Processing method for predicting transformer area load based on electric vehicle data

Abstract

The embodiment of the invention relates to a processing method for predicting court load based on electric vehicle data. The method comprises the following steps: carrying out all-weather data acquisition on all electric vehicles running in a first court power supply area to obtain a first vehicle data set; all-weather data acquisition is carried out on various electrical loads of the first transformer area to obtain a first transformer area data set; constructing a transformer area load prediction model; constructing a model training data set based on the first vehicle / transformer area data set to train a transformer area load prediction model; and after the model training is finished, predicting various electrical loads of the first transformer area in the future first prediction time period by using the transformer area load prediction model according to the collected data in the first vehicle data set in the latest first sampling time period. According to the invention, the technical problem of how to predict various electrical loads in a transformer area based on the electric vehicle data is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a processing method for predicting area load based on electric vehicle data. Background Art

[0002] The management model of the smart grid hopes to dynamically regulate the power supply of the distribution station area. The premise is that it should be able to predict various types of power loads in the distribution station area (such as the power load generated by the photovoltaic power station in the area, the power load consumed by the energy storage implementation in the area, the power load consumed by the charging piles in the area, and the power load generated by the daily life of residents and industrial and commercial facilities in the area). Through data collection, it is found that for the distribution station area with electric vehicle (referred to as electric vehicle) charging piles in the power supply area, there is a correlation between the various types of power load data in the area and the electric vehicle data in the area (referred to as electric vehicle data). From this, it can be inferred that it is possible to predict the corresponding types of power loads based on the collected electric vehicle data. How to predict various types of power loads in the area based on electric vehicle data is also the technical problem that the present invention needs to solve. Summary of the invention

[0003] The purpose of the present invention is to provide a processing method for predicting substation load based on electric vehicle data in response to the defects of the prior art. The present invention collects data of all electric vehicles traveling in the power supply area of ​​the substation around the clock to obtain a vehicle data set, and collects data of various types of power loads in the substation around the clock to obtain a substation data set; and constructs a substation load prediction model for predicting multiple types of power loads in the substation according to the vehicle embedded coding tensor input by the model; and constructs a model training data set based on the vehicle / substation data set to train the substation load prediction model; and after the model training is completed, the substation load prediction model is used to predict various types of power loads in the substation in the future specified time period according to the collected data in the vehicle data set within the most recent specified time period. The present invention solves the technical problem of how to predict various types of power loads in the substation based on electric vehicle data.

[0004] To achieve the above object, an embodiment of the present invention provides a method for predicting load of a distribution area based on electric vehicle data, the method comprising:

[0005] The power supply area of ​​the first area is recorded as the corresponding first area; all electric vehicles traveling in the first area are collected around the clock to obtain a corresponding first vehicle data set; and all types of power loads in the first area are collected around the clock to obtain a corresponding first area data set;

[0006] Constructing a load prediction model for an area; the load prediction model for an area is used to perform area power load prediction processing according to the vehicle embedded coding tensor input by the model and output a corresponding load prediction tensor for the area; the load prediction tensor for the area at least includes a photovoltaic power station load prediction vector, an energy storage load prediction vector, a tram charging load prediction vector and a daily power load prediction vector;

[0007] Set the data sampling duration to the first sampling duration L S ; and set the prediction interval length to the first interval length L A ; and set the predicted duration to the first predicted duration L P ; and based on the first vehicle data set, the first station data set, the first sampling time L S , the first interval length L A and the first prediction duration L P The model training data set is recorded as a first data set; and the load forecasting model of the substation is trained based on the first data set;

[0008] After the model training is completed, the load prediction model of the substation is used according to the first sampling time L most recently in the first vehicle data set. S The collected data within and the first prediction time L P Predict various types of power loads in the first prediction period in the future of the first substation; the interval between the start time of the first prediction period and the current time is the first interval time L A The length of the first prediction period is the first prediction duration L P .

[0009] Preferably, the first vehicle data set includes multiple first vehicle data records; the first vehicle data record includes a first collection period, a first vehicle identification, a first location type, a first vehicle type, a first parking state, a first starting travel state, a first navigation mode, a first charging mode, and a first charging power; the first collection period includes a first period start time and a first period end time, and the period length between the first period start time and the first period end time is fixedly recorded as a first period length △L1; the first vehicle identification is a unique identification of the corresponding electric vehicle; the first location type is used to mark the location type of the corresponding electric vehicle in the current period, and the first location type includes commercial places, residential areas, and roads; the first vehicle type includes private cars and operating vehicle; the first parking state is used to mark the parking state of the corresponding electric vehicle in the current time period, and the first parking state includes yes and no; the first starting travel state is used to mark whether the corresponding electric vehicle is in the starting time period of travel in the current time period, and the first starting travel state includes yes and no; the first navigation mode is used to mark the navigation mode adopted by the corresponding electric vehicle in the current time period, and the first navigation mode includes the shortest driving path navigation mode and the shortest driving time navigation mode; the first charging mode is used to mark whether the corresponding electric vehicle is in the charging state in the current time period and the corresponding charging mode, and the first charging mode includes uncharged, regular charging and fast charging; the first charging power is the total charging power of the corresponding electric vehicle in the current time period, and the first charging mode is 0 when the first charging mode is uncharged;

[0010] The first area data set includes multiple first area data records; the first area data record includes the second collection period, the first power grid power distribution, the first photovoltaic power generation load, the first energy storage load, the first tram charging load, and the first daily power load; the second collection period includes the second period start time and the second period end time, and the period length between the second period start time and the second period end time is fixedly recorded as the second period length △L2; the first power grid power distribution is the total power grid-side power distribution of the first area in the current second collection period; the first photovoltaic power generation load is the total power load generated by all photovoltaic power stations in the first area in the current second collection period; the first energy storage load is the total power load consumed by all energy storage implementations in the first area in the current second collection period; the first tram charging load is the total power load consumed by all charging piles in the first area in the current second collection period; the first daily power load is the total power load of daily residents and industrial and commercial facilities generated in the first area in the current second collection period;

[0011] The first sampling time L S is an integer multiple of the first time period length △L1; the first prediction time length L P is an integer multiple of the length of the second time period ΔL2;

[0012] The first data set includes multiple first data records; the first data record includes a first vehicle embedding coding tensor and a first power load label tensor; the first vehicle embedding coding tensor is composed of multiple first vehicle embedding coding vectors; each of the first vehicle embedding coding vectors corresponds to an electric vehicle; the vector lengths of all the first vehicle embedding coding vectors are equal to the vector length M1, M1=L S / △L1; the first vehicle embedded coding vector is composed of M1 first time period coding groups arranged in chronological order; each first time period coding group corresponds to a first vehicle data record; the first time period coding group includes a venue type code, a vehicle type code, a parking state code, a starting travel state code, a navigation mode code, a charging mode code, and a charging power code; the first power load label tensor includes a first power generation load label vector, a first energy storage load label vector, a first charging load label vector, and a first daily load label vector, and the vector lengths of the four label vectors are equal to the vector length M2, M2=L P / △L2; the first power generation load label vector is formed by sequentially sorting M2 first power generation load label quantities; the first energy storage load label vector is formed by sequentially sorting M2 first energy storage load label quantities; the first charging load label vector is formed by sequentially sorting M2 first charging load label quantities; the first daily load label vector is formed by sequentially sorting M2 first daily load label quantities.

[0013] Preferably, the substation load forecasting model includes a feature extraction network and a regression prediction network; the substation load forecasting model has at least two model implementation modes, one based on the Transformer model and the other based on the Bi-LSTM model; when the substation load forecasting model is implemented based on the Transformer model, the feature extraction network and the regression prediction network are implemented based on the encoder and decoder of the Transformer model respectively; when the substation load forecasting model is implemented based on the Bi-LSTM model, the feature extraction network is implemented by connecting the CNN network with the linear layer, and the regression prediction network is implemented by connecting the Bi-LSTM model with the MLP network;

[0014] The feature extraction network is used to receive the vehicle embedded coding tensor input by the model, and perform electric vehicle power consumption feature extraction processing on the vehicle embedded coding tensor to obtain the corresponding electric vehicle power consumption feature tensor and send it to the regression prediction network; the regression prediction network is used to perform multi-class power load prediction processing based on the electric vehicle power consumption feature tensor to obtain the corresponding station load prediction tensor and output it.

[0015] Preferably, the first vehicle data set, the first station area data set, and the first sampling time L S , the first interval length L A and the first prediction duration L P The model training data set is recorded as the first data set, which specifically includes:

[0016] Step 41: according to the first sampling time L S Sequentially segmenting the first vehicle data set to obtain a corresponding plurality of first segmented data sets;

[0017] Each of the first segmented data sets is composed of a plurality of the first vehicle data records; and the time span of each of the first segmented data sets is the first sampling time length L S ;

[0018] Step 42, taking the first of the first segmented data sets as the corresponding current segmented data set;

[0019] Step 43: taking the segment end time of the current segment data set as the corresponding current end time; and summing the current end time with the first interval time L A Add the time obtained as the corresponding current predicted start time; and add the current predicted start time to the first predicted duration L P The time obtained by adding them is used as the corresponding current prediction end time; and the current prediction start time and the current prediction end time form the corresponding current prediction period;

[0020] Step 44, extract all the first area data records in the first area data set whose second collection period and the current prediction period have a time intersection to form a corresponding current area data record set; extract the M2 first photovoltaic power generation load total amounts that are earlier in time in the current area data record set as the corresponding M2 first power generation load label amounts and sort them in chronological order to form a corresponding first power generation load label vector; extract the M2 first energy storage load total amounts that are earlier in time in the current area data record set as the corresponding M2 first energy storage load label amounts and sort them in chronological order to form a corresponding first energy storage load label vector; and The M2 first tram charging load totals that are earlier in time of the current area data record set are extracted as the corresponding M2 first charging load label quantities and are sorted in chronological order to form a corresponding first charging load label vector; and the M2 first daily power load totals that are earlier in time of the current area data record set are extracted as the corresponding M2 first daily load label quantities and are sorted in chronological order to form a corresponding first daily load label vector; and the obtained first power generation load label vector, the first energy storage load label vector, the first charging load label vector and the first daily load label vector form a corresponding first power load label tensor;

[0021] Step 45, grouping the first vehicle data records with the same first vehicle identifier in the current segmented data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding first record sequence;

[0022] Step 46, taking each of the first record sequences as the corresponding current record sequence; and setting a corresponding first vehicle embedded coding vector as the corresponding current coding vector for the current record sequence according to the vector data format of the first vehicle embedded coding vector; and initializing the coding values ​​of all the codings of all the first time point coding groups of the current coding vector to 0; and establishing a corresponding relationship between each of the first vehicle data records of the current record sequence and a first time period coding group in the current coding vector according to the time period correspondence; and performing a round of traversal of all the first vehicle data records of the current record sequence; and during this round of traversal, taking the first vehicle data record currently traversed as the corresponding current record; and performing the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and the first vehicle type of the current record. The first charging mode is respectively subjected to one-hot encoding to obtain the corresponding current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code and current charging mode code; and based on a preset charging power embedding coding rule, the first charging power of the current record is embedded and encoded to obtain the corresponding current charging power code; and based on the obtained current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code, current charging mode code and current charging power code, the encoding values ​​of the place type code, the vehicle type code, the parking state code, the starting travel state code, the navigation mode code, the charging mode code and the charging power code of the first time period code group corresponding to the current record in the current encoding vector are reset;

[0023] Step 47, after all the first vehicle embedding code vectors corresponding to the current segmented data set are set, a corresponding first vehicle embedding code tensor is formed by all the first vehicle embedding code vectors corresponding to the current segmented data set; and a corresponding first data record is formed by the first vehicle embedding code tensor and the first power load label vector corresponding to the current segmented data set;

[0024] Step 48, identifying whether the current segmented data set is the last of the first segmented data set; if not, taking the next first segmented data set as the new current segmented data set and returning to step 43; if so, forming the corresponding first data set from all the obtained first data records.

[0025] Preferably, the training of the substation load prediction model based on the first data set specifically includes:

[0026] Step 51, based on a preset first segmentation ratio, the first data set is divided into two data subsets recorded as a corresponding first training set and a first evaluation set;

[0027] Wherein, both the first training set and the first evaluation set include a plurality of the first data records; the ratio of the total number of records in the first training set and the first evaluation set meets the first segmentation ratio;

[0028] Step 52, taking the first first data record of the first training set as the corresponding current training record;

[0029] Step 53, inputting the first vehicle embedding coding tensor of the current training record as the corresponding vehicle embedding coding tensor into the substation load prediction model to perform substation power load prediction processing and using the substation load prediction tensor output by the model as the corresponding first power load prediction tensor;

[0030] Step 54, bringing the first power load prediction tensor and the first power load label tensor of the current training record into a preset first model loss function; and based on a preset first model optimizer, performing a round of modulation on the model parameters of the substation load prediction model in a direction in which the first model loss function reaches a minimum value;

[0031] Wherein, the first model loss function includes at least an L1 loss function, an L2 loss function and a cross entropy loss function; the first model optimizer includes at least an SGD optimizer and an Adam optimizer;

[0032] Step 55, identifying whether the current training record is the last first data record of the first training set; if not, taking the next first data record as the new current training record and returning to step 53; if yes, going to step 56;

[0033] Step 56, perform a round of traversal on all the first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; input the first vehicle embedded coding tensor of the current evaluation record as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and use the substation load prediction tensor output by the model as the corresponding second power load prediction tensor; and form a corresponding first prediction-label pair by the second power load prediction tensor and the first power load label tensor of the current evaluation record; and at the end of this round of traversal, bring all the first prediction-label pairs obtained into the preset first model evaluation function to calculate and obtain the corresponding first evaluation value;

[0034] Wherein, the first model evaluation function at least includes an RMSE function;

[0035] Step 57, identifying whether the first evaluation value satisfies a preset first evaluation value range; if not, returning to step 52 to continue training; if satisfied, stopping model training and confirming that the prediction model training is completed.

[0036] Preferably, the use of the substation load prediction model is based on the first sampling time L most recently in the first vehicle data set. S The collected data within and the first prediction time L P Predict various types of power loads in the first prediction period of the first substation in the future, including:

[0037] Step 61: regularly use the current time as the corresponding first sampling end time according to the preset first time frequency; and subtract the first sampling duration L from the first sampling end time. S The obtained time is used as the corresponding first sampling start time; and the first sampling start time and the first sampling end time form a corresponding first sampling period; and the first sampling end time and the first interval length L A The added time is used as the corresponding first predicted starting time; and the first predicted starting time is added to the first predicted duration L P The added time is used as the corresponding first prediction end time; and the first prediction start time and the first prediction end time form the corresponding first prediction period;

[0038] Step 62, extracting all the first data records in the first vehicle data set whose first collection period and the first sampling period have a time intersection, and sorting them in chronological order to form a corresponding sampled vehicle data set;

[0039] Step 63, grouping the first vehicle data records with the same first vehicle identifier in the sampled vehicle data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding second single-vehicle record sequence;

[0040] Step 64, take each of the second bicycle record sequences as the corresponding current bicycle record sequence; and set a corresponding second vehicle embedded coding vector for the current bicycle record sequence as the corresponding current vehicle embedded coding vector according to the vector data format of the first vehicle embedded coding vector; and initialize the coding values ​​of all the first time point coding groups of the current vehicle embedded coding vector to 0; and establish a corresponding relationship between each of the first vehicle data records of the current bicycle record sequence and a first time period coding group in the current vehicle embedded coding vector according to the time period correspondence; and perform a round of traversal on all the first vehicle data records of the current bicycle record sequence; and during this round of traversal, take the first vehicle data record currently traversed as the corresponding current record; and perform unique hot encoding on the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and the first charging mode of the current record to obtain the corresponding The current place type code, the current vehicle type code, the current parking state code, the current starting travel state code, the current navigation mode code and the current charging mode code; and based on the preset charging power embedding coding rule, the first charging power of the current record is embedded and coded to obtain the corresponding current charging power code; and based on the obtained current place type code, the current vehicle type code, the current parking state code, the current starting travel state code, the current navigation mode code, the current charging mode code and the current charging power code, the coding values ​​of the place type code, the vehicle type code, the parking state code, the starting travel state code, the navigation mode code, the charging mode code and the charging power code of the first time period coding group corresponding to the current record in the current vehicle embedding coding vector are reset; and at the end of this round of traversal, a corresponding second vehicle embedding coding tensor is formed by all the second vehicle embedding coding vectors corresponding to the sampled vehicle data set;

[0041] Step 65, inputting the second vehicle embedded coding tensor as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and using the substation load prediction tensor output by the model as the corresponding first substation load prediction tensor;

[0042] Step 66, based on the photovoltaic power station load prediction vector, the energy storage load prediction vector, the electric vehicle charging load prediction vector and the daily power load prediction vector of the first area load prediction tensor, the time curves of the four types of power loads in the first prediction period are constructed to obtain the corresponding photovoltaic power station load prediction curve, the energy storage load prediction curve, the charging load prediction curve and the common power load prediction curve; and the constructed time curves of the four types of power loads form the corresponding first area load prediction curve set;

[0043] Step 67, use the unique substation identifier of the first substation as the corresponding first substation identifier; and use the preset data monitoring interface of the power grid side management system as the corresponding first monitoring interface; and the first substation identifier, the first prediction time period, the first substation load prediction tensor and the first substation load prediction curve set form the corresponding first substation prediction record; and send the first substation prediction record to the power grid side management system through the first monitoring interface.

[0044] The embodiment of the present invention provides a processing method for predicting substation load based on electric vehicle data. As can be seen from the above content, the embodiment of the present invention collects data on all electric vehicles traveling in the power supply area of ​​the substation around the clock to obtain a vehicle data set, and collects data on various types of power loads in the substation around the clock to obtain a substation data set; and constructs a substation load prediction model for predicting multiple types of power loads in the substation based on the vehicle embedded coding tensor input by the model; and constructs a model training data set based on the vehicle / substation data set to train the substation load prediction model; and after the model training is completed, the substation load prediction model is used to predict various types of power loads in the substation in the future specified time period based on the collected data in the vehicle data set within the most recent specified time period. The embodiment of the present invention solves the technical problem of how to predict various types of power loads in the substation based on electric vehicle data. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a processing method for predicting area load based on electric vehicle data provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the data structure of a first vehicle data set, a first station area data set and a first segmented data set provided in an embodiment of the present invention;

[0047] Figure 3 A module schematic diagram of a substation load prediction model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The embodiment of the present invention provides a method for predicting the load of a distribution area based on electric vehicle data for a smart terminal or system on the side of a distribution area or a smart grid. Figure 1 A processing method for predicting area load based on electric vehicle data provided by an embodiment of the present invention is shown in a schematic diagram, which mainly includes the following steps:

[0050] Step 1: record the power supply area of ​​the first substation as the corresponding first area; collect data on all electric vehicles traveling in the first area around the clock to obtain the corresponding first vehicle data set; and collect data on various types of power loads in the first substation around the clock to obtain the corresponding first substation data set.

[0051] Here, if Figure 2 As shown in the data structure diagram of the first vehicle data set, the first area data set and the first segmented data set provided in the embodiment of the present invention, the first vehicle data set of the embodiment of the present invention includes multiple first vehicle data records; the first vehicle data record includes a first collection period, a first vehicle identification, a first location type, a first vehicle type, a first parking state, a first starting travel state, a first navigation mode, a first charging mode, and a first charging power; the first collection period includes a first period start time and a first period end time, and the period length between the first period start time and the first period end time is fixedly recorded as a first period length △L1; the first vehicle identification is a unique identification of the corresponding electric vehicle; the first location type is used to mark the location type of the location of the corresponding electric vehicle in the current period, and the first location type includes a commercial location the first vehicle type includes private cars and commercial vehicles; the first parking status is used to mark the parking status of the corresponding electric vehicle in the current time period, and the first parking status includes yes and no; the first starting travel status is used to mark whether the corresponding electric vehicle is in the starting time period of the travel in the current time period, and the first starting travel status includes yes and no; the first navigation mode is used to mark the navigation mode adopted by the corresponding electric vehicle in the current time period, and the first navigation mode includes the shortest driving path navigation mode and the shortest driving time navigation mode; the first charging mode is used to mark whether the corresponding electric vehicle is in the charging state in the current time period and the corresponding charging mode, and the first charging mode includes not charged, regular charging and fast charging; the first charging power is the total charging power of the corresponding electric vehicle in the current time period, and the first charging mode is 0 when the first charging power is not charged.

[0052] like Figure 2 As shown, the first area data set of the embodiment of the present invention includes multiple first area data records; the first area data record includes the second collection period, the first power grid distribution total, the first photovoltaic power generation load total, the first energy storage load total, the first tram charging load total, and the first daily power load total; the second collection period includes the second period start time and the second period end time, and the period length between the second period start time and the second period end time is fixedly recorded as the second period length △L2; the first power grid distribution total is the total power grid-side distribution of the first area in the current second collection period; the first photovoltaic power generation load total is the total power load generated by all photovoltaic power stations in the first area in the current second collection period; the first energy storage load total is the total power load consumed by all energy storage implementations in the first area in the current second collection period; the first tram charging load total is the total power load consumed by all charging piles in the first area in the current second collection period; the first daily power load total is the total power load of daily residents and industrial and commercial facilities generated in the first area in the current second collection period.

[0053] Step 2: Build a load forecasting model for the substation area.

[0054] Here, the substation load prediction model of an embodiment of the present invention is used to perform substation power load prediction processing based on the vehicle embedded coding tensor input by the model and output the corresponding substation load prediction tensor; wherein the substation load prediction tensor includes at least a photovoltaic power station load prediction vector, an energy storage load prediction vector, a tram charging load prediction vector and a daily power load prediction vector.

[0055] like Figure 3 As shown in the module schematic diagram of the substation load prediction model provided by the embodiment of the present invention, the substation load prediction model of the embodiment of the present invention includes a feature extraction network and a regression prediction network.

[0056] It should be noted that the substation load forecasting model in the embodiment of the present invention has at least two model implementation methods, one is based on the Transformer model and the other is based on the Bi-LSTM model; when the substation load forecasting model is implemented based on the Transformer model, the feature extraction network and the regression prediction network are implemented based on the encoder and decoder of the Transformer model respectively; when the substation load forecasting model is implemented based on the Bi-LSTM model, the feature extraction network is implemented by connecting the CNN network with the linear layer, and the regression prediction network is implemented by connecting the Bi-LSTM model with the MLP network.

[0057] It should also be noted that the feature extraction network of the substation load prediction model is used to receive the vehicle embedded coding tensor input by the model, and perform electric vehicle power consumption feature extraction processing on the vehicle embedded coding tensor to obtain the corresponding electric vehicle power consumption feature tensor and send it to the regression prediction network; the regression prediction network of the substation load prediction model is used to perform multi-class power load prediction processing based on the electric vehicle power consumption feature tensor to obtain the corresponding substation load prediction tensor and output it.

[0058] Step 3: Set the data sampling duration to the first sampling duration L S ; and set the prediction interval length to the first interval length L A ; and set the predicted duration to the first predicted duration L P ; and based on the first vehicle data set, the first station data set, the first sampling time L S , first interval length L A and the first prediction duration L P The model training data set is recorded as the first data set; and the load forecasting model of the substation is trained based on the first data set;

[0059] Specifically comprising: Step 31, setting the data sampling time length to the first sampling time length L S ; and set the prediction interval length to the first interval length L A ; and set the predicted duration to the first predicted duration L P ;

[0060] Here, the first sampling duration L of the embodiment of the present invention is S is an integer multiple of the first time period length △L1; the first prediction time length L P is an integer multiple of the second time period length △L2;

[0061] Step 32, based on the first vehicle data set, the first station data set, and the first sampling time L S , first interval length L A and the first prediction duration L P The dataset for model training is recorded as the first dataset;

[0062] The first data set includes multiple first data records; the first data record includes a first vehicle embedding coding tensor and a first power load label tensor; the first vehicle embedding coding tensor is composed of multiple first vehicle embedding coding vectors; each first vehicle embedding coding vector corresponds to an electric vehicle; the vector lengths of all first vehicle embedding coding vectors are equal to the vector length M1, M1=L S / △L1; the first vehicle embedded coding vector is composed of M1 first time period coding groups sorted in chronological order; each first time period coding group corresponds to a first vehicle data record; the first time period coding group includes a venue type code, a vehicle type code, a parking state code, a starting travel state code, a navigation mode code, a charging mode code, and a charging power code; the first power load label tensor includes a first power generation load label vector, a first energy storage load label vector, a first charging load label vector, and a first daily load label vector, and the vector lengths of the four label vectors are equal to the vector length M2, M2 = L P / △L2; the first power generation load label vector is formed by sequentially sorting M2 first power generation load label quantities; the first energy storage load label vector is formed by sequentially sorting M2 first energy storage load label quantities; the first charging load label vector is formed by sequentially sorting M2 first charging load label quantities; the first daily load label vector is formed by sequentially sorting M2 first daily load label quantities;

[0063] The current step 32 specifically includes: step 321, according to the first sampling time length L S Sequentially segmenting the first vehicle data set to obtain a corresponding plurality of first segmented data sets;

[0064] Each first segmented data set is composed of a plurality of first vehicle data records; and the time span of each first segmented data set is the first sampling time length L S ;

[0065] Step 322, taking the first first segmented data set as the corresponding current segmented data set;

[0066] Step 323: The segment end time of the current segment data set is used as the corresponding current end time; and the current end time is compared with the first interval time L. A Add the time obtained as the corresponding current prediction start time; and add the current prediction start time to the first prediction duration L P The added time is used as the corresponding current prediction end time; and the current prediction start time and the current prediction end time form the corresponding current prediction period;

[0067] Step 324, extract all first area data records in the first area data set that have a time intersection with the second acquisition period and the current prediction period to form a corresponding current area data record set; extract the M2 first photovoltaic power generation load total amounts that are earlier in time in the current area data record set as the corresponding M2 first power generation load label quantities and sort them in chronological order to form a corresponding first power generation load label vector; extract the M2 first energy storage load total amounts that are earlier in time in the current area data record set as the corresponding M2 first energy storage load label quantities and sort them in chronological order to form a corresponding first energy storage load label vector; and Extract the M2 first tram charging load totals that are closer in time to the current area data record set as the corresponding M2 first charging load label quantities and sort them in chronological order to form a corresponding first charging load label vector; extract the M2 first daily power load totals that are closer in time to the current area data record set as the corresponding M2 first daily load label quantities and sort them in chronological order to form a corresponding first daily load label vector; and form a corresponding first power load label tensor with the obtained first power generation load label vector, first energy storage load label vector, first charging load label vector and first daily load label vector;

[0068] Step 325, clustering the first vehicle data records with the same first vehicle identifier in the current segmented data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding first record sequence;

[0069] Step 326, taking each first record sequence as the corresponding current record sequence; and setting a corresponding first vehicle embedded coding vector as the corresponding current coding vector for the current record sequence according to the vector data format of the first vehicle embedded coding vector; and initializing the coding values ​​of all the codes of all the first time point coding groups of the current coding vector to 0; and establishing a corresponding relationship between each first vehicle data record of the current record sequence and a first time period coding group in the current coding vector according to the time period correspondence; and performing a round of traversal of all the first vehicle data records of the current record sequence; and in this round of traversal, taking the currently traversed first vehicle data record as the corresponding current record; and performing the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and The first charging mode is respectively single-hot encoded to obtain the corresponding current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code and current charging mode code; and based on the preset charging power embedding coding rule, the first charging power of the current record is embedded and encoded to obtain the corresponding current charging power code; and based on the obtained current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code, current charging mode code and current charging power code, the coding values ​​of the place type code, vehicle type code, parking state code, starting travel state code, navigation mode code, charging mode code and charging power code of the first time period coding group corresponding to the current record in the current coding vector are reset;

[0070] Here, the charging power embedding coding rule can be customized based on application requirements. By default, a normalized embedded coding method can be used for coding. For example, all charging powers are normalized with the rated load of the area as the maximum load, or all charging powers are normalized with the rated load of the charging pile as the maximum load.

[0071] Step 327, after all the first vehicle embedding code vectors corresponding to the current segmented data set are set, a corresponding first vehicle embedding code tensor is formed by all the first vehicle embedding code vectors corresponding to the current segmented data set; and a corresponding first data record is formed by the first vehicle embedding code tensor and the first power load label vector corresponding to the current segmented data set;

[0072] Step 328, identifying whether the current segmented data set is the last first segmented data set; if not, taking the next first segmented data set as the new current segmented data set and returning to step 323; if so, forming the corresponding first data set from all the first data records obtained;

[0073] Step 33, training the load forecasting model of the substation based on the first data set;

[0074] Specifically, it includes: step 331, dividing the first data set into two data subsets based on a preset first division ratio and recording them as a corresponding first training set and a first evaluation set;

[0075] The first segmentation ratio is a preset ratio parameter, such as 8:2; the first training set and the first evaluation set both include a plurality of first data records; the ratio of the total number of records in the first training set to the first evaluation set satisfies the first segmentation ratio;

[0076] Step 332, taking the first first data record of the first training set as the corresponding current training record;

[0077] Step 333, input the first vehicle embedding code tensor of the current training record as the corresponding vehicle embedding code tensor into the substation load prediction model to perform substation power load prediction processing and use the substation load prediction tensor output by the model as the corresponding first power load prediction tensor;

[0078] Step 334, bringing the first power load prediction tensor and the first power load label tensor of the current training record into a preset first model loss function; and based on the preset first model optimizer, performing a round of modulation on the model parameters of the substation load prediction model in a direction to minimize the first model loss function;

[0079] The first model loss function includes at least an L1 loss function, an L2 loss function, and a cross entropy loss function; the first model optimizer includes at least an SGD optimizer and an Adam optimizer;

[0080] Step 335, identifying whether the current training record is the last first data record of the first training set; if not, taking the next first data record as the new current training record and returning to step 333; if yes, going to step 336;

[0081] Step 336, perform a round of traversal on all first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; input the first vehicle embedded coding tensor of the current evaluation record as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and use the substation load prediction tensor output by the model as the corresponding second power load prediction tensor; and form a corresponding first prediction-label pair by the second power load prediction tensor and the first power load label tensor of the current evaluation record; and at the end of this round of traversal, bring all the obtained first prediction-label pairs into the preset first model evaluation function to calculate and obtain the corresponding first evaluation value;

[0082] Wherein, the first model evaluation function at least includes the RMSE function;

[0083] Step 337, identifying whether the first evaluation value meets the preset first evaluation value range; if not, returning to step 332 to continue training; if satisfied, stopping model training and confirming the completion of prediction model training.

[0084] Here, the first evaluation value range is a preset value range.

[0085] Step 4: After the model training is completed, the load prediction model of the substation is used to calculate the first sampling time L in the first vehicle data set. S The collected data and the first prediction duration L P Predict various types of power loads in the first forecast period of the first transformer area in the future;

[0086] The interval between the start time of the first prediction period and the current time is the first interval length L. A ; The length of the first prediction period is the first prediction duration L P ;

[0087] Specifically, step 41, regularly taking the current time as the corresponding first sampling end time according to the preset first time frequency; and subtracting the first sampling duration L from the first sampling end time S The obtained time is used as the corresponding first sampling start time; and the first sampling start time and the first sampling end time form the corresponding first sampling period; and the first sampling end time and the first interval length L A The added time is used as the corresponding first prediction start time; and the first prediction start time and the first prediction duration L P The added time is used as the corresponding first prediction end time; and the first prediction start time and the first prediction end time form the corresponding first prediction period;

[0088] Here, the first time frequency is a preset time frequency parameter;

[0089] Step 42, extract all first data records in the first vehicle data set whose first collection period and the first sampling period have a time intersection, and sort them in chronological order to form a corresponding sampled vehicle data set;

[0090] Step 43, clustering the first vehicle data records with the same first vehicle identifier in the sampled vehicle data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding second single vehicle record sequence;

[0091] Step 44, taking each second bicycle record sequence as the corresponding current bicycle record sequence; and setting a corresponding second vehicle embedded coding vector as the corresponding current vehicle embedded coding vector for the current bicycle record sequence according to the vector data format of the first vehicle embedded coding vector; and initializing the coding values ​​of all the first time point coding groups of the current vehicle embedded coding vector to 0; and according to the time period correspondence, establishing a correspondence between each first vehicle data record of the current bicycle record sequence and a first time period coding group in the current vehicle embedded coding vector; and performing a round of traversal on all the first vehicle data records of the current bicycle record sequence; and in this round of traversal, taking the currently traversed first vehicle data record as the corresponding current record; and performing unique hot encoding on the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and the first charging mode of the current record to obtain The corresponding current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code and current charging mode code; and based on the charging power embedding coding rule, the first charging power of the current record is embedded and coded to obtain the corresponding current charging power code; and based on the obtained current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code, current charging mode code and current charging power code, the coding values ​​of the place type code, vehicle type code, parking state code, starting travel state code, navigation mode code, charging mode code and charging power code of the first time period coding group corresponding to the current record in the current vehicle embedding coding vector are reset; and at the end of this round of traversal, a corresponding second vehicle embedding coding tensor is formed by all the second vehicle embedding coding vectors corresponding to the sampled vehicle data set;

[0092] Step 45, inputting the second vehicle embedded coding tensor as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and using the substation load prediction tensor output by the model as the corresponding first substation load prediction tensor;

[0093] Step 46, based on the photovoltaic power station load prediction vector, energy storage load prediction vector, electric vehicle charging load prediction vector and daily power load prediction vector of the first substation load prediction tensor, construct the time curves of the four types of power loads in the first prediction period to obtain the corresponding photovoltaic power station load prediction curve, the energy storage load prediction curve, the charging load prediction curve and the common power load prediction curve; and the constructed time curves of the four types of power loads form the corresponding first substation load prediction curve set;

[0094] Step 47, using the unique area identifier of the first area as the corresponding first area identifier; and using the preset data monitoring interface of the power grid side management system as the corresponding first monitoring interface; and the first area identifier, the first prediction time period, the first area load prediction tensor and the first area load prediction curve set form the corresponding first area prediction record; and sending the first area prediction record to the power grid side management system through the first monitoring interface.

[0095] In summary, the embodiment of the present invention provides a processing method for predicting substation load based on electric vehicle data. As can be seen from the above content, the embodiment of the present invention collects data on all electric vehicles traveling in the power supply area of ​​the substation around the clock to obtain a vehicle data set, and collects data on various types of power loads in the substation around the clock to obtain a substation data set; and constructs a substation load prediction model for predicting multiple types of power loads in the substation according to the vehicle embedded coding tensor input by the model; and constructs a model training data set based on the vehicle / substation data set to train the substation load prediction model; and after the model training is completed, the substation load prediction model is used to predict various types of power loads in the substation in the future specified time period according to the collected data in the vehicle data set within the most recent specified time period. The embodiment of the present invention solves the technical problem of how to predict various types of power loads in the substation based on electric vehicle data.

[0096] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0097] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0098] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for predicting load in a distribution area based on electric vehicle data, characterized in that: The method comprises: The power supply area of ​​the first area is recorded as the corresponding first area; all electric vehicles traveling in the first area are collected around the clock to obtain a corresponding first vehicle data set; and all types of power loads in the first area are collected around the clock to obtain a corresponding first area data set; Constructing a load prediction model for an area; the load prediction model for an area is used to perform area power load prediction processing according to the vehicle embedded coding tensor input by the model and output a corresponding load prediction tensor for the area; the load prediction tensor for the area at least includes a photovoltaic power station load prediction vector, an energy storage load prediction vector, a tram charging load prediction vector and a daily power load prediction vector; Set the data sampling duration to the first sampling duration L S ; and set the prediction interval length to the first interval length L A ; and set the predicted duration to the first predicted duration L P ; and based on the first vehicle data set, the first station data set, the first sampling time L S , the first interval length L A and the first prediction duration L P The model training data set is recorded as a first data set; and the load forecasting model of the substation is trained based on the first data set; After the model training is completed, the load prediction model of the substation is used according to the first sampling time L most recently in the first vehicle data set. S The collected data within and the first prediction time L P Predict various types of power loads in the first prediction period in the future of the first substation; the interval between the start time of the first prediction period and the current time is the first interval time L A The length of the first prediction period is the first prediction duration L P .

2. The method for predicting load of a substation based on electric vehicle data according to claim 1, characterized in that: The first vehicle data set includes a plurality of first vehicle data records; the first vehicle data record includes a first collection period, a first vehicle identifier, a first location type, a first vehicle type, a first parking state, a first starting travel state, a first navigation mode, a first charging mode, and a first charging power; the first collection period includes a first period start time and a first period end time, and the period length between the first period start time and the first period end time is fixedly recorded as a first period length △L1; the first vehicle identifier is a unique identifier of the corresponding electric vehicle; the first location type is used to mark the location type of the corresponding electric vehicle in the current period, and the first location type includes commercial places, residential areas, and roads; the first vehicle type includes private cars and operating vehicles; The first parking state is used to mark the parking state of the corresponding electric vehicle in the current time period, and the first parking state includes yes and no; the first starting travel state is used to mark whether the corresponding electric vehicle is in the starting time period of travel in the current time period, and the first starting travel state includes yes and no; the first navigation mode is used to mark the navigation mode adopted by the corresponding electric vehicle in the current time period, and the first navigation mode includes the shortest driving path navigation mode and the shortest driving time navigation mode; The first charging mode is used to mark whether the corresponding electric vehicle is in a charging state and the corresponding charging mode in the current time period, and the first charging mode includes no charging, normal charging and fast charging; the first charging power is the total charging power of the corresponding electric vehicle in the current time period, and the first charging power is 0 when the first charging mode is no charging; The first area data set includes multiple first area data records; the first area data record includes the second collection period, the first power grid power distribution, the first photovoltaic power generation load, the first energy storage load, the first tram charging load, and the first daily power load; the second collection period includes the second period start time and the second period end time, and the period length between the second period start time and the second period end time is fixedly recorded as the second period length △L2; the first power grid power distribution is the total power grid-side power distribution of the first area in the current second collection period; the first photovoltaic power generation load is the total power load generated by all photovoltaic power stations in the first area in the current second collection period; the first energy storage load is the total power load consumed by all energy storage implementations in the first area in the current second collection period; the first tram charging load is the total power load consumed by all charging piles in the first area in the current second collection period; the first daily power load is the total power load of daily residents and industrial and commercial facilities generated in the first area in the current second collection period; The first sampling time L S is an integer multiple of the first time period length △L1; the first prediction time length L P is an integer multiple of the length of the second time period ΔL2; The first data set includes multiple first data records; the first data record includes a first vehicle embedding coding tensor and a first power load label tensor; the first vehicle embedding coding tensor is composed of multiple first vehicle embedding coding vectors; each of the first vehicle embedding coding vectors corresponds to an electric vehicle; the vector lengths of all the first vehicle embedding coding vectors are equal to the vector length M1, M1=L S / △L1; the first vehicle embedded coding vector is formed by M1 first time period coding groups arranged in chronological order; each first time period coding group corresponds to one first vehicle data record; the first time period coding group includes a place type code, a vehicle type code, a parking state code, a starting travel state code, a navigation mode code, a charging mode code, and a charging power code; The first power load label tensor includes a first power generation load label vector, a first energy storage load label vector, a first charging load label vector and a first daily load label vector. The vector lengths of the four label vectors are equal to the vector length M2, M2=L P / △L2; the first power generation load label vector is formed by sequentially sorting M2 first power generation load label quantities; the first energy storage load label vector is formed by sequentially sorting M2 first energy storage load label quantities; the first charging load label vector is formed by sequentially sorting M2 first charging load label quantities; the first daily load label vector is formed by sequentially sorting M2 first daily load label quantities.

3. The method for predicting load of a distribution area based on electric vehicle data according to claim 2, characterized in that: The substation load prediction model includes a feature extraction network and a regression prediction network; the substation load prediction model has at least two model implementation modes, one based on the Transformer model and the other based on the Bi-LSTM model; when the substation load prediction model is implemented based on the Transformer model, the feature extraction network and the regression prediction network are implemented based on the encoder and decoder of the Transformer model respectively; when the substation load prediction model is implemented based on the Bi-LSTM model, the feature extraction network is implemented by connecting the CNN network with the linear layer, and the regression prediction network is implemented by connecting the Bi-LSTM model with the MLP network; The feature extraction network is used to receive the vehicle embedded coding tensor input by the model, and perform electric vehicle power consumption feature extraction processing on the vehicle embedded coding tensor to obtain the corresponding electric vehicle power consumption feature tensor and send it to the regression prediction network; the regression prediction network is used to perform multi-class power load prediction processing based on the electric vehicle power consumption feature tensor to obtain the corresponding station load prediction tensor and output it.

4. The method for predicting load of a substation based on electric vehicle data according to claim 2, characterized in that: The first vehicle data set, the first station area data set, and the first sampling time length L S , the first interval length L A and the first prediction duration L P The model training data set is recorded as the first data set, which specifically includes: Step 41: according to the first sampling time L S Sequentially segmenting the first vehicle data set to obtain a corresponding plurality of first segmented data sets; Each of the first segmented data sets is composed of a plurality of the first vehicle data records; and the time span of each of the first segmented data sets is the first sampling time length L S ; Step 42, taking the first of the first segmented data sets as the corresponding current segmented data set; Step 43: taking the segment end time of the current segment data set as the corresponding current end time; and summing the current end time with the first interval time L A Add the time obtained as the corresponding current predicted start time; and add the current predicted start time to the first predicted duration L P The time obtained by adding them is used as the corresponding current prediction end time; and the current prediction start time and the current prediction end time form the corresponding current prediction period; Step 44, extract all the first area data records in the first area data set whose second collection period and the current prediction period have a time intersection to form a corresponding current area data record set; extract the M2 first photovoltaic power generation load total amounts that are earlier in time in the current area data record set as the corresponding M2 first power generation load label amounts and sort them in chronological order to form a corresponding first power generation load label vector; extract the M2 first energy storage load total amounts that are earlier in time in the current area data record set as the corresponding M2 first energy storage load label amounts and sort them in chronological order to form a corresponding first energy storage load label vector; and The M2 first tram charging load totals that are earlier in time of the current area data record set are extracted as the corresponding M2 first charging load label quantities and are sorted in chronological order to form a corresponding first charging load label vector; and the M2 first daily power load totals that are earlier in time of the current area data record set are extracted as the corresponding M2 first daily load label quantities and are sorted in chronological order to form a corresponding first daily load label vector; and the obtained first power generation load label vector, the first energy storage load label vector, the first charging load label vector and the first daily load label vector form a corresponding first power load label tensor; Step 45, grouping the first vehicle data records with the same first vehicle identifier in the current segmented data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding first record sequence; Step 46, taking each of the first record sequences as the corresponding current record sequence; and setting a corresponding first vehicle embedded coding vector as the corresponding current coding vector for the current record sequence according to the vector data format of the first vehicle embedded coding vector; and initializing the coding values ​​of all the codings of all the first time point coding groups of the current coding vector to 0; and establishing a corresponding relationship between each of the first vehicle data records of the current record sequence and a first time period coding group in the current coding vector according to the time period correspondence; and performing a round of traversal of all the first vehicle data records of the current record sequence; and during this round of traversal, taking the first vehicle data record currently traversed as the corresponding current record; and performing the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and the first vehicle type of the current record. The first charging mode is respectively subjected to one-hot encoding to obtain the corresponding current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code and current charging mode code; and based on a preset charging power embedding coding rule, the first charging power of the current record is embedded and encoded to obtain the corresponding current charging power code; and based on the obtained current place type code, current vehicle type code, current parking state code, current starting travel state code, current navigation mode code, current charging mode code and current charging power code, the encoding values ​​of the place type code, the vehicle type code, the parking state code, the starting travel state code, the navigation mode code, the charging mode code and the charging power code of the first time period code group corresponding to the current record in the current encoding vector are reset; Step 47, after all the first vehicle embedding code vectors corresponding to the current segmented data set are set, a corresponding first vehicle embedding code tensor is formed by all the first vehicle embedding code vectors corresponding to the current segmented data set; and a corresponding first data record is formed by the first vehicle embedding code tensor and the first power load label vector corresponding to the current segmented data set; Step 48, identifying whether the current segmented data set is the last of the first segmented data set; if not, taking the next first segmented data set as the new current segmented data set and returning to step 43; if so, forming the corresponding first data set from all the obtained first data records.

5. The method for predicting load of a substation based on electric vehicle data according to claim 2, characterized in that: The training of the substation load prediction model based on the first data set specifically includes: Step 51, based on a preset first segmentation ratio, the first data set is divided into two data subsets recorded as a corresponding first training set and a first evaluation set; Wherein, both the first training set and the first evaluation set include a plurality of the first data records; the ratio of the total number of records in the first training set and the first evaluation set meets the first segmentation ratio; Step 52, taking the first first data record of the first training set as the corresponding current training record; Step 53, inputting the first vehicle embedding coding tensor of the current training record as the corresponding vehicle embedding coding tensor into the substation load prediction model to perform substation power load prediction processing and using the substation load prediction tensor output by the model as the corresponding first power load prediction tensor; Step 54, bringing the first power load prediction tensor and the first power load label tensor of the current training record into a preset first model loss function; and based on a preset first model optimizer, performing a round of modulation on the model parameters of the substation load prediction model in a direction in which the first model loss function reaches a minimum value; Wherein, the first model loss function includes at least an L1 loss function, an L2 loss function and a cross entropy loss function; the first model optimizer includes at least an SGD optimizer and an Adam optimizer; Step 55, identifying whether the current training record is the last first data record of the first training set; if not, taking the next first data record as the new current training record and returning to step 53; if yes, going to step 56; Step 56, perform a round of traversal on all the first data records of the first evaluation set; and in this round of traversal, use the first data record currently traversed as the corresponding current evaluation record; input the first vehicle embedded coding tensor of the current evaluation record as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and use the substation load prediction tensor output by the model as the corresponding second power load prediction tensor; and form a corresponding first prediction-label pair by the second power load prediction tensor and the first power load label tensor of the current evaluation record; and at the end of this round of traversal, bring all the first prediction-label pairs obtained into the preset first model evaluation function to calculate and obtain the corresponding first evaluation value; Wherein, the first model evaluation function at least includes an RMSE function; Step 57, identifying whether the first evaluation value meets the preset first evaluation value range; if not, returning to step 52 to continue training; if satisfied, stopping model training and confirming that the prediction model training is completed.

6. The method for predicting load of a substation based on electric vehicle data according to claim 2, characterized in that: The load prediction model of the substation is used to predict the first sampling time L most recently in the first vehicle data set. S The collected data within and the first prediction time L P Predict various types of power loads in the first prediction period of the first substation in the future, including: Step 61: regularly use the current time as the corresponding first sampling end time according to the preset first time frequency; and subtract the first sampling duration L from the first sampling end time. S The obtained time is used as the corresponding first sampling start time; and the first sampling start time and the first sampling end time form a corresponding first sampling period; and the first sampling end time and the first interval length L A The added time is used as the corresponding first predicted starting time; and the first predicted starting time is added to the first predicted duration L P The added time is used as the corresponding first prediction end time; and the first prediction start time and the first prediction end time form the corresponding first prediction period; Step 62, extracting all the first data records in the first vehicle data set whose first collection period and the first sampling period have a time intersection, and sorting them in chronological order to form a corresponding sampled vehicle data set; Step 63, grouping the first vehicle data records with the same first vehicle identifier in the sampled vehicle data set into one category and sorting all the first vehicle data records belonging to the same category in chronological order to form a corresponding second single-vehicle record sequence; Step 64, take each of the second bicycle record sequences as the corresponding current bicycle record sequence; and set a corresponding second vehicle embedded coding vector for the current bicycle record sequence as the corresponding current vehicle embedded coding vector according to the vector data format of the first vehicle embedded coding vector; and initialize the coding values ​​of all the first time point coding groups of the current vehicle embedded coding vector to 0; and establish a corresponding relationship between each of the first vehicle data records of the current bicycle record sequence and a first time period coding group in the current vehicle embedded coding vector according to the time period correspondence; and perform a round of traversal on all the first vehicle data records of the current bicycle record sequence; and during this round of traversal, take the first vehicle data record currently traversed as the corresponding current record; and perform unique hot encoding on the first location type, the first vehicle type, the first parking state, the first starting travel state, the first navigation mode and the first charging mode of the current record to obtain the corresponding The current place type code, the current vehicle type code, the current parking state code, the current starting travel state code, the current navigation mode code and the current charging mode code; and based on the preset charging power embedding coding rule, the first charging power of the current record is embedded and coded to obtain the corresponding current charging power code; and based on the obtained current place type code, the current vehicle type code, the current parking state code, the current starting travel state code, the current navigation mode code, the current charging mode code and the current charging power code, the coding values ​​of the place type code, the vehicle type code, the parking state code, the starting travel state code, the navigation mode code, the charging mode code and the charging power code of the first time period coding group corresponding to the current record in the current vehicle embedding coding vector are reset; and at the end of this round of traversal, a corresponding second vehicle embedding coding tensor is formed by all the second vehicle embedding coding vectors corresponding to the sampled vehicle data set; Step 65, inputting the second vehicle embedded coding tensor as the corresponding vehicle embedded coding tensor into the substation load prediction model to perform substation power load prediction processing and using the substation load prediction tensor output by the model as the corresponding first substation load prediction tensor; Step 66, based on the photovoltaic power station load prediction vector, the energy storage load prediction vector, the electric vehicle charging load prediction vector and the daily power load prediction vector of the first area load prediction tensor, the time curves of the four types of power loads in the first prediction period are constructed to obtain the corresponding photovoltaic power station load prediction curve, the energy storage load prediction curve, the charging load prediction curve and the common power load prediction curve; and the constructed time curves of the four types of power loads form the corresponding first area load prediction curve set; Step 67, use the unique substation identifier of the first substation as the corresponding first substation identifier; and use the preset data monitoring interface of the power grid side management system as the corresponding first monitoring interface; and the first substation identifier, the first prediction time period, the first substation load prediction tensor and the first substation load prediction curve set form the corresponding first substation prediction record; and send the first substation prediction record to the power grid side management system through the first monitoring interface.

Images