Electric power operation data processing method and system based on heterogeneous data fusion

Abstract

The invention discloses an electric power operation data processing method and system based on heterogeneous data fusion. The method comprises the steps of obtaining a charging behavior of a charging station and historical data of power supply of a power grid; cleaning and filling the two kinds of data in sequence; extracting features of the charging behavior data, and analyzing the features according to a correlation analysis algorithm to obtain a target feature set; screening the charging behavior data according to the target feature set to obtain target charging behavior data; correcting the power grid power supply data according to the power grid terminal execution standard to obtain target power grid power supply data; fusing the two kinds of data based on a decision tree method; using the fused data to train a charging load prediction model; and performing prediction based on the model to obtain a charging load prediction result. The method provided by the invention provides reliable technical support for power grid dispatching and charging station operation.

Description

Technical Field

[0001] The present application relates to the technical field of electric vehicle charging, and in particular to a method and system for processing electric power operation data based on heterogeneous data fusion. Background Art

[0002] With the development of electric vehicle charging technology, the problem of multi-source data is particularly prominent. The charging process involves multiple data types such as vehicle battery status, charging station facility information, power grid power supply status, and user charging behavior. These data come from a wide range of sources and in various formats, making it difficult to obtain accurate charging loads, which in turn brings challenges to the formulation of charging strategies, the improvement of charging efficiency, and the optimization of charging facilities.

[0003] In the prior art, a simple data aggregation method is used to achieve charging load prediction for multi-source heterogeneous data. This method ignores the correlation between data, has poor data fusion effect, and low data accuracy, resulting in low accuracy of the predicted charging load.

[0004] It can be seen that how to improve the prediction accuracy of charging load and then formulate a reasonable charging strategy has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present application provides a method and system for processing electric power operation data based on heterogeneous data fusion to improve the accuracy of charging load prediction, achieve the effect of accurately predicting charging load and formulating reasonable charging strategies.

[0006] In order to solve the above technical problems, the embodiment of the present application provides a method for processing power operation data based on heterogeneous data fusion, including:

[0007] The acquired charging behavior history data and grid power supply behavior history data of the target charging station are cleaned and filled in turn to obtain first charging behavior data and first grid power supply data respectively;

[0008] Analyze the user features, time series features, and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data;

[0009] The first charging behavior data is screened based on the target feature set to obtain target charging behavior data; the first power grid power supply data is corrected according to a predetermined power grid terminal execution standard to obtain target power grid power supply data;

[0010] Based on the decision tree method, the target charging behavior data and the target power grid power supply data are integrated to obtain a target sample set;

[0011] Training the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model;

[0012] In the actual charging load prediction process, prediction is performed based on the target charging load prediction model to obtain a charging load prediction result.

[0013] As one of the preferred solutions, the user characteristics, time series characteristics and charging mode characteristics are analyzed in sequence according to the correlation analysis algorithm to obtain a target feature set matching the first charging behavior data, including:

[0014] Calculate the correlation coefficients between the user characteristics, time series characteristics, charging mode characteristics and the first charging behavior data respectively based on the Pearson correlation analysis algorithm;

[0015] The correlation coefficients are screened based on a preset correlation threshold, and the target feature set is constructed based on the screening results.

[0016] As one of the preferred solutions, the grid terminal implementation standard includes a power factor standard;

[0017] The correcting the first power grid power supply data according to the predetermined power grid terminal execution standard to obtain the target power grid power supply data includes:

[0018] Comparing and analyzing the active power output and reactive power output in the extracted historical data of the power supply behavior of the power grid, and determining the target power factor according to the analysis results;

[0019] constructing the power factor standard with the target power factor;

[0020] A current power factor is extracted from the first power grid power supply data, and the current power factor is corrected based on the power factor standard to obtain the corrected target power grid power supply data.

[0021] As one of the preferred solutions, the charging load prediction model constructed based on the target sample set is trained to obtain a target charging load prediction model, including:

[0022] Construct an initial charging load prediction model based on long short-term memory network;

[0023] Expanding the target sample set according to a resampling method to obtain an expanded data set;

[0024] The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain a target charging load prediction model.

[0025] As one preferred solution, after obtaining the target charging load prediction model, the method further includes:

[0026] The target charging load prediction model is verified based on a pre-selected verification data set, and the target charging load prediction model is optimized based on the verification result.

[0027] Another embodiment of the present application provides a power operation data processing system based on heterogeneous data fusion, which is characterized by comprising:

[0028] An acquisition module, used to clean and fill the acquired charging behavior history data and grid power supply behavior history data of the target charging station in turn, to obtain first charging behavior data and first grid power supply data respectively;

[0029] an analysis module, configured to analyze the user features, time series features, and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data;

[0030] an extraction module, configured to screen the first charging behavior data based on the target feature set to obtain target charging behavior data; and to correct the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data;

[0031] A fusion module, used for fusing the target charging behavior data and the target power grid power supply data based on a decision tree method to obtain a target sample set;

[0032] A training module, used to train the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model;

[0033] The prediction module is used to perform prediction based on the target charging load prediction model in the actual charging load prediction process to obtain a charging load prediction result.

[0034] As one preferred solution, the analysis module is specifically used for:

[0035] Calculate the correlation coefficients between the user characteristics, time series characteristics, charging mode characteristics and the first charging behavior data respectively based on the Pearson correlation analysis algorithm;

[0036] The correlation coefficients are screened based on a preset correlation threshold, and the target feature set is constructed based on the screening results.

[0037] As one of the preferred solutions, the grid terminal implementation standard includes a power factor standard;

[0038] The extraction module is specifically used for:

[0039] Comparing and analyzing the active power output and reactive power output in the extracted historical data of the power supply behavior of the power grid, and determining the target power factor according to the analysis results;

[0040] constructing the power factor standard with the target power factor;

[0041] A current power factor is extracted from the first power grid power supply data, and the current power factor is corrected based on the power factor standard to obtain the corrected target power grid power supply data.

[0042] As one preferred solution, the prediction module is specifically used for:

[0043] Construct an initial charging load prediction model based on long short-term memory network;

[0044] Expanding the target sample set according to a resampling method to obtain an expanded data set;

[0045] The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain a target charging load prediction model.

[0046] As one preferred solution, the prediction module is further used for:

[0047] The target charging load prediction model is verified based on a pre-selected verification data set, and the target charging load prediction model is optimized based on the verification result.

[0048] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0049] (1) Through correlation analysis, this application can screen out key features that have an important impact on charging load prediction, thereby improving the prediction accuracy and efficiency of the model.

[0050] (2) This application uses the decision tree method to fully utilize the complementarity between the two heterogeneous data and improve the overall quality and predictive value of the data. At the same time, the intuitiveness and interpretability of the decision tree method also make the fusion process clearer and easier to understand.

[0051] (3) The model obtained through training in this application can accurately reflect the changing pattern of charging load and provide reliable prediction support for the operation and dispatch of the power system. At the same time, the prediction results of the model can also provide important reference for the operation optimization of charging stations and the improvement of user experience.

[0052] (4) The charging load prediction method based on heterogeneous data fusion proposed in this application realizes accurate prediction and efficient management of charging load. This method not only improves the accuracy and stability of the prediction, but also provides strong support for the optimized operation of the power system and the operational optimization of charging stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flowchart of a method for processing electric power operation data based on heterogeneous data fusion in one embodiment of the present application;

[0054] Figure 2 It is a module diagram of an electric power operation data processing system based on heterogeneous data fusion in one of the embodiments of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0057] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0058] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0059] The present application embodiment provides a method for processing power operation data based on heterogeneous data fusion. For details, please refer to Figure 1 , Figure 1 The flowchart of the method for processing power operation data based on heterogeneous data fusion in one embodiment of the present application is shown, including steps S1 to S6:

[0060] S1: Cleaning and filling the acquired charging behavior history data and grid power supply behavior history data of the target charging station in turn to obtain first charging behavior data and first grid power supply data respectively;

[0061] In one embodiment of the present application, the first charging behavior data mainly reflects the charging activities of electric vehicle users at charging stations, specifically including:

[0062] User information: such as user ID, user type (such as private user, operational user, etc.), user vehicle information (such as model, battery capacity, etc.).

[0063] Charging time information: including charging start time, charging end time, charging duration, etc. These data help to understand the user's charging habits, charging time distribution, etc.

[0064] Charging capacity information: such as the amount of power charged each time, the remaining power before charging, the power after charging, etc. These data reflect the user's charging needs and charging efficiency.

[0065] Charging station information: such as charging station ID, charging station location, charging pile type (such as AC charging pile, DC charging pile), etc.

[0066] Charging cost information: such as the cost of each charge, charging unit price, etc.

[0067] The first power grid power supply data mainly reflects the power supply situation and stability of the power grid, including:

[0068] Grid load information: such as real-time grid load, load peak, load fluctuation, etc. These data help to understand the power supply capacity and stability of the grid.

[0069] Power supply quality information: such as voltage stability, frequency stability, power factor, etc. These data reflect the power supply quality of the power grid.

[0070] Grid fault information: such as grid fault type, fault time, fault impact range, etc. These data are of great significance for evaluating the reliability and safety of the grid.

[0071] Electricity price information: such as electricity prices at different times, peak and valley price differences, etc. These data reflect the price mechanism of the electricity market and the electricity costs of users.

[0072] Among them, data cleaning is preferably performed by methods such as outlier processing, duplicate data deletion, data consistency processing and data normalization, and data filling is preferably performed by methods such as mean filling, median filling, interpolation, multiple interpolation, K nearest neighbor filling and regression prediction filling, which are not specifically limited in the embodiments of the present application.

[0073] S2: analyzing the user features, time series features, and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data;

[0074] Preferably, in one embodiment of the present application, the user characteristics, time series characteristics and charging mode characteristics are analyzed in sequence according to the correlation analysis algorithm to obtain a target feature set matching the first charging behavior data, including:

[0075] Based on the Pearson correlation analysis algorithm, the correlation coefficients between the user characteristics, the time series characteristics, the charging mode characteristics and the first charging behavior data are calculated respectively;

[0076] Each correlation coefficient is screened based on a pre-set correlation threshold, and the target feature set is constructed based on the screening results.

[0077] The Pearson correlation analysis algorithm is a statistical method used to measure the degree of linear correlation between two continuous variables. In one embodiment of the present application, calculating the correlation coefficient based on the Pearson correlation analysis algorithm includes:

[0078] Extract user feature data sets, such as user type, vehicle type, charging frequency, etc. For each user feature, use the Pearson correlation analysis algorithm to calculate the correlation coefficient between it and the first charging behavior data (such as charging amount, charging times, etc.).

[0079] Extract time series feature data sets, such as daily charging capacity change trends, weekly or monthly charging capacity fluctuations, etc. For each time series feature, the Pearson correlation analysis algorithm is also used to calculate the correlation coefficient between it and the first charging behavior data.

[0080] Extract the charging mode feature data set, such as the charging start and end time, charging speed, charging power, etc. For each charging mode feature, use the Pearson correlation analysis algorithm to calculate the correlation coefficient between it and the first charging behavior data.

[0081] Furthermore, a reasonable correlation threshold is set according to business requirements and data characteristics. Usually, this threshold can be determined based on experience or business requirements, such as selecting 0.3, 0.5 or 0.7 as the threshold. According to the set correlation threshold, user features, time series features and charging mode features whose correlation coefficient with the first charging behavior data is greater than or equal to the threshold are screened out. These screened features constitute the target feature set.

[0082] S3: Screening the first charging behavior data based on the target feature set to obtain target charging behavior data; correcting the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data;

[0083] The target feature set obtained from step S2 accurately reflects the key elements of charging behavior, such as user type, charging period, charging amount, etc. In one embodiment of the present application, the first charging behavior data is targeted and screened using the target feature set. The specific operation is to select records that match the target feature set from the original data set. For example, if the target feature set emphasizes the charging behavior of a specific user type (such as a private user) during a specific period (such as at night), the charging records that meet these conditions are screened out. The screened data is verified to ensure its accuracy, completeness, and consistency. This includes checking whether the data format, data type, data range, etc. meet expectations, and correcting any possible errors, which are not specifically limited in the embodiments of the present application.

[0084] Preferably, in one embodiment of the present application, the grid terminal execution standard includes a power factor standard;

[0085] Correcting the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data includes:

[0086] Compare and analyze the active power output and reactive power output in the extracted historical data of power grid power supply behavior, and determine the target power factor based on the analysis results;

[0087] Constructing power factor standards with target power factors;

[0088] A current power factor is extracted from the first power grid power supply data, and the current power factor is corrected based on a power factor standard to obtain corrected target power grid power supply data.

[0089] It should be noted that in the power system, the implementation standards of power grid terminals are crucial to ensure the stable operation and efficient power supply of the power grid. Among them, the power factor standard is a key implementation standard, which reflects the proportional relationship between active power and apparent power in the power grid and is an important indicator to measure the degree of effective utilization of electricity.

[0090] In this step, a comparative analysis of active power and reactive power is performed to understand the changes in the power factor of the power grid in different time periods and under different load conditions. According to the results of the comparative analysis, combined with the actual operation of the power grid and business needs, a reasonable target power factor is determined. Generally, the target power factor should be higher than or equal to the value specified in the national standard to ensure the efficient operation of the power grid. For general industrial and commercial electricity, the power factor of power grids with a rated voltage of 1000V and below should be above 0.9 and not less than 0.8; for power grids with a rated voltage exceeding 1000V, the power factor should be above 0.95 and not less than 0.9.

[0091] The current power factor data is extracted from the first power grid power supply data. This can be obtained in real time through a power grid monitoring system or a data acquisition system. The extracted current power factor is compared with the constructed power factor standard. If the current power factor is lower than the specified value in the standard, correction is required.

[0092] The correction method may include adjusting the load distribution of the power grid, adding reactive compensation equipment (such as capacitor banks, static VAR compensators, etc.) to improve the power factor, which is not limited here. During the correction process, the changes in the power factor should be monitored in real time to ensure that the corrected power factor meets the standard requirements.

[0093] S4: Based on the decision tree method, the target charging behavior data and the target power grid power supply data are integrated to obtain a target sample set;

[0094] Among them, the decision tree algorithm is a commonly used classification and regression method, which mainly classifies or predicts data through a series of questions (i.e., feature selection and division). Its model structure is similar to the shape of a tree, where each node of the tree represents a test on a feature, each branch represents a test result, and the leaf node of the tree represents a category or output value.

[0095] It is understandable that the most important feature is first selected as the root node, which should be able to best divide the data set. For example, if this application needs to obtain the impact of charging behavior on the power grid in different time periods, then time can be used as a root node feature.

[0096] According to the feature value of the root node, the data set is divided into different subsets. For each subset, a new feature is recursively selected as the division criterion for the child node until the stopping condition is met (such as the number of samples in the node is less than a certain threshold, or the purity improvement after division is no longer significant). The leaf node represents the final decision result or category. In the scenario of fused data, the leaf node can represent a specific combination of charging behavior and grid power supply status.

[0097] In this step, starting from the root node, the decision tree is traversed according to the feature values ​​of the target charging behavior data and the target grid power supply data. Each time a leaf node is reached, a sample is generated. This sample contains the values ​​of all the features from the root node to the leaf node. All the generated samples are combined to form a target sample set. This set contains the fused charging behavior and grid power supply data.

[0098] S5: training the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model;

[0099] Preferably, in one embodiment of the present application, the constructed charging load prediction model is trained based on the target sample set to obtain the target charging load prediction model, including:

[0100] Construct an initial charging load prediction model based on long short-term memory network;

[0101] Expand the target sample set according to the resampling method to obtain an expanded data set;

[0102] The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain the target charging load prediction model.

[0103] In this step, use a deep learning framework (such as TensorFlow, PyTorch, etc.) to build an LSTM network. Set the network's input layer, LSTM layer (which can contain multiple stacked LSTM units), fully connected layer, and output layer. Select appropriate activation functions (such as ReLU, Sigmoid, etc.) and loss functions (such as MSE, MAE, etc.).

[0104] Among them, a suitable resampling method is selected according to the distribution and characteristics of the data, such as random oversampling, random undersampling, SMOTE (synthetic minority class oversampling technology), etc., which is not limited here. In one embodiment of the present application, statistical indicators (such as category distribution, data volume, etc.) and visualization methods (such as scatter plots, histograms, etc.) are used to evaluate whether the resampled data set meets the requirements.

[0105] Specifically, the expanded data set is used to train the initial LSTM charging load prediction model. Among them, the Bayesian optimization algorithm is selected as the hyperparameter tuning method. Bayesian optimization approximates the objective function (the loss function of the model in this embodiment) by constructing a probabilistic model, and uses this model to select the next hyperparameter combination to be evaluated. The optimal hyperparameter combination is selected from the Bayesian optimization process, and the LSTM model is retrained using this combination.

[0106] Preferably, in one embodiment of the present application, the method further comprises:

[0107] Based on a pre-selected validation data set, the target charging load prediction model is validated, and based on the validation results, the target charging load prediction model is optimized.

[0108] Specifically, the trained model is evaluated, including the performance on the test set, the stability and interpretability of the model, etc. If it meets the requirements, it is deployed and used as the target charging load prediction model.

[0109] S6: In the actual charging load prediction process, prediction is performed based on the target charging load prediction model to obtain a charging load prediction result.

[0110] In this step, data related to charging load forecasting is collected in real time or regularly from relevant data sources (e.g., charging station monitoring system, power grid dispatching system, etc.). The prepared input data is input into the target charging load forecasting model for forecasting calculation. The model will output the corresponding charging load forecasting results based on the characteristics of the input data.

[0111] Obtain prediction results from the model. These results include the predicted value of charging load in the future, the confidence interval of the predicted value, etc. In one embodiment of the present application, the prediction results can be visualized, such as drawing a prediction curve graph, so as to understand the prediction results more intuitively.

[0112] Specifically, the prediction results can be applied to the operation and management of charging stations, such as formulating charging plans and optimizing the resource allocation of charging stations; or the prediction results can be provided to the grid dispatching department to help them better understand the future charging load demand and formulate a more reasonable grid dispatching plan. Or the prediction results can be used as the basis for policy formulation and planning, such as formulating electric vehicle charging infrastructure construction plans and optimizing charging policies.

[0113] Another embodiment of the present application provides a power operation data processing system for heterogeneous data fusion. For details, see Figure 2 , Figure 2 The module schematic diagram of the power operation data processing system for heterogeneous data fusion in one embodiment of the present application is shown, including:

[0114] An acquisition module 11 is used to clean and fill the acquired charging behavior history data and grid power supply behavior history data of the target charging station in turn, and obtain first charging behavior data and first grid power supply data respectively;

[0115] An analysis module 12 is used to analyze the user features, time series features and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data;

[0116] The extraction module 13 is used to screen the first charging behavior data based on the target feature set to obtain target charging behavior data; and to correct the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data;

[0117] A fusion module 14 is used to fuse the target charging behavior data and the target power grid power supply data based on a decision tree method to obtain a target sample set;

[0118] A training module 15 is used to train the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model;

[0119] The prediction module 16 is used to perform prediction based on the target charging load prediction model in the actual charging load prediction process to obtain a charging load prediction result.

[0120] Preferably, in one embodiment of the present application, the analysis module is specifically used for:

[0121] Based on the Pearson correlation analysis algorithm, the correlation coefficients between the user characteristics, the time series characteristics, the charging mode characteristics and the first charging behavior data are calculated respectively;

[0122] Each correlation coefficient is screened based on a pre-set correlation threshold, and the target feature set is constructed based on the screening results.

[0123] Preferably, in one embodiment of the present application, the grid terminal execution standard includes a power factor standard;

[0124] Extraction module, specifically used for:

[0125] Compare and analyze the active power output and reactive power output in the extracted historical data of power grid power supply behavior, and determine the target power factor based on the analysis results;

[0126] Constructing power factor standards with target power factors;

[0127] A current power factor is extracted from the first power grid power supply data, and the current power factor is corrected based on a power factor standard to obtain corrected target power grid power supply data.

[0128] Preferably, in one embodiment of the present application, the prediction module is specifically used for:

[0129] Construct an initial charging load prediction model based on long short-term memory network;

[0130] Expand the target sample set according to the resampling method to obtain an expanded data set;

[0131] The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain the target charging load prediction model.

[0132] Preferably, in one embodiment of the present application, the prediction module is further used for:

[0133] Based on a pre-selected validation data set, the target charging load prediction model is validated, and based on the validation results, the target charging load prediction model is optimized.

[0134] The method and system for processing electric power operation data by fusion of heterogeneous data provided in the embodiments of the present application have the beneficial effects of at least one of the following:

[0135] (1) Through correlation analysis, this application can screen out key features that have an important impact on charging load prediction, thereby improving the prediction accuracy and efficiency of the model.

[0136] (2) This application uses the decision tree method to fully utilize the complementarity between the two heterogeneous data and improve the overall quality and predictive value of the data. At the same time, the intuitiveness and interpretability of the decision tree method also make the fusion process clearer and easier to understand.

[0137] (3) The model obtained through training in this application can accurately reflect the changing pattern of charging load and provide reliable prediction support for the operation and dispatch of the power system. At the same time, the prediction results of the model can also provide important reference for the operation optimization of charging stations and the improvement of user experience.

[0138] (4) The charging load prediction method based on heterogeneous data fusion proposed in this application realizes accurate prediction and efficient management of charging load. This method not only improves the accuracy and stability of the prediction, but also provides strong support for the optimized operation of the power system and the operational optimization of charging stations.

[0139] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing power operation data based on heterogeneous data fusion, characterized in that: include: The acquired charging behavior history data and grid power supply behavior history data of the target charging station are cleaned and filled in turn to obtain first charging behavior data and first grid power supply data respectively; Analyze the user features, time series features, and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data; Filtering the first charging behavior data based on the target feature set to obtain target charging behavior data; Correcting the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data; Based on the decision tree method, the target charging behavior data and the target power grid power supply data are integrated to obtain a target sample set; Training the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model; In the actual charging load prediction process, prediction is performed based on the target charging load prediction model to obtain a charging load prediction result.

2. The method for processing electric power operation data based on heterogeneous data fusion according to claim 1, characterized in that: The user characteristics, time series characteristics and charging mode characteristics are analyzed in sequence according to the correlation analysis algorithm to obtain a target feature set matching the first charging behavior data, including: Calculate the correlation coefficients between the user characteristics, time series characteristics, charging mode characteristics and the first charging behavior data respectively based on the Pearson correlation analysis algorithm; The correlation coefficients are screened based on a preset correlation threshold, and the target feature set is constructed based on the screening results.

3. The method for processing electric power operation data based on heterogeneous data fusion according to claim 1, characterized in that: The grid terminal implementation standards include power factor standards; The correcting the first power grid power supply data according to the predetermined power grid terminal execution standard to obtain the target power grid power supply data includes: Comparing and analyzing the active power output and reactive power output in the extracted historical data of the power supply behavior of the power grid, and determining the target power factor according to the analysis results; constructing the power factor standard with the target power factor; The current power factor in the first power grid power supply data is extracted, and the current power factor is corrected based on the power factor standard to obtain the corrected target power grid power supply data.

4. The method for processing electric power operation data based on heterogeneous data fusion according to claim 1, characterized in that: The charging load prediction model constructed based on the target sample set is trained to obtain a target charging load prediction model, including: Construct an initial charging load prediction model based on long short-term memory network; Expanding the target sample set according to a resampling method to obtain an expanded data set; The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain a target charging load prediction model.

5. The method for processing electric power operation data based on heterogeneous data fusion according to claim 4, characterized in that: After obtaining the target charging load prediction model, the method further includes: The target charging load prediction model is verified based on a pre-selected verification data set, and the target charging load prediction model is optimized based on the verification result.

6. A power operation data processing system based on heterogeneous data fusion, characterized in that: include: An acquisition module, used to clean and fill the acquired charging behavior history data and grid power supply behavior history data of the target charging station in turn, to obtain first charging behavior data and first grid power supply data respectively; an analysis module, configured to analyze the user features, time series features, and charging mode features extracted from the first charging behavior data according to a correlation analysis algorithm to obtain a target feature set that matches the first charging behavior data; an extraction module, configured to filter the first charging behavior data based on the target feature set to obtain target charging behavior data; Correcting the first power grid power supply data according to a predetermined power grid terminal execution standard to obtain target power grid power supply data; A fusion module, used for fusing the target charging behavior data and the target power grid power supply data based on a decision tree method to obtain a target sample set; A training module, used to train the constructed charging load prediction model based on the target sample set to obtain a target charging load prediction model; The prediction module is used to perform prediction based on the target charging load prediction model in the actual charging load prediction process to obtain a charging load prediction result.

7. The electric power operation data processing system based on heterogeneous data fusion according to claim 6, characterized in that: The analysis module is specifically used for: Calculate the correlation coefficients between the user characteristics, time series characteristics, charging mode characteristics and the first charging behavior data respectively based on the Pearson correlation analysis algorithm; The correlation coefficients are screened based on a preset correlation threshold, and the target feature set is constructed based on the screening results.

8. The electric power operation data processing system based on heterogeneous data fusion according to claim 6, characterized in that: The grid terminal implementation standards include power factor standards; The extraction module is specifically used for: Comparing and analyzing the active power output and reactive power output in the extracted historical data of the power supply behavior of the power grid, and determining the target power factor according to the analysis results; constructing the power factor standard with the target power factor; The current power factor in the first power grid power supply data is extracted, and the current power factor is corrected based on the power factor standard to obtain the corrected target power grid power supply data.

9. The electric power operation data processing system based on heterogeneous data fusion according to claim 6, characterized in that: The prediction module is specifically used for: Construct an initial charging load prediction model based on long short-term memory network; Expanding the target sample set according to a resampling method to obtain an expanded data set; The initial charging load prediction model is trained based on the expanded data set and the Bayesian optimization algorithm to obtain a target charging load prediction model.

10. The electric power operation data processing system based on heterogeneous data fusion according to claim 9, characterized in that: The prediction module is further used for: The target charging load prediction model is verified based on a pre-selected verification data set, and the target charging load prediction model is optimized based on the verification result.

Images