Electric vehicle charging station load power prediction method and device based on ICEEMDAN-TimesNet

Abstract

The invention relates to the field of electric vehicle charging station load power prediction, and discloses an electric vehicle charging station load power prediction method and device based on ICEEMDAN-TimesNet, and the method comprises the steps: obtaining historical charging station load power data and characteristic variables; the method comprises the following steps: decomposing historical charging station load power data by adopting an ICEEMDAN decomposition algorithm, and extracting intrinsic mode functions and residual errors on different time scales; determining input data of the TimesNet model based on the intrinsic mode function, the residual error and the characteristic variable; and extracting the time sequence change representation of the input data by using the TimesNet model, and predicting the future charging station load power based on the time sequence change representation. The method integrates the advantages of time sequence analysis and deep learning, has stronger nonlinear modeling capability and time sequence feature extraction capability, can better describe the complex time dynamic characteristics of charging load data, has lower parameter dependence and stronger generalization capability, can improve the prediction accuracy, and has good application prospects. The modeling capability of large-scale data is enhanced, and real-time and efficient load prediction is realized.

Description

Technical Field

[0001] The present application relates to the field of load power prediction of electric vehicle charging stations, and specifically to a method and device for predicting load power of electric vehicle charging stations based on ICEEMDAN-TimesNet. Background Art

[0002] With the rapid development of electric vehicles, the construction of charging infrastructure is becoming increasingly important. Accurately predicting the power load of charging stations is of great significance for the rational planning of charging infrastructure, improving the efficiency of power grid dispatching, and reducing the construction and operation costs of charging infrastructure. On the one hand, it can help charging station operators to reasonably arrange the allocation of charging resources and optimize the daily operation and management of power stations; on the other hand, it also provides an important dispatching reference for the upper power grid, helps to balance the power grid load and ensure the stability and safety of the power grid. The load power of electric vehicle charging stations is affected by many factors, including but not limited to the random charging demand of electric vehicles, time period changes, user behavior patterns, weather conditions, etc. These factors make the time series data of load power highly nonlinear, dynamic and random, which brings great challenges to the accurate prediction of charging station load power.

[0003] There are three main methods for predicting the load power of electric vehicle charging stations: prediction methods based on statistical models, prediction methods based on physical models, and prediction methods based on machine learning. Prediction methods based on statistical models usually use statistical models such as time series analysis and Markov chain to predict charging loads, but they cannot fully capture complex electricity consumption behavior patterns and nonlinear characteristics. Since electric vehicle charging behavior is affected by many factors and has significant seasonality, periodicity, and randomness, prediction methods based on statistical models are difficult to accurately describe these complex characteristics, and the prediction accuracy is low.

[0004] The physical model-based method mainly refers to building a physical law model that describes the operation of charging stations, such as vehicle driving behavior, battery characteristics, charging facility characteristics, etc., and then combining Monte Carlo simulation and other technologies to predict load. This method usually requires a large amount of charging station operating parameters and environmental data as input, but this information is difficult to fully obtain in practical applications. The modeling process is complex and the calculation complexity is high, making it difficult to meet the real-time requirements of power grid dispatching.

[0005] The machine learning-based method refers to the use of historical charging data and related features, and the application of machine learning algorithms such as linear regression, decision trees, support vector machines, and neural networks to perform charging load forecasting modeling. Although it can capture nonlinear characteristics to a certain extent, it cannot fully explore the complex patterns and long-term and short-term dependencies in time series data. Electric vehicle charging behavior has significant time series characteristics, and the time series modeling capabilities of traditional machine learning models are limited, resulting in prediction accuracy that cannot meet requirements; at the same time, the model's computational complexity and real-time defects are also important reasons that hinder its application in actual power grid dispatching.

[0006] Based on the above, the existing charging station load power forecasting methods are difficult to capture these nonlinear factors well, and cannot fully explore the complex patterns and long-term and short-term dependencies in time series data, which affects the prediction accuracy. Summary of the invention

[0007] The present application provides an electric vehicle charging station load power prediction method based on ICEEMDAN-TimesNet to solve the problem in the prior art that the existing charging station load power prediction method is difficult to capture these nonlinear factors well, cannot fully explore the complex patterns and long-term and short-term dependencies in time series data, and affects the prediction accuracy.

[0008] Correspondingly, the present application also provides an electric vehicle charging station load power prediction device based on ICEEMDAN-TimesNet, an electronic device, and a computer-readable storage medium to ensure the implementation and application of the above method.

[0009] In order to solve the above technical problems, the present application discloses a method for predicting load power of electric vehicle charging stations based on ICEEMDAN-TimesNet, the method comprising:

[0010] Obtain historical charging station load power data and characteristic variables;

[0011] The ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data to extract the intrinsic mode functions and residuals on different time scales;

[0012] Determine the input data of the TimesNet model based on the intrinsic mode function, residual and characteristic variables;

[0013] The TimesNet model is used to extract the temporal variation representation of the input data, and the future load power of the charging station is predicted based on the temporal variation representation.

[0014] The present application also discloses a load power prediction device for an electric vehicle charging station based on ICEEMDAN-TimesNet, the device comprising:

[0015] A data acquisition module is used to obtain historical charging station load power data and characteristic variables;

[0016] The data processing module is used to decompose the historical charging station load power data using the ICEEMDAN decomposition algorithm to extract the intrinsic mode functions and residuals on different time scales;

[0017] The data processing module is also used to determine the input data of the TimesNet model based on the intrinsic mode function, residual and characteristic variables;

[0018] The prediction output module is used to extract the time series variation representation of the input data using the TimesNet model, and predict the future load power of the charging station based on the time series variation representation.

[0019] The present application also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, one or more methods described in the present application are implemented.

[0020] The present application also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, one or more methods described in the present application are implemented.

[0021] In this application, the historical charging station load power data and characteristic variables are obtained, and the ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data into multiple intrinsic mode functions. The input data of the TimesNet model is determined based on the intrinsic mode functions, residuals and characteristic variables, which can provide richer and more effective feature inputs for time series prediction modeling in the TimesNet model, which helps to improve the accuracy and robustness of the prediction. The TimesNet model is used to extract the temporal variation representation of the input data, and the future charging station load power is predicted based on the temporal variation representation, which can better capture complex nonlinear patterns and long-term and short-term dependencies. Based on the above, the embodiment of the present application combines the advantages of time series analysis and deep learning, has stronger nonlinear modeling capabilities and time series feature extraction capabilities, can better characterize the complex time dynamic characteristics of charging load data, and also has lower parameter dependence and stronger generalization capabilities, can improve prediction accuracy, enhance the modeling capabilities of large-scale data, and realize real-time and efficient load forecasting, providing more valuable support for power system management.

[0022] Additional aspects and advantages of the present application will be given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flow chart of a method for predicting load power of an electric vehicle charging station based on ICEEMDAN-TimesNet provided in an embodiment of the present application;

[0025] Figure 2 TimesNet framework diagram provided for the embodiment of the present application;

[0026] Figure 3 A flow chart of the electric vehicle charging station prediction model training provided in an embodiment of the present application;

[0027] Figure 4 A schematic diagram of the structure of an electric vehicle charging station load power prediction device based on ICEEMDAN-TimesNet provided in an embodiment of the present application;

[0028] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0030] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0031] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the field to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0032] The solution provided in the embodiments of the present application can be executed by any electronic device, such as a terminal device or a server, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this. With regard to the technical problems existing in the prior art, the electric vehicle charging station load power prediction method and device based on ICEEMDAN-TimesNet provided in this application is intended to solve at least one of the technical problems of the prior art.

[0033] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0034] The present application embodiment provides a possible implementation method, such as Figure 1 As shown, a flowchart of an electric vehicle charging station load power prediction method based on ICEEMDAN-TimesNet is provided. The scheme can be executed by any electronic device, and optionally, can be executed on a server or terminal device.

[0035] like Figure 1 As shown in , the method may include the following steps:

[0036] Step 101, obtaining historical charging station load power data and characteristic variables, wherein the characteristic variables include meteorological data and charging facility data.

[0037] The historical load power data of electric vehicle charging stations usually includes a series of power values ​​measured in time sequence, which represent the power load borne by the charging station at different time points. Since these data have obvious time attributes and change over time, they are typical time series data. Analyzing and predicting these time series data can help charging station operators and power grid dispatchers better understand the load change rules, conduct resource planning and power grid optimization management.

[0038] Step 102: Decompose the historical charging station load power data using the ICEEMDAN decomposition algorithm to extract intrinsic mode functions and residuals on different time scales.

[0039] The Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) algorithm improves the classic Empirical Mode Decomposition (EMD) algorithm and can decompose the complex time series signals of historical charging station load power data into multiple intrinsic mode functions (IMFs) on different time scales.

[0040] Step 103, determining the input data of the TimesNet model based on the intrinsic mode function, the residual and the characteristic variable;

[0041] Step 104: Use the TimesNet model to extract the time series variation representation of the input data, and predict the future charging station load power based on the time series variation representation.

[0042] In the embodiment of the present application, the intrinsic mode function, residual and characteristic data obtained by decomposing the historical charging station load power data are used as input, and the charging station load power at the future moment is used as output, and multiple groups of such input-output pairs are constructed and divided into training set, validation set and test set. The TimesNet model is trained by the training set, the validation set monitors the generalization ability of the TimesNet model, and the test set is used to test the prediction ability of the TimesNet model.

[0043] In the embodiment of the present application, the historical charging station load power data and characteristic variables are obtained, and the ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data into multiple intrinsic mode functions. The input data of the TimesNet model is determined based on the intrinsic mode functions, residuals and characteristic variables, which can provide richer and more effective feature inputs for time series prediction modeling in the TimesNet model, which helps to improve the accuracy and robustness of the prediction. The TimesNet model is used to extract the temporal variation representation of the input data, and the future charging station load power is predicted based on the temporal variation representation, which can better capture complex nonlinear patterns and long-term and short-term dependencies. Based on the above, the embodiment of the present application combines the advantages of time series analysis and deep learning, has stronger nonlinear modeling capabilities and temporal feature extraction capabilities, can better characterize the complex time dynamic characteristics of charging load data, and also has lower parameter dependence and stronger generalization capabilities, can improve prediction accuracy, enhance the modeling capabilities of large-scale data, and realize real-time and efficient load forecasting, providing more valuable support for power system management.

[0044] In an optional embodiment, obtaining historical charging station load power data and characteristic variables includes:

[0045] Collect basic forecast data, including historical charging station operation data, meteorological data and charging facility data;

[0046] The prediction basic data is preprocessed and the preprocessed data is divided into historical charging station load power data and characteristic variables; the preprocessing methods include outlier cleaning, noise data cleaning and missing value filling.

[0047] The problem of load power prediction of electric vehicle charging stations in the embodiment of the present application requires combining historical charging station load power data, meteorological data and charging facility data to predict the load power in the future. First, auxiliary data such as historical charging station operation data, meteorological data and charging facility data need to be collected. Then the collected data is preprocessed, including cleaning of outliers and noise data and filling missing values ​​with interpolation operations. The preprocessed data is then divided into historical charging station load power data and characteristic variables.

[0048] In an optional embodiment, the ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data to extract the intrinsic mode functions and residuals on different time scales, including:

[0049] Based on envelope mean calculation and adaptive noise, empirical mode decomposition is performed on the historical charging station load power data to obtain multiple intrinsic mode functions, and the residual component obtained from the last decomposition is used as the final residual.

[0050] ICEEMDAN is an improved algorithm based on EMD (Empirical Mode Decomposition), which is mainly used to process nonlinear and non-stationary signals. The algorithm introduces envelope mean calculation and adaptive noise to solve the problem of modal aliasing, thereby improving the accuracy and efficiency of decomposition. The specific method of using ICEEMDAN to process historical charging station load power data in the embodiment of this application is as follows:

[0051] In the embodiment of the present application, the historical charging station load power data is represented by x={x k ,k=1,2,...,L} means, let E k (w( i )) is the kth IMF component obtained by EMD decomposition after adding the i-th Gaussian noise, w( i )(i=1,2,...I) is the i-th noise added.

[0052] Add E to the original charging station load power sequence k (w( i ))Generate a new sequence:

[0053]

[0054] Among them, β 0 represents the specified signal-to-noise ratio, and std(·) is the calculation of the standard deviation.

[0055] Calculate x( i ) and take its mean as the first residual component R 1 :

[0056]

[0057] Among them, M(x( i )) is the local mean of the i-th decomposition signal, and M(·) is the local mean operator.

[0058] Then the first intrinsic mode function (IMF) is calculated:

[0059] IMF 1 =xR 1 (3)

[0060] By analogy, the remaining intrinsic mode functions are IMFs k =R k-1 -R k , where k is greater than 1. The kth residual is:

[0061]

[0062] Until the calculation and decomposition are completed, all intrinsic mode functions and residuals are obtained. The original historical charging station load power data x can be expressed as the sum of multiple IMFs and the residuals obtained from the last decomposition, as shown below:

[0063]

[0064] Among them, R m is the final residual, and m is the number of IMFs.

[0065] In an optional embodiment, the input data of the TimesNet model is determined based on the intrinsic mode function, the residual and the characteristic variable, including:

[0066] Normalizing the intrinsic mode functions, residuals, and feature variables to obtain the input data of the TimesNet model can ensure that feature data of different dimensions are in the same range, which is conducive to the convergence of model training.

[0067] In an optional embodiment, the TimesNet model is used to extract the time series variation representation of the input data, and the future charging station load power is predicted based on the time series variation representation, including:

[0068] The encoder of the TimesNet model is used to extract the temporal features of the input data; the encoder of the TimesNet model is composed of multiple TimesBlocks stacked together, and multi-scale temporal convolution and attention mechanisms are used to capture temporal patterns to extract high-level temporal dependency features of the input data.

[0069] The decoder of the TimesNet model is used to predict the time series features and obtain the intrinsic mode functions of each future time step;

[0070] The inherent mode functions of each future time step are superimposed to obtain the future charging station load power.

[0071] The TimesNet model is a deep learning model for time series analysis. It effectively captures intra-cycle and inter-cycle changes by converting one-dimensional time series data into a two-dimensional representation. The core idea of ​​the TimesNet model is to convert complex time series data into a two-dimensional space for processing while retaining its periodic characteristics. Figure 2As shown in the figure, the TimesNet model is composed of multiple TimesBlocks stacked together. First, data is input, and after the input data is standardized, it is passed through the embedding layer to obtain deep features. In the embedding layer, data encoding is performed to obtain deep features. The data encoding includes numerical encoding, time encoding, and position encoding. Then, a series of TimesBlocks are used to model two-dimensional changes. Specifically, the deep features are sequentially converted from the FFT time domain to the frequency domain, converted into two-dimensional tensors, and extracted through convolution. These features are then integrated through adaptive aggregation, and the final features are obtained through model stacking. Finally, the data of the length to be predicted is output through the fully connected layer.

[0072] In an optional embodiment, the encoder of the TimesNet model is used to extract the temporal features of the input data, including:

[0073] Extract the period of the input data and convert the input data into a two-dimensional tensor to express the two-dimensional time series changes:

[0074]

[0075] Where, FFT(·) represents Fast Fourier Transform (FFT), Amp(·) represents the calculation of amplitude; X 1D represents input data, which is a one-dimensional time series feature; A represents X 1D The amplitude of each frequency component in, Avg(·) represents its average value. 1 ,…,f k} represents the frequency of the first k amplitudes, which also corresponds to the k period lengths {p 1 ,…,p k}. Padding(·) means adding 0 to the end of the sequence so that the sequence length T can be p i divisible, Indicates folding the original one-dimensional data according to the selected period.

[0076] The two-dimensional time series variation representation is extracted based on the two-dimensional tensor. Specifically, for the two-dimensional tensor Due to its two-dimensional locality, in order to use 2D convolution to extract information, the classic Inception model was selected, namely:

[0077]

[0078] Convert the two-dimensional time series representation back to one-dimensional space to obtain a one-dimensional time series representation:

[0079]

[0080] Wherein, Trunc(·) means removing the 0 added by the Padding(·) operation in equation (6);

[0081] The intensity of the corresponding frequency of the one-dimensional time series representation is weighted and summed to obtain the time series feature:

[0082]

[0083] In an optional embodiment, the decoder of the TimesNet model is used to predict the time series features to obtain the intrinsic mode functions of each future time step, including:

[0084] Multi-layer time-aware units are used to predict time series features and obtain the intrinsic mode functions of each future time step.

[0085] The decoder of the TimesNet model consists of multiple TimesBlocks, each of which contains multiple time-aware units, which can effectively model the dynamic changes in time series. The decoder of TimesNet receives time series features from the encoder, which contain multi-scale time dependencies in the input data. The decoder uses these time series features to perform step-by-step prediction and restoration through a series of TimesBlock modules. By connecting multiple TimesBlock modules in series, the decoder can gradually predict the intrinsic mode functions of each future time step. Among them, for each intrinsic mode function obtained by ICEEMDAN decomposing the historical charging station load power data, the TimesNet model will generate a corresponding prediction result.

[0086] Based on the above, the present application embodiment provides a flow chart of electric vehicle charging station prediction model training. Figure 3As shown, first obtain the historical charging station operation data and meteorological data, and perform data preprocessing. Specifically, the methods of outlier cleaning, noise data cleaning, and missing value filling can be used to preprocess the historical charging station operation data and meteorological data. After that, the preprocessed data is divided into characteristic variables such as historical charging station load data and meteorological data. In the embodiment of the present application, after the historical charging station load data is decomposed by ICEEMDAN to obtain multiple intrinsic mode functions, it is merged with characteristic variables such as meteorological data into a new data set and normalized, wherein the normalization process can ensure that the characteristic data of different dimensions are in the same range, which is conducive to the convergence of model training. After that, the normalized data set is divided into a training set, a validation set, and a test set, wherein the training set is used to train the TimesNet model, the validation set monitors the generalization ability of the TimesNet model, and the test set is used to test the prediction ability of the TimesNet model. Specifically, the training set is used as the input of the TimesNet model for model training, and the training results are evaluated based on the validation set to determine whether the training results meet expectations. If the training results do not meet expectations, the hyperparameters of the TimesNet model are optimized and the model is retrained; if the training results meet expectations, the prediction results of the test set are output and the result error analysis is performed. The prediction results are the intrinsic mode functions of each future time step. Finally, the prediction results are aggregated, that is, the multiple intrinsic mode functions obtained by the prediction are superimposed to obtain the future charging station load power.

[0087] The method in the embodiment of the present application can be extended to similar electric vehicle charging station load power prediction problems with complex time dependence, nonlinear dynamic characteristics, data quality issues, and other similar prediction problems.

[0088] Based on the same principle as the method provided in the embodiment of the present application, the embodiment of the present application also provides an electric vehicle charging station load power prediction device based on ICEEMDAN-TimesNet, such as Figure 4 As shown, the device comprises:

[0089] Data acquisition module 401, used to obtain historical charging station load power data and characteristic variables;

[0090] The data processing module 402 is used to decompose the historical charging station load power data using the ICEEMDAN decomposition algorithm to extract the intrinsic mode functions and residuals on different time scales;

[0091] The data processing module 402 is further used to determine the input data of the TimesNet model based on the intrinsic mode function, the residual and the characteristic variable;

[0092] The prediction output module 403 is used to extract the time series variation representation of the input data using the TimesNet model, and predict the future charging station load power based on the time series variation representation.

[0093] In the embodiment of the present application, the historical charging station load power data and characteristic variables are obtained, and the ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data into multiple intrinsic mode functions. The input data of the TimesNet model is determined based on the intrinsic mode functions, residuals and characteristic variables, which can provide richer and more effective feature inputs for time series prediction modeling in the TimesNet model, which helps to improve the accuracy and robustness of the prediction. The TimesNet model is used to extract the temporal variation representation of the input data, and the future charging station load power is predicted based on the temporal variation representation, which can better capture complex nonlinear patterns and long-term and short-term dependencies. Based on the above, the embodiment of the present application combines the advantages of time series analysis and deep learning, has stronger nonlinear modeling capabilities and temporal feature extraction capabilities, can better characterize the complex time dynamic characteristics of charging load data, and also has lower parameter dependence and stronger generalization capabilities, can improve prediction accuracy, enhance the modeling capabilities of large-scale data, and realize real-time and efficient load forecasting, providing more valuable support for power system management.

[0094] The electric vehicle charging station load power prediction device based on ICEEMDAN-TimesNet provided in the embodiment of the present application can achieve Figures 1 to 3 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0095] The ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction device of the embodiment of the present application can execute the ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction method provided in the embodiment of the present application, and its implementation principle is similar. The actions performed by each module and unit in the ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction device in each embodiment of the present application correspond to the steps in the ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction method in each embodiment of the present application. For the detailed functional description of each module of the ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction device, please refer to the corresponding description of the ICEEMDAN-TimesNet-based electric vehicle charging station load power prediction method shown in the previous text, which will not be repeated here.

[0096] Based on the same principle as the method shown in the embodiment of the present application, the embodiment of the present application also provides an electronic device, which may include but is not limited to: a processor and a memory; a memory for storing a computer program; a processor for executing the electric vehicle charging station load power prediction method based on ICEEMDAN-TimesNet shown in any optional embodiment of the present application by calling a computer program. Compared with the prior art, the electric vehicle charging station load power prediction method based on ICEEMDAN-TimesNet provided in the present application combines the advantages of time series analysis and deep learning, has stronger nonlinear modeling capabilities and time series feature extraction capabilities, can better characterize the complex time dynamic characteristics of charging load data, and also has lower parameter dependence and stronger generalization capabilities, can improve prediction accuracy, enhance the modeling capabilities of large-scale data, and realize real-time and efficient load prediction, providing more valuable support for power system management.

[0097] In an optional embodiment, an electronic device is also provided, such as Figure 5 As shown, Figure 5 The electronic device 500 shown may be a server, including: a processor 501 and a memory 503. The processor 501 and the memory 503 are connected, such as through a bus 502. Optionally, the electronic device 500 may further include a transceiver 504. It should be noted that in actual applications, the transceiver 504 is not limited to one, and the structure of the electronic device 500 does not constitute a limitation on the embodiments of the present application.

[0098] Processor 501 may be a CPU (Central Processing Unit), a general purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. Processor 501 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0099] The bus 502 may include a path to transmit information between the above components. The bus 502 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 502 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0100] The memory 503 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0101] The memory 503 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the application code stored in the memory 503 to implement the contents shown in the above method embodiment.

[0102] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0103] The server provided in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected by wired or wireless communication, and this application does not limit this.

[0104] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0105] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0106] It should be noted that the computer-readable storage medium mentioned above in the present application can also be a computer-readable signal medium or a combination of a computer-readable storage medium and a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0107] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0108] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0109] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method and device for predicting the load power of an electric vehicle charging station based on ICEEMDAN-TimesNet provided in the above-mentioned various optional implementations.

[0110] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the data acquisition module can also be described as a "data acquisition module for acquiring historical charging station load power data and characteristic variables".

[0113] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for predicting load power of electric vehicle charging stations based on ICEEMDAN-TimesNet, characterized in that: The method comprises: Obtain historical charging station load power data and characteristic variables; The ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data to extract intrinsic mode functions and residuals on different time scales; Determining input data of a TimesNet model based on the intrinsic mode function, the residual and the characteristic variable; The TimesNet model is used to extract the time series variation representation of the input data, and the future charging station load power is predicted based on the time series variation representation.

2. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 1, characterized in that: The ICEEMDAN decomposition algorithm is used to decompose the historical charging station load power data to extract intrinsic mode functions and residuals on different time scales, including: Based on envelope mean calculation and adaptive noise, empirical mode decomposition is performed on the historical charging station load power data to obtain multiple intrinsic mode functions, and the residual component obtained by the last decomposition is used as the final residual.

3. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 1, characterized in that: Determining the input data of the TimesNet model based on the intrinsic mode function, the residual and the characteristic variable includes: The intrinsic mode function, the residual and the characteristic variable are normalized to obtain input data of the TimesNet model.

4. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 1, characterized in that: The extracting the time series variation representation of the input data by using the TimesNet model, and predicting the future charging station load power based on the time series variation representation, includes: Extracting the temporal features of the input data using the encoder of the TimesNet model; Using the decoder of the TimesNet model to predict the time series features, obtaining the intrinsic mode function of each future time step; The inherent mode functions of each future time step are superimposed to obtain the future charging station load power.

5. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 4, characterized in that: The extracting the time series features of the input data using the encoder of the TimesNet model includes: Extracting a period from the input data, and converting the input data into a two-dimensional tensor to express a two-dimensional time series change; Extracting a two-dimensional temporal variation representation based on the two-dimensional tensor; Converting the two-dimensional time series representation back to one-dimensional space to obtain a one-dimensional time series representation; The intensity of the frequency corresponding to the one-dimensional time series representation is weighted and summed to obtain the time series feature.

6. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 1, characterized in that: The obtaining of historical charging station load power data and characteristic variables includes: Collecting forecast basic data, the forecast basic data including historical charging station operation data, meteorological data and charging facility data; The prediction basic data is preprocessed, and the preprocessed data is divided into the historical charging station load power data and characteristic variables; the preprocessing method includes outlier cleaning, noise data cleaning and missing value filling.

7. The method for predicting electric vehicle charging station load power based on ICEEMDAN-TimesNet according to claim 1, characterized in that: The method of using the decoder of the TimesNet model to predict the time series features to obtain the intrinsic mode functions of each future time step includes: The time series features are predicted using a multi-layer time perception unit to obtain the intrinsic mode functions of each future time step.

8. An electric vehicle charging station load power prediction device based on ICEEMDAN-TimesNet, characterized in that: The device comprises: A data acquisition module is used to obtain historical charging station load power data and characteristic variables; A data processing module, used to decompose the historical charging station load power data using an ICEEMDAN decomposition algorithm to extract intrinsic mode functions and residuals on different time scales; The data processing module is further used to determine the input data of the TimesNet model based on the intrinsic mode function, the residual and the characteristic variable; The prediction output module is used to extract the time series variation representation of the input data using the TimesNet model, and predict the future charging station load power based on the time series variation representation.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images