Data processing method and system for mobile energy storage power supply

Abstract

The invention provides a data processing method and system for a mobile energy storage power supply, and relates to the technical field of data processing, and the method comprises the steps: obtaining a charging rescue demand, and determining a nearby mobile energy storage power supply according to the demand; setting a battery capacity demand threshold value, performing battery capacity state evaluation on the nearby mobile energy storage power supplies, and screening out the mobile energy storage power supplies of which the available electric quantity or the residual electric quantity meets the demand threshold value; performing charging and discharging performance evaluation on the mobile energy storage power supply meeting the threshold value, and selecting the mobile energy storage power supply with a first evaluation result for charging rescue; in the charging rescue process, the environment temperature and the power source temperature are considered, and discharging parameters are adjusted till charging rescue is completed; wherein the charge and discharge performance evaluation mainly constructs a charge and discharge performance evaluation model through a time sequence predictor based on sequence core fusion. According to the invention, available equipment can be quickly locked, charging and discharging performance data can be analyzed and evaluated in real time, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a data processing method and system for a mobile energy storage power supply. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] At present, the power grid is gradually using wind power and solar energy for power generation, but at certain times, too much electricity is generated, and the energy storage station cannot store the electricity after reaching the upper limit, which will lead to the loss of some energy. At the same time, in terms of power allocation of the power grid, there are some special time periods when users are at peak power consumption, and power consumption increases sharply, causing the risk of insufficient power supply. Therefore, it is necessary to use a mobile integrated source-grid-load-storage power supply, that is, a mobile energy storage power supply, to store power from the power grid when the power supply is sufficient, and to provide power supply needs when the city power is insufficient, so as to solve the problem of insufficient power supply or power loss. At the same time, it solves the problem of mobile external multi-functional discharge, which can be discharged off-grid, connected to the grid, or discharged to the outside with direct current, and provide rapid charging rescue for electric vehicles.

[0004] Currently, mobile energy storage power sources mostly use lithium batteries as power supply. Due to the high capacity density, high conversion efficiency, low self-discharge rate and long service life of lithium batteries, they have been applied in many fields. Mobile energy storage power sources using lithium batteries as power supply are applied in various scenarios such as rapid charging and rescue of electric vehicles.

[0005] In the multifunctional mobile lithium battery energy storage power supply vehicle system, cloud platform and control method with application number CN201910715723.2, a multifunctional mobile lithium battery energy storage power supply vehicle system is specifically disclosed, including: a mobile carrier composed of a vehicle board and a carriage, the interior of the carriage is divided into two compartments, front and rear, the first compartment at the front is provided with: a lithium battery energy storage cabinet, a charging pile cabinet, and a control cabinet, and the second compartment at the rear is provided with: an isolation transformer cabinet, an electric winding machine, an energy storage converter cabinet, a system distribution cabinet, a battery management system BMS host, and a UPS uninterruptible power supply. This type of power supply system can not only provide power for important loads, but also serve as an emergency power supply, absorb new energy power generation, and charge electric vehicles, and can quickly respond to power supply and charging needs.

[0006] However, the following problems still exist when the above-mentioned mobile energy storage power source is used for charging rescue: Because mobile energy storage power supplies can not only charge and rescue electric vehicles, but also discharge off-grid and on-grid for mains power supply. Therefore, energy storage power supplies may be placed in different places to store power and meet power supply needs. When charging and rescuing electric vehicles, it is necessary to confirm in advance whether there is an available mobile energy storage power supply nearby and locate and distribute it nearby.

[0007] And because the mobile energy storage power supply may be affected by the length of use, collision, etc., causing internal aging, damage, or power supply circuit problems, it is necessary to perform an operating status test before determining whether it can be used for charging rescue.

[0008] In addition, when the mobile energy storage power supply is charging for rescue operations, problems such as overcharging and over-discharging may occur during the discharge process, leading to thermal runaway and further evolving into a deflagration of the energy storage system. Therefore, it is impossible to guarantee the smooth operation of the energy storage power supply during the charging and rescue operation. Once the energy storage power supply fails in operation, it will affect the power supply status, thereby further affecting the rescue efficiency and delaying the rescue progress. Summary of the invention

[0009] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides a data processing method and system for a mobile energy storage power supply, which can be applied to a mobile energy storage power supply device to perform data processing on its battery management system, and judge whether the operating status of the energy storage power supply can be used for charging rescue by performing real-time processing and analysis on the basic data and charging and discharging performance data of the mobile energy storage power supply, and monitor the charging and discharging status during the charging and rescue, thereby improving the operating efficiency of the energy storage power supply during charging and rescue.

[0010] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: A first aspect of the present invention provides a data processing method for a mobile energy storage power supply.

[0011] A data processing method for a mobile energy storage power supply, comprising: Obtain charging rescue needs and determine nearby mobile energy storage power sources based on the needs; Set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power sources, and select mobile energy storage power sources whose available power or remaining power meets the demand threshold; Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; During the charging rescue process, the ambient temperature and power supply temperature are taken into consideration and the discharge parameters are adjusted until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

[0012] A second aspect of the present invention provides a data processing system for a mobile energy storage power supply.

[0013] A data processing system for a mobile energy storage power supply, comprising: The demand acquisition module is configured to acquire charging rescue demand and determine a nearby mobile energy storage power source according to the demand; The energy storage power source evaluation module is configured to set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power sources, and screen out mobile energy storage power sources whose available power or remaining power meets the demand threshold; Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; The process monitoring module is configured to adjust the discharge parameters in consideration of the ambient temperature and the power supply temperature during the charging rescue process until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

[0014] The third aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in a method as described in the first aspect of the present invention are implemented.

[0015] A fourth aspect of the present invention provides a computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in a method as described in the first aspect of the present invention.

[0016] A fifth aspect of the present invention provides a computer program product comprising instructions, which, when running on a computer, enables the computer program to implement the steps in a method as described in the first aspect of the present invention when executed by a processor.

[0017] One or more of the above technical solutions have the following beneficial effects: The present invention can quickly locate a mobile energy storage power supply that can be used for charging and rescue by confirming the battery capacity data of the mobile energy storage power supply through a demand threshold, and can judge the charging and discharging state of the mobile energy storage power supply by processing and analyzing the charging and discharging state data, thereby ensuring safety and high efficiency during rescue, improving the operating efficiency of the energy storage power supply and improving the success rate of rescue.

[0018] When charging rescue is needed for an electric vehicle, the present invention can quickly obtain rescue needs, quickly confirm nearby available and suitable mobile energy storage power sources, locate and distribute them nearby, thereby speeding up the rescue efficiency and improving the success rate of the rescue.

[0019] The present invention uses a new time series predictor based on sequence core fusion to comprehensively predict multivariate time series data based on historical charging and discharging data and environmental information, and evaluates the most suitable and effective mobile energy storage power supply for charging rescue. This method adopts a centralized strategy to learn the interaction between different sequences, thereby achieving the most advanced performance in multivariate prediction tasks, introducing a new star aggregation scheduling module to learn the interaction between time series, reducing the overall complexity of the model, and being able to more effectively process large data sets with multiple sequences.

[0020] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0022] Figure 1 This is a flow chart of a data processing method for a mobile energy storage power supply according to the first embodiment of the present invention; Figure 2 This is a structural diagram of a charging and discharging performance evaluation model in a data processing method for a mobile energy storage power supply according to Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0024] It should be noted that the terms used herein are for describing specific embodiments only and are not intended to be limiting of exemplary embodiments according to the present invention.

[0025] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0026] Embodiment 1 This embodiment discloses a data processing method for a mobile energy storage power supply, which can be applied to a multifunctional mobile energy storage power supply device, and performs battery management through a battery management system, and processes and analyzes the data obtained in the battery management system, such as Figure 1 As shown, specifically including: Step 1: Obtain charging rescue needs and determine nearby mobile energy storage power sources based on the needs; Step 2: Set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power supplies, and select mobile energy storage power supplies whose available power or remaining power meets the demand threshold; Step 3: Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; Step 4: During the charging rescue process, consider the ambient temperature and power supply temperature and adjust the discharge parameters until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

[0027] In order to more clearly illustrate this embodiment, a data processing method for a mobile energy storage power supply can be specifically described as follows: Step 1: Obtain charging rescue needs and determine nearby mobile energy storage power sources based on the needs.

[0028] Specifically, when an electric car needs fast charging and rescue, the charging and rescue requirements including the vehicle model, vehicle battery capacity, and vehicle location will be uploaded to the system to initiate a new distress message.

[0029] After obtaining the charging rescue demand uploaded by the electric vehicle, the mobile energy storage power source in idle state within a certain distance nearby (for example, within a radius of 10 to 20 kilometers) is determined according to the vehicle location positioning in the demand.

[0030] By clearly defining rescue needs, narrowing the range of options, and reducing the amount of parameters for data processing, it is possible to quickly lock in available mobile energy storage power sources and implement them for rescue.

[0031] Step 2: Set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power supplies, and select mobile energy storage power supplies whose available power or remaining power meets the demand threshold.

[0032] Specifically, according to the vehicle battery capacity and vehicle model in the uploaded charging rescue demand, a minimum battery capacity demand threshold that can meet the demand is set, and the battery capacity of the mobile energy storage power sources in idle state within a certain distance nearby is evaluated.

[0033] Battery capacity evaluation, as follows: 1. Make sure the energy storage power supply is fully charged or not fully charged.

[0034] 2. When the energy storage power source is fully charged, calculate the available power.

[0035] The formula for calculating the available power of the energy storage power supply is: Available power = rated capacity of energy storage power station × cycle efficiency × number of charge and discharge times; Among them, the rated capacity of the energy storage station refers to the maximum energy it can store, usually in kilowatt-hours (kWh); the cycle efficiency refers to the proportion of energy lost during the charging and discharging process of the energy storage station to the total energy, usually expressed as a percentage; the number of charge and discharge times refers to the number of times the energy storage station completes charging and discharging during its service life.

[0036] 3. When the energy storage power source is not fully charged, determine the remaining power.

[0037] Through the battery's charge and discharge curve, the amount of electricity used can be calculated, thereby estimating the remaining power.

[0038] When it is determined that the available power or remaining power meets the demand threshold, the mobile energy storage power supplies whose available power or remaining power is higher than the set minimum battery capacity demand threshold can be screened out for subsequent charging and discharging performance evaluation.

[0039] By confirming the most important power conditions, the selection range can be further narrowed, the parameters of data processing can be reduced, and the efficiency of model operation can be improved.

[0040] Step 3: Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue.

[0041] Step 301: Obtain a data set for evaluating charging and discharging performance of a mobile energy storage power source.

[0042] Specifically, obtain the basic performance data of the mobile energy storage power supply, including: rated capacity, rated charge and discharge time, and rated cycle life, etc.

[0043] Calculate and obtain usage data of mobile energy storage power supply: including capacity attenuation index, charging coefficient and discharging coefficient, etc.

[0044] Then obtain the environmental data of the internal environment of the mobile energy storage power supply, the internal environmental data including the humidity value, temperature value, etc. within a certain unit time.

[0045] Finally, the historical charge and discharge record data with time sequence within a certain unit time is obtained, including the voltage, current, temperature, power, etc. during charge and discharge.

[0046] Step 302: construct a charge and discharge performance evaluation model based on the time series predictor fused with the sequence core.

[0047] The time series predictor based on sequence core fusion, SOFTS (Series-core Fused TimeSeries), is actually a model based on a multi-layer perceptron (MLP). It can model the relationship between channels by fusing the sequence representation of multiple channels with the core representation of the entire multivariate sequence. It mainly adopts a centralized strategy to learn the interaction between different sequences, thereby achieving better performance in multivariate prediction tasks. The overall complexity of the model is low.

[0048] The model proposes to build on the STAR (STar Aggregate-Redistribute) module. The STAR module is designed as a centralized structure that uses a core to aggregate and exchange information from various channels, extract serial correlations between different channels, and finally make predictions about the future of each channel through a linear layer. Compared with distributed structures such as the attention mechanism, STAR not only reduces complexity, but also improves robustness to abnormal situations in the channel.

[0049] The sequence representation of multiple channels first needs to be mapped through an MLP, and then a core vector is obtained through a pooling operation of a pooling layer. This core vector combines the characteristics of different sequences and represents the global information of the entire sequence. This core vector is then concatenated to each representation and fused with another MLP layer. The computational complexity of the entire process is only linearly related to the number of channels, sequence length, etc.

[0050] like Figure 2 As shown, the specific steps are as follows: Step 3021: Based on the data set for charging and discharging performance evaluation of the mobile energy storage power source obtained in step 301 as multi-channel data input, define the size of the verification set and the test set as well as the frequency of the data and the prediction time span.

[0051] Step 3022: normalize and embed the data set for charging and discharging performance evaluation of the mobile energy storage power source obtained in step 301 to obtain a sequence representation of each channel.

[0052] Specifically, normalization is used to calibrate the distribution of the input sequence. Using reversible instance normalization (RevIn), the sequence data is centered to zero mean and calculated with unit variance. Each series is then embedded separately. And the normalization of the prediction sequence is reversed.

[0053] Specifically, sequence embedding refers to embedding the sequence of each channel using a linear projection.

[0054] Step 3023, the embedded sequence is passed through an MLP layer and a pooling layer, and then the learned representations are concatenated to form a core vector, which is repeated and concatenated.

[0055] Specifically, channel correlation is captured through multi-layer STAR modules. First, the sequence representation is aggregated through MLP and pooling layers to obtain the global core vector representation. Then the core vector representation is repeatedly connected to each sequence for redistribution. Finally, each sequence that encodes local information is fused through an MLP layer.

[0056] Step 3024, information not captured by the MLP layer and the pooling layer can also be added to the core vector representation through the residual connection. During the fusion operation, the core vector representation and its corresponding series of residuals are sent through the MLP layer.

[0057] Step 3025: After passing through N layers of STAR modules, a linear predictor is used through a linear layer to generate a prediction result for each sequence.

[0058] Specifically, a multiple linear regression model can be used to estimate parameters using the least squares method.

[0059] Step 3026: Finally, the prediction results of each sequence are weighted and concatenated to obtain the overall evaluation prediction result.

[0060] Specifically, a corresponding weight value is assigned according to the different importance of each sequence, and finally the prediction results of each sequence are weighted and fused to obtain the overall evaluation prediction result.

[0061] The above model building process is performed on one of the mobile energy storage power supplies that meets the threshold conditions. When there are multiple mobile energy storage power supplies that meet the conditions, the evaluation results of the energy storage power supplies that meet the conditions need to be ranked. The mobile energy storage power supply that ranks first, that is, the one with the best charging and discharging effect after evaluation, is selected for this charging rescue.

[0062] Through the new time series predictor based on sequence core fusion, comprehensive prediction of multivariate time series data based on historical charging and discharging data and environmental information can be performed to evaluate the most suitable and effective mobile energy storage power supply for charging rescue. This method adopts a centralized strategy to learn the interaction between different sequences, thereby achieving the most advanced performance in multivariate prediction tasks, introducing a new star aggregation scheduling module to learn the interaction between time series, reducing the overall complexity of the model, and being able to more effectively process large data sets with multiple sequences. And because the overall complexity of the model is reduced, the model operation efficiency is improved, and fast calculations can be performed, which once again reduces the waiting time for charging rescue and improves the overall efficiency of rescue.

[0063] Step 4: During the charging rescue process, consider the ambient temperature and power supply temperature and adjust the discharge parameters until the charging rescue is completed.

[0064] Specifically, during the charging rescue process, the mobile energy storage power supply is mainly in a discharging state. If the battery voltage is lower than the discharge cut-off voltage and continues to discharge, it may cause over-discharge of the battery and cause irreversible damage to the battery. The battery management system of the device usually takes corresponding measures when the battery voltage approaches the discharge cut-off voltage, such as reminding the user to charge or automatically shutting down, to protect the battery.

[0065] Therefore, when using mobile energy storage power supplies for charging rescue, it is necessary to set discharge parameters for the power supply, monitor the ambient temperature in real time, and adjust the discharge parameters to ensure the safety performance of the battery.

[0066] At the same time, the PCS module in the mobile energy storage power source monitors the status of the battery components, such as voltage, current, temperature, etc., and performs troubleshooting when an abnormal state occurs. The PCS can also be controlled through the BMS to adjust the charge and discharge power and improve the charge and discharge efficiency and performance of the battery.

[0067] When using lithium batteries, you should try to ensure that their working environment is within the specified temperature range to ensure the performance and safety of the battery. If the temperature exceeds the specified range, the performance of the battery may be affected and even safety problems may occur.

[0068] In this embodiment, a data processing method for a mobile energy storage power supply can be applied to a multifunctional mobile energy storage power supply device, and the battery management is performed through the battery management system, and the data in the battery management system is processed and analyzed.

[0069] Embodiment 2 The purpose of this embodiment is to provide a data processing system for a mobile energy storage power supply.

[0070] A data processing system for a mobile energy storage power supply, comprising: The demand acquisition module is configured to acquire charging rescue demand and determine a nearby mobile energy storage power source according to the demand; The energy storage power source evaluation module is configured to set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power sources, and screen out mobile energy storage power sources whose available power or remaining power meets the demand threshold; Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; The process monitoring module is configured to adjust the discharge parameters in consideration of the ambient temperature and the power supply temperature during the charging rescue process until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

[0071] Embodiment 3 The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the program.

[0072] Embodiment 4 The purpose of this embodiment is to provide a computer-readable storage medium.

[0073] A computer-readable storage medium stores a computer program, which executes the steps of the above method when executed by a processor.

[0074] Embodiment 5 The purpose of this embodiment is to provide a computer program product containing instructions, which, when running on a computer, enables the computer to execute the methods and functions involved in any of the above embodiments. The steps involved in the apparatus of the above embodiment correspond to the method embodiment 1, and the specific implementation method can refer to the relevant description part of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0075] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0076] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A data processing method for a mobile energy storage power supply, characterized in that: include: Obtain charging rescue needs and determine nearby mobile energy storage power sources based on the needs; Set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power sources, and select mobile energy storage power sources whose available power or remaining power meets the demand threshold; Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; During the charging rescue process, the ambient temperature and power supply temperature are taken into consideration and the discharge parameters are adjusted until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

2. A data processing method for a mobile energy storage power supply according to claim 1, characterized in that: The battery capacity status evaluation specifically includes: determining whether the power of the energy storage power supply is fully charged or not fully charged; when the power of the energy storage power supply is fully charged, calculating the available power; when the power of the energy storage power supply is not fully charged, determining the remaining power; after determining that the available power or the remaining power meets the demand threshold, screening out the mobile energy storage power supplies whose available power or remaining power is higher than the set minimum battery capacity demand threshold for subsequent charge and discharge performance evaluation.

3. A data processing method for a mobile energy storage power supply according to claim 1, characterized in that: The charge and discharge performance evaluation mainly constructs a charge and discharge performance evaluation model by a time series predictor based on sequence core fusion, specifically including: normalizing and embedding the acquired data set for charge and discharge performance evaluation of the mobile energy storage power supply; Pass the embedded sequence through an MLP layer and a pooling layer, then concatenate the learned representations to form a core vector, repeat and concatenate; Each sequence that encodes local information is fused through an MLP layer; A linear predictor is used through the linear layer to generate the prediction results for each sequence; Finally, the prediction results of each sequence are weighted and concatenated to obtain the overall evaluation prediction results.

4. A data processing method for a mobile energy storage power supply as claimed in claim 3, characterized in that: The obtained data set for evaluating the charging and discharging performance of the mobile energy storage power source is normalized and embedded. Specifically, the distribution of the input sequence is calibrated using normalization: the sequence data is concentrated to zero mean using reversible instance normalization and calculated according to unit variance; each series is then embedded separately; and the normalization of the prediction sequence is reversed; Sequence embedding of a dataset acquired for charging and discharging performance evaluation of a mobile energy storage power source refers to embedding the sequence of each channel using a linear projection.

5. A data processing method for a mobile energy storage power supply according to claim 1, characterized in that: When using mobile energy storage power supplies for charging rescue, it is necessary to set discharge parameters for the power supply, monitor the ambient temperature in real time, and adjust the discharge parameters; monitor the status of the battery components through the PCS module in the mobile energy storage power supply, and perform troubleshooting.

6. A data processing method for a mobile energy storage power supply as claimed in claim 3, characterized in that: The linear layer uses a linear predictor to generate the prediction result of each sequence, specifically, a multivariate linear regression model is used to perform parameter estimation using the least squares method.

7. A data processing system for a mobile energy storage power supply, characterized in that: include: The demand acquisition module is configured to acquire charging rescue demand and determine a nearby mobile energy storage power source according to the demand; The energy storage power source evaluation module is configured to set a battery capacity demand threshold, evaluate the battery capacity status of nearby mobile energy storage power sources, and screen out mobile energy storage power sources whose available power or remaining power meets the demand threshold; Evaluate the charging and discharging performance of the mobile energy storage power supplies that meet the threshold, and select the mobile energy storage power supply with the highest evaluation result for charging rescue; The process monitoring module is configured to adjust the discharge parameters in consideration of the ambient temperature and the power supply temperature during the charging rescue process until the charging rescue is completed; Among them, the charging and discharging performance evaluation mainly constructs a charging and discharging performance evaluation model through a time series predictor based on sequence core fusion, and performs performance evaluation based on the basic information data of the energy storage power source, environmental information time series data, and historical charging and discharging time series data.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the method described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 6 are performed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images