reality, as the normalized operation mode set of elements actually existing in the power grid; The second clustering module is used to establish a weighted feature vector of the operation mode, cluster the normalized operation mode of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; Merging processing module: used to merge the operation modes in the rough set of power grid operation modes, calibrate the special operation modes of the power grid, and supplement the potential operation modes of the power grid to obtain the final set of power grid operation modes.

[0070] Embodiment 5 The present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for dividing the operation mode for a high-proportion distributed new energy power grid are implemented.

[0071] Embodiment 6 The present invention provides a computer-readable storage medium, which stores a computer program, and is characterized in that when the computer program is executed by a processor, the steps of the method for dividing the operation mode for a high-proportion distributed new energy power grid are implemented.

[0072] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented 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.

[0073] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0074] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0075] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit its protection scope. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that after reading the present invention, those skilled in the art can still make various changes, modifications or equivalent substitutions to the specific implementation methods of the invention, but these changes, modifications or equivalent substitutions are all within the protection scope of the pending claims of the invention.

Claims

1. The method for dividing the operation modes of a high-proportion distributed renewable energy power grid is characterized in that: The steps include: Acquire power grid operation data and pre-process the power grid operation data; Based on the pre-processed grid operation data, the factors affecting the operation mode of the power system are comprehensively analyzed, and the characteristics of each factor are obtained through logical analysis; Define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; According to the normalized feature quantity of each element, each element is clustered to obtain several typical scenes of the elements, and the typical curve of the typical scene of each element is extracted; Combining the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, the combination mode of typical curves of typical scenarios of elements in reality is obtained as the normalized operation mode set of elements actually existing in the power grid; Establish a weighted feature vector of the operation mode, cluster the normalized operation modes of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; The operation modes in the rough set of power grid operation modes are merged, the special power grid operation modes are calibrated, and the potential power grid operation modes are supplemented to obtain the final power grid operation mode set.

2. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 1 is characterized in that: The power grid operation data includes power grid load, photovoltaic, wind power, thermal power, hydropower, nuclear energy and external power operation data; the preprocessing includes cleaning and denoising.

3. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 2 is characterized in that: The denoising is specifically as follows: using wavelet transform to decompose the noise-contaminated power grid operation data, and obtaining the noise-free power grid operation data by reconstructing the processed wavelet coefficients.

4. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 1 is characterized in that: The factors include photovoltaic power, wind power, thermal power, hydropower, nuclear power, external electricity and load. The characteristics of each factor include the power generation, volatility, and correlation between output and load changes of photovoltaic and wind power, the daily power generation of thermal power, hydropower, nuclear power and external electricity, as well as the daily power consumption of load and the daily maximum load utilization time.

5. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 4 is characterized in that: The characteristic quantity expression corresponding to the characteristics of each element specifically includes: 1) Calculate the daily power generation of all power sources or the daily power consumption of loads: in, is the number of power supply daily data collection, is the sampling period, Indicates the daily power generation of the power source or the daily power consumption of the load. Indicates the daily sampling point number, Indicates the electricity consumption or generation data at the sampling time; 2) Define wind power fluctuation quantity: in, For the Maximum daily wind power output, For the Minimum daily wind power output; 3) Define wind power peak offset: in, For the The serial number of the sampling point for the corresponding wind power output on the day; 4) Perform Fourier decomposition on the normalized photovoltaic output to obtain the various frequency intensities after decomposition. Sum the various frequency intensities of the day to obtain the photovoltaic daily fluctuation, which is specifically expressed as follows: in, Indicates the frequency domain sampling point number of Fourier transform, represents the frequency domain intensity, The photovoltaic power generation per day is The amount of effort at any given moment, Indicates the daily fluctuation of photovoltaic power; 5) Define photovoltaic output and load related quantities: in, Indicates photovoltaic The amount of electricity generated at the time of day, Represents the quantity related to photovoltaic and load, Indicates load Electricity consumption at different times of the day; 6) Define the maximum load utilization time of the load day: in, Indicates the maximum load utilization time, Indicates the daily power consumption of the load.

6. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 5 is characterized in that: The calculation obtains the characteristic value of each element and normalizes the characteristic value of each element, specifically: Substitute the preprocessed grid operation data into the characteristic quantity expression for calculation, and then normalize the result to obtain the normalized element characteristic quantity: wind power daily power generation series 、Wind power daily fluctuation quantity series , Wind power daily peak offset sequence , Photovoltaic daily power generation series , Photovoltaic daily fluctuation quantity series , Photovoltaic daily load related quantity series 、Daily power generation series of thermal power , Hydropower daily power generation series 、Nuclear power daily power generation series 、External power daily quantity series , Load daily power consumption sequence , Load day maximum load utilization time series .

7. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 6 is characterized in that: According to the normalized feature quantity of each element, each element is clustered to obtain several typical scenes of the elements, and the typical curve of the typical scene of each element is extracted, which is specifically: Based on the normalized feature quantities of each element, a daily feature vector is formed. , photovoltaic day feature vector , wind power daily feature vector , load day characteristic vector ; Based on the k-means clustering algorithm, the Elbow Method and Silhouette Coefficient are used for comprehensive judgment. The combined results are then clustered to obtain typical scenarios of each element, including typical photovoltaic scenario categories. , Typical wind power scenario categories , Typical scenario categories of traditional power supply combination And load typical scenario categories ; The mean curve of typical scenarios of the same type of elements is taken as the typical curve of the typical scenario to obtain the mean of the daily data series: in, For a certain element Typical daily scenes of the day data points, For the The number of days the class runs.

8. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 1 is characterized in that: The normalized operation mode set of the elements is expressed as: in, Represents a set of normalized operation modes of elements. Indicates the number of operating modes.

9. The method for dividing the operation modes of a high-proportion distributed new energy power grid according to claim 1 is characterized in that: The weighted feature vector of the operation mode is established, and the normalized operation mode of each element is clustered according to the weighted feature vector to obtain a rough set of power grid operation modes, which is specifically: Normalized operation mode set of actual elements in the power grid , based on the element characteristic quantity, solve the characteristic vector under different operation modes: in, is the operating mode characteristic vector, grid The superscripts are abbreviated and represent solar Photovoltaic, wind Wind power, thermal Thermal power, water Hydropower, nuclear nuclear power, external External calls and load load, j Represents the sample number in each type of operation mode, For the The number of sample curves for the class operation mode; Based on the operating mode feature vector, the further weighted definition of the operating mode weighted feature vector is as follows: in, is the experience weight sequence, Weighted feature vector for operation mode; Weighted feature vector sequence for operation mode Perform k-means cluster analysis again to obtain a rough set of power grid operation modes ,in, represents the samples in the rough set of running modes, Indicates the number of samples in the rough set of running modes.

10. The operation mode classification system for high-proportion distributed new energy power grid is characterized by: include: Data acquisition and processing module: used to acquire power grid operation data and pre-process the power grid operation data; Data analysis module: used to coordinate the factors affecting the operation mode of the power system based on the pre-processed power grid operation data, and obtain the characteristics of each factor through logical analysis; Normalization module: used to define the feature quantity expression corresponding to each element feature, calculate the feature quantity of each element, and normalize the feature quantity of each element; The first clustering module is used to cluster each element according to the normalized feature quantity of each element, obtain several typical scenes of the elements, and extract the typical curve of the typical scene of each element; Combination module: used to combine the permutations and combinations of typical curves of typical scenarios of various elements in actual daily operation, and obtain the combination mode of typical curves of typical scenarios of elements in reality, as the normalized operation mode set of elements actually existing in the power grid; The second clustering module is used to establish a weighted feature vector of the operation mode, cluster the normalized operation mode of each element according to the weighted feature vector, and obtain a rough set of power grid operation modes; Merging processing module: used to merge the operation modes in the rough set of power grid operation modes, calibrate the special operation modes of the power grid, and supplement the potential operation modes of the power grid to obtain the final set of power grid operation modes.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for dividing the operation mode for a high-proportion distributed new energy power grid are implemented as described in any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for dividing the operation mode for a high-proportion distributed new energy power grid are implemented as described in any one of claims 1 to 9.

Images