Electric vehicle generalized energy storage space-time prediction method based on BERT

Abstract

The invention discloses an electric vehicle generalized energy storage space-time prediction method based on BERT. The method comprises the steps that time information and space information of an electric vehicle are collected; the method comprises the following steps: constructing an electric vehicle generalized energy storage equivalent model of a spatial dimension, training on-line collected electric vehicle spatial information by using an electric vehicle generalized energy storage equivalent space parameter identification model based on a BERT algorithm, and identifying parameters of the electric vehicle generalized energy storage equivalent model; the method comprises the steps that an electric vehicle generalized energy storage equivalent model of a time dimension is constructed, an electric vehicle generalized energy storage equivalent time parameter identification model based on a BERT algorithm is used for training time information, collected online, of an electric vehicle, and parameters of the electric vehicle generalized energy storage equivalent model are identified. The method can accurately capture the geographic distribution of the energy storage of the electric vehicle, optimizes the regional scheduling of the charging and discharging behaviors, deeply excavates the time rule of the energy storage behavior of the electric vehicle, and provides dynamic and accurate time sequence prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of power system regulation and control, and in particular to a BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles. Background Art

[0002] Constructing a spatiotemporal equivalent model of generalized energy storage for electric vehicles is a key technology for achieving deep integration of electric vehicles and power grids, and has significant economic, social and environmental benefits. At the economic level, the model can optimize the charging and discharging behavior of electric vehicles, guide vehicles to charge when electricity prices are low and discharge at peak times, achieve grid load balance, and help car owners reduce charging costs and increase vehicle-to-grid (V2G) service revenue. In addition, it can optimize the layout of the power grid and charging infrastructure, avoid unnecessary investment, and improve the economic efficiency of power grid planning and operation. At the social level, the model enhances the flexibility and reliability of the power grid by coordinating the distributed energy storage characteristics of electric vehicles. It can help the power grid to absorb intermittent new energy more efficiently, reduce the phenomenon of wind and solar power abandonment, and provide technical support for the construction of energy Internet and the optimization of energy structure. At the same time, the model also promotes the coordinated development of transportation and energy fields and realizes the optimal allocation of resources across fields. At the environmental level, the model can effectively improve the utilization rate of clean energy, reduce dependence on fossil energy, and thus reduce carbon emissions from the power system. This technology will also help low-carbon travel and green electricity trading, and promote renewable energy consumption and sustainable development.

[0003] The existing methods have the following deficiencies: 1) Lack of coupled analysis of the spatiotemporal characteristics of electric vehicles. The mobility of electric vehicles makes the distribution of their energy storage characteristics not fixed. Existing models are mostly based on regional static analysis, ignoring the dynamics of the spatial dimension; they fail to fully consider the impact of the geographical distribution of electric vehicles and the location distribution of charging piles on the energy storage characteristics. 2) Insufficient spatial optimization granularity. Existing methods lack spatial accuracy for resource distribution and are difficult to support refined regional power grid scheduling; lack of in-depth modeling of the relationship between vehicle distribution, mobile paths and energy allocation, resulting in low resource utilization. 3) Insufficient dynamic prediction capabilities. The energy storage state of electric vehicles changes significantly over time. Existing models mostly use simple linear or time series models, which are difficult to capture complex time dynamic relationships; they ignore the impact of historical behavior patterns on future behavior and are difficult to accurately predict the charging and discharging behavior of electric vehicles. 4) Timing optimization is not precise enough. There is a lack of detailed analysis of the matching of charging and discharging demand with the output time of new energy; the ability to respond to peak and valley demand is not reflected in timing control, resulting in insufficient system economy and reliability. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles, which can deeply explore the temporal laws of electric vehicle energy storage behavior and provide dynamic and accurate time series prediction.

[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0006] The present invention is a BERT-based electric vehicle generalized energy storage spatiotemporal prediction method, comprising the following operations:

[0007] Collecting time and space information of electric vehicles;

[0008] A BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles is constructed, and the time and space information of electric vehicles is used to train the BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles, including: constructing a spatial dimension of a generalized energy storage equivalent model for electric vehicles, using a BERT-based generalized energy storage equivalent spatial parameter identification model for electric vehicles to train the spatial information of electric vehicles collected online, and identify the parameters of the generalized energy storage equivalent model for electric vehicles; constructing a temporal dimension of a generalized energy storage equivalent model for electric vehicles, using a BERT-based generalized energy storage equivalent temporal parameter identification model for electric vehicles to train the temporal information of electric vehicles collected online, and identify the parameters of the generalized energy storage equivalent model for electric vehicles.

[0009] A further improvement of the present invention is that the time information of the electric vehicle includes the time when the electric vehicle starts charging, the time when the electric vehicle is fully charged for the first time, the time when the last stage of charging starts before the electric vehicle leaves, and the time when the electric vehicle leaves, and the expression is:

[0010] X S (t) = [T dao (t),T dao1 (t),T li1 (t),T li (t)]

[0011] Among them, X S (t) is the electric time information collected at time t, T dao (t) is the time when the electric vehicle starts charging at time t, T dao1 (t) is the first full charge time of the electric vehicle collected at time t, T li1 (t) is the charging time of the last stage before the electric car leaves the vehicle, collected at time t, T li (t) is the departure time of the electric vehicle collected at time t.

[0012] The further improvement of the present invention is that the spatial information of the electric vehicle includes: the driving power of the electric vehicle, the power of the auxiliary equipment of the electric vehicle, the equivalent state of charge of the electric vehicle, the rated capacity of the battery of the electric vehicle, the actual equivalent charging power of the electric vehicle, the nominal charging power of the electric vehicle, the actual equivalent discharge power of the electric vehicle, the nominal discharge power of the electric vehicle, the actual equivalent energy storage capacity of the electric vehicle, and the maximum discharge power of the electric vehicle, and the expression is:

[0013]

[0014] Among them, X K (t) is the electric space information collected at time t, P drive (t) is the driving power of the electric vehicle collected at time t, P aux (t) is the power of the auxiliary equipment of the electric vehicle collected at time t, SOC eq (t) is the equivalent state of charge of the electric vehicle collected at time t, C bat is the rated capacity of the electric vehicle battery, is the actual equivalent charging power of the electric vehicle collected at time t, is the nominal charging power of the electric vehicle, is the actual equivalent discharge power of the electric vehicle collected at time t, is the nominal discharge power of the electric vehicle, E eff (t) is the actual equivalent energy storage capacity of the electric vehicle collected at time t, is the maximum discharge power of the electric vehicle.

[0015] A further improvement of the present invention is that the expression of the generalized energy storage equivalent model of electric vehicles in the spatial dimension is:

[0016] P run (t) = P drive (t)+P aux (t)

[0017] E eq (t) = SOC eq (t)+C bat

[0018]

[0019] E eff (t) = η e ·E eq (t)

[0020]

[0021] η sys =η ch ·η dis

[0022] Among them, P run (t) is the operating power of the generalized energy storage equivalent model of electric vehicles, E eq (t) is the equivalent storage capacity of the generalized energy storage equivalent model of electric vehicles, η ch is the equivalent charging power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η dis is the equivalent discharge power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η e is the equivalent storage capacity conversion coefficient of the generalized energy storage equivalent model of electric vehicles, κ dis (t) is the sustainable discharge parameter of the generalized energy storage equivalent model of electric vehicles, η sys It is the equivalent comprehensive efficiency parameter of the generalized energy storage equivalent model of electric vehicles.

[0023] A further improvement of the present invention is that the expression of the electric vehicle generalized energy storage equivalent space parameter identification model based on the BERT algorithm is:

[0024]

[0025] H 0 =Embed(X' K )

[0026] H l = Transformer(H l-1 )

[0027]

[0028] Among them, X' K is the normalized spatial feature vector, X K is the spatial feature vector, μ and σ are the feature mean and standard deviation respectively, Embed() is the BERT embedding layer processing function, and the normalized spatial feature vector X' K Processing, H 0 is the initial embedding layer, Transformer() is the Transformer layer encoding function, H l is the output of layer l, is the spatial parameter identified for the i-th sample, y K,i is the real space parameter, H L is the hidden state, N is the total number of samples, L K is the loss value, θ K is the model parameter, α K For learning efficiency, is the gradient descent function, It is a BERT-based generalized energy storage space parameter identification model for electric vehicles. is the final identified electric vehicle generalized energy storage equivalent space parameter, To identify the operating power, To identify the equivalent storage capacity, is the equivalent charging power conversion factor identified, is the identified equivalent discharge power conversion factor, is the equivalent storage capacity conversion factor identified, To identify the sustainable discharge parameters, is the identified equivalent comprehensive efficiency parameter.

[0029] A further improvement of the present invention is that the expression of the generalized energy storage equivalent model of electric vehicles is:

[0030]

[0031] Among them, δ S It is the generalized equivalent state of the electric vehicle, 0 represents the moving state, 1 represents the charging state, and -1 represents the discharging state.

[0032] A further improvement of the present invention is that the expression of the electric vehicle generalized energy storage equivalent time parameter identification model based on the BERT algorithm is:

[0033]

[0034] in, is a BERT-based generalized energy storage time parameter identification model for electric vehicles, X S Input feature for time, is the final identified equivalent time parameter of generalized energy storage of electric vehicles, is the start time of charging of the electric vehicle of the identified generalized energy storage equivalent model of the electric vehicle, The first full charge time of the identified electric vehicle, To identify the time when the electric car starts charging before leaving the final stage, To identify the departure time of the electric vehicle, It is the generalized equivalent energy storage charging state of the electric vehicle after identification.

[0035] The beneficial effects of the present invention are as follows: the present invention can deeply explore the time regularity of electric vehicle energy storage behavior and provide dynamic and accurate time series prediction. The present invention supports refined grid regulation, provides equivalent distribution of generalized energy storage of electric vehicles under different time and space states, and supports accurate load peak shaving and valley filling and auxiliary service scheduling in the region.

[0036] The present invention can promote the consumption of new energy. The generalized energy storage equivalent model of electric vehicles in the spatial dimension optimizes the energy storage regulation in the region, which is conducive to the local consumption of new energy in the region. The generalized energy storage equivalent model of electric vehicles in the time dimension predicts the dynamic behavior of energy storage of electric vehicles, and improves the time matching degree between energy storage and new energy power generation.

[0037] The present invention enhances the capabilities of virtual power plants and energy internets, supports efficient management of electric vehicle energy storage resources in virtual power plants, optimizes vehicle-grid interaction, and helps achieve cross-regional (electric vehicles can be mobile, move in different energy internets, and choose to charge or discharge in different energy internets) and cross-time collaborative optimization of energy internet resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0040] like Figure 1 As shown, this embodiment is a BERT-based electric vehicle generalized energy storage spatiotemporal prediction method, comprising the following steps:

[0041] Step 1: Collect the time information and space information of the electric vehicle.

[0042] The collected spatial information includes electric vehicle driving power, electric vehicle auxiliary equipment power, electric vehicle equivalent state of charge, electric vehicle battery rated capacity, electric vehicle actual equivalent charging power, electric vehicle nominal charging power, electric vehicle actual equivalent discharge power, electric vehicle nominal discharge power, electric vehicle actual equivalent energy storage capacity, and electric vehicle maximum discharge power. The expression of spatial information is:

[0043]

[0044] Among them, X K (t) is the electric space information collected at time t, P drive (t) is the driving power of the electric vehicle collected at time t, P aux (t) is the power of the auxiliary equipment of the electric vehicle collected at time t, SOC eq (t) is the equivalent state of charge of the electric vehicle collected at time t, C batis the rated capacity of the electric vehicle battery, is the actual equivalent charging power of the electric vehicle collected at time t, is the nominal charging power of the electric vehicle, is the actual equivalent discharge power of the electric vehicle collected at time t, is the nominal discharge power of the electric vehicle, is the actual equivalent energy storage capacity of the electric vehicle collected at time t, is the maximum discharge power of the electric vehicle.

[0045] The collected time information includes the time when the electric vehicle starts charging, the time when the electric vehicle is fully charged for the first time, the time when the electric vehicle starts charging in the last stage before leaving, and the time when the electric vehicle leaves. The expression of time information is shown in formula (2), where T dao (t) to T dao1 (t), the electric vehicle is equivalent to energy storage in a charging state. dao1 (t) to T li1 (t), the electric vehicle is equivalent to energy storage and can be charged or discharged. li1 (t) to T li (t), the electric vehicle is equivalent to energy storage in a charging state. dao (t) to T li During the time other than (t), electric vehicles are equivalent to mobile energy storage.

[0046] X S (t) = [T dao (t),T dao1 (t),T li1 (t),T li (t)] (2)

[0047] Among them, X S (t) is the electric time information collected at time t, T dao (t) is the time when the electric vehicle starts charging at time t, T dao1 (t) is the first full charge time of the electric vehicle collected at time t, T li1 (t) is the charging time of the last stage before the electric car leaves the vehicle, collected at time t, T li (t) is the departure time of the electric vehicle collected at time t.

[0048] Step 2: Build a BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles, and use the temporal and spatial information of electric vehicles to train the BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles.

[0049] Step 2.1, construct a generalized energy storage equivalent model of electric vehicles in the spatial dimension. The constructed generalized energy storage equivalent model of electric vehicles includes operating power, equivalent storage capacity, equivalent charging power conversion coefficient, equivalent discharge power conversion coefficient, equivalent storage capacity conversion coefficient, sustainable discharge parameter, and equivalent comprehensive efficiency parameter. The expressions of the generalized energy storage equivalent model of electric vehicles in this embodiment are shown in (3) to (9). Among them, expression (3) is the operating power, which represents the power demand of the electric vehicle in the operating state. Expression (4) is the equivalent storage capacity, which represents the equivalent electric energy reserve under the standardized state. Expression (5) is the equivalent charging power conversion coefficient, which represents the ratio of the actual input power to the nominal charging power during the charging process. Expression (6) is the equivalent discharge power conversion coefficient, which represents the equivalent coefficient of the output power during the discharge process. Expression (7) is the equivalent storage capacity conversion coefficient, which represents the conversion ratio of the storage capacity from to the system output. Expression (8) is the sustainable discharge parameter, which represents the performance parameter during continuous discharge. Expression (9) is the equivalent comprehensive efficiency parameter, which represents the overall efficiency of the system during the charge and discharge cycle.

[0050] P run (t) = P drive (t)+P aux (t) (3)

[0051] E eq (t) = SOC eq (t)+C bat (4)

[0052]

[0053] E eff (t) = η e ·E eq (t) (7)

[0054]

[0055] η sys =η ch ·η dis (9)

[0056] Among them, P run (t) is the operating power of the generalized energy storage equivalent model of electric vehicles, E eq (t) is the equivalent storage capacity of the generalized energy storage equivalent model of electric vehicles, η ch is the equivalent charging power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η dis is the equivalent discharge power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η e is the equivalent storage capacity conversion coefficient of the generalized energy storage equivalent model of electric vehicles, κ dis(t) is the sustainable discharge parameter of the generalized energy storage equivalent model of electric vehicles, η sys It is the equivalent comprehensive efficiency parameter of the generalized energy storage equivalent model of electric vehicles.

[0057] Different types of electric vehicles have different parameters, and the parameters will change during actual operation, so it is necessary to identify the parameters online. This embodiment uses an electric vehicle generalized energy storage equivalent spatial parameter identification model based on the BERT algorithm to train the spatial information of electric vehicles collected online to identify the operating power, equivalent storage capacity, equivalent charging power conversion coefficient, equivalent discharge power conversion coefficient, equivalent storage capacity conversion coefficient, sustainable discharge parameters, and equivalent comprehensive efficiency parameters of the electric vehicle generalized energy storage equivalent model. The operations of this embodiment to construct an electric vehicle generalized energy storage equivalent spatial parameter identification model based on the BERT algorithm are shown in expressions (10) to (17), where expression (10) is an input feature normalization operation model, and the input feature is a spatial feature vector. Expression (11) is a BERT embedding layer processing model, which processes the normalized spatial feature vector X' K Expression (12) is the Transformer layer encoding (multi-layer self-attention mechanism). BERT uses multi-layer Transformer to model the input and defines the output of the lth layer as H l Expression (13) is the output layer model, and the hidden state H of the last layer is L is sent to the fully connected layer to predict the generalized equivalent energy storage space parameters of electric vehicles. Expression (14) is the loss function, and the mean square error (MSE) is used as the loss function. Expression (15) is the parameter optimization model, and the model parameters are updated using gradient descent (such as Adam optimizer). Expression (16) is, and Expression (17) is the electric vehicle generalized energy storage space parameter identification model based on BERT. Based on the BERT algorithm, X K The data is trained and the spatial parameters are finally identified as shown in formula (17).

[0058]

[0059] H 0 =Embed(X' K ) (11)

[0060] H l = Transformer(H l-1 ) (12)

[0061]

[0062] Among them, X' K is the normalized spatial feature vector, X Kis the spatial feature vector, μ and σ are the feature mean and standard deviation respectively, Embed() is the BERT embedding layer processing function, and the normalized spatial feature vector X' K Processing, H 0 is the initial embedding layer, Transformer() is the Transformer layer encoding function, H l is the output of layer l, is the spatial parameter identified for the i-th sample, y K,i is the real space parameter, H L is the hidden state, N is the total number of samples, L K is the loss value, θ K is the model parameter, α K For learning efficiency, is the gradient descent function, It is a BERT-based generalized energy storage space parameter identification model for electric vehicles. is the final identified electric vehicle generalized energy storage equivalent space parameter, To identify the operating power, To identify the equivalent storage capacity, is the equivalent charging power conversion factor identified, is the identified equivalent discharge power conversion factor, is the equivalent storage capacity conversion factor identified, To identify the sustainable discharge parameters, is the identified equivalent comprehensive efficiency parameter.

[0063] Step 2.2, construct the time dimension electric vehicle generalized energy storage equivalent model, as shown in expression (18), where T dao (t) to T dao1 (t), the electric vehicle is equivalent to energy storage in a charging state. dao1 (t) to T li1 (t), the electric vehicle is equivalent to energy storage and can be charged or discharged. li1 (t) to T li (t), the electric vehicle is equivalent to energy storage in a charging state. dao (t) to T li During the time other than (t), electric vehicles are equivalent to mobile energy storage.

[0064]

[0065] Among them, δ S It is the generalized equivalent state of the electric vehicle, 0 represents the moving state, 1 represents the charging state, and -1 represents the discharging state.

[0066] This embodiment uses the electric vehicle generalized energy storage equivalent time parameter identification model based on the BERT algorithm to train the time information of the electric vehicle collected online to identify the parameters of the electric vehicle generalized energy storage equivalent model, as shown in expressions (19) to (21):

[0067]

[0068]

[0069] in, is a BERT-based generalized energy storage time parameter identification model for electric vehicles, X S Input feature for time, is the final identified equivalent time parameter of generalized energy storage of electric vehicles, is the start time of charging of the electric vehicle of the identified generalized energy storage equivalent model of the electric vehicle, The first full charge time of the identified electric vehicle, To identify the time when the electric car starts charging before leaving the final stage, To identify the departure time of the electric vehicle, It is the generalized equivalent energy storage charging state of the electric vehicle after identification.

[0070] The BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles proposed in this invention can improve prediction accuracy, accurately capture the geographical distribution of electric vehicle energy storage, optimize the regional scheduling of charging and discharging behaviors, deeply explore the temporal laws of electric vehicle energy storage behaviors, and provide dynamic and accurate time series predictions. It supports refined grid regulation, promotes the consumption of new energy, improves the time matching degree between energy storage and new energy generation, enhances the capabilities of virtual power plants and energy Internet, and helps realize cross-regional and cross-time coordinated optimization of energy Internet resources.

[0071] It will be understood by those skilled in the art 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 art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have the same meaning as in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless defined similarly here.

[0072] 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 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 BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles, characterized by: The following operations are included: Collecting time and space information of electric vehicles; A BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles is constructed, and the time and space information of electric vehicles is used to train the BERT-based spatiotemporal equivalent model of generalized energy storage for electric vehicles, including: constructing a spatial dimension of a generalized energy storage equivalent model for electric vehicles, using a BERT-based generalized energy storage equivalent spatial parameter identification model for electric vehicles to train the spatial information of electric vehicles collected online, and identify the parameters of the generalized energy storage equivalent model for electric vehicles; constructing a temporal dimension of a generalized energy storage equivalent model for electric vehicles, using a BERT-based generalized energy storage equivalent temporal parameter identification model for electric vehicles to train the temporal information of electric vehicles collected online, and identify the parameters of the generalized energy storage equivalent model for electric vehicles.

2. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 1, characterized in that: The time information of the electric vehicle includes the time when the electric vehicle starts charging, the time when the electric vehicle is fully charged for the first time, the time when the last stage of charging starts before the electric vehicle leaves, and the time when the electric vehicle leaves, and the expression is: X S (t)=[T dao (t),T dao1 (t),T li1 (t),T li (t)] Among them, X S (t) is the electric time information collected at time t, T dao (t) is the time when the electric vehicle starts charging at time t, T dao1 (t) is the first full charge time of the electric vehicle collected at time t, T li1 (t) is the charging time of the last stage before the electric car leaves the vehicle, collected at time t, T li (t) is the departure time of the electric vehicle collected at time t.

3. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 1, characterized in that: The spatial information of the electric vehicle includes: electric vehicle driving power, electric vehicle auxiliary equipment power, electric vehicle equivalent state of charge, electric vehicle battery rated capacity, electric vehicle actual equivalent charging power, electric vehicle nominal charging power, electric vehicle actual equivalent discharge power, electric vehicle nominal discharge power, electric vehicle actual equivalent energy storage capacity, and electric vehicle maximum discharge power, and the expression is: Among them, X K (t) is the electric space information collected at time t, P drive (t) is the driving power of the electric vehicle collected at time t, P aux (t) is the power of the auxiliary equipment of the electric vehicle collected at time t, SOC eq (t) is the equivalent state of charge of the electric vehicle collected at time t, C bat is the rated capacity of the electric vehicle battery, is the actual equivalent charging power of the electric vehicle collected at time t, is the nominal charging power of the electric vehicle, is the actual equivalent discharge power of the electric vehicle collected at time t, is the nominal discharge power of the electric vehicle, E eff (t) is the actual equivalent energy storage capacity of the electric vehicle collected at time t, is the maximum discharge power of the electric vehicle.

4. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 3, characterized in that: The expression of the generalized energy storage equivalent model of electric vehicles in the spatial dimension is: P run (t)=P drive (t)+P aux (t) IN eq (t)=SOC eq (t)+C bat AND eff (t)=η e ·AND eq (t) or sys =the ch ·or dis Among them, P run (t) is the operating power of the generalized energy storage equivalent model of electric vehicles, E eq (t) is the equivalent storage capacity of the generalized energy storage equivalent model of electric vehicles, η ch is the equivalent charging power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η dis is the equivalent discharge power conversion coefficient of the generalized energy storage equivalent model of electric vehicles, η e is the equivalent storage capacity conversion coefficient of the generalized energy storage equivalent model of electric vehicles, κ dis (t) is the sustainable discharge parameter of the generalized energy storage equivalent model of electric vehicles, η sys It is the equivalent comprehensive efficiency parameter of the generalized energy storage equivalent model of electric vehicles.

5. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 4, characterized in that: The expression of the electric vehicle generalized energy storage equivalent space parameter identification model based on the BERT algorithm is: H0=Embed(X' K ) H l =Transformer(H l-1 ) Among them, X' K is the normalized spatial feature vector, X K is the spatial feature vector, μ and σ are the feature mean and standard deviation respectively, Embed() is the BERT embedding layer processing function, and the normalized spatial feature vector X' K For processing, H0 is the initial embedding layer, Transformer() is the Transformer layer encoding function, H l is the output of layer l, is the spatial parameter identified for the i-th sample, y K,i is the real space parameter, H L is the hidden state, N is the total number of samples, L K is the loss value, θ K is the model parameter, α K For learning efficiency, is the gradient descent function, It is a BERT-based generalized energy storage space parameter identification model for electric vehicles. is the final identified electric vehicle generalized energy storage equivalent space parameter, To identify the operating power, To identify the equivalent storage capacity, is the equivalent charging power conversion factor identified, is the identified equivalent discharge power conversion factor, is the equivalent storage capacity conversion factor identified, To identify the sustainable discharge parameters, is the identified equivalent comprehensive efficiency parameter.

6. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 2, characterized in that: The expression of the generalized energy storage equivalent model of electric vehicles is: Among them, δ S It is the generalized equivalent state of the electric vehicle, 0 represents the moving state, 1 represents the charging state, and -1 represents the discharging state.

7. The BERT-based spatiotemporal prediction method for generalized energy storage of electric vehicles according to claim 6, characterized in that: The expression of the electric vehicle generalized energy storage equivalent time parameter identification model based on the BERT algorithm is: in, is a BERT-based generalized energy storage time parameter identification model for electric vehicles, X S Input feature for time, is the final identified equivalent time parameter of generalized energy storage of electric vehicles, is the start time of charging of the electric vehicle of the identified generalized energy storage equivalent model of the electric vehicle, The first full charge time of the identified electric vehicle, To identify the time when the electric car starts charging before leaving the final stage, To identify the departure time of the electric vehicle, It is the generalized equivalent energy storage charging state of the electric vehicle after identification.

Images