Analysis Method and System for Output Characteristics of New Energy and Ultra-Large-Scale Energy Storage Combined Power Station

Abstract

The present invention provides a method and system for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station. The method includes obtaining the new energy output and energy storage system operation data in the new energy and ultra-large-scale energy storage combined power station, and performing standardization processing; performing hierarchical clustering analysis; performing hierarchical clustering analysis on the time series data of the obtained combined power station, gradually merging a large number of characteristic data vectors into clusters, and generating typical characteristic operations and their respective weights. It can extract representative operation characteristic results from the massive operation data of the new energy and ultra-large-scale energy storage combined power station, provide necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly, and day-ahead, and formulating the unit output and start-stop plan, provide a basis for formulating the energy management and control strategy of the energy storage power station, and have guiding significance for the investment in units, energy storage systems, and transmission lines in the power system.

Description

Technical Field

[0001] The present invention belongs to the field of electrical engineering, and mainly relates to an analysis method for the output characteristics of a combined power station of new energy and ultra-large-scale battery energy storage and a system thereof. Background Art

[0002] At present, the energy consumption structure is accelerating towards clean and low-carbon, and new energy acting as the main energy source is the future dominant development direction. However, in reality, the resource endowment and energy consumption load are unbalanced, and coupled with the spatio-temporal mismatch of new energy, the large-scale access of wind power and photovoltaic power in new energy to the power grid has increasingly amplified the impact of their volatility and intermittency on the power grid. The peak shaving and consumption pressure of the power grid is huge, and more flexible resources are needed to provide necessary support for the safe, stable and efficient operation of the power system. The organic combination of new energy and large-scale battery energy storage systems can give play to the two-way characteristics of large-scale energy storage systems, realize the spatio-temporal transfer of new energy output through energy throughput, provide the necessary support required by the power grid while reducing carbon dioxide emissions and promoting new energy consumption, and is an inevitable development direction of future power grids.

[0003] With the combination of new energy and ultra-large-scale energy storage gradually becoming the consensus of the energy industry and the gradual popularization of combined power stations of new energy and ultra-large-scale battery energy storage, how to make the economy of the combined power station better under the condition of ensuring the balance of power supply and demand, and how to reasonably adjust the output of new energy and the output of energy storage power stations according to the changing rules of electricity consumption throughout the year are crucial for the construction and management of power stations. However, in the existing technology, most attention is paid to the surface of these problems, and it has not been noticed that the fundamental solution lies in the analysis of the output characteristics of the combined power station. Therefore, it is necessary for us to focus on the analysis of the output characteristics of the combined power station to meet the urgent needs of the current investment and operation of combined power stations. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes an analysis method for the output characteristics of a combined power station of new energy and ultra-large-scale energy storage, which can extract representative output situations and their corresponding weights from a large amount of new energy output data and energy storage system operation data, provide necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly and day-ahead, and formulating unit output and start-stop plans, and bring certain guiding significance to the investment in units, energy storage systems and transmission lines in the power system.

[0005] The present invention proposes a method for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station, which includes obtaining the output data of new energy and the energy storage system in the new energy and ultra-large-scale energy storage combined power station, and performing standardization processing; extracting output feature vectors from the standardized data, and calculating the Euclidean distance between each output feature vector; merging the output feature vectors with close Euclidean distances into one cluster; calculating the distances between clusters, merging the clusters with close distances to form new clusters, and continuing to calculate the distances between the new clusters or the distances between the new clusters and the original clusters and merging until reaching a root node clustering that includes all elements; generating a system tree diagram of the output feature data set according to the relationships between the data nodes during the clustering process; and obtaining each output feature data set and its corresponding weight according to the system tree diagram as the result of the output characteristic analysis.

[0006] In the method for analyzing the output characteristics of the new energy and ultra-large-scale energy storage combined power station provided in this embodiment, hierarchical clustering analysis is performed on the obtained output data of the new energy and ultra-large-scale energy storage combined power station, and a large number of output feature vectors are merged into clusters layer by layer, so that the combined output under various typical output characteristics and their corresponding weights can be obtained. It can extract representative typical output characteristics and their corresponding weights from a large amount of new energy output data and energy storage system operation data, provide necessary technical support for ensuring the power and energy balance in different time series periods such as annual, monthly, and day-ahead, and formulating unit output and start-stop plans, and bring certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0007] Preferably, when obtaining the output data, the output data of new energy and the energy storage system of the new energy and ultra-large-scale energy storage combined power station are extracted on an annual basis. In this embodiment, when obtaining time series data, on an annual basis, the operation data of the combined power station can obtain the typical output characteristics and their corresponding weights in that year after hierarchical clustering analysis. Studying the output characteristics of the new energy and ultra-large-scale energy storage combined power station according to the time series changes of the four seasons of the year provides necessary technical support for ensuring the power and energy balance in different time series periods such as annual, monthly, and day-ahead, and formulating unit output and start-stop plans, and brings certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0008] Preferably in the above embodiment, the standardization processing includes summing the output data of new energy and the energy storage system of the new energy and ultra-large-scale energy storage combined power station on an annual basis, and normalizing the sum using the mean square deviation formula.

[0009] Preferably in the above embodiment, the output feature vector is the sum of the output data of new energy and the energy storage system of the new energy and ultra-large-scale energy storage combined power station after standardization processing.

[0010] Preferably, in the above embodiments, the distance between each cluster is calculated by the average linkage method.

[0011] The present invention also provides an analysis system for the output characteristics of a new energy and ultra-large-scale energy storage combined power station, including a data processing module for extracting the output data of the new energy and the energy storage system in the new energy and ultra-large-scale energy storage combined power station and performing standardized processing; a feature vector calculation module for extracting output feature vectors from the standardized data and calculating the Euclidean distance between each output feature vector; a hierarchical clustering analysis module for merging the output feature vectors with close distances into a cluster according to the calculated Euclidean distance; calculating the distance between each cluster, merging the clusters with close distances to form new clusters, and continuing to calculate and merge the distances between the new clusters or between the new clusters and the original clusters until a root node clustering containing all elements is reached; and an operating characteristic result output module for generating a dendrogram of the output feature data set during the clustering process, and obtaining each output feature data set and its corresponding weight according to the dendrogram as the output characteristic analysis result.

[0012] In the analysis system for the output characteristics of the new energy and ultra-large-scale energy storage combined power station provided in this embodiment, hierarchical clustering analysis is performed on the obtained time series data of the combined power station, and a large number of output feature vectors are merged into clusters layer by layer, so as to obtain typical output characteristics and their corresponding weights. It can extract representative typical output characteristics and their corresponding weights from the massive annual new energy output data and energy storage system output data, providing necessary technical support for ensuring the power and energy balance in different time series periods such as annual, monthly, and day-ahead, and formulating the unit output and start-stop plans, etc., and bringing certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0013] Preferably, in any of the above embodiments, the data processing module includes a data extraction unit and a standardized processing unit; the data extraction unit is used to extract the output data of the new energy and the energy storage system in the new energy and ultra-large-scale energy storage combined power station on an annual basis.

[0014] Preferably, in any of the above embodiments, the standardized processing unit is used to perform normalization processing on the sum of the new energy output data and the energy storage system output data extracted from the new energy and ultra-large-scale energy storage combined power station by using the mean square deviation formula.

[0015] Preferably, in any of the above embodiments, the feature vector calculation module is used to extract output feature vectors, and the output feature vectors are the sum of the new energy output data and the energy storage system output data in the new energy and ultra-large-scale energy storage combined power station after standardized processing.

[0016] Preferably, in any of the above embodiments, the hierarchical clustering analysis module includes an output feature vector merging module and a cluster merging module; the output feature vector merging module merges feature vectors with close Euclidean distances into one cluster according to the Euclidean distances between the feature vectors; the cluster merging module merges clusters with close distances into a new cluster according to the average linkage distance between the clusters, continues to calculate the distances between the new clusters or the distances between the new clusters and the original clusters and merges them until a root node clustering containing all elements is formed. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which form a part of this application, are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0018] Figure 1 is a flowchart of a method for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station provided by an embodiment of the present application;

[0019] Figure 2 is a structural block diagram of a system for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station provided by an embodiment of the present application;

[0020] In the figure: 1. Data processing module; 101. Data extraction unit; 102. Standardization processing unit; 2. Feature vector calculation module; 3. Hierarchical clustering analysis module; 301. Output feature vector merging module; 302. Cluster merging module; 4. Typical output characteristic output module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments. It should be noted that, without conflict, the embodiments and features in the present application can be combined with each other.

[0022] The following detailed descriptions are all exemplary descriptions, aiming to provide a further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0023] As Figure 1 shown, the present invention proposes a method for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station, including the following steps:

[0024] S1. Obtain the operation data of the new energy and ultra-large-scale energy storage combined power station, where the operation data is the output data of the new energy and the energy storage system in annual units; perform standardization processing;

[0025] In this embodiment, when obtaining time-series data, the operation data of the power station is combined on an annual basis. After hierarchical clustering analysis, the operation characteristic results and their respective corresponding weights in that year can be obtained. Analyze and refine the output characteristics of new energy and ultra-large-scale energy storage power stations to provide necessary technical support for ensuring power and electricity balance in different time-series cycles such as annual, monthly, and day-ahead, and formulating unit output and start-stop plans.

[0026] The standardization process includes extracting the new energy output data and the energy storage system output data from the operation data of the new energy and ultra-large-scale energy storage combined power station; performing data standardization on the sum of the two; and performing standardization on the sum of the new energy output data and the energy storage system output in step 1 through mean square deviation normalization to obtain a new distribution, weakening the influence of outliers. The standardization formula is shown in formula (1).

[0027]

[0028] Among them, Xi is the original time-series data of the new energy or ultra-large-scale energy storage system output, μ is the data mean, and σ is the data standard deviation.

[0029] S2. Extract the output feature vectors from the standardized data and calculate the Euclidean distance between each output feature vector; it also includes using the sum of the new energy output and the energy storage system output of the new energy and ultra-large-scale energy storage combined power station after standardization as the output feature vector.

[0030] S3. Combine the output feature vectors with similar Euclidean distances into a cluster to generate a new set of feature data.

[0031] S4. Calculate the distance between each cluster, merge the clusters with close distances to form new clusters, continue to calculate the distance between the new clusters or the distance between the new clusters and the original clusters and merge them until a root node clustering containing all elements is reached.

[0032] Preferably, in the above embodiment, the distance between each feature vector is the Euclidean distance between the standardized data; the distance between clusters is calculated by the average linkage method to obtain the distance between each cluster.

[0033] Calculate the Euclidean distance between the standardized data, and the formula is shown in formula (2). Compare them and merge the data with the closest distance into a cluster.

[0034] D(x i , x j ) = ||x i - x j || (2)

[0035] The obtained data are recalculated with the inter-cluster distances, and the inter-cluster distances can be calculated by a formula such as formula (3) to obtain the inter-cluster distances under the average linkage method;

[0036] The distance calculation formula of the average linkage method is shown in formula (3) below

[0037]

[0038] where x i and x j are the elements in clusters X i and X j respectively.

[0039] S5. Generate a dendrogram of the output characteristic data set according to the relationships of each data node in the clustering process;

[0040] S6. According to the dendrogram, obtain each output characteristic data set and its corresponding weight as the analysis result of the output characteristics; Due to the above extraction method, the present invention can analyze the output characteristics of the new energy and ultra-large-scale energy storage combined power station. It is more suitable for the organic combination form of the new energy + energy storage system in the future power grid.

[0041] In the method for analyzing the output characteristics of the new energy and ultra-large-scale energy storage combined power station provided in this embodiment, hierarchical clustering analysis is performed on the obtained time-series output data of the combined power station, and a large number of feature data vectors are merged into clusters layer by layer, so that the operation characteristic results and their corresponding weights can be obtained, providing necessary technical support for ensuring the power and energy balance in different time-series periods such as annual, monthly, and day-ahead, and formulating the unit output and start-stop plans, etc., and bringing certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0042] The present invention also provides a system for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station for implementing the above method, including a data processing module 1 for performing standardization processing on the output data of the new energy and energy storage systems in the new energy and ultra-large-scale energy storage combined power station; a feature vector calculation module 2 for extracting feature data vectors from the standardized data and calculating the Euclidean distances between the feature vectors;

[0043] It should be noted that the data processing module 1 includes a data extraction unit 101 and a standardization processing unit 102; the data extraction unit 101 is used to extract the operation data of the combined power station in units of years, and the operation data includes the output of the new energy and the output data of the energy storage system of the new energy and ultra-large-scale energy storage combined power station in a year. The standardization processing unit 102,

[0044] The standardization processing unit is used to normalize the sum of the new energy output data and the energy storage system output data in the new energy and ultra-large-scale energy storage combined power station by using the mean square error formula.

[0045] The feature vector calculation module 2 is used to extract the feature data vector, and the feature data vector is the sum of the new energy output data and the energy storage system output data in the new energy and ultra-large-scale energy storage combined power station after standardization processing.

[0046] The hierarchical clustering analysis module 3 is used to merge the output feature vectors with close distances into one cluster according to the calculation results to generate a new feature data set; calculate the distances between clusters, merge the clusters with close distances, update the feature data set and repeat; until reaching a root node containing all elements; the hierarchical clustering analysis module 3 includes a feature vector merging module 301 and a cluster merging module 302; the feature vector merging module 301 merges the feature vectors with close Euclidean distances into one cluster according to the Euclidean distances between the feature vectors; the cluster merging module 302 merges the clusters with close distances into a new cluster according to the distances between the clusters calculated by the average linkage method, continues to calculate the distances between the new clusters or the distances between the new clusters and the original clusters and merges them until a root node clustering containing all elements is formed.

[0047] The operation characteristic result output module 4, according to the system tree diagram generated during the clustering process, obtains each output feature data set and its corresponding weight as the output characteristic analysis result.

[0048] In the new energy and ultra-large-scale energy storage combined power station output characteristic analysis system provided in this embodiment, by performing hierarchical clustering analysis on the obtained time series data of the new energy and ultra-large-scale energy storage combined power station and gradually merging a large number of feature data vectors into clusters, the operation characteristic results and their corresponding weights can be obtained to analyze the output characteristics of the new energy and ultra-large-scale energy storage combined power station. At the same time, it provides necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly, and day-ahead, and formulating the unit output and start-stop plans, and brings certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0049] The hierarchical clustering method belongs to the unsupervised learning method. Applying the hierarchical clustering method to classify the output data of the new energy and ultra-large-scale energy storage combined power station can obtain the operation characteristic results and their corresponding weights, provide necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly, and day-ahead, and formulating the unit output and start-stop plans, and bring certain guiding significance to the investment in units, energy storage systems, and transmission lines in the power system.

[0050] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can 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.) that contain computer-usable program code.

[0051] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0052] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0053] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0054] As is known by common technical knowledge, the present invention can be implemented by other embodiments that do not depart from its spiritual essence or essential features. Therefore, the above-disclosed embodiments are illustrative in all aspects and not exclusive. All changes within the scope of the present invention or within the scope equivalent to the present invention are encompassed by the present invention.

Claims

1. Analysis method for output characteristics of new energy and ultra-large-scale energy storage combined power station, characterized in that, Including: Obtain the output data of new energy and energy storage system in the combined power station of new energy and ultra-large-scale energy storage, and perform standardization processing; Extract the output feature vectors from the standardized data. The output feature vector is the sum of the output data of new energy and the output data of the energy storage system in the combined power station of new energy and ultra-large-scale energy storage after standardization processing, and calculate the Euclidean distance between each output feature vector; Gradually merge a large number of output feature vectors into clusters, and merge the output feature vectors with close Euclidean distances into one cluster; Use the average linkage method to calculate the distances between clusters, merge the clusters with close distances to form new clusters, continue to calculate the distances between new clusters or the distances between new clusters and original clusters and merge them until reaching a root node clustering that contains all elements; Generate a dendrogram of the output feature data set according to the relationships of each data node during the clustering process; According to the dendrogram, obtain each output feature data set and its corresponding weight as the output characteristic analysis result, providing necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly and day-ahead, and formulating the unit output and start-stop plan; 2. The method for analyzing the output characteristics of the new energy and ultra-large-scale energy storage combined power station according to claim 1, wherein When obtaining the output data, extract the output data of new energy and the output data of the energy storage system in the combined power station of new energy and ultra-large-scale energy storage on an annual basis.

3. The method for analyzing the output characteristics of a new energy and ultra-large-scale energy storage combined power station according to claim 1, characterized in that, The standardization processing includes Sum the output data of new energy and the output data of the energy storage system in the combined power station of new energy and ultra-large-scale energy storage on an annual basis, and normalize the sum using the mean square deviation formula.

4. Analysis system for output characteristics of new energy and ultra-large-scale energy storage combined power station, characterized in that Including A data processing module for extracting the output data of new energy and the energy storage system in the combined power station of new energy and ultra-large-scale energy storage and performing standardization processing; A feature vector calculation module for extracting output feature vectors from the standardized data. The output feature vector is the sum of the output data of new energy and the output data of the energy storage system in the combined power station of new energy and ultra-large-scale energy storage after standardization processing, and calculating the Euclidean distance between each output feature vector; A hierarchical clustering analysis module for gradually merging a large number of output feature vectors into clusters, merging the output feature vectors with close distances into one cluster according to the calculated Euclidean distance; using the average linkage method to calculate the distances between clusters, merging the clusters with close distances to form new clusters, continuing to calculate the distances between new clusters or the distances between new clusters and original clusters and merging them until reaching a root node clustering that contains all elements; An operating characteristic result output module for generating a dendrogram of the output feature data set according to the clustering process, and obtaining each output feature data set and its corresponding weight as the output characteristic analysis result according to the dendrogram; providing necessary technical support for ensuring the power and electricity balance in different time series periods such as annual, monthly and day-ahead, and formulating the unit output and start-stop plan; The hierarchical clustering analysis module includes an output feature vector merging module and a cluster merging module; The output feature vector merging module merges the feature vectors with close Euclidean distances into one cluster according to the Euclidean distance between each feature vector; The cluster merging module merges clusters with close distances into a new cluster according to the average connection distance between clusters, continues to calculate the distances between the new clusters or the distances between the new clusters and the original clusters and merges them until a root node clustering containing all elements is formed.

5. The output characteristic analysis system for a new energy and ultra-large-scale energy storage combined power station according to claim 4, characterized in that, The data processing module includes a data extraction unit and a normalization processing unit; the data extraction unit is used to extract the output data of new energy and the energy storage system of the new energy and ultra-large-scale energy storage combined power station on an annual basis.

6. The analysis system for the output characteristics of the new energy and ultra-large-scale energy storage combined power station according to claim 5, characterized in that The normalization processing unit is used to perform normalization processing on the sum of the output data of new energy and the output data of the energy storage system in the extracted new energy and ultra-large-scale energy storage combined power station by using the mean square deviation formula.

7. The output characteristic analysis system of the new energy and ultra-large scale energy storage combined power station according to claim 6, wherein The feature vector calculation module is used to extract the output feature vector, and the output feature vector is the sum of the output data of new energy and the output data of the energy storage system in the new energy and ultra-large-scale energy storage combined power station after normalization processing.

Images