Construction method, system and equipment for load characteristics of electric bicycle and storage medium

Abstract

The invention discloses an electric bicycle load characteristic construction method, system and device and a storage medium, and belongs to the field of electric bicycle charging management, and the method comprises the following steps: obtaining baseline electric energy data when an electric bicycle is not charged in a home, and actual household consumption data when the electric bicycle is charged in the home; when the electric bicycle is charged at an outdoor charging pile, acquiring output electric energy data of the charging pile and rechargeable battery state data of the electric bicycle; loading the output electric energy data of the charging pile as disturbance to the baseline electric energy data, and generating virtual household electric energy consumption data; fusing the virtual household electric energy consumption data with the actual household consumption data to generate household consumption data to be processed; extracting power grid side charging load characteristics; performing clustering analysis on the state data of the rechargeable battery based on a hierarchical clustering model, and extracting load characteristics of the rechargeable battery; and carrying out feature fusion on the power grid side charging load feature and the rechargeable battery load feature, and constructing a comprehensive load feature of the electric bicycle.

Description

Technical Field

[0001] The invention belongs to the field of electric bicycle charging management and relates to a method, system, device and storage medium for constructing load characteristics of an electric bicycle. Background Art

[0002] With the enhancement of environmental awareness and the development of urban transportation, electric bicycles have become a convenient and environmentally friendly means of short-distance travel. According to statistics, the number of electric bicycles has continued to grow rapidly and has become one of the important choices for residents' daily travel.

[0003] The charging behavior of electric bicycles has a significant impact on the load characteristics of the power grid. On the one hand, the charging time and charging power of electric bicycles are random and dispersed. When a large number of electric bicycles are charged together, it may cause excessive load on the local power grid, affecting the stability and reliability of the power grid. On the other hand, there are various ways to charge electric bicycles, including charging at charging piles and charging at home. Different charging methods have different effects on the power grid. Therefore, accurately constructing the load characteristics of electric bicycles is of great significance for rationally planning the power grid, optimizing the allocation of power resources, and improving the operating efficiency of the power grid.

[0004] At present, the research on the load characteristics of electric bicycles mainly focuses on a single charging scenario or simple load analysis. For example, some studies only consider the load conditions of electric bicycles when charging at outdoor charging piles, while ignoring the impact of home charging on household electricity load; other studies do not fully consider the impact of the state of the electric bicycle charging battery on the load characteristics. In addition, most of the existing load feature extraction methods are based on simple statistical analysis or traditional clustering algorithms, which are difficult to accurately capture the complex load characteristics of electric bicycles.

[0005] In actual applications, due to the lack of accurate load characteristics of electric bicycles, it is difficult for power grid operators to effectively guide and manage the charging behavior of electric bicycles, resulting in large fluctuations in power grid load and increasing the cost and risk of power grid operation. At the same time, for electric bicycle users, they cannot get more reasonable charging suggestions, which affects the user experience and battery life of electric bicycles. Summary of the invention

[0006] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a method, system, device and storage medium for constructing load characteristics of electric bicycles, which improves the accuracy and reliability of load characteristic extraction of electric bicycles and is conducive to the implementation of subsequent applications.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions: A method for constructing load characteristics of an electric bicycle includes the following steps: Obtain the baseline power data of the electric bicycle when it is not charged at home, and the actual household consumption data when it is charged at home; When the electric bicycle is charged at an outdoor charging pile, obtain the output power data of the charging pile and the charging battery status data of the electric bicycle; Load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; Fuse the virtual household power consumption data with the actual household consumption data to generate the to-be-processed household consumption data; Perform clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side; Perform clustering analysis on the charging battery status data based on a hierarchical clustering model to extract the charging battery load characteristics; Perform feature fusion on the charging load characteristics on the grid side and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0008] Preferably, the specific process of performing clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side is as follows: Initialize the number of clusters, define the fuzzy membership matrix and the cluster center matrix; Iteratively calculate the fuzzy membership of the to-be-processed household consumption data at each time point, and update the cluster center; When the iteration stop condition is met, output the cluster center as the charging load characteristics on the grid side.

[0009] Preferably, the specific process of performing clustering analysis on the charging battery status data based on a hierarchical clustering model to extract the charging battery load characteristics is as follows: Preprocess the charging battery status data; Use the agglomerative hierarchical clustering algorithm to cluster each independent sample in the charging battery status data, and then extract the charging battery load characteristics.

[0010] Preferably, the specific process of using the agglomerative hierarchical clustering algorithm to cluster each independent sample in the charging battery status data is as follows: Consider each independent sample in the charging battery status data as a separate cluster. In each iteration, calculate the distance between all clusters, and merge the two closest clusters into a new cluster. Repeat the iterative merging process until the stop condition is met.

[0011] Preferably, the process of extracting the charging battery load characteristics is as follows: Judge the distribution and characteristics of the charging battery status data in different clusters, extract representative characteristics from each cluster, and explain the behavior patterns and performance of the charging battery under different load conditions based on the clustering results and the extracted characteristics.

[0012] Preferably, the specific process of fusing the grid-side charging load characteristics and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle is as follows: concatenate the grid-side charging load characteristics and the charging battery load characteristics into a feature matrix; calculate the covariance matrix of the feature matrix, and construct a principal component space based on the covariance matrix; project the concatenated feature matrix onto the principal component space to generate the fused comprehensive load characteristics.

[0013] Preferably, when constructing the principal component space, first perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues and corresponding eigenvectors, select the corresponding eigenvectors according to the magnitudes of the eigenvalues, and construct the principal component space using the principal components corresponding to the selected eigenvectors.

[0014] A system for constructing the load characteristics of an electric bicycle includes: An electricity consumption data acquisition module, configured to acquire the baseline power data when the electric bicycle is charging without being connected to the household grid, and the actual household consumption data when it is charging while connected to the household grid; A charging data acquisition module, configured to acquire the output power data of the charging pile and the charging battery state data of the electric bicycle when the electric bicycle is charging at an outdoor charging pile; A virtual household power consumption data module, configured to load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; A to-be-processed household consumption data module, configured to fuse the virtual household power consumption data with the actual household consumption data to generate to-be-processed household consumption data; A grid-side charging load characteristic extraction module, configured to perform clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the grid-side charging load characteristics; A charging battery load characteristic extraction module, configured to perform clustering analysis on the charging battery state data based on a hierarchical clustering model to extract the charging battery load characteristics; A comprehensive load characteristic construction module, configured to fuse the grid-side charging load characteristics and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0015] A computer device includes 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 constructing the load characteristics of the electric bicycle are implemented.

[0016] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for constructing the load characteristics of the electric bicycle are implemented.

[0017] Compared with the prior art, the present invention has the following beneficial effects: Based on a set fuzzy clustering model, the present invention performs clustering analysis on the household consumption data to be processed to extract the charging load characteristics on the grid side. The fuzzy clustering model can more comprehensively describe the clustering structure of the household consumption data to be processed by assigning a fuzzy membership degree belonging to each cluster to each data point, including those data points that may be on the edge of multiple clusters, which helps to more accurately capture the charging load characteristics on the grid side. Based on a set hierarchical clustering model, clustering analysis is performed on the charging battery status data to extract the charging battery load characteristics, providing the load characteristics of the charging battery under different conditions. This hierarchical structure helps to understand the change trend and potential problems of the battery performance. Since the fuzzy clustering model and the hierarchical clustering model are optimized for different characteristics of the data respectively, the present invention makes full use of the advantages of these two feature analysis methods to construct a feature fusion strategy, improve the accuracy and reliability of feature extraction, and construct the comprehensive load characteristics of the electric bicycle. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of the method for constructing the load characteristics of the electric bicycle in Embodiment 1 of the present invention; Figure 2 It is a flowchart of the method for constructing the load characteristics of the electric bicycle in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0020] Embodiment 1: As Figure 1 shown, it is the method for constructing the load characteristics of the electric bicycle described in this embodiment, including the following processes: S100, Obtain the baseline power data when the electric bicycle is charged outdoors and the actual household consumption data when it is charged indoors.

[0021] S200, When the electric bicycle is charged at the outdoor charging pile, obtain the output power data of the charging pile and the charging battery status data of the electric bicycle.

[0022] S300, Load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data.

[0023] S400, Fuse the virtual household power consumption data with the actual household consumption data to generate the household consumption data to be processed.

[0024] S500, Based on the fuzzy clustering model, perform clustering analysis on the household consumption data to be processed to extract the charging load characteristics on the grid side; S600, perform clustering analysis on the charging battery status data based on the hierarchical clustering model to extract the charging battery load characteristics.

[0025] S700, perform feature fusion on the grid-side charging load characteristics and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0026] Embodiment 2: As Figure 2 shown, it is the construction method of the electric bicycle load characteristics described in this embodiment. This embodiment introduces the specific implementation manner of the solution in Embodiment 1, including the following steps: S1, based on the edge device, obtain the power consumption data of the smart meter when the electric bicycle is charging outdoors without entering the household and the actual household consumption data of the smart meter when the electric bicycle is charging indoors, and use the power consumption data as the baseline power data.

[0027] S2, when the electric bicycle is charging at the outdoor charging pile, obtain the output power data of the charging pile and the charging battery status data of the electric bicycle.

[0028] S3, use the output power data of the charging pile as a perturbation and load it into the baseline power data to obtain the virtual household power consumption data.

[0029] S4, fuse the virtual household power consumption data and the actual household consumption data to generate the to-be-processed household consumption data.

[0030] S5, based on the set fuzzy clustering model, perform clustering analysis on the to-be-processed household consumption data to extract the grid-side charging load characteristics.

[0031] S6, based on the set hierarchical clustering model, perform clustering analysis on the charging battery status data to extract the charging battery load characteristics.

[0032] S7, fuse the grid-side charging load characteristics and the charging battery load characteristics to construct the load characteristics when the electric bicycle is charging indoors.

[0033] Optionally in this embodiment, based on the set fuzzy clustering model, perform clustering analysis on the to-be-processed household consumption data to extract the grid-side charging load characteristics, including the following steps: Initialization: Determine the number of clusters c (that is, it is considered how many different load patterns exist in the to-be-processed household consumption data).

[0034] Initialize the fuzzy membership matrix U and the cluster center matrix V.

[0035] Iterative calculation: For each data point (the household consumption data to be processed at each time point), calculate its fuzzy membership degree u belonging to each cluster i,j This scheme calculates the distance between the data point and the cluster center and optimizes it according to the objective function of fuzzy C-means

[0036] Update the cluster center vj, which is usually the weighted average result of the data points according to their fuzzy membership degrees

[0037] Repeat the iterative calculation until the stopping condition is met (such as the number of iterations reaches a preset value or the change in the cluster center is less than a certain threshold, etc.)

[0038] Result analysis: Each cluster center represents a load pattern, and the clustering result shows the typical load characteristics of the household consumption data to be processed in different time periods

[0039] The charging load characteristics on the grid side, such as the charging time distribution, power change, etc., can be analyzed according to the clustering result

[0040] Optionally in this embodiment, based on the set hierarchical clustering model, perform clustering analysis on the charging battery state data to extract the charging battery load characteristics, including the following process 1. Data preprocessing Data collection: First, collect the state data of the charging battery under different conditions, such as voltage, current, temperature, and SOC (State of Charge; the state of charge of the battery), etc

[0041] Data cleaning: Remove outliers, missing values, or noisy data to ensure the accuracy and integrity of the charging battery state data

[0042] Feature selection: Select relevant features according to the analysis objective. For example, if the charging performance of the battery is concerned, voltage, current, and SOC are important features

[0043] Data standardization / normalization: To eliminate the dimensional differences between different features, perform standardization or normalization processing on the charging battery state data

[0044] 2. Set the hierarchical clustering model Select the hierarchical clustering algorithm: Common hierarchical clustering algorithms include agglomerative hierarchical clustering (bottom-up) and divisive hierarchical clustering (top-down). In most cases, agglomerative hierarchical clustering is more commonly used

[0045] Determine the distance metric: Select a suitable distance metric method (such as Euclidean distance or Manhattan distance, etc.) to calculate the similarity or distance between data points

[0046] Set stop conditions: Determine the stop conditions for the hierarchical clustering process, such as reaching a preset number of clusters or the distance between clusters exceeding a certain threshold, etc.

[0047] 3. Perform hierarchical clustering Initialization: Consider each data point as a separate cluster.

[0048] Data points refer to independent samples in the preprocessed charging battery status data. These data points are sourced from the collection of charging battery status data under different conditions. In actual operation, data such as voltage, current, temperature, and SOC (State of Charge, the remaining charge of the battery) of the charging battery will be collected. For example, when monitoring a batch of electric bicycle charging batteries, the voltage, current, temperature, and SOC values of each battery are recorded at regular time intervals (such as every 1 minute). Each set of recorded data constitutes a data point. Each data point is a multi-dimensional vector, and the dimension of the vector depends on the number of selected features. If 4 features, namely voltage, current, temperature, and SOC, are determined as the analysis basis in the feature selection stage, then each data point is a four-dimensional vector, such as [voltage value, current value, temperature value, SOC value]. At the start of the hierarchical clustering algorithm, each such data point is regarded as an independent cluster. As the algorithm iterates, the distances between various clusters (initially the individual data points) are calculated, and then the two closest clusters are merged into a new cluster. This process is repeated continuously until the preset stop conditions (such as reaching a preset number of clusters or the distance between clusters exceeding a certain threshold, etc.) are met, thereby completing the clustering analysis of the charging battery status data and finally extracting the charging battery load characteristics.

[0049] Iterative merging: In each iteration, calculate the distances between all clusters (usually the distances between the closest data points or the cluster centers), and merge the two closest clusters into a new cluster.

[0050] Update clusters: Repeat the above steps until the stop conditions are satisfied.

[0051] 4. Extract charging battery load characteristics Analyze the clustering results: Observe the results of hierarchical clustering and judge the distribution and characteristics of the charging battery status data in different clusters.

[0052] Extract features: Extract representative features from each cluster, such as average voltage, maximum current, temperature change range, SOC change rate, etc. These features can reflect the load characteristics of the charging battery under different conditions.

[0053] Explanation feature: Based on the clustering results and the extracted features, explain the behavior patterns and performance of rechargeable batteries under different load conditions.

[0054] Optionally, in this embodiment, the grid-side charging load characteristics and the charging battery load characteristics are fused to construct the load characteristics when an electric bicycle is charged at home, including the following steps: Construct a feature matrix: Concatenate the grid-side charging load characteristics and the charging battery load characteristics into a large feature matrix as the original data. Assume there are m features on the grid side and n features of the charging battery. For p observation points (such as different time periods or charging events), the dimension of the feature matrix will be p×(m + n).

[0055] After the feature matrix is constructed, principal component analysis is performed.

[0056] Calculate the covariance matrix: First, calculate the covariance matrix of the concatenated feature matrix. If the data has been standardized, then calculate the covariance matrix A according to the formula which is equal to the transpose of the data matrix multiplied by the data matrix X divided by the number of observations minus one, that is, p - 1.

[0057] Calculate the eigenvalues and eigenvectors: Perform eigen decomposition on the covariance matrix to obtain the eigenvalues and the corresponding eigenvectors. The eigenvalues represent the importance of each principal component (i.e., the variance contribution rate), and the eigenvectors define the direction of each principal component.

[0058] Select the principal components: Select the first k principal components corresponding to the eigenvectors according to the magnitudes of the eigenvalues, where k is an integer less than or equal to (m + n). The selection criterion can be that the cumulative contribution rate of the eigenvalues reaches a certain threshold (such as 80% or 90%).

[0059] Construct the principal component space: Use the first k principal components corresponding to the selected eigenvectors to construct the principal component space. These eigenvectors serve as the axes of the new coordinate system for projecting the original data into this low-dimensional space.

[0060] Project the data: Project the original data, that is, the concatenated feature matrix, onto the principal component space to obtain the data after dimensionality reduction. This is usually achieved by multiplying the original data by the eigenvector matrix (only containing the selected first k eigenvectors). The data after dimensionality reduction is the fused load characteristics of the electric bicycle.

[0061] In this embodiment, the comprehensive load characteristics of the electric bicycle can be used to optimize the charging strategy of the electric bicycle to reduce the load pressure on the grid; in battery health management, the comprehensive load characteristics of the electric bicycle can be used to predict the remaining life and performance degradation trend of the battery, so as to take maintenance measures in advance.

[0062] Embodiment 3: In this embodiment, a construction system for the load characteristics of an electric bicycle is provided. This construction system for the load characteristics of an electric bicycle can be used to implement the above-mentioned construction method for the load characteristics of an electric bicycle. Specifically, the construction system for the load characteristics of an electric bicycle includes an electricity consumption data acquisition module, a charging data acquisition module, a virtual household power consumption data module, a household consumption data to be processed module, a grid-side charging load characteristic extraction module, a charging battery load characteristic extraction module, and a comprehensive load characteristic construction module.

[0063] Among them, the electricity consumption data acquisition module is used to acquire the baseline power data when the electric bicycle is charged outside the household and the actual household consumption data when it is charged inside the household.

[0064] The charging data acquisition module is used to acquire the output power data of the charging pile and the charging battery state data of the electric bicycle when the electric bicycle is charged at the charging pile outdoors.

[0065] The virtual household power consumption data module is used to load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data.

[0066] The household consumption data to be processed module is used to fuse the virtual household power consumption data with the actual household consumption data to generate the household consumption data to be processed.

[0067] The grid-side charging load characteristic extraction module is used to perform clustering analysis on the household consumption data to be processed based on a fuzzy clustering model to extract the grid-side charging load characteristics.

[0068] The charging battery load characteristic extraction module is used to perform clustering analysis on the charging battery state data based on a hierarchical clustering model to extract the charging battery load characteristics.

[0069] The comprehensive load characteristic construction module is used to perform feature fusion on the grid-side charging load characteristics and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0070] Embodiment 4: In this embodiment, a terminal device is provided. The terminal device includes a processor and a memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used for the operation of the method for constructing the load characteristics of an electric bicycle, including: obtaining the baseline power data when the electric bicycle is charged outdoors and the actual household consumption data when it is charged indoors; when the electric bicycle is charged at a charging pile outdoors, obtaining the output power data of the charging pile and the charging battery state data of the electric bicycle; loading the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; fusing the virtual household power consumption data with the actual household consumption data to generate the to-be-processed household consumption data; performing clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side; performing clustering analysis on the charging battery state data based on a hierarchical clustering model to extract the charging battery load characteristics; and performing feature fusion on the charging load characteristics on the grid side and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0071] Embodiment 5: In this embodiment, a computer-readable storage medium (Memory) is provided. The computer-readable storage medium is a memory device in a terminal device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, in this storage space, one or more instructions suitable for being loaded and executed by a processor are also stored. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, and a read-only memory (ROM, Read-Only Memory).

[0072] One or more instructions stored in the computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the method for constructing the load characteristics of an electric bicycle in the above embodiment; one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps: obtaining the baseline power data when the electric bicycle is charged outdoors and the actual household consumption data when it is charged indoors; when the electric bicycle is charged at a charging pile outdoors, obtaining the output power data of the charging pile and the charging battery state data of the electric bicycle; loading the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; fusing the virtual household power consumption data with the actual household consumption data to generate the to-be-processed household consumption data; performing clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side; performing clustering analysis on the charging battery state data based on a hierarchical clustering model to extract the charging battery load characteristics; and performing feature fusion on the charging load characteristics on the grid side and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

[0073] 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 complete hardware embodiment, a complete 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, optical storage, etc.) containing computer-usable program codes.

[0074] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to 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, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in multiple blocks.

[0075] 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 produce a manufactured article including an instruction means that implements the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in multiple blocks.

[0076] 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 one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or a means for implementing the functions specified in multiple blocks.

[0077] In the above embodiments of the present application, the descriptions of the various embodiments each have their own focuses. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art in the technical field of the present application, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

[0079] It should be understood that the above description is for illustrative purposes and not for limitation. By reading the above description, many embodiments and many applications other than the provided examples will be obvious to those skilled in the art.

Claims

1. A method for constructing the load characteristics of an electric bicycle, characterized in that, It includes the following processes: Obtain the baseline power data when the electric bicycle is charged outdoors and the actual household consumption data when it is charged indoors; When the electric bicycle is charged at an outdoor charging pile, obtain the output power data of the charging pile and the charging battery status data of the electric bicycle; Load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; Fuse the virtual household power consumption data with the actual household consumption data to generate the to-be-processed household consumption data; Perform clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side; Perform clustering analysis on the charging battery status data based on a hierarchical clustering model to extract the charging battery load characteristics; Fuse the charging load characteristics on the grid side and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle.

2. The method for constructing the load characteristics of an electric bicycle according to claim 1, characterized in that, The specific process of performing clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract the charging load characteristics on the grid side is as follows: Initialize the number of clusters, define the fuzzy membership matrix and the cluster center matrix; Iteratively calculate the fuzzy membership of the to-be-processed household consumption data at each time point and update the cluster center; When the iteration stop condition is met, output the cluster center as the charging load characteristics on the grid side.

3. The method for constructing the load characteristics of an electric bicycle according to claim 1, characterized in that, The specific process of performing clustering analysis on the charging battery status data based on a hierarchical clustering model to extract the charging battery load characteristics is as follows: Preprocess the charging battery status data; Use the agglomerative hierarchical clustering algorithm to cluster each independent sample in the charging battery status data, and then extract the charging battery load characteristics.

4. The method for constructing the load characteristics of an electric bicycle according to claim 3, wherein The specific process of using the agglomerative hierarchical clustering algorithm to cluster each independent sample in the charging battery status data is as follows: Consider each independent sample in the charging battery status data as a separate cluster. In each iteration, calculate the distance between all clusters and merge the two closest clusters into a new cluster. Repeat the iterative merging process until the stop condition is met.

5. The method for constructing the load characteristics of an electric bicycle according to claim 3, wherein The process of extracting the charging battery load characteristics is as follows: Judge the distribution and characteristics of the charging battery status data in different clusters, extract representative characteristics from each cluster, and explain the behavior patterns and performance of the charging battery under different load conditions based on the clustering results and the extracted characteristics.

6. The method for constructing the load characteristics of an electric bicycle according to claim 1, characterized in that, The specific process of fusing the charging load characteristics on the grid side and the charging battery load characteristics to construct the comprehensive load characteristics of the electric bicycle is as follows: Concatenate the charging load characteristics on the grid side and the charging battery load characteristics into a feature matrix; Calculate the covariance matrix of the feature matrix and construct the principal component space according to the covariance matrix; Project the concatenated feature matrix into the principal component space to generate the fused comprehensive load characteristics.

7. The method for constructing the load characteristics of an electric bicycle according to claim 6, wherein When constructing the principal component space, first perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalues and the corresponding eigenvectors. Select the corresponding eigenvectors according to the magnitudes of the eigenvalues, and use the principal components corresponding to the selected eigenvectors to construct the principal component space.

8. A construction system for the load characteristics of an electric bicycle, characterized in that, It includes: An electricity data acquisition module, which is used to obtain the baseline power data when the electric bicycle is charged outdoors and the actual household consumption data when it is charged indoors; A charging data acquisition module, which is used to acquire the output power data of the charging pile and the charging battery status data of the electric bicycle when the electric bicycle is charging at an outdoor charging pile; A virtual household power consumption data module, which is used to load the output power data of the charging pile as a perturbation into the baseline power data to generate virtual household power consumption data; A to-be-processed household consumption data module, which is used to fuse the virtual household power consumption data with the actual household consumption data to generate to-be-processed household consumption data; A grid-side charging load feature extraction module, which is used to perform clustering analysis on the to-be-processed household consumption data based on a fuzzy clustering model to extract grid-side charging load features; A charging battery load feature extraction module, which is used to perform clustering analysis on the charging battery status data based on a hierarchical clustering model to extract charging battery load features; A comprehensive load feature construction module, which is used to perform feature fusion on the grid-side charging load features and the charging battery load features to construct the comprehensive load features of the electric bicycle.

9. 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, it implements the steps of the method for constructing the load characteristics of the electric bicycle according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for constructing the load characteristics of the electric bicycle according to any one of claims 1 to 7.

Images