Charging demand dynamic prediction method and system

Abstract

The invention relates to a charging demand dynamic prediction method and system, and relates to the technical field of charging prediction, and the method comprises the steps: obtaining the actual temperature and actual charging power of a battery in a target vehicle, and obtaining an actual vehicle portrait of the target vehicle; based on the actual temperature, the historical down-regulation amplitude of the plurality of historical vehicle charging powers and the real-time temperature of the battery before the historical down-regulation amplitude appears, determining whether the target vehicle has the risk of power down-regulation; if it is determined that the target vehicle has the risk of power down-regulation, the appropriate down-regulation amplitude of the charging power of the target vehicle is determined, and the initial charging demand of the target vehicle after the current time is determined according to the actual charging power and the appropriate down-regulation amplitude; and obtaining an actual SOC value of the battery in the target vehicle, and adjusting and optimizing the initial charging demand according to the actual SOC value to obtain a final charging demand of the target vehicle. The method and the device have the effect of improving the charging demand prediction accuracy.

Description

Technical Field

[0001] This application relates to the field of charging prediction technology, specifically to a method and system for dynamic prediction of charging demand. Background Technology

[0002] The charging demand of new energy vehicles (NEVs) comprehensively reflects a series of core and scenario-based needs arising from users' demands for battery replenishment during vehicle use. Among these, the charging load during charging can be understood as the most common charging demand for NEVs. The significance of predicting NEV charging demand lies in the coordinated optimization of multiple core scenarios. It serves as a crucial basis for supporting the scientific planning and efficient operation of charging infrastructure, and is also an important foundation for improving the user charging experience, ensuring stable grid operation, and promoting the sustainable development of the NEV industry. Therefore, effectively predicting the charging demand of NEVs is a problem that urgently needs to be solved.

[0003] Currently, the common method for predicting the charging demand of new energy vehicles is to collect data on a single dimension related to the charging demand, such as the vehicle's battery temperature, and then analyze the data to predict the charging demand. However, in complex scenarios, the dimensions related to the charging demand of new energy vehicles are diverse, and relying solely on data from a single dimension to predict charging demand results in poor accuracy. Summary of the Invention

[0004] To improve the accuracy of charging demand forecasting, this application provides a method and system for dynamic charging demand forecasting.

[0005] The first aspect of this application provides a method for dynamically predicting charging demand, specifically including: The actual temperature and actual charging power of the battery in the target vehicle are obtained, and the actual vehicle profile of the target vehicle is obtained. Based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred, it is determined whether the target vehicle is at risk of power reduction. The vehicle profile of the historical vehicles is the same as the actual vehicle profile, and the historical reduction range is the charging power reduction range triggered by battery temperature. If it is determined that the target vehicle is at risk of power reduction, then the appropriate reduction range of the target vehicle's charging power is determined, and based on the actual charging power and the appropriate reduction range, the initial charging demand of the target vehicle after the current time is determined. Obtain the actual SOC value of the battery in the target vehicle, and adjust and optimize the initial charging demand based on the actual SOC value to obtain the final charging demand of the target vehicle.

[0006] By employing the aforementioned technical solution, the actual temperature and charging power of the target vehicle's battery, along with the vehicle's actual profile, are obtained. Based on historical reduction rates and the real-time battery temperature before the occurrence of historical reduction rates, the likelihood of the target vehicle's battery triggering a reduction in charging power due to temperature fluctuations at its current actual temperature is analyzed. This allows for a more accurate determination of whether the target vehicle faces a risk of power reduction. Furthermore, when a risk of power reduction is identified, the most likely reduction rate in the target vehicle's charging power after the current situation is determined, i.e., the appropriate reduction rate. Then, combining the appropriate reduction rate and the current actual charging power, the initial charging demand of the target vehicle is predicted relatively accurately from the perspective of battery temperature. Finally, since the actual SOC value of the target battery during charging is also related to charging demand, the initial charging demand is adjusted and optimized based on the actual SOC value. This allows for the prediction of the target vehicle's charging demand from multiple dimensions, thereby improving the accuracy of charging demand prediction.

[0007] In one implementation, determining whether the target vehicle is at risk of power reduction based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred specifically includes: Based on the historical reduction range of charging power for multiple historical vehicles, at least one reduction range is determined, wherein the reduction range is the range in which the historical reduction range of the historical vehicles is likely to fall; Filter at least one target reduction range within the reduction range from all the historical reduction ranges, and determine at least one battery temperature range corresponding to the reduction range based on the real-time temperature corresponding to each target reduction range. The battery temperature range is a temperature range that is easy to trigger power reduction. Determine a first weighting coefficient for the range of decrease, and determine a second weighting coefficient for each of the battery temperature ranges; Based on the actual temperature, the first weighting coefficient, and each of the second weighting coefficients, it is determined whether the target vehicle is at risk of power reduction.

[0008] In one implementation, determining whether the target vehicle is at risk of power reduction based on the actual temperature, the first weighting coefficient, and each of the second weighting coefficients specifically includes: If the battery temperature range corresponding to the reduction range includes the actual temperature, then the reduction range is determined as an important reduction range, and the battery temperature range that includes the actual temperature is determined as an important temperature range. The first risk value is obtained by multiplying the first weighting coefficient of at least one of the important downward adjustment ranges with the second weighting coefficient of the corresponding important temperature range; The first risk values ​​are summed to obtain the first overall risk value, and the first overall risk value is compared with the preset risk threshold. If the first overall risk value is greater than the risk threshold, it is determined that the target vehicle is at risk of power reduction. If the first overall risk value is not greater than the risk threshold, it is determined that the target vehicle does not have the risk of power reduction.

[0009] In one implementation, determining the appropriate reduction range of the target vehicle's charging power specifically includes: Select the largest first risk value from all the first risk values; The minimum value in the important reduction range corresponding to the maximum first risk value is determined as the appropriate reduction range for the charging power of the target vehicle.

[0010] In one embodiment, the method further includes: Obtain the non-trigger temperature range of the battery cooling system of the target vehicle, wherein the non-trigger temperature range is the temperature range of the battery when the battery cooling system is not triggered; The battery temperature range included in the non-trigger temperature range is determined as the key temperature range. If there is at least one key temperature range among the battery temperature ranges corresponding to the reduction range, then the reduction range is determined as the key reduction range. The second risk value is obtained by multiplying the first weighting coefficient of the key downward adjustment range with the second weighting coefficient of the corresponding key temperature range. The second risk value corresponding to each of the key reduction ranges is summed to obtain the second overall risk value. If the second overall risk value is not greater than the preset risk threshold, then the non-trigger temperature range is verified to be correct.

[0011] In one embodiment, the method further includes: Obtain the non-trigger temperature range of the battery cooling system of the target vehicle, wherein the non-trigger temperature range is the temperature range of the battery when the battery cooling system is not triggered; The third risk value is obtained by multiplying the first weighting coefficient of each of the aforementioned downward adjustment ranges with the second weighting coefficient of the corresponding battery temperature ranges. The third overall risk value is obtained by summing the third risk values ​​corresponding to each target temperature range among all the third risk values ​​corresponding to the lowering ranges. There is an intersection among the target temperature ranges. If the third overall risk value is greater than the preset risk threshold, then the temperature intersection interval of each target temperature interval is determined. If at least one of the temperature intersection intervals does not intersect with the non-trigger temperature interval, the non-trigger temperature interval is verified to be correct.

[0012] In one embodiment, the method further includes: When the charging power of the target vehicle is reduced, the actual reduction range of the charging power of the target vehicle is obtained, the trigger temperature that triggers the actual reduction range is obtained, and the reduction range range in which the actual reduction range is located is determined as the reference reduction range range. If the battery temperature range corresponding to the reference reduction range includes the trigger temperature, then the corresponding battery temperature range is determined as the reference temperature range, and the first weighting coefficient of the reference reduction range is multiplied by the second weighting coefficient of the reference temperature range to obtain the fourth risk value. If the fourth risk value is greater than the preset product threshold, the non-trigger temperature range of the battery cooling system of the target vehicle is obtained, and if the trigger temperature is not in the non-trigger temperature range, the non-trigger temperature range is verified to be correct. The non-trigger temperature range is the temperature range in which the battery temperature is when the battery cooling system is not triggered.

[0013] A second aspect of this application provides a dynamic charging demand prediction system, specifically comprising: The data acquisition module is used to acquire the actual temperature and actual charging power of the battery in the target vehicle, and to acquire the actual vehicle profile of the target vehicle. The risk assessment module is used to determine whether the target vehicle is at risk of power reduction based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred. The vehicle profile of the historical vehicles is the same as the profile of the actual vehicle, and the historical reduction range is the reduction range of charging power triggered by battery temperature. The first prediction module is used to determine the appropriate reduction range of the charging power of the target vehicle if it is determined that there is a risk of power reduction of the target vehicle, and to determine the initial charging demand of the target vehicle after the current time based on the actual charging power and the appropriate reduction range. The second prediction module is used to obtain the actual SOC value of the battery in the target vehicle, adjust and optimize the initial charging demand based on the actual SOC value, and obtain the final charging demand of the target vehicle.

[0014] By employing the above technical solution, the data acquisition module obtains the actual temperature, actual charging power, and actual vehicle profile. Then, the risk assessment module, based on the actual temperature, historical reductions in charging power for multiple vehicles, and the real-time battery temperature before the historical reduction occurred, determines whether the target vehicle faces a risk of power reduction. Next, the first prediction module, upon determining the risk of power reduction, determines an appropriate reduction range in the target vehicle's charging power and, based on the actual charging power and the appropriate reduction range, determines the initial charging demand for the target vehicle after the current time. Finally, the second prediction module obtains the actual SOC value of the battery in the target vehicle and adjusts and optimizes the initial charging demand based on the actual SOC value to obtain the final charging demand for the target vehicle.

[0015] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when loaded and executed by a processor, performs the steps of the method described in any one of the first aspects.

[0016] A fourth aspect of this application provides an electronic device, specifically comprising: A processor, a memory, and a computer program stored in the memory and capable of running on the processor, the processor being configured to load and execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of the first aspects.

[0017] In summary, this application includes at least one of the following beneficial technical effects: After obtaining the actual temperature and charging power of the target vehicle's battery, as well as the vehicle's profile, the analysis considers historical reduction rates and the real-time battery temperature before those reductions. It then assesses the likelihood of a charging power reduction triggered by battery temperature at the current actual temperature, thus accurately determining if the target vehicle faces a risk of power reduction. Further, when a power reduction risk is identified, the most likely reduction rate (ideal reduction rate) is determined. Then, combining the appropriate reduction rate with the current actual charging power, the initial charging demand of the target vehicle is predicted relatively accurately from the perspective of battery temperature. Finally, since the actual State of Charge (SOC) value of the target battery during charging is also related to charging demand, the initial charging demand is adjusted and optimized based on the actual SOC value. This allows for prediction of the target vehicle's charging demand from multiple dimensions, thereby improving the accuracy of charging demand prediction. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a dynamic charging demand prediction method provided in an embodiment of this application. Figure 2 This is a schematic diagram illustrating the relationship between the reduction range and the battery temperature range provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a dynamic charging demand prediction system provided in an embodiment of this application; Figure 4 This is a schematic diagram of another charging demand dynamic prediction system provided in an embodiment of this application.

[0019] Explanation of reference numerals in the attached diagram: 11. Data acquisition module; 12. Risk assessment module; 13. First prediction module; 14. Second prediction module; 15. First verification module; 16. Second verification module; 17. Third verification module. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0021] In the description of the embodiments of this application, words such as "exemplarily," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0022] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0023] See Figure 1This application discloses a flowchart of a method for dynamically predicting charging demand, applicable to a dynamic charging demand prediction system, and can also be implemented using a computer program. This computer program can be integrated into the application or run as a standalone utility application, specifically including: S101: Obtain the actual temperature and actual charging power of the battery in the target vehicle, and obtain the actual vehicle profile of the target vehicle.

[0024] Specifically, in this embodiment of the application, the target vehicle is a new energy vehicle currently charging at a charging pile in a charging station. The actual vehicle profile can be understood as "labeling" the target vehicle with a set of core attributes (hardware, status, usage habits, etc.) to accurately outline its "full features", just like giving a person a comprehensive description of "personality + behavior + physical condition", which makes it easy to quickly judge its performance, risk points, etc.

[0025] A feasible way to obtain the actual temperature and actual charging power of a target vehicle's battery is to obtain the actual temperature and actual charging power of the target vehicle's battery through a charging pile that is charging the target vehicle. The main reason is that, according to the national standard charging protocol, the charging pile and the vehicle's battery management system (BMS) will continuously communicate through CAN bus and other means. As core safety and control parameters, battery temperature and charging power will be exchanged and transmitted in real time. Therefore, the actual temperature and actual charging power of the target vehicle's battery can be obtained through the charging pile.

[0026] Furthermore, a feasible method for obtaining the actual vehicle profile of the target vehicle is as follows: Obtain the target vehicle's hardware information, vehicle status information, and usage habit information. Hardware information includes, but is not limited to, battery type and capacity; vehicle status information includes, but is not limited to, vehicle age and battery health; usage habit information includes, but is not limited to, frequency of fast and slow charging, and vehicle usage environment (high temperature in the south / low temperature in the north). Then, input this three-dimensional information into a pre-defined profile prediction model to obtain the actual vehicle profile. The profile prediction model is a trained logistic regression model or a random forest model. The training process is briefly described as follows: Information from different vehicles labeled with vehicle profiles in the three dimensions is used as sample data. The sample data is divided into training, validation, and test sets. The model is trained using these datasets, with continuous parameter tuning to minimize the model's loss function until the model converges. The loss function is the cross-entropy loss function, which is existing technology and will not be elaborated upon here.

[0027] S102: Based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred, determine whether the target vehicle is at risk of power reduction.

[0028] Specifically, the historical vehicle profile is the same as the current vehicle profile, and the historical reduction range refers to the reduction in charging power triggered by battery temperature. This reduction in charging power triggered by battery temperature can be understood as a protective action by the vehicle's BMS (Battery Management System) to actively "slow down" charging when the battery temperature deviates from the ideal range. The core principle is to reduce battery heat generation by reducing power, preventing further temperature increases that could lead to accelerated aging or thermal runaway. Essentially, it's a balancing strategy of "safety over charging speed." It should be noted that the fault codes corresponding to the power reduction in the historical vehicle can be obtained through the vehicle's BMS system. For example, fault codes such as "P1B00 - Battery temperature too high," "P1B01 - Cell voltage imbalance," and "P1B02 - Thermal management system fault" can all directly determine the cause of the power reduction.

[0029] Based on historical charging records cached in the database, the system obtains the historical reduction range of charging power for multiple vehicles, as well as the real-time battery temperature before each historical reduction occurred, i.e., the temperature that triggered the power reduction. Furthermore, the reduction range of charging power can be understood as the percentage of power reduction compared to the power before the reduction. For example, if a vehicle's current charging power is 250kW, and the battery temperature rises to 50°C due to fast charging or a high-temperature environment, the BMS will activate strong current limiting protection, directly reducing the charging power to 120kW, a reduction of 52%. The historical charging records include information such as the temperature at which the power reduction was triggered and the magnitude of the reduction for different actual vehicle profiles.

[0030] Clustering algorithms are used to perform cluster analysis on multiple historical reduction magnitudes, dividing them into multiple ranges that cover all historical reduction magnitudes. For example, there are multiple historical reduction magnitudes in the following order: 50%, 51%, 55%, 42%, 43%, and 45%. Therefore, the resulting ranges are 50%~55% and 40%~45%. Next, the number of historical reduction magnitudes contained in each range is counted and compared with a preset threshold. If the number exceeds the threshold, it indicates that the corresponding range contains a large number of historical reduction magnitudes, suggesting that the actual vehicle profile is more likely to experience power reductions triggered by temperature within that range. Therefore, this range is defined as the reduction magnitude interval, i.e., the interval where historical reduction magnitudes are likely to fall.

[0031] Furthermore, from all historical reduction ranges, at least one target reduction range falling within a single reduction range is selected. Then, a clustering algorithm is used to perform cluster analysis on the real-time temperatures (battery temperatures that trigger the target reduction in charging power) corresponding to each target reduction range, dividing the data into multiple temperature ranges covering all selected real-time temperatures. Next, the number of real-time temperatures contained in each temperature range is counted. If the number exceeds a preset threshold, the temperature range is determined as the battery temperature range, i.e., the temperature range that is likely to trigger a reduction in vehicle charging power based on the actual vehicle profile.

[0032] A first weighting coefficient is determined for each reduction range. This first weighting coefficient is the ratio of the number of instances corresponding to this reduction range to the sum of the numbers corresponding to all reduction ranges. This first weighting coefficient represents the probability that the charging power reduction triggered by battery temperature in the actual vehicle profile falls within this reduction range. Then, a second weighting coefficient is determined for each battery temperature range corresponding to this reduction range. This second weighting coefficient is the ratio of the number of instances corresponding to a single battery temperature range to the sum of the numbers corresponding to all battery temperature ranges. This second weighting coefficient represents the probability that the corresponding battery temperature range will trigger a power reduction. For example, there are three price reduction ranges: A, B, and C. Range A has 10 corresponding ranges, range B has 30, and range C has 60. Therefore, the first weighting coefficient for range A is 10 / (10+30+60) = 0.1. Range A also corresponds to battery temperature ranges a1, a2, and a3. Battery temperature range a1 has 40 corresponding ranges, a2 has 40, and a3 has 20. Therefore, the second weighting coefficient for battery temperature range a1 is 40 / (40+40+20) = 0.4. See details in [link to relevant documentation]. Figure 2 In the figure, a1, a2, etc. are all battery temperature ranges corresponding to the downward adjustment range A.

[0033] Finally, based on the actual temperature, the first weighting coefficient, and the second weighting coefficient, it is determined whether the current target vehicle faces the risk of a power reduction (power reduction triggered by battery temperature). One feasible implementation is as follows: if the battery temperature range corresponding to a single reduction range includes the actual temperature, then that reduction range is determined as a significant reduction range, i.e., the range in which the target vehicle's charging power reduction might occur, and at least one significant reduction range exists. Simultaneously, the battery temperature range containing the actual temperature is determined as a significant temperature range. Further, the first weighting coefficient of each significant reduction range is multiplied by the second weighting coefficient of the corresponding significant temperature range to obtain a first risk value. The first risk value characterizes the probability that, at the actual battery temperature, the target vehicle will trigger a power reduction, and the power reduction will fall within that significant reduction range.

[0034] Then, the first risk values ​​corresponding to each significant reduction range are summed to obtain the first overall risk value. This first overall risk value characterizes the overall probability of the target vehicle triggering a power reduction due to battery temperature under actual conditions. If the first overall risk value is greater than a preset risk threshold, it indicates a high probability that the target vehicle will trigger a power reduction due to battery temperature, thus confirming a risk of power reduction for the target vehicle. Conversely, if the first overall risk value is not greater than the risk threshold, it indicates a low probability that the target vehicle will trigger a power reduction due to battery temperature, thus confirming no risk of power reduction for the target vehicle. The risk threshold is the critical value used to define the probability of a vehicle triggering a power reduction due to battery temperature.

[0035] S103: If it is determined that there is a risk of power reduction for the target vehicle, then determine the appropriate reduction range of the target vehicle's charging power, and determine the initial charging demand of the target vehicle after the current time based on the actual charging power and the appropriate reduction range.

[0036] Specifically, if it is determined that the target vehicle is at risk of power reduction, then the appropriate reduction range of the target vehicle's charging power after the current state is determined, that is, the most likely reduction range of charging power. In this embodiment of the application, one feasible implementation method is: select the largest first risk value from various first risk values. The important reduction range corresponding to the largest first risk value can be understood as: the reduction range in which the power reduction triggered by the battery at the current actual temperature is most likely to be located. Then, the minimum value in the important reduction range corresponding to the largest first risk value is determined as the appropriate reduction range of the target vehicle's charging power.

[0037] Once the appropriate reduction range is determined, the current actual charging power is multiplied by the appropriate reduction range to obtain the initial charging demand of the target vehicle. This allows for a more accurate prediction of the target vehicle's charging demand from the perspective of battery temperature.

[0038] In other embodiments, the non-triggered temperature range of the target vehicle's battery cooling system is obtained, i.e., the temperature range where the battery temperature is when the battery cooling system is not triggered. One feasible method is to determine the non-triggered temperature range through the target vehicle's BMS, since the BMS continuously collects battery temperature and stores thermal management strategy parameters, including the temperature threshold for the battery cooling system to start. By comparing the threshold with the temperature data under normal operating conditions, the non-triggered temperature range is determined. Further, the battery temperature range included in the non-triggered temperature range is determined as the key temperature range. If a key temperature range exists among the various battery temperature ranges corresponding to a single reduction range, then that reduction range is determined as the key reduction range. There is at least one key reduction range. Then, the first weighting coefficient of a single key reduction range is multiplied by the second weighting coefficient of the corresponding key temperature range to obtain a second risk value. The second risk value characterizes the probability that when the battery temperature is in the key temperature range, the target vehicle will trigger a power reduction during charging, and the reduction range will be within the corresponding key reduction range. Next, the second risk values ​​corresponding to each key reduction range are summed to obtain the second overall risk value. This second overall risk value characterizes the overall probability of trigger power reduction when the target vehicle's battery temperature is within the non-trigger temperature range. Finally, the second overall risk value is compared with a risk threshold. If the second overall risk value is not greater than the risk threshold, it indicates that the overall probability of trigger power reduction is low when the target vehicle's battery temperature is within the non-trigger temperature range. This suggests that the temperature within the non-trigger temperature range is relatively safe, and heat dissipation through the battery cooling system is unnecessary. Therefore, the verification of the target vehicle's non-trigger temperature range is correct. It should be noted that after long-term use, battery aging and deterioration of cooling components may cause the initial non-trigger temperature range to become unsuitable. Verifying the non-trigger temperature range confirms whether it can still prevent battery "temperature runaway." For example, if the upper limit of the non-trigger temperature range is 35℃, and the battery is already showing a slow temperature rise at 35℃ due to decreased heat dissipation efficiency, the range can be adjusted downwards in time to avoid overheating risks.

[0039] In one embodiment, the first weighting coefficient of each reduction range is multiplied by the second weighting coefficient of the corresponding battery temperature range to obtain the third risk value corresponding to that reduction range. The third risk value represents the probability that the charging power reduction will be triggered when the vehicle battery temperature is within the corresponding battery temperature range, and the reduction range is within the reduction range. The third risk values ​​corresponding to each target temperature range are summed among the third risk values ​​corresponding to all reduction ranges to obtain the third overall risk value. There is an intersection between the target temperature ranges. The third overall risk value represents the overall probability that the charging power reduction will be triggered when the battery temperature is simultaneously within each target temperature range. If the third overall risk value is greater than a preset risk threshold, it indicates that the overall probability of triggering a charging power reduction is relatively high when the battery temperature is simultaneously within each target temperature range. Therefore, an intersection operation is performed on the target temperature ranges to obtain the temperature intersection range. Finally, it is determined whether at least one temperature intersection range intersects with a non-triggering temperature range. If none of the temperature intersection ranges intersect with a non-triggering temperature range, it indicates that there is no temperature within the non-triggering temperature range with a high probability of triggering a power reduction, and the non-triggering temperature range is verified as correct.

[0040] In another embodiment, when the target vehicle experiences a reduction in charging power, the previous historical charging power is obtained from the charging power record of the charging station where the target vehicle is being charged. The previous historical charging power is greater than the current charging power. The actual reduction in the target vehicle's charging power is determined through the following calculation: (Previous historical charging power - Actual charging power) / Previous historical charging power. Simultaneously, based on the battery temperature monitoring record of the target vehicle while it is being charged by the charging station, the battery temperature consistent with the previous historical charging power time point is obtained; this is the trigger temperature that triggers the actual reduction. Further, the reduction range within which the actual reduction occurs is determined as a reference reduction range. If the battery temperature range corresponding to the reference reduction range includes this trigger temperature, then that battery temperature range is determined as the reference temperature range.

[0041] Furthermore, the first weighting coefficient of the reference reduction range is multiplied by the second weighting coefficient of the reference temperature range to obtain the fourth risk value. The fourth risk value characterizes the probability that the charging power reduction will be triggered when the battery temperature is within the reference temperature range, and the reduction range is within the reference reduction range. Finally, the fourth risk value is compared with a preset product threshold. If the fourth risk value is greater than the product threshold, it indicates that the power reduction of the target vehicle is more likely to be triggered by the battery temperature. Then, it is determined whether the triggering temperature is within the non-triggering temperature range. If it is not within the non-triggering temperature range, then the non-triggering temperature range is verified to be correct. Furthermore, if the target vehicle's battery cooling system is not activated, it is determined that the battery cooling system may be faulty, and a corresponding warning message is sent to the target vehicle owner's terminal.

[0042] S104: Obtain the actual SOC value of the battery in the target vehicle, adjust and optimize the initial charging demand based on the actual SOC value, and obtain the final charging demand of the target vehicle.

[0043] Specifically, after determining the initial charging demand, the actual State of Charge (SOC) value of the battery in the target vehicle is obtained through the charging station that charges the target vehicle. This actual SOC value is compared with a preset SOC threshold. If the actual SOC value reaches the threshold, it indicates that the target vehicle's battery is close to fully charged. To protect the battery cells and extend their lifespan, trickle charging is required, and the battery's charging demand (charging load or charging power) decreases. The SOC threshold is set at 80%. Further, a feasible way to adjust and optimize the initial charging demand when the actual SOC value reaches the threshold is as follows: based on historical data showing the decrease in charging power after the battery reaches the SOC threshold, the number of times each individual decrease occurs is counted, and the decrease with the highest number of repetitions is determined as the optimal decrease. Finally, the initial charging demand is multiplied by the optimal decrease to obtain the final charging demand for the target vehicle.

[0044] The implementation principle of the dynamic charging demand prediction method in this application embodiment is as follows: After obtaining the actual temperature and actual charging power of the target vehicle's battery, as well as the actual vehicle profile, based on the historical reduction range and the real-time battery temperature before the historical reduction range occurred, the likelihood of the target vehicle's battery triggering a reduction in charging power due to battery temperature at the current actual temperature is analyzed, thereby accurately determining whether the target vehicle is at risk of power reduction. Further, when the risk of power reduction is determined, the most likely reduction range of the target vehicle's charging power after the current situation is determined, i.e., the appropriate reduction range. Then, combining the appropriate reduction range and the current actual charging power, the initial charging demand of the target vehicle is initially predicted more accurately from the perspective of battery temperature. Finally, since the actual SOC value of the target battery during charging is also related to the charging demand, the initial charging demand is adjusted and optimized based on the actual SOC value, enabling the prediction of the target vehicle's charging demand from multiple dimensions, thereby improving the accuracy of charging demand prediction.

[0045] The following are system embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the system embodiments of this application, please refer to the method embodiments of this application.

[0046] Please see Figure 3 This is a schematic diagram of the charging demand dynamic prediction system provided in an embodiment of this application. This system, applied to the charging demand dynamic prediction system, can be implemented as all or part of a system through software, hardware, or a combination of both. The system includes a data acquisition module 11, a risk assessment module 12, a first prediction module 13, and a second prediction module 14.

[0047] The data acquisition module 11 is used to acquire the actual temperature and actual charging power of the battery in the target vehicle, and to acquire the actual vehicle profile of the target vehicle. The risk assessment module 12 is used to determine whether the target vehicle is at risk of power reduction based on the actual temperature, the historical reduction range of charging power of multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred. The vehicle profile of the historical vehicle is the same as the actual vehicle profile, and the historical reduction range is the reduction range of charging power triggered by battery temperature. The first prediction module 13 is used to determine the appropriate reduction range of the charging power of the target vehicle if it is determined that there is a risk of power reduction of the target vehicle, and to determine the initial charging demand of the target vehicle after the current time based on the actual charging power and the appropriate reduction range. The second prediction module 14 is used to obtain the actual SOC value of the battery in the target vehicle, adjust and optimize the initial charging demand based on the actual SOC value, and obtain the final charging demand of the target vehicle.

[0048] Optional, risk assessment module 12, specifically used for: Based on the historical reduction range of charging power for multiple historical vehicles, at least one reduction range is determined, which is the range in which the historical reduction range of historical vehicles is likely to fall; Select at least one target reduction range from all historical reduction ranges that falls within the reduction range range, and determine at least one battery temperature range corresponding to the reduction range range based on the real-time temperature corresponding to each target reduction range. The battery temperature range is the temperature range that is easy to trigger power reduction. Determine the first weighting coefficient for the range of downward adjustment, and determine the second weighting coefficient for each battery temperature range; Based on the actual temperature, the first weighting coefficient, and each of the second weighting coefficients, determine whether the target vehicle is at risk of power reduction.

[0049] Optional, risk assessment module 12, specifically used for: If the battery temperature range corresponding to the downward adjustment range includes the actual temperature, then the downward adjustment range is determined as an important downward adjustment range, and the battery temperature range that includes the actual temperature is determined as an important temperature range. The first risk value is obtained by multiplying the first weighting coefficient of at least one important downward adjustment range with the second weighting coefficient of the corresponding important temperature range. The first risk values ​​are summed to obtain the first overall risk value, and then the first overall risk value is compared with the preset risk threshold. If the first overall risk value is greater than the risk threshold, it is determined that the target vehicle is at risk of power reduction. If the first overall risk value is not greater than the risk threshold, it is determined that there is no risk of power reduction for the target vehicle.

[0050] Optionally, the first prediction module 13 is specifically used for: Select the largest first risk value from all the first risk values; The minimum value in the important reduction range corresponding to the maximum first risk value is determined as the appropriate reduction range for the target vehicle's charging power.

[0051] Optional, such as Figure 4 As shown, the system also includes a first verification module 15, specifically used for: Obtain the non-triggered temperature range of the battery cooling system of the target vehicle. The non-triggered temperature range is the temperature range of the battery when the battery cooling system is not triggered. The battery temperature range included in the non-trigger temperature range is determined as the key temperature range. If there is at least one key temperature range among the battery temperature ranges corresponding to the reduction range, then the reduction range is determined as the key reduction range. The second risk value is obtained by multiplying the first weighting coefficient of the key downward adjustment range with the second weighting coefficient of the corresponding key temperature range. The second risk value corresponding to each key downward adjustment range is summed to obtain the second overall risk value. If the second overall risk value is not greater than the preset risk threshold, the non-trigger temperature range is verified to be correct.

[0052] Optionally, the system also includes a second verification module 16, specifically used for: Obtain the non-triggered temperature range of the battery cooling system of the target vehicle. The non-triggered temperature range is the temperature range of the battery when the battery cooling system is not triggered. The third risk value is obtained by multiplying the first weighting coefficient of each downward adjustment range with the second weighting coefficient of the corresponding battery temperature range. The third overall risk value is obtained by summing the third risk values ​​corresponding to each target temperature range among all the third risk values ​​corresponding to the lowering ranges. There is an intersection between the target temperature ranges. If the overall risk value of the third group is greater than the preset risk threshold, then the temperature intersection interval of each target temperature interval is determined. If at least one temperature intersection interval does not intersect with the non-trigger temperature interval, the non-trigger temperature interval is verified to be correct.

[0053] Optionally, the system also includes a third verification module 17, specifically used for: When the charging power of the target vehicle is reduced, the actual reduction range of the charging power of the target vehicle is obtained, the trigger temperature that triggers the actual reduction range is obtained, and the reduction range range in which the actual reduction range is located is determined as the reference reduction range range. If the battery temperature range corresponding to the reference reduction range includes the trigger temperature, then the corresponding battery temperature range is determined as the reference temperature range, and the first weighting coefficient of the reference reduction range is multiplied by the second weighting coefficient of the reference temperature range to obtain the fourth risk value. If the fourth risk value is greater than the preset product threshold, the non-trigger temperature range of the target vehicle's battery cooling system is obtained. If the trigger temperature is not in the non-trigger temperature range, the non-trigger temperature range is verified to be correct. The non-trigger temperature range is the temperature range in which the battery temperature is when the battery cooling system is not triggered.

[0054] It should be noted that the above-described embodiment of the dynamic charging demand prediction system, when executing the dynamic charging demand prediction method, only illustrates the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the dynamic charging demand prediction system and the dynamic charging demand prediction method embodiment provided above belong to the same concept, and their implementation process is detailed in the method embodiment, which will not be repeated here.

[0055] This application also discloses a computer-readable storage medium, which stores a computer program, wherein when the computer program is executed by a processor, it implements a dynamic charging demand prediction method according to the above embodiments.

[0056] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0057] The above-described method for dynamic prediction of charging demand is stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the method.

[0058] This application also discloses an electronic device in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, it implements the above-mentioned method for dynamic prediction of charging demand.

[0059] The electronic device can be a desktop computer, a laptop computer, or a cloud server, and includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and buses.

[0060] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0061] The memory can be an internal storage unit of an electronic device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the electronic device. Furthermore, the memory can be a combination of an internal storage unit and an external storage device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0062] In this electronic device, the charging demand dynamic prediction method of the above embodiment is stored in the memory of the electronic device and loaded and executed on the processor of the electronic device for convenient use.

[0063] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for dynamically predicting charging demand, characterized in that, The method includes: The actual temperature and actual charging power of the battery in the target vehicle are obtained, and the actual vehicle profile of the target vehicle is obtained. Based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred, it is determined whether the target vehicle is at risk of power reduction. The vehicle profile of the historical vehicles is the same as the actual vehicle profile, and the historical reduction range is the charging power reduction range triggered by battery temperature. If it is determined that the target vehicle is at risk of power reduction, then the appropriate reduction range of the target vehicle's charging power is determined, and based on the actual charging power and the appropriate reduction range, the initial charging demand of the target vehicle after the current time is determined. Obtain the actual SOC value of the battery in the target vehicle, and adjust and optimize the initial charging demand based on the actual SOC value to obtain the final charging demand of the target vehicle.

2. The method for dynamic prediction of charging demand according to claim 1, characterized in that, The determination of whether the target vehicle is at risk of power reduction based on the actual temperature, the historical reduction range of charging power for multiple historical vehicles, and the real-time temperature of the battery before the historical reduction range occurred includes: Based on the historical reduction range of charging power for multiple historical vehicles, at least one reduction range is determined, wherein the reduction range is the range in which the historical reduction range of the historical vehicles is likely to fall; Filter at least one target reduction range within the reduction range from all the historical reduction ranges, and determine at least one battery temperature range corresponding to the reduction range based on the real-time temperature corresponding to each target reduction range. The battery temperature range is a temperature range that is easy to trigger power reduction. Determine a first weighting coefficient for the range of decrease, and determine a second weighting coefficient for each of the battery temperature ranges; Based on the actual temperature, the first weighting coefficient, and each of the second weighting coefficients, it is determined whether the target vehicle is at risk of power reduction.

3. The dynamic charging demand prediction method according to claim 2, characterized in that, The step of determining whether the target vehicle is at risk of power reduction based on the actual temperature, the first weighting coefficient, and each of the second weighting coefficients specifically includes: If the battery temperature range corresponding to the reduction range includes the actual temperature, then the reduction range is determined as an important reduction range, and the battery temperature range that includes the actual temperature is determined as an important temperature range. The first risk value is obtained by multiplying the first weighting coefficient of at least one of the important downward adjustment ranges with the second weighting coefficient of the corresponding important temperature range; The first risk values ​​are summed to obtain the first overall risk value, and the first overall risk value is compared with the preset risk threshold. If the first overall risk value is greater than the risk threshold, it is determined that the target vehicle is at risk of power reduction. If the first overall risk value is not greater than the risk threshold, it is determined that the target vehicle does not have the risk of power reduction.

4. The method for dynamic prediction of charging demand according to claim 3, characterized in that, Determining the appropriate reduction range of the charging power of the target vehicle specifically includes: Select the largest first risk value from all the first risk values; The minimum value in the important reduction range corresponding to the maximum first risk value is determined as the appropriate reduction range for the charging power of the target vehicle.

5. The method for dynamic prediction of charging demand according to claim 2, characterized in that, The method further includes: Obtain the non-trigger temperature range of the battery cooling system of the target vehicle, wherein the non-trigger temperature range is the temperature range of the battery when the battery cooling system is not triggered; The battery temperature range included in the non-trigger temperature range is determined as the key temperature range. If there is at least one key temperature range among the battery temperature ranges corresponding to the reduction range, then the reduction range is determined as the key reduction range. The second risk value is obtained by multiplying the first weighting coefficient of the key downward adjustment range with the second weighting coefficient of the corresponding key temperature range. The second risk value corresponding to each of the key reduction ranges is summed to obtain the second overall risk value. If the second overall risk value is not greater than the preset risk threshold, then the non-trigger temperature range is verified to be correct.

6. The method for dynamic prediction of charging demand according to claim 2, characterized in that, The method further includes: Obtain the non-trigger temperature range of the battery cooling system of the target vehicle, wherein the non-trigger temperature range is the temperature range of the battery when the battery cooling system is not triggered; The third risk value is obtained by multiplying the first weighting coefficient of each of the aforementioned downward adjustment ranges with the second weighting coefficient of the corresponding battery temperature ranges. The third overall risk value is obtained by summing the third risk values ​​corresponding to each target temperature range among all the third risk values ​​corresponding to the lowering ranges. There is an intersection among the target temperature ranges. If the third overall risk value is greater than the preset risk threshold, then the temperature intersection interval of each target temperature interval is determined. If at least one of the temperature intersection intervals does not intersect with the non-trigger temperature interval, the non-trigger temperature interval is verified to be correct.

7. The method for dynamic prediction of charging demand according to claim 2, characterized in that, The method further includes: When the charging power of the target vehicle is reduced, the actual reduction range of the charging power of the target vehicle is obtained, the trigger temperature that triggers the actual reduction range is obtained, and the reduction range range in which the actual reduction range is located is determined as the reference reduction range range. If the battery temperature range corresponding to the reference reduction range includes the trigger temperature, then the corresponding battery temperature range is determined as the reference temperature range, and the first weighting coefficient of the reference reduction range is multiplied by the second weighting coefficient of the reference temperature range to obtain the fourth risk value. If the fourth risk value is greater than the preset product threshold, the non-trigger temperature range of the battery cooling system of the target vehicle is obtained. If the trigger temperature is not in the non-trigger temperature range, the non-trigger temperature range is verified to be correct. The non-trigger temperature range is the temperature range in which the battery temperature is when the battery cooling system is not triggered.

8. A dynamic charging demand prediction system, characterized in that, include: The data acquisition module (11) is used to acquire the actual temperature and actual charging power of the battery in the target vehicle, and to acquire the actual vehicle profile of the target vehicle. The risk assessment module (12) is used to determine whether the target vehicle is at risk of power reduction based on the actual temperature, the historical reduction range of charging power of multiple historical vehicles and the real-time temperature of the battery before the historical reduction range occurs. The vehicle profile of the historical vehicle is the same as the actual vehicle profile. The historical reduction range is the charging power reduction range triggered by battery temperature. The first prediction module (13) is used to determine the appropriate reduction range of the charging power of the target vehicle if it is determined that there is a risk of power reduction of the target vehicle, and to determine the initial charging demand of the target vehicle after the current time based on the actual charging power and the appropriate reduction range. The second prediction module (14) is used to obtain the actual SOC value of the battery in the target vehicle, adjust and optimize the initial charging demand based on the actual SOC value, and obtain the final charging demand of the target vehicle.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the method of any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, it implements the method of any one of claims 1-7.

Images