Method, device and equipment for adjusting power of fuel cell system, vehicle and medium

Abstract

The invention relates to a method, a device, equipment, a vehicle and a medium for adjusting power of a fuel cell system. The method includes determining a first average power consumption of the vehicle for a first time window and a second average power consumption of the vehicle for a second time window, the first time window being greater than the second time window. The method also includes determining a first weight for the first average power consumption and a second weight for the second average power consumption. The method further includes determining a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. Further, the method includes adjusting a power of a fuel cell system of the vehicle based on the predicted average power consumption. In this way, the performance and efficiency of the fuel cell system can be improved, and resources consumed by the fuel cell system can also be saved.

Description

Technical Field

[0001] The present disclosure relates to the field of hydrogen energy vehicles, and more particularly, to methods, devices, equipment, vehicles, and media for adjusting the power of a fuel cell system. Background Art

[0002] A fuel cell system and a power battery are two important components in a hydrogen energy vehicle, and the two work together to provide the power required for the vehicle. The fuel cell system utilizes the redox reaction between hydrogen and oxygen to generate electrical energy, and it generally includes components such as a hydrogen storage tank, an oxygen supply system, a fuel cell stack, a current collector, and a control system. The electrical energy generated by the fuel cell system can be directly supplied to the motor to drive the vehicle, or transmitted to the power battery to charge the power battery. The power battery generally refers to a battery pack, and its main functions are to store electrical energy, provide additional power, and maintain the normal operation of the vehicle. The power battery can supply the required electrical energy to the motor to drive the vehicle, or supply power to other vehicle accessories other than the motor, and these accessories can be, for example, the vehicle's auxiliary systems, electronic devices, air conditioners, etc.

[0003] In summary, the fuel cell system and the power battery are the two main power parts of a hydrogen energy vehicle. The fuel cell system is responsible for directly converting hydrogen into electrical energy, while the power battery is responsible for storing and managing electrical energy to provide the power required for the vehicle. In some hydrogen energy vehicles, the power battery can also be used to provide temporary additional power. The overall design and control system of the vehicle need to effectively coordinate these two systems to ensure optimal performance and efficiency. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method, an apparatus, a vehicle, and a medium for adjusting the power of a fuel cell system. In the embodiments of the present disclosure, the average power consumption of the vehicle over a relatively long period of time in the past (also referred to as long-term power consumption in this document) and the average power consumption of the vehicle over a relatively short period of time in the past (also referred to as short-term power consumption in this document) can be determined. Then, the weights of the long-term average power and the short-term average power can be determined according to different situations. In this way, the predicted average power consumption can be determined based on the long-term average power, the short-term average power, and their respective weights. The determined predicted average power consumption means a prediction of the average value of the power that the vehicle will consume in a future period of time. Then, the embodiments of the present disclosure can adjust the power of the fuel cell system of the vehicle based on the determined predicted average power consumption. In this way, not only can the power consumption of the vehicle in the future be predicted based on the power consumption of the vehicle in the past period of time, but also the weights for the long-term average power consumption and the short-term average power consumption can be determined in real time according to different driving situations, thereby improving the accuracy of the predicted future power consumption. Compared with adjusting the power of the fuel cell system based on the power consumption of the vehicle at the current moment, this method can make the power of the fuel cell system more stable, reduce large power fluctuations, and thus improve the performance and efficiency of the fuel cell system. In addition, it is also possible to determine the globally optimal power distribution for the fuel cell system based on historical power consumption, thereby being able to save the consumed resources and improve the efficiency of the fuel cell system.

[0005] In a first aspect of the present disclosure, a method for adjusting the power of a fuel cell system is provided. The method includes determining a first average power consumption of the vehicle within a first time window and a second average power consumption of the vehicle within a second time window, where the first time window is greater than the second time window. The method further includes determining a first weight for the first average power consumption and a second weight for the second average power consumption. The method further includes determining a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. In addition, the method further includes adjusting the power of the fuel cell system of the vehicle based on the predicted average power consumption.

[0006] In a second aspect of the present disclosure, there is provided an apparatus for adjusting the power of a fuel cell system. The apparatus includes a historical consumption determination unit configured to determine a first average power consumption of a vehicle within a first time window and a second average power consumption of the vehicle within a second time window, the first time window being greater than the second time window. The apparatus further includes a weight determination unit configured to determine a first weight for the first average power consumption and a second weight for the second average power consumption. The apparatus also includes an average consumption determination unit configured to determine a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. In addition, the apparatus includes a power adjustment unit configured to adjust the power of the fuel cell system of the vehicle based on the predicted average power consumption.

[0007] In a third aspect of the present disclosure, there is provided an electronic device. The electronic device includes one or more processors; and a storage device for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement a method for adjusting the power of a fuel cell system. The method includes determining a first average power consumption of a vehicle within a first time window and a second average power consumption of the vehicle within a second time window, the first time window being greater than the second time window. The method further includes determining a first weight for the first average power consumption and a second weight for the second average power consumption. The method also includes determining a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. In addition, the method includes adjusting the power of the fuel cell system of the vehicle based on the predicted average power consumption.

[0008] In a fourth aspect of the present disclosure, there is provided a vehicle. The vehicle includes the electronic device provided according to the third aspect of the present disclosure.

[0009] In a fifth aspect of the present disclosure, there is provided a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, wherein the computer-executable instructions are executed by a processor to implement the method provided according to the first aspect of the present disclosure.

[0010] It should be understood that the content described in the summary of the invention section is not intended to limit the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In combination with the drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. In the drawings, the same or similar reference numerals denote the same or similar elements, where:

[0012] Figure 1 A schematic diagram showing an example environment in which multiple embodiments of the present disclosure can be implemented;

[0013] Figure 2 A flowchart showing a method for adjusting the power of a fuel cell system according to some embodiments of the present disclosure;

[0014] Figure 3 A schematic diagram showing an example process for adjusting the power of a fuel cell system according to some embodiments of the present disclosure;

[0015] Figure 4 A schematic diagram showing an example process for determining weights for long-term average power consumption and weights for short-term average power consumption based on the remaining power of a power battery according to some embodiments of the present disclosure;

[0016] Figure 5 A schematic diagram showing an example process for adjusting predicted average power consumption by determining a maximum power limit and a minimum power limit according to some embodiments of the present disclosure;

[0017] Figure 6 A schematic diagram showing an example process for switching from a prediction mode to a real-time mode according to some embodiments of the present disclosure;

[0018] Figure 7 A schematic diagram showing an example process for determining long-term average power consumption and short-term average power consumption by determining accessory average power consumption and motor average power consumption according to some embodiments of the present disclosure;

[0019] Figure 8 A schematic diagram showing an example process for determining average power consumption according to some embodiments of the present disclosure;

[0020] Figure 9 A block diagram showing an apparatus for adjusting the power of a fuel cell system according to some embodiments of the present disclosure; and

[0021] Figure 10 A block diagram showing a device that can implement multiple embodiments of the present disclosure. Detailed Description

[0022] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure. The embodiments of the present disclosure described below with reference to the drawings are only for exemplary purposes.

[0023] The power battery of an electric vehicle (also known as a high-voltage battery) can be divided into an energy-type battery and a power-type battery. The energy-type battery is designed to store more electrical energy to meet the energy demand for a long time. Due to the advantages of low price and long battery life, energy-type batteries are commonly used in traditional electric vehicles. However, energy-type batteries have disadvantages such as relatively low charge and discharge rates, large volume, and heavy weight. The power-type battery is designed to provide high-power output to meet the high-current demand instantaneously or in a short period of time. It can provide better driving performance, and due to its small volume and light weight, it can reduce the energy consumption brought by the battery itself. In a hydrogen energy vehicle, a fuel cell system can be used to charge the power-type battery, but the power-type battery can store less electrical energy, and how to maintain the remaining power of the power-type battery within the range that can operate normally is a problem to be solved.

[0024] In some traditional solutions, the vehicle control unit can determine the power consumption required by the vehicle at the current moment, and then determine the power of the fuel cell system based on this power consumption. In this way, when the power consumption required by the vehicle is large, the power of the fuel cell system can be increased, and when the power consumption required by the vehicle is small, the power of the fuel cell system can be decreased. However, this will cause the power of the fuel cell system to fluctuate frequently, and the fluctuation amplitude may be large, thereby reducing the performance and efficiency of the fuel cell system. In addition, since only the power consumption required by the vehicle at the current moment is considered to adjust the power of the fuel cell system, the determined power distribution scheme is not the global optimal solution.

[0025] To this end, embodiments of the present disclosure provide a solution for adjusting the power of a fuel cell system. In this solution, the average power consumption of the vehicle over a relatively long period in the past (also referred to as long-term power consumption herein) and the average power consumption of the vehicle over a relatively short period in the past (also referred to as short-term power consumption herein) can be determined. Then, the weights of the long-term average power and the short-term average power can be determined according to different situations. In this way, the predicted average power consumption can be determined based on the long-term average power, the short-term average power, and their respective weights. The determined predicted average power consumption means a prediction of the average value of the power that the vehicle will consume over a future period. Then, this solution can adjust the power of the fuel cell system of the vehicle based on the determined predicted average power consumption. In this way, not only can the power consumption of the vehicle in the future be predicted based on the power consumption of the vehicle in the past period, but also the weights for the long-term average power consumption and the short-term average power consumption can be determined in real time according to different driving situations, thereby improving the accuracy of the predicted future power consumption. Compared with adjusting the power of the fuel cell system based on the power consumption of the vehicle at the current moment, this method can make the power of the fuel cell system more stable, reduce large power fluctuations, and thus improve the performance and lifespan of the fuel cell system. In addition, it is also possible to determine the globally optimal power distribution for the fuel cell system based on historical power consumption, thereby being able to save the consumed resources and improve the efficiency of the fuel cell system.

[0026] Figure 1 FIG. shows a schematic diagram of an example environment 100 in which multiple embodiments of the present disclosure can be implemented. As Figure 1 shown, the environment 100 includes a vehicle 102, and the vehicle 102 is equipped with a fuel cell system 104 and a power battery 106. The power battery 106 is a high-voltage battery, which can be an energy-type high-voltage battery capable of storing a relatively large amount of electrical energy and having a relatively low instantaneous power, or a power-type high-voltage battery capable of storing a relatively small amount of electrical energy and having a relatively high instantaneous power. Since the power-type high-voltage battery can store less electrical energy, when the power battery 106 is a power-type high-voltage battery, it becomes particularly important to effectively adjust the power of the fuel cell system 104 to keep the remaining power of the power battery 106 within an appropriate range. In the environment 100, the vehicle 102 can send a power request to the fuel cell system 104 through, for example, a vehicle control unit, and then the fuel cell system 104 can adjust its own power in response to the received power request and output electrical energy. The electrical energy output by the fuel cell system 104 can be transmitted to the power battery 106 to charge the power battery 106 and keep the remaining power of the power battery 106 within an appropriate range.

[0027] During the driving of vehicle 102, the power battery 106 can supply electrical energy to the motor 108 and accessories 110 of vehicle 102, where the accessories 110 can be all components in vehicle 102 that consume electrical energy except the motor 108, such as the air conditioning system, the cooling system, and so on. Therefore, during the driving of vehicle 102, the power battery 106 stores electrical energy. When the power battery 106 supplies electrical energy to the motor 108 and accessories 110, the stored electrical energy decreases; when the fuel cell 104 charges the power battery 106, the electrical energy stored in the power battery 106 increases. In some traditional solutions, when the power consumption required by vehicle 102 increases currently (for example, when stepping on the accelerator deeply to accelerate or climbing a slope), the electrical energy in the power battery 106 that needs to be consumed also increases. Therefore, the vehicle control unit will immediately send a request to increase the power to the fuel cell system 104; when the power consumption required by vehicle 102 decreases currently (for example, during coasting energy recovery or going downhill), the electrical energy in the power battery 106 that needs to be consumed also decreases. Therefore, the vehicle control unit will immediately send a request to decrease the power to the fuel cell system 104. In this way, the power of the fuel cell system 104 is not globally optimal, thus wasting the stored energy. In addition, due to large power fluctuations, the performance and efficiency of the fuel cell system 104 will also decrease.

[0028] As Figure 1 shown, the curve 112 represents the actual power consumption of vehicle 102 from time 114 to time 120 during driving, and this actual power consumption includes the actual power consumption of the motor 108 and the actual power consumption of the accessories 110. Between time 116 and time 120 is the time window 122 (also called the first time window), and between time 118 and time 120 is the time window 126 (also called the second time window). Since the length of the time window 122 is greater than the length of the time window 126, the time window 122 is also called the long-time window in this article, and the time window 126 is also called the short-time window. Correspondingly, the average power consumption 124 within the long-time window 122 is called the long-time average power consumption (also called the first average power consumption), and the average power consumption 128 within the time window 126 is called the short-time average power consumption (also called the second average power consumption). At time 120, some embodiments of the present disclosure can predict the predicted average power consumption 130 within a future period of time based on the long-time average power consumption 124 within a past relatively long period of time (i.e., within the long-time window 122) and the short-time average power consumption 128 within a past relatively short period of time (i.e., within the short-time window 126). Then, the vehicle control unit can send a power request to the fuel cell system 104 based on the predicted average power consumption 130 to adjust the power of the fuel cell system 104.

[0029] In this way, the power of the fuel cell system 104 is determined based on data over a past period of time. Therefore, sometimes the electrical energy charged by the fuel cell system 104 to the power battery 106 may be higher than the electrical energy required at the current moment, resulting in an increase in the remaining power in the power battery 106. Sometimes, the electrical energy charged by the fuel cell system 104 to the power battery 106 may be lower than the electrical energy required at the current moment, resulting in a decrease in the remaining power in the power battery 106. However, from a longer time range, the remaining power in the power battery 106 can always be maintained within a suitable range. In this way, although the actual power consumption required by the vehicle 102 changes constantly at each moment (and the change range may be large), the change range of the predicted average power consumption can be very small, thereby improving the performance and efficiency of the fuel cell system 104. In addition, the predicted average power is determined based on the power consumption over a relatively long past period of time and the power consumption over a relatively short past period of time. Therefore, this power distribution scheme is closer to the global optimal solution, thereby saving various resources consumed by the fuel cell system 104.

[0030] Figure 2 FIG. 4 shows a flowchart of a method 200 for adjusting the power of a fuel cell system according to some embodiments of the present disclosure. The method 200 can be executed, for example, by a vehicle control unit. As Figure 2 shown, at block 202, the method 200 can determine a first average power consumption of the vehicle within a first time window and a second average power consumption of the vehicle within a second time window, where the first time window is greater than the second time window. For example, in Figure 1 the environment 100 shown, at time 120, the vehicle control unit of the vehicle 102 can determine a long-term average power consumption 124 of the vehicle 102 within a long-term time window 122 and a short-term average power consumption 128 of the vehicle 102 within a short-term time window 126. The lengths of the long-term time window 122 and the short-term time window 126 can be pre-determined values, which can be manually calibrated values or values determined based on collected historical data (for example, values determined by learning using a neural network). For example, the length of the long-term time window 122 can be 3600 seconds, and the length of the short-term time window 128 can be 60 seconds. It should be understood that although Figure 1 the long-term average power consumption 124 shown in FIG. 4 is greater than the short-term average power consumption 128, the long-term average power consumption 124 can also be less than or equal to the short-term average power consumption 128. For example, when the driver has just turned on the air conditioning system, the short-term average power consumption 128 may be higher than the long-term power consumption 124.

[0031] At block 204, the method 200 can determine a first weight for the first average power consumption and a second weight for the second average power consumption. For example, inFigure 1 In the illustrated environment 100, the vehicle control unit of vehicle 102 may determine a weight for the long-term average power consumption 124 and a weight for the short-term average power consumption 128. During the driving of vehicle 102, various indicators associated with vehicle 102 (such as the remaining power of the power battery 106) may continuously change. Therefore, the weight for the long-term average power consumption 124 and the weight for the short-term average power consumption 128 can be continuously updated based on the changes of these indicators.

[0032] In block 206, method 200 may determine a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. For example, in Figure 1 the illustrated environment 100, the vehicle control unit of vehicle 102 may determine the predicted average power consumption 130 based on the long-term average power consumption 124, the previously determined weight for the long-term average power consumption 124, the short-term average power consumption 128, and the previously determined weight for the short-term average power consumption 128. For example, the long-term average power consumption 124 and the short-term average power consumption 124 may be weighted and summed to determine the predicted average power consumption 130.

[0033] In block 208, method 200 may adjust the power of the fuel cell system of the vehicle based on the predicted average power consumption. For example, in Figure 1 the illustrated environment 100, the vehicle control unit of vehicle 102 may determine a power request sent to the fuel cell system 104 based on the determined predicted average power consumption 130 and using some power distribution algorithms, so that the fuel cell system 104 can adjust the power based on the received power request. Since the long-term average power consumption 124 is determined based on the actual power consumption over a relatively long period of time, it can indicate a more global average power consumption. Since the short-term average power consumption 128 is determined based on the actual power consumption over a relatively short period of time, it can indicate a power consumption closer to the current actual demand. Therefore, when the weight for the long-term average power consumption 124 is larger, the fluctuation range of the determined predicted average power consumption 130 is smaller and it is closer to the global optimal solution. When the weight for the short-term average power consumption 128 is larger, the determined predicted average power consumption 130 has a stronger adjustment ability.

[0034] In this way, although the actual power consumption required by the vehicle at each moment is constantly changing and the change range may be large, the change range of the predicted average power consumption can be small, thereby improving the performance and efficiency of the fuel cell system. In addition, the predicted average power is determined based on the power consumption over a relatively long period in the past and the power consumption over a relatively short period in the past. Therefore, while pursuing the globally optimal power distribution scheme, the remaining power of the power battery can be maintained within a suitable range, thereby saving various resources consumed by the fuel cell system.

[0035] In some embodiments, when determining the weight for the long-term average power consumption and the weight for the short-term average power consumption, the remaining power of the vehicle's power battery can be obtained, and based on the remaining power of the power battery, the weight for the long-term average power consumption and the weight for the short-term average power consumption can be determined. In some embodiments, when determining the predicted average power consumption, the maximum power limit and the minimum power limit of the vehicle can be determined, and based on the maximum power limit and the minimum power limit, the determined predicted average power consumption can be adjusted. In some embodiments, the actual required power consumption of the vehicle's motor and accessories at the current moment can be determined, and it can be determined whether the predicted average power consumption meets a predetermined condition for keeping the remaining power of the power battery within a suitable and safe range. In some embodiments, in response to determining that the predicted average power consumption meets the predetermined condition, the power of the fuel cell system is adjusted based on the predicted average power consumption; or in response to determining that the predicted average power consumption does not meet the predetermined condition, the power of the fuel cell system is adjusted based on the actual required power consumption of the vehicle's motor and accessories.

[0036] Figure 3 A schematic diagram showing an example process 300 for adjusting the power of a fuel cell system according to some embodiments of the present disclosure is shown. As Figure 3 shown, at a certain moment, process 300 can determine the long-term average power consumption 302 and the short-term average power consumption 304 of the vehicle (for example, Figure 1The long-term average power consumption 124 and the short-term average power consumption 128 at the indicated time 120). Then, process 300 may obtain the remaining battery power 306 of the power battery at the current time (e.g., 40%, 60%, 80%, etc.), and determine the weight 308 for the long-term average power consumption 302 and the weight 310 for the short-term average power consumption 304 based on the remaining battery power 306 of the power battery at the current time. In some embodiments, a mapping curve of the remaining battery power and the weight may be pre-calibrated, and the weight 308 for the long-term average power consumption 302 and the weight 310 for the short-term average power consumption 304 may be determined based on this mapping curve and the remaining battery power 306. Then, process 300 may determine the predicted average power consumption 312 based on the long-term average power consumption 302, the weight 308, the short-term average power consumption 304, and the weight 310. For example, process 300 may determine the predicted average power consumption 312 by performing a weighted sum of the long-term average power 302 and the short-term average power 304.

[0037] As Figure 3 shown, after determining the predicted average power consumption 312, process 300 may determine the maximum power limit 314 and the minimum power limit 316 that the vehicle can output. If the calculated predicted average power consumption 312 is greater than the maximum power limit 314 that the vehicle can output, it means that the power that the vehicle can output cannot reach the predicted average power consumption 312, then the predicted average power 312 is adjusted to the maximum power limit 314. If the predicted average power consumption 312 is less than the minimum power limit 316 that the vehicle must output, it means that the power output by the vehicle cannot be reduced to the predicted average power consumption 312, then the predicted average power consumption 312 is adjusted to the minimum power limit 316. After adjusting the predicted average power consumption 312, process 300 may determine the updated predicted average power consumption 318, and the value of the predicted average power consumption 318 is one of the values of the predicted average power consumption 312, the maximum power limit 314, and the minimum power limit 316.

[0038] As Figure 3As shown, process 300 can also determine the actual required power 322 of the vehicle's motor and accessories at the current moment, and the mode switching module 320 can determine whether to use the prediction mode or the real-time mode to adjust the power of the fuel cell system based on the predicted average power consumption 318 and the actual required power 322. In the prediction mode, process 300 will use the predicted average power consumption 318 to adjust the power of the fuel cell system, and in the real-time mode, process 300 will use the actual required power 322 to adjust the power of the fuel cell system. In some embodiments, the mode switching module 320 can determine whether the predicted average power consumption 318 can keep the remaining power of the power battery within a safe range based on the current remaining power of the power battery, the predicted average power consumption 318, and the actual required power 322. If the mode switching module 320 determines that the remaining power of the power battery cannot be kept within a safe range, the actual required power 322 is used to adjust the power of the fuel cell system, so as to quickly adjust the remaining power of the power battery. If the mode switching module 320 determines that the remaining power of the power battery can be kept within a safe range, the predicted average power consumption 318 is used to adjust the power of the fuel cell system. Then, the power distribution module 324 can use the power distribution algorithm and determine the global optimal power request 326 sent to the fuel cell system based on the predicted average power consumption 318 or the actual required power 322.

[0039] By determining the weights 308 for the long-term average power consumption 302 and the weights 310 for the short-term average power consumption 304 based on the remaining power 306 of the power battery, the weights 308 and 310 can be adjusted in real time, so that the calculated predicted average power consumption 312 can achieve the global optimal solution of power distribution while keeping the remaining power 306 of the power battery within a safe range. By considering the maximum power limit and the minimum power limit that the vehicle can output, the predicted average power consumption 318 can match the actual power output ability of the vehicle, and improve the rationality of the data output to the subsequent modules, thereby improving the stability of the entire system. Through the switching between the prediction mode and the real-time mode, the deviation can be quickly corrected according to the current actual situation of the vehicle, so that the remaining power of the power battery can be adjusted in time when it is about to exceed or has exceeded the safe range, improving the safety of the vehicle.

[0040] In some embodiments, when determining the weights for the long-term average power consumption and the weights for the short-term average power consumption based on the remaining power of the power battery, in response to the remaining power of the power battery being greater than the maximum power threshold, the weight for the long-term average power consumption can be increased; or in response to the remaining power of the power battery being less than the minimum power threshold, the weight for the long-term average power consumption can be increased.

[0041] Figure 4 FIG. 400 is a schematic diagram showing an example process for determining weights for long-term average power consumption and short-term average power consumption based on the remaining power of a power battery according to some embodiments of the present disclosure. As Figure 4 shown, process 400 may determine a long-term average power consumption 402 within a long-term time window before the current moment and a short-term average power consumption 404 within a short-term time window before the current moment. Then, process 400 may obtain the remaining power of the power battery. If the current remaining power is remaining power 406, indicating a relatively large remaining power, the weight 408 for the long-term average power consumption 402 may be increased, and correspondingly, the weight 410 for the short-term average power consumption 404 may be decreased. When the sum of weight 408 and weight 410 is one, weight 408 will be greater than weight 410. Then, a predicted average power consumption 412 may be determined based on the long-term average power consumption 402, weight 408, short-term average power consumption 404, and weight 410. When the remaining power 406 is sufficient, the contribution of the long-term average power consumption 402 to the predicted average power consumption 412 will be greater than the contribution of the short-term average power consumption 404 to the predicted average power consumption 412.

[0042] If the current remaining power is remaining power 416, indicating a relatively small remaining power, the weight 420 for the short-term average power consumption 404 may be increased, and correspondingly, the weight 418 for the long-term average power consumption 402 may be decreased. When the sum of weight 418 and weight 420 is one, weight 420 will be greater than weight 418. Then, a predicted average power consumption 422 may be determined based on the long-term average power consumption 402, weight 418, short-term average power consumption 404, and weight 420. When the remaining power 416 is insufficient, the contribution of the short-term average power consumption 404 to the predicted average power consumption 422 will be greater than the contribution of the long-term average power consumption 402 to the predicted average power consumption 422.

[0043] In this way, the weights for long-term average power consumption and short-term average power consumption can be dynamically adjusted according to the current remaining power of the power battery, so that the predicted power consumption is stable when the remaining power is relatively large, and the predicted power consumption can be closer to the actual power consumption required at the current moment when the remaining power is relatively small, thereby enabling quick adjustment of the power of the fuel cell system to supplement the remaining power of the power battery.

[0044] In some embodiments, when determining the predicted average power consumption, the maximum discharge power of the vehicle's power battery and the maximum output power of the fuel cell system can be determined. Then, based on the maximum discharge power of the power battery and the maximum output power of the fuel cell system, the maximum power limit can be determined. In response to the predicted average power consumption being greater than the maximum power limit, the predicted average power consumption is reduced to the maximum power limit. In some embodiments, the maximum charge power of the power battery and the minimum output power of the fuel cell system can be determined. Then, based on the maximum charge power of the power battery and the minimum output power of the fuel cell system, the minimum power limit can be determined. In response to the predicted average power consumption being less than the minimum power limit, the predicted average power consumption is increased to the minimum power limit.

[0045] Figure 5 FIG. shows a schematic diagram of an example process 500 for adjusting the predicted average power consumption by determining the maximum power limit and the minimum power limit according to some embodiments of the present disclosure. As Figure 5 shown, the process 500 can obtain the maximum discharge power 522 of the power battery and the maximum output power 524 of the fuel cell system, and then can determine the maximum power limit 514 of the vehicle based on the maximum discharge power 522 and the maximum output power 524. In addition, the process 500 can also determine the maximum charge power 526 of the power battery and the minimum output power 528 of the fuel cell system, and then can determine the minimum power limit 516 based on the maximum charge power 526 and the minimum output power 528, where the maximum charge power 526 of the power battery can be represented by a negative number, and the minimum output power 528 of the fuel cell system can be represented by a positive number.

[0046] As Figure 5 shown, the process 500 can compare the previously determined predicted average power consumption 512 with the maximum power limit 514 and the minimum power limit 516 of the vehicle. If the predicted average power consumption 512 is between the maximum power limit 514 and the minimum power limit 516, the predicted average power limit 512 can be determined as the predicted average power limit 518. If the predicted average power consumption 512 is greater than the maximum power limit 514, the maximum power limit can be determined as the predicted average power consumption 518. If the predicted average power consumption 512 is less than the minimum power limit 516, the minimum power limit 516 can be determined as the predicted average power consumption 518.

[0047] In this way, when determining the predicted average power consumption, the maximum power limit and the minimum power limit that the vehicle can output can be taken into account, so that the predicted average power consumption 518 can match the actual power output capacity of the vehicle, and the rationality of the data output to the subsequent modules can be improved, thereby improving the stability of the entire system.

[0048] In some embodiments, when adjusting the power of a fuel cell system based on predicted average power consumption, the required wheel-end torque can be determined, and the actual power consumption of accessories can be determined, where the accessories are components in the vehicle other than the motor. Then, the total required power can be determined based on the required wheel-end torque and the actual power consumption of the accessories. Then, the power of the fuel cell system can be adjusted based on the predicted average power consumption and the total required power. In some embodiments, the minimum safe battery charge and the maximum safe battery charge of the power battery can be obtained, and the remaining battery charge of the power battery can be obtained. In response to the remaining charge being less than the minimum safe charge or greater than the maximum safe charge, the power of the fuel cell system can be adjusted based on the total required power. In response to the remaining charge being between the minimum safe charge and the maximum safe charge, the power of the fuel cell system can be adjusted based on the predicted average power consumption.

[0049] Figure 6 A schematic diagram showing an example process 600 of switching from a prediction mode to a real-time mode according to some embodiments of the present disclosure is shown. As Figure 6 shown, process 600 can obtain the required wheel-end torque 626 at the current moment, and then convert the required wheel-end torque 626 into required motor power 628. In addition, process 600 can also determine the actual accessory power consumption 630 at the current moment, where the motor can be, for example, Figure 1 the motor 108 as shown, and the accessories can be, for example, Figure 1 the accessories 110 as shown, and the accessories 110 are a set of components in the vehicle 102 that consume power other than the motor 108. Then, process 600 can determine the actual required power 622 (e.g., Figure 3 the actual required power 322 in

[0050] As Figure 6 shown, process 600 can input the previously determined predicted average power consumption 618 (e.g., Figure 3 the predicted average power consumption 318 in

[0051] If the current remaining battery power is greater than the maximum safe power or less than the minimum safe power, it indicates that the power of the fuel cell system needs to be adjusted as soon as possible so that the remaining battery power of the power battery can be restored to the safe power range as soon as possible. At this time, the process mode switching module 620 can use the actual required power 622 instead of the predicted average power consumption 618 to adjust the power of the fuel cell system. If the current remaining battery power of the power battery is between the maximum safe power and the minimum safe power, the predicted average power consumption 618 can be used to adjust the power of the fuel cell system. For example, in Figure 6 In the example shown, the mode switching module 620 can determine that the current remaining battery power of the power battery is less than the minimum safe power, so the actual required power 622 can be determined as the power 624 and the power 624 is sent to the subsequent module to adjust the power of the fuel cell system.

[0052] As Figure 6 shown, in some embodiments, the mode switching module 620 can also determine the difference between the predicted average power consumption 618 and the actual power consumption 622 and compare this difference with a difference threshold. If this difference is greater than the difference threshold and lasts for a threshold duration, it indicates that in the past threshold duration, the predicted average power consumption and the actual required power have been continuously quite different, so the remaining battery power of the power battery is very likely to exceed the maximum safe power or be lower than the minimum safe power in the future. In this case, the mode switching module 620 can use the actual required power 622 instead of the predicted average power consumption 618 to adjust the power of the fuel cell system.

[0053] In this way, it is possible to quickly correct the deviation when the remaining battery power of the power battery has exceeded the safe range or is about to exceed the safe range according to the current actual situation of the vehicle, so that the remaining battery power of the power battery can be restored to the safe range as soon as possible, improving the safety of the vehicle.

[0054] In some embodiments, when determining the long-term average power consumption of the vehicle within a long time window and the short-term average power consumption of the vehicle within a short time window, the air conditioning system state, the cooling system state, the current ambient temperature, the actual accessory power consumption, the actual motor power consumption, and the driving mode can be obtained. In addition, the long-term average accessory power consumption within the long time window can be determined based on the air conditioning system state, the cooling system state, the current ambient temperature, and the actual accessory power consumption. In addition, the long-term average motor power consumption within the short time window can be determined based on the actual motor power consumption and the driving mode. In addition, the total long-term average power consumption within the long time window can be determined based on the long-term average accessory power consumption and the long-term average motor power consumption.

[0055] In some embodiments, when determining the long - term average power consumption of a vehicle within a long - term time window and the short - term average power consumption of the vehicle within a short - term time window, the short - term average power consumption of accessories within the short - term time window can be determined based on the air - conditioning system state, the cooling system state, the current ambient temperature, and the actual accessory power consumption. In addition, the short - term average power consumption of the motor within the short - term time window can be determined based on the actual motor power consumption and the power mode. Further, the total short - term average power consumption within the short - term time window can be determined based on the short - term average power consumption of accessories and the short - term average power consumption of the motor.

[0056] Figure 7 FIG. shows a schematic diagram of an example process 700 for determining the long - term average power consumption and the short - term average power consumption by determining the average power consumption of accessories and the average power consumption of the motor according to some embodiments of the present disclosure. As Figure 7 shown, the process 700 can determine the air - conditioning system state 704, where the air - conditioning system state 704 indicates whether there is a request to turn on the air - conditioning system within a relatively short time or since the last calculation of the predicted average power consumption. The process 700 can also determine the cooling system state 706, where the cooling system state 706 indicates whether there is a request to turn on the cooling system within a relatively short time or since the last calculation of the predicted average power consumption. The process 700 can also determine the current ambient temperature 708 and the actual accessory power consumption 710. Then, the accessory power consumption determination module 702 can determine the long - term average power consumption 712 and the short - term average power consumption 714 of the accessories of the vehicle based on the air - conditioning system state 704, the cooling system state 706, the ambient temperature 708, and the actual accessory power consumption 710.

[0057] In some embodiments, in response to the air - conditioning system state 704 indicating a request to turn on the air - conditioning system, or the cooling system state 706 indicating a request to turn on the cooling system, the long - term average power consumption 712 and the short - term average power consumption 714 of the accessories can be increased. In some embodiments, in response to the air - conditioning system state 704 indicating a request to turn on the air - conditioning system, or the cooling system state 706 indicating a request to turn on the cooling system, the determined long - term average power consumption 712 and the short - term average power consumption 714 of the accessories can be multiplied by a coefficient greater than one, respectively. In this way, the short - term average power consumption 714 can be adjusted based on the air - conditioning system state 704 and the cooling system state 706, so that the impact of the event of turning on the air - conditioning system or the cooling system on power consumption can be reflected in the predicted average power consumption in a timely manner.

[0058] As Figure 7As shown, process 700 may also determine the actual motor power consumption 724, power mode 726, post-start driving distance 728, and vehicle speed 730. The driving mode 726 may be, for example, an economy mode or a sport mode. In the sport mode, the vehicle may provide higher power performance, while in the economy mode, the vehicle may reduce energy consumption. In some embodiments, the motor power consumption determination module 722 may determine the long-term average power consumption 732 and short-term average power consumption 734 of the motor based on the actual motor power consumption 724 and the power mode 726. In some embodiments, the motor power consumption determination module 722 may determine the long-term average power consumption 732 and short-term average power consumption 734 of the motor based on the actual motor power consumption 724, power mode 72, post-start driving distance 728, and vehicle speed 730.

[0059] In some embodiments, in response to the power mode 726 indicating a request to switch from the economy mode to the sport mode, the long-term average power consumption 732 and short-term average power consumption 734 of the motor may be increased. In some embodiments, in response to the power mode 726 indicating a request to switch from the economy mode to the sport mode, the determined long-term average power consumption 732 and short-term average power consumption 734 of the motor may be multiplied by a coefficient greater than one, respectively. In this way, the short-term average power consumption 734 may be adjusted based on the power mode 726, so that the impact of the event of the power mode switching from the economy mode to the sport mode on the power consumption can be reflected in the predicted average power consumption in a timely manner.

[0060] As Figure 7 shown, process 700 may determine the total long-term average power consumption 742 based on the long-term average power consumption 712 of the accessory and the long-term average power consumption 732 of the motor. The total long-term average power consumption 742 may be, for example, Figure 3 the long-term average power consumption 302 in Figure 3 In addition, process 700 may determine the total short-term average power consumption 744 based on the short-term average power consumption 714 of the accessory and the short-term average power consumption 734 of the motor. The total short-term average power consumption 744 may be, for example,

[0061] In this way, the long-term average power consumption and short-term average power consumption of the motor can be determined based on the data associated with the motor of the vehicle, and the long-term average power consumption and short-term average power consumption of the accessories can be determined based on the data associated with the accessories of the vehicle, so as to further determine the total long-term average power consumption and total short-term average power consumption, improving the accuracy of the calculated long-term average power consumption and short-term average power consumption, and thus being able to improve the accuracy of predicting the average power consumption. In addition, by taking into account the impact of the power mode switching from the economy mode to the sport mode on the power consumption and the impact of turning on the air conditioning system or the cooling system on the power consumption when calculating the predicted average power consumption, the accuracy of predicting the average power consumption can be further improved.

[0062] Figure 8 FIG. shows a schematic diagram of an example process 800 for determining average power consumption according to some embodiments of the present disclosure. As Figure 8 shown, curve 802 indicates the actual power consumption of a vehicle (e.g., Figure 1 vehicle 102 in ). At time 808, process 800 can determine the average per-unit power consumption within time window 812 (from time 804 to time 808). In an embodiment of the present disclosure, the per-unit power consumption refers to converting the power consumption under the current ambient temperature, current air conditioning system and cooling system states to the power consumption under a predetermined ambient temperature, predetermined air conditioning system and cooling system states. For example, the predetermined ambient temperature can be 25 degrees Celsius, and the predetermined air conditioning system and cooling system states can be the air conditioning system and cooling system not being turned on. In some embodiments, a mapping relationship between the ambient temperature, air conditioning system and cooling system states and the per-unit value conversion coefficient can be determined, and then the accessory power consumption can be converted into per-unit power consumption based on the current ambient temperature, current air conditioning system and cooling system states, and the corresponding per-unit value conversion coefficient. In some embodiments, the per-unit value conversion coefficient corresponding to the predetermined ambient temperature, predetermined air conditioning system and cooling system states can be determined based on the actual accessory power consumption of the vehicle when driving under this condition obtained in real time. In some embodiments, the ratio of the accessory power consumption under the current ambient temperature and air conditioning system and cooling system states to the accessory power consumption under the predetermined ambient temperature (e.g., 25 degrees Celsius) and predetermined air conditioning system and cooling system states (e.g., no request to turn on the air conditioning system and cooling system) can be determined to determine the per-unit value conversion coefficient for the current condition. In some embodiments, a mapping relationship between the power mode and the per-unit value conversion coefficient can be determined, and then the motor accessory power consumption can be converted into per-unit power consumption based on the current power mode and the corresponding per-unit value conversion coefficient. By converting the power consumption under various conditions into per-unit power consumption for calculation, the accuracy of the determined average power consumption can be improved.

[0063] When the vehicle is initially started, since there has been no power consumption in the past period of time, the average per-unit power consumption within the time window 812 at this time can be determined to be zero. As Figure 8 shown, after an incremental duration 818, it is necessary to determine the average power consumption of the time window 814 (from time 806 to time 810) at time 810, where the length of the time window remains unchanged, that is, the time window 812 is the same as the time window 814. The process 800 can determine the duration 816 based on the length of the time window 814 and the incremental duration 818, and then determine the cumulative per-unit power consumption between time 806 and time 808 based on the average per-unit power consumption within the time window 812. In addition, the process 800 can determine the cumulative per-unit power consumption between time 808 and time 810 based on the incremental duration 818 and the per-unit power consumption at any time within the incremental duration 818 (because when the incremental duration 818 is short, it can be considered that the power consumption at any time between time 808 and time 810 is the same). In this way, the process 800 can determine the average per-unit power consumption within the time window 814 based on the previously determined cumulative per-unit power consumption between time 806 and time 808, the cumulative per-unit power consumption between time 808 and time 810, the duration 816, and the incremental duration 818. Then, the process 800 can convert the average per-unit power consumption within the time window 814 into an average power consumption by using a per-unit value conversion coefficient corresponding to the current ambient temperature and the current states of the air conditioning system and the cooling system.

[0064] In this way, the power consumption within the current time window can be determined based on the power consumption within the previous time window and the power consumption within the incremental duration, improving the accuracy of the determined average power consumption. In addition, converting the power consumption under various conditions into per-unit power consumption for calculation can improve the accuracy of the determined average power consumption.

[0065] Figure 9 shows a block diagram of an apparatus 900 for adjusting the power of a fuel cell system according to some embodiments of the present disclosure. As Figure 9As shown, device 900 includes a historical consumption determination unit 902 configured to determine a first average power consumption of the vehicle within a first time window and a second average power consumption of the vehicle within a second time window, where the first time window is greater than the second time window. Device 900 further includes a weight determination unit 904 configured to determine a first weight for the first average power consumption and a second weight for the second average power consumption. Device 900 also includes an average consumption determination unit 906 configured to determine a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight. Additionally, device 900 includes a power adjustment unit 908 configured to adjust the power of the fuel cell system of the vehicle based on the predicted average power consumption.

[0066] It can be understood that by using device 900 of the present disclosure, at least one of the many advantages achievable by the method or process described above can be realized. For example, device 900 can improve the performance and efficiency of the fuel cell system. Additionally, device 900 can also keep the remaining power of the power battery within a suitable range while pursuing a globally optimal power distribution scheme, thereby saving various resources consumed by the fuel cell system.

[0067] Figure 10 A block diagram of a device 1000 in which multiple embodiments of the present disclosure can be implemented is shown. Device 1000 can be, for example, a vehicle control unit of a vehicle 102 as shown in Figure 1 As shown, device 1000 includes a computing unit 1001 that can execute various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 1002 and loaded into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0068] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 executes the various methods and processes described above, such as method 200. For example, in some embodiments, method 200 may be implemented as a computer software program tangibly embodied in a machine-readable medium. In some embodiments, part or all of the computer program may be loaded and / or installed onto the device 1000 via the ROM 1002. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method 200 described above may be executed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute method 200 in any other suitable manner (e.g., by means of firmware).

[0069] The functions described above herein may be performed, at least in part, by one or more hardware logic components. By way of example, and not limitation, the types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), systems on a chip system (SOC), complex programmable logic devices (CPLD), and the like.

[0070] The program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0071] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. Further, although the operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the foregoing discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, the various features that are described in the context of a single implementation can also be implemented separately or in any suitable sub-combination in multiple implementations.

[0072] Although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for adjusting the power of a fuel cell system, comprising: determining a first average power consumption of the vehicle within a first time window and a second average power consumption of the vehicle within a second time window, wherein the first time window is greater than the second time window; determining a first weight for the first average power consumption and a second weight for the second average power consumption; determining a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight; and adjusting the power of the fuel cell system of the vehicle based on the predicted average power consumption.

2. The method according to claim 1, wherein determining the first weight for the first average power consumption and the second weight for the second average power consumption comprises: obtaining the remaining power of the power battery of the vehicle; and determining the first weight for the first average power consumption and the second weight for the second average power consumption based on the remaining power of the power battery.

3. The method according to claim 2, wherein determining the first weight for the first average power consumption and the second weight for the second average power consumption based on the remaining power of the power battery comprises: responding to the remaining power of the power battery being greater than a first power threshold by increasing the first weight for the first average power consumption; or responding to the remaining power of the power battery being less than a second power threshold by increasing the second weight for the second average power consumption.

4. The method according to claim 1, wherein determining the predicted average power consumption further comprises: determining the maximum discharge power of the power battery of the vehicle and the maximum output power of the fuel cell system; determining a maximum power limit based on the maximum discharge power of the power battery and the maximum output power of the fuel cell system; and responding to the predicted average power consumption being greater than the maximum power limit by reducing the predicted average power consumption to the maximum power limit.

5. The method according to claim 1, wherein determining the predicted average power consumption further comprises: determining the maximum charging power of the power battery of the vehicle and the minimum output power of the fuel cell system; determining a minimum power limit based on the maximum charging power of the power battery and the minimum output power of the fuel cell system; and responding to the predicted average power consumption being less than the minimum power limit by increasing the predicted average power consumption to the minimum power limit.

6. The method according to claim 1, wherein adjusting the power of the fuel cell system of the vehicle based on the predicted average power consumption comprises: determining the required wheel-end torque; determining the actual power consumption of accessories, where the accessories are components in the vehicle other than the motor; determining the total required power based on the required wheel-end torque and the actual power consumption of the accessories; and Adjust the power of the fuel cell system of the vehicle based on the predicted average power consumption and the total required power.

7. The method according to claim 6, wherein adjusting the power of the fuel cell system of the vehicle based on the predicted average power consumption and the total required power comprises: obtaining a minimum safe power level and a maximum safe power level of a power battery of the vehicle; obtaining a remaining power level of the power battery; in response to the remaining power level being less than the minimum safe power level or the remaining power level being greater than the maximum safe power level, adjusting the power of the fuel cell system based on the total required power; and in response to the remaining power level being between the minimum safe power level and the maximum safe power level, adjusting the power of the fuel cell system based on the predicted average power consumption.

8. The method according to claim 1, wherein determining the first average power consumption of the vehicle within the first time window and the second average power consumption of the vehicle within the second time window comprises: obtaining an air conditioning system state, a cooling system state, a current ambient temperature, an actual accessory power consumption, an actual motor power consumption, and a power mode; determining a third average power consumption within the first time window based on the air conditioning system state, the cooling system state, the current ambient temperature, and the actual accessory power consumption; determining a fourth average power consumption within the first time window based on the actual motor power consumption and the power mode; and determining the first average power consumption within the first time window based on the third average power consumption and the fourth average power consumption.

9. The method according to claim 8, wherein determining the first average power consumption of the vehicle within the first time window and the second average power consumption of the vehicle within the second time window comprises: determining a fifth average power consumption within the second time window based on the air conditioning system state, the cooling system state, the current ambient temperature, and the actual accessory power consumption; determining a sixth average power consumption within the second time window based on the actual motor power consumption and the power mode; and determining the second average power consumption within the second time window based on the fifth average power consumption and the sixth average power consumption.

10. The method according to claim 9, further comprises: in response to the air conditioning system state indicating a request to turn on the air conditioning system or the cooling system state indicating a request to turn on the cooling system, increasing the third average power consumption and the fifth average power consumption.

11. The method according to claim 9, further comprises: in response to the power mode indicating a request to switch from an economy mode to a sport mode, increasing the fourth average power consumption and the sixth average power consumption.

12. An apparatus for adjusting the power of a fuel cell system, comprises: A historical consumption determination unit, configured to determine a first average power consumption of the vehicle within a first time window and a second average power consumption of the vehicle within a second time window, wherein the first time window is greater than the second time window; A weight determination unit, configured to determine a first weight for the first average power consumption and a second weight for the second average power consumption; An average consumption determination unit, configured to determine a predicted average power consumption based on the first average power consumption, the first weight, the second average power consumption, and the second weight; And A power adjustment unit, configured to adjust the power of the fuel cell system of the vehicle based on the predicted average power consumption.

13. An electronic device, Comprising: At least one processor; And A memory, coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, cause the device to perform the method according to any one of claims 1-11.

14. A vehicle, comprising the electronic device according to claim 13.

15. A computer-readable storage medium, having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1-11.

Images