Fuel cell auxiliary power supply method based on power consumption state prediction

Abstract

The present invention discloses a fuel cell auxiliary power supply method based on power consumption state prediction, which relates to the field related to fuel cells. The method includes: collecting battery temperature, collecting power demand characteristics and heat demand characteristics; performing power consumption state and heat consumption state prediction analysis to obtain power consumption state prediction results and heat consumption state prediction results; performing analysis and decision-making on auxiliary power supply of fuel cells to obtain auxiliary power supply coefficients, and when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, using fuel cells for auxiliary power supply; heating the fuel cell to the operating temperature, optimizing the power generation control parameters of the fuel cell, and obtaining the optimal power generation control parameters; controlling the fuel cell power generation for auxiliary power supply and heat supply. The method solves the technical problem of the difficulty in realizing efficient energy utilization and accurate satisfaction of user needs in the existing fuel cell auxiliary power supply, and achieves the technical effect of realizing efficient energy utilization and accurate satisfaction of user needs.

Description

Technical Field

[0001] The present application relates to the field of fuel cells, and in particular to a fuel cell auxiliary power supply method based on power consumption state prediction. Background Art

[0002] As an efficient and clean energy conversion device, solid oxide fuel cells have significant advantages in the field of cogeneration. In a cogeneration system, the demand for electricity and heat fluctuates greatly. How to adjust the operating state of the fuel cell according to real-time demand to maximize its energy utilization efficiency and meet user needs has become an urgent problem to be solved. Traditional solid oxide fuel cell cogeneration systems usually adopt a fixed operating strategy, that is, they work according to preset power generation and heating parameters. Although this method is simple, due to the inability to accurately predict the power and heat consumption status, the system is often in a state of overpower or underpowered, which not only wastes energy, but also makes it difficult to meet the actual needs of users.

[0003] Among the current related technologies, fuel cell auxiliary power supply has the technical problem of being difficult to achieve efficient energy utilization and accurate satisfaction of user needs. Summary of the invention

[0004] The present application provides a fuel cell auxiliary power supply method based on power consumption status prediction, uses real-time collection of the battery temperature of the solid oxide fuel cell and the power demand characteristics and heat demand characteristics on the power side and the heat side to perform predictive analysis of the power consumption status and the heat consumption status. According to the prediction results, the operating status of the fuel cell is adjusted in advance, the power generation control parameters are optimized, and other technical means are used to achieve the technical effect of achieving efficient energy utilization and accurate satisfaction of user needs.

[0005] The present application provides a fuel cell auxiliary power supply method based on power consumption state prediction, including:

[0006] The battery temperature of the solid oxide fuel cell currently performing cogeneration is collected, as well as the current electricity demand characteristics and heat demand characteristics of the electricity side and the heat side; according to the electricity demand characteristics and the heat demand characteristics, the electricity state and the heat state are predicted and analyzed to obtain the electricity state prediction results and the heat state prediction results, wherein the electricity state prediction results include the electricity continuity parameter and the maximum electricity load parameter; according to the battery temperature, the electricity state prediction results and the heat state prediction results, the auxiliary power supply of the fuel cell is analyzed and decided to obtain the auxiliary power supply coefficient, and when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, the fuel cell is used for auxiliary power supply; the fuel cell is heated to the operating temperature, and according to the electricity state prediction results and the heat state prediction results, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, wherein the optimization is performed for the purpose of improving the electricity supply and heat supply degree of the electricity side and the heat side, and improving the power generation efficiency and heat generation efficiency of the fuel cell; the optimal power generation control parameters are used to control the fuel cell power generation for auxiliary power supply and heat supply.

[0007] In a possible implementation, the battery temperature of the solid oxide fuel cell currently performing cogeneration is collected, and the current power demand characteristics and heat demand characteristics of the power consumption side and the heat consumption side are collected, and the following processing is performed:

[0008] Collect the battery temperature of the solid oxide fuel cell currently performing cogeneration; collect the current timestamp information, as well as the electricity demand parameters and electricity user information on the electricity user side; collect the current heat demand parameters and heat user information on the heat user side; generate electricity demand characteristics based on the timestamp information combined with the electricity demand parameters and electricity user information, and generate heat demand characteristics based on the timestamp information combined with the heat demand parameters and heat user information.

[0009] In a possible implementation, according to the electricity demand characteristics and the heat demand characteristics, the electricity state and the heat state prediction analysis are performed to obtain the electricity state prediction result and the heat state prediction result, and the following processing is performed:

[0010] Based on the historical electricity demand data on the electricity consumption side, a set of sample electricity demand features is collected, and the electricity continuity parameters and maximum electricity load parameters of electricity consumption under different sample electricity demand characteristics are obtained to obtain a sample electricity state set; the sample electricity demand feature set and the sample electricity state set are used to train the electricity state prediction path until the training converges; the electricity state prediction path with converged training is used to predict the electricity state of the electricity demand characteristics to obtain the electricity state prediction result; based on the historical heat demand data on the heat consumption side, a set of sample heat demand features is collected, and the heat continuity parameters and maximum heat load parameters of heat consumption under different sample heat demand characteristics are obtained to obtain a sample heat state set; the sample heat demand feature set and the sample heat state set are used to train the heat state prediction path until the training converges; the heat state prediction path with converged training is used to predict the heat state of the heat demand characteristics to obtain the heat state prediction result.

[0011] In a possible implementation, the auxiliary power supply of the fuel cell is analyzed and decided according to the battery temperature, the power consumption state prediction result and the heat consumption state prediction result, the auxiliary power supply coefficient is obtained, and the following processing is performed:

[0012] The battery temperature is input into a heating cost coefficient comparison table for indexing to obtain a heating cost coefficient, wherein the heating cost coefficient comparison table includes an index relationship between a plurality of sample battery temperatures and a plurality of sample heating cost coefficients, and the size of the sample battery temperature is negatively correlated with the size of the sample heating cost coefficient; according to the maximum power load parameter in the power consumption state prediction result, the basic power generation utilization efficiency when the power generation power of the fuel cell reaches the maximum power load parameter is analyzed, and according to the power consumption continuity parameter, the basic power generation utilization efficiency is corrected to obtain a corrected power generation utilization efficiency, and a power generation utilization coefficient is obtained; according to the maximum heat load parameter in the heat consumption state prediction result, the basic heat utilization efficiency when the heat generation power of the fuel cell reaches the maximum heat load parameter is analyzed, and according to the heat consumption continuity parameter, the basic heat utilization efficiency is corrected to obtain a corrected heat utilization efficiency, and a heat utilization coefficient is obtained; the heating cost coefficient, the power generation utilization coefficient and the heat utilization coefficient are weightedly calculated to obtain an auxiliary power supply coefficient; when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, the fuel cell is used for auxiliary power supply, and when the auxiliary power supply coefficient is not greater than the auxiliary power supply coefficient threshold, the fuel cell is not used for auxiliary power supply.

[0013] In a possible implementation, according to the maximum power load parameter in the power consumption state prediction result, the basic power generation efficiency when the power generation power of the fuel cell reaches the maximum power load parameter is analyzed, and according to the power consumption continuity parameter, the basic power generation efficiency is corrected, and the following processing is performed:

[0014] According to the historical working data of the solid oxide fuel cell, a sample power generation efficiency set and a sample power generation utilization efficiency set are collected; the sample power generation efficiency set and the sample power generation utilization efficiency set are used to construct a power generation utilization efficiency classifier, and the maximum power load parameter is input and classified to obtain a basic power generation utilization efficiency; according to the ratio of the power consumption continuity parameter and the preset power consumption continuity parameter, the basic power generation utilization efficiency is corrected and calculated to obtain a corrected power generation utilization efficiency.

[0015] In a possible implementation, according to the power consumption state prediction result and the heat consumption state prediction result, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, and the following processing is performed:

[0016] According to the fuel flow rate regulation range, air flow rate regulation range and temperature regulation range when the fuel cell generates electricity, the power generation control parameter space is generated; with the purpose of improving the power supply degree and heat supply degree of the power consumption side and the heat consumption side, and improving the power generation efficiency and heat utilization efficiency of the fuel cell, the fuel cell control function is constructed as follows: Among them, FCF is the battery fitness, w1, w2, w3 and w4 are weights, α p is the ratio of the power consumption continuity parameter to the maximum power consumption continuity parameter, α h is the ratio of the heat continuity parameter to the maximum heat continuity parameter, P c and H c The power generation and heating power of the fuel cell when generating electricity according to the optimized power generation control parameters, P x and H x is the maximum power load parameter and the maximum heat load parameter, P s and H s The fuel input electric power and fuel input thermal power are used for power generation according to the optimized power generation control parameters; within the power generation control parameter space, the power generation control parameters of the fuel cell are optimized according to the fuel cell control function to obtain the optimal power generation control parameters.

[0017] In a possible implementation, within the power generation control parameter space, according to the fuel cell control function, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, and the following processing is performed:

[0018] In the power generation control parameter space, a plurality of first power generation control parameters are randomly generated; based on the fuel flow parameters, air flow parameters and temperature parameters in the plurality of first power generation control parameters, a plurality of first fuel input electric powers and first fuel input thermal powers, as well as a plurality of first power generation powers and a plurality of first heating powers are analyzed and obtained, and in combination with the maximum power load parameters and the maximum thermal load parameters, a plurality of first battery fitnesses are calculated and obtained; based on the plurality of first battery fitnesses, a plurality of first power generation control parameters are clustered and iteratively optimized, and after the optimization converges, the power generation control parameters corresponding to the maximum battery fitness in the converged power generation control parameter cluster are output to obtain the optimal power generation control parameters.

[0019] In a possible implementation, clustering and iterative optimization of a plurality of first power generation control parameters are performed according to the plurality of first battery fitnesses, and the following processing is performed:

[0020] According to the multiple first battery fitnesses, the first power generation control parameters corresponding to the largest number of first battery fitnesses are divided into several excellent first power generation control parameters; using several excellent first power generation control parameters, other first power generation control parameters are approximately classified to obtain several power generation control parameter clusters, wherein the approximate classification includes classifying other first power generation control parameters into the cluster of the closest excellent first power generation control parameters; taking several excellent first power generation control parameters as the adjustment direction, other first power generation control parameters in each power generation control parameter cluster are adjusted to obtain second power generation control parameters, and several power generation control parameter clusters are updated; based on the battery fitness of multiple power generation control parameters in the updated several power generation control parameter clusters, the excellent power generation control parameters are updated; and the adjustment and optimization based on the updated excellent first power generation control parameters is continued until the converged optimization times are reached, and the power generation control parameter cluster with the largest total battery fitness is output to obtain a converged power generation control parameter cluster.

[0021] The fuel cell auxiliary power supply method based on power consumption state prediction proposed in this application is to first collect the battery temperature of the solid oxide fuel cell currently performing cogeneration, as well as the power demand characteristics and heat demand characteristics of the current power side and the heat side, and then perform power consumption state and heat consumption state prediction analysis based on the power demand characteristics and heat demand characteristics to obtain power consumption state prediction results and heat consumption state prediction results, wherein the power consumption state prediction results include power consumption continuity parameters and maximum power load parameters, and then perform analysis and decision on the auxiliary power supply of the fuel cell based on the battery temperature, power consumption state prediction results and heat consumption state prediction results to obtain Auxiliary power supply coefficient, when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, a fuel cell is used for auxiliary power supply, and then the fuel cell is heated to the operating temperature, and the power generation control parameters of the fuel cell are optimized according to the power consumption state prediction results and the heat consumption state prediction results, to obtain the optimal power generation control parameters, wherein the optimization is carried out with the purpose of improving the power supply and heat supply on the power consumption side and the heat consumption side, and improving the power generation efficiency and heat generation efficiency of the fuel cell, and finally the optimal power generation control parameters are used to control the fuel cell power generation for auxiliary power supply and heat supply, thereby achieving the technical effect of realizing efficient energy utilization and precise satisfaction of user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A schematic flow chart of a fuel cell auxiliary power supply method based on power consumption status prediction provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of a flow chart for obtaining a convergent power generation control parameter cluster in a fuel cell auxiliary power supply method based on power consumption state prediction provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0026] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0027] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0028] The present application embodiment provides a fuel cell auxiliary power supply method based on power consumption state prediction, such as Figure 1 As shown, the method includes:

[0029] Step S100, collect the battery temperature of the solid oxide fuel cell currently performing cogeneration, and collect the current electricity demand characteristics and heat demand characteristics of the electricity side and the heat side. Specifically, the solid oxide fuel cell is an efficient and environmentally friendly fuel cell that can directly react the fuel (such as hydrogen or natural gas) with the oxidant (such as oxygen in the air) at high temperature to generate electricity and heat. The solid oxide fuel cell is used in the cogeneration system (the process of generating electricity and heat in one system at the same time), which can meet the demand for electricity and heat at the same time. Use the temperature sensor installed on the solid oxide fuel cell to detect and record the current battery temperature in real time, and transmit the detected temperature data to the central control system or data processing unit. Through the smart meter or the sensor directly connected to the power consumption equipment, the power consumption of the current power consumption side is monitored and recorded in real time, the power consumption data is analyzed, and the power demand characteristics are extracted, such as the power consumption rate, the peak time of power consumption, the change of power load, etc., and the power demand characteristic data is transmitted to the central control system or data processing unit. Use temperature sensors or heat metering equipment to monitor and record the current heat demand on the heating side in real time, analyze the heat demand data, extract the heat demand characteristics, such as required heat, heat load changes, heat load peaks, etc., and transmit the heat demand characteristic data to the central control system or data processing unit.

[0030] In a possible implementation, the battery temperature of the solid oxide fuel cell currently performing cogeneration is collected, and the power demand characteristics and heat demand characteristics of the current power side and heat side are collected. Step S100 further includes step S110, collecting the battery temperature of the solid oxide fuel cell currently performing cogeneration. Specifically, the temperature sensor is connected to the battery module of the solid oxide fuel cell, and the data of the temperature sensor is regularly read using a data acquisition system or a PLC (programmable logic controller) to obtain the battery temperature data. Step S120, collect the current timestamp information, as well as the power demand parameters and power subject information of the power side. Specifically, the current timestamp information is obtained from the system clock or time server, and the current power demand parameters are read through devices such as smart meters and power load management systems, that is, the specific parameters of the power demand of the power side, such as total power, power distribution of each power-consuming device, etc., and the power subject information of the current power side is recorded, such as the power unit, the type of power-consuming device, etc. Step S130, collect the heat demand parameters and heat subject information of the current heat side. Specifically, the current heat demand parameters, i.e., the specific parameters of the heat demand, such as heat load, hot water flow, etc., are read through heat metering equipment, temperature sensors and other equipment, and the heat user information of the current heat user side, such as heat unit, heat device type, etc., is recorded. Step S140, based on the timestamp information combined with the electricity demand parameters and the electricity user information, the electricity demand characteristics are generated, and based on the timestamp information combined with the heat demand parameters and the heat user information, the heat demand characteristics are generated. Specifically, the timestamp information, the electricity demand parameters and the electricity user information, the heat demand parameters and the heat user information are integrated, and the electricity demand characteristics and the heat demand characteristics are extracted from the integrated data using data analysis tools or algorithms, including the peak period of electricity consumption, the distribution of types of electricity users, and the trend of heat load changes. This implementation method ensures the real-time and accuracy of the data by directly collecting the electricity demand parameters and the heat demand parameters at the current timestamp, and combining the electricity user information and the heat user information, thereby achieving a technical effect of helping to more accurately predict the dynamic changes in electricity and heat demand.

[0031] Step S200, according to the power demand characteristics and heat demand characteristics, the power state and heat state prediction analysis are performed to obtain the power state prediction result and the heat state prediction result, wherein the power state prediction result includes the power continuity parameter and the maximum power load parameter. Specifically, the collected power demand characteristics and heat demand characteristics are cleaned, outliers, missing values ​​or duplicate data are removed, and the data is standardized or normalized for better use in the prediction model. Features related to the prediction of power state and heat state are selected from the preprocessed data, including historical power load, weather conditions, time factors (such as seasons, weekdays / weekends, holidays, etc.), user behavior patterns, etc. The prediction model (such as a machine learning model) is trained using historical data to learn the relationship between the power state and heat state and the characteristics. The currently collected power demand characteristics are input into the trained prediction model to predict the power state, and the prediction results include the power continuity parameter (indicating whether the power demand is continuous or intermittent in the future) and the maximum power load parameter (the predicted maximum power demand at a certain point in time in the future). Similarly, the currently collected heat demand characteristics are input into the trained prediction model to predict the heat status. The prediction results also include heat continuity parameters and maximum heat load parameters.

[0032] In a possible implementation, according to the electricity demand characteristics and heat demand characteristics, the electricity state and heat state prediction analysis are performed to obtain the electricity state prediction result and the heat state prediction result, and step S200 further includes step S210, based on the historical electricity demand data on the electricity side, a sample electricity demand feature set is collected, and the electricity continuity parameters and maximum electricity load parameters of electricity consumption under different sample electricity demand characteristics are obtained to obtain a sample electricity state set. Specifically, historical electricity demand data are collected, including various factors such as time, weather, holidays, economic activities, etc., and electricity demand characteristics are extracted from these data, such as daily average electricity consumption, peak electricity consumption period, and valley electricity consumption period. According to these characteristics, the electricity continuity parameter (continuity and stability of electricity consumption over a period of time, such as continuous electricity consumption duration) and the maximum electricity load parameter (the maximum value of electricity load in a certain period of time, such as the highest instantaneous electricity consumption) under each sample are calculated, and these parameters are combined into a sample electricity state set. Step S220, using the sample power demand feature set and the sample power state set, train the power state prediction path until the training converges. Specifically, select or design a suitable machine learning or deep learning model, use the sample power demand feature set as input, and the sample power state set as output, train the model, and iteratively optimize the model parameters until the performance of the model on the validation set reaches a preset threshold or the number of training times reaches a maximum limit. Step S230, using the power state prediction path with converged training, predict the power state of the power demand feature to obtain a power state prediction result. Specifically, the new power demand feature is input into the trained model, and the model outputs the predicted power state, including the predicted power continuity and maximum power load. Step S240, based on the historical heat demand data on the heat-using side, collect a sample heat demand feature set, and obtain the heat continuity parameters and maximum heat load parameters of heat use under different sample heat demand characteristics to obtain a sample heat state set; step S250, use the sample heat demand feature set and the sample heat state set to train the heat state prediction path until the training converges; step S260, use the heat state prediction path with converged training to predict the heat state of the heat demand characteristics to obtain the heat state prediction result. Specifically, steps S240 to S260 are similar to the electricity state prediction, except that they are replaced with parameters and features related to heat use, such as heat continuity parameters and maximum heat load parameters. This implementation method achieves the technical effect of improving the efficiency and accuracy of the prediction by constructing a prediction model based on historical data to predict the state of electricity and heat use.

[0033] Step S300, analyze and decide on the auxiliary power supply of the fuel cell according to the battery temperature, the power state prediction result and the heat state prediction result, obtain the auxiliary power supply coefficient, and use the fuel cell for auxiliary power supply when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold. Specifically, the collected battery temperature, power state prediction results (including power continuity parameters and maximum power load parameters) and heat state prediction results (including heat continuity parameters and maximum heat load parameters) are integrated. Analyze the current battery temperature of the fuel cell and evaluate its working state and performance. According to the power state prediction results and the heat state prediction results, analyze the power and heat demand in the current and future period, and evaluate the matching degree of these demands with the power supply and heating capacity of the fuel cell. Based on the integrated data and evaluation results, calculate the auxiliary power supply coefficient, which is a comprehensive indicator used to evaluate whether it is necessary to use a fuel cell for auxiliary power supply and heating in the current situation.

[0034] The calculated auxiliary power supply coefficient is compared with the preset auxiliary power supply coefficient threshold. If the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, it means that it is reasonable to use the fuel cell for auxiliary power supply and heating under the current situation. If the decision result is that auxiliary power supply is needed, the start-up and control mechanism of the fuel cell is triggered to perform auxiliary power supply and heating.

[0035] In a possible implementation, the auxiliary power supply of the fuel cell is analyzed and decided based on the battery temperature, the power consumption state prediction result and the heat consumption state prediction result to obtain the auxiliary power supply coefficient. Step S300 further includes step S310, inputting the battery temperature into a heating cost coefficient comparison table for indexing to obtain the heating cost coefficient, wherein the heating cost coefficient comparison table includes an index relationship between multiple sample battery temperatures and multiple sample heating cost coefficients, and the size of the sample battery temperature is negatively correlated with the size of the sample heating cost coefficient. Specifically, a heating cost coefficient comparison table is obtained, which includes an index relationship between multiple sample battery temperatures and corresponding sample heating cost coefficients. When the current battery temperature is known, a search is performed in the heating cost coefficient comparison table to find the heating cost coefficient corresponding to the sample battery temperature closest to the current battery temperature, wherein the heating cost coefficient reflects the additional energy consumption or cost required to heat to the power generation operating temperature at a specific battery temperature. Step S320, according to the maximum power load parameter in the power state prediction result, the basic power generation efficiency when the power generation power of the fuel cell reaches the maximum power load parameter is analyzed, and according to the power continuity parameter, the basic power generation efficiency is corrected to obtain the corrected power generation efficiency, and the power generation utilization coefficient is obtained. Specifically, the maximum power load parameter is extracted from the power state prediction result, and whether the power generation power of the fuel cell can reach the maximum power load parameter is analyzed, and the basic power generation efficiency at this time is calculated. Combined with the power continuity parameter, that is, the stability and duration of the power load, the basic power generation efficiency is corrected to obtain the corrected power generation efficiency, and the corrected power generation efficiency is the power generation utilization coefficient, which represents the power generation efficiency of the fuel cell under a specific power load and duration. Step S330, according to the maximum heat load parameter in the heat state prediction result, the basic heat utilization efficiency when the heat power of the fuel cell reaches the maximum heat load parameter is analyzed, and according to the heat continuity parameter, the basic heat utilization efficiency is corrected to obtain the corrected heat utilization efficiency, and the heat utilization coefficient is obtained. Specifically, this step is similar to step S320, except that the analysis is on the heating utilization. Step S340, weighted calculation is performed on the heating cost coefficient, power generation utilization coefficient and heating utilization coefficient to obtain the auxiliary power supply coefficient. Specifically, according to actual needs or experience, a weight is assigned to each coefficient, and the three coefficients are weighted summed to obtain the auxiliary power supply coefficient. Step S350, when the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, a fuel cell is used for auxiliary power supply, and when the auxiliary power supply coefficient is not greater than the auxiliary power supply coefficient threshold, a fuel cell is not used for auxiliary power supply.Specifically, an auxiliary power supply coefficient threshold is set. When the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, it is considered that the use of fuel cells for auxiliary power supply is economical and effective, so it is selected for use; when the auxiliary power supply coefficient is less than or equal to the auxiliary power supply coefficient threshold, it is considered that the use of fuel cells for auxiliary power supply is costly or inefficient, so it is selected not to use. This implementation method calculates the heating cost coefficient, the power generation utilization coefficient, and the heat generation utilization coefficient, comprehensively considering the operating cost and efficiency of the fuel cell under different conditions, and achieves the technical effect of improving the accuracy of the auxiliary power supply coefficient calculation.

[0036] In a possible implementation, according to the maximum power load parameter in the power consumption state prediction result, the basic power generation efficiency when the power generation power of the fuel cell reaches the maximum power load parameter is analyzed, and according to the power consumption continuity parameter, the basic power generation efficiency is corrected, and step S320 further includes step S321, according to the historical working data of the solid oxide fuel cell, a sample power generation efficiency set and a sample power generation efficiency set are collected. Specifically, a sample power generation efficiency set and a sample power generation efficiency set related to the solid oxide fuel cell are extracted from the historical working data, and these historical working data include the performance data of the fuel cell under different loads and working conditions. Among them, the sample power generation efficiency set contains the power generation efficiency data of the fuel cell under different working conditions, and the power generation efficiency is the ratio of the electric energy generated by the fuel cell to the input chemical energy; in addition to the power generation efficiency, the sample power generation efficiency set also combines other factors (such as energy transmission loss, etc.) to evaluate the power utilization performance of the fuel cell. Step S322, using the sample power generation efficiency set and the sample power generation efficiency set, a power generation efficiency classifier is constructed, and the maximum power load parameter is input and classified to obtain the basic power generation efficiency. Specifically, using the collected sample power generation efficiency set and sample power generation utilization efficiency set, a classifier model is constructed through machine learning or statistical learning methods. The power generation utilization efficiency classifier can predict or classify the corresponding basic power generation utilization efficiency according to the input maximum power load parameter. Step S323, according to the ratio of the power continuity parameter and the preset power continuity parameter, the basic power generation utilization efficiency is corrected and calculated to obtain the corrected power generation utilization efficiency. Specifically, a ratio is calculated according to the current power continuity parameter and the preset power continuity parameter, and the basic power generation utilization efficiency is corrected using this ratio to obtain the corrected power generation utilization efficiency. The corrected power generation utilization efficiency is a more accurate performance evaluation indicator obtained by correcting the basic power generation utilization efficiency in combination with the power continuity parameter. The correction method can be a simple multiplication, addition or other complex mathematical operations. Among them, the preset power continuity parameter is a reference value set based on the historical working duration parameter of the fuel cell, such as the mean of the historical working duration. This implementation method collects historical data and uses this data to build a power generation efficiency classifier, accurately predicting the performance of the fuel cell under different maximum power load conditions. At the same time, it further corrects the prediction results based on the impact of power continuity parameters on power generation efficiency, achieving the technical effect of making the power generation utilization coefficient more in line with actual conditions.

[0037] Step S400, heating the fuel cell to the operating temperature, optimizing the power generation control parameters of the fuel cell according to the power state prediction results and the heat state prediction results, and obtaining the optimal power generation control parameters, wherein the optimization is performed for the purpose of improving the power supply degree and heat supply degree of the power side and the heat side, and improving the power generation efficiency and heat generation efficiency of the fuel cell. Specifically, when it is determined that the fuel cell needs to be auxiliary powered (i.e., the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold), the preheating procedure of the fuel cell is first started. During the preheating process, the temperature of the fuel cell is gradually increased to its normal operating temperature range according to the guide provided by the manufacturer of the fuel cell or the preset heating curve. The power state prediction results and the heat state prediction results are analyzed in detail, and the key parameters such as the urgency, duration, and peak load of the power demand and heat demand are evaluated to determine the changing trend of the power and heat demand in the current and future period. According to the prediction results of power consumption state, heat consumption state and the current state of the fuel cell, the power generation control parameters are optimized. The power generation control parameters refer to the parameters used to control the power generation performance of the fuel cell, including fuel flow, oxygen flow, working pressure, current density, etc. The power generation control parameters are adjusted and optimized using optimization algorithms (such as genetic algorithms, gradient descent methods, neural networks, etc.). During the optimization process, the power supply and heat supply of the power and heat sides, as well as the power generation efficiency and heat generation efficiency of the fuel cell are considered at the same time. Among them, the power supply is used to evaluate the degree to which the power supply meets the power demand. A high power supply means that the power supply can fully meet the power demand and there will be no power shortage; the heat supply is used to evaluate the degree to which the heat supply meets the heat demand. A high heat supply means that the heat supply can fully meet the heat demand and there will be no heat shortage; the power generation efficiency refers to the degree to which the electric energy generated by the fuel cell in the power generation process is effectively utilized; the heat generation efficiency refers to the degree to which the heat energy generated by the fuel cell in the power generation process is effectively utilized. High power generation efficiency and high heat generation efficiency mean high energy utilization efficiency.

[0038] In one possible implementation, the power generation control parameters of the fuel cell are optimized according to the power consumption state prediction results and the heat consumption state prediction results to obtain the optimal power generation control parameters. Step S400 further includes step S410, generating a power generation control parameter space according to the fuel flow adjustment range, air flow adjustment range and temperature adjustment range when the fuel cell generates electricity. Specifically, according to the technical specifications and performance parameters of the fuel cell, the adjustable ranges of the fuel flow, air flow and temperature are determined, and the above adjustment ranges are converted into a series of operable parameter values ​​to form a power generation control parameter space. The power generation control parameter space contains all possible power generation control parameter combinations for subsequent parameter optimization. Step S420, with the purpose of improving the power supply and heat supply on the power consumption side and the heat consumption side, and improving the power generation efficiency and heat utilization efficiency of the fuel cell, construct a fuel cell control function as follows:

[0039]

[0040] Among them, FCF is the battery fitness, w1, w2, w3 and w4 are weights, α p is the ratio of the power consumption continuity parameter to the maximum power consumption continuity parameter, α h is the ratio of the heat continuity parameter to the maximum heat continuity parameter, P c and H c The power generation and heating power of the fuel cell when generating electricity according to the optimized power generation control parameters, P x and H x is the maximum power load parameter and the maximum heat load parameter, P s and H s It is the fuel input electric power and fuel input thermal power when power generation is performed according to the optimized power generation control parameters. Specifically, the optimization goal is to improve the power supply and heat supply of the power and heat sides, as well as to improve the power generation efficiency and heat generation efficiency of the fuel cell. According to actual needs, corresponding weights are set for different goals. These weights reflect the importance of different goals in the optimization process. and Respectively reflect the degree of electricity supply and heat supply, and Respectively reflect the power generation efficiency and heat generation efficiency. The battery fitness is a comprehensive indicator for measuring the performance of a fuel cell, which is used to evaluate the performance of the fuel cell under the current power generation control parameters. Step S430, in the power generation control parameter space, according to the fuel cell control function, optimize the power generation control parameters of the fuel cell to obtain the optimal power generation control parameters. Specifically, a set of power generation control parameters is randomly selected from the power generation control parameter space as a starting point, and an optimization algorithm (such as a genetic algorithm, a particle swarm algorithm, etc.) is used to search in the power generation control parameter space to find the power generation control parameter combination that makes the fuel cell control function (i.e., the battery fitness FCF) reach the optimal value. When the algorithm reaches a certain number of iterations or the improvement of the battery fitness FCF is less than a preset threshold, it is considered that the algorithm has converged and the current optimal power generation control parameters are output. This implementation method converts the power generation control parameter optimization problem of the fuel cell into an optimization problem by constructing the power generation control parameter space and the fuel cell control function, and searches for the optimal solution in the power generation control parameter space through the optimization algorithm, thereby achieving the technical effect of improving the efficiency and accuracy of obtaining the optimal power generation control parameters.

[0041] In a possible implementation, within the power generation control parameter space, according to the fuel cell control function, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, and step S430 further includes step S431, randomly generating multiple first power generation control parameters within the power generation control parameter space. Specifically, within the power generation control parameter space, according to the boundaries and constraints of the space, a plurality of initial power generation control parameter combinations, i.e., first power generation control parameters (randomly generated, unoptimized power generation control parameter combinations at the beginning of the optimization process), are randomly generated, including fuel flow parameters, air flow parameters, and temperature parameters, and each power generation control parameter combination can be represented as a vector or array, such as [fuel flow, air flow, temperature]. Step S432, according to the fuel flow parameters, air flow parameters, and temperature parameters within the plurality of first power generation control parameters, multiple first fuel input electric powers and first fuel input thermal powers, as well as multiple first power generation powers and multiple first heating powers are analyzed and obtained, and multiple first battery fitness is calculated in combination with the maximum power load parameter and the maximum thermal load parameter. Specifically, the fuel cell model (which may be a physical model, an empirical model or a data-driven model) is used to predict the corresponding fuel input electric power, fuel input thermal power, power generation power and heating power according to each first power generation control parameter combination (including fuel flow parameters, air flow parameters and temperature parameters). Combined with the fuel cell control function defined in step S420, the relevant parameters are substituted into the function to calculate the battery fitness (FCF) corresponding to each first power generation control parameter combination. Step S433, according to the multiple first battery fitness, clustering and iterative optimization of multiple first power generation control parameters are performed. After the optimization converges, the power generation control parameters corresponding to the maximum battery fitness in the converged power generation control parameter cluster are output to obtain the optimal power generation control parameters. Specifically, according to the multiple first battery fitness, a clustering algorithm (such as K-means) is used to divide the first power generation control parameters into different clusters (or "populations"), and the power generation control parameter combinations within the clusters are relatively close in performance. In each cluster, a power generation control parameter combination with a higher battery fitness is selected as a "seed", and iterative optimization is performed through optimization algorithms such as genetic algorithms and particle swarm algorithms to find a better power generation control parameter combination. During the iteration process, a new and better combination of power generation control parameters may be found. At this time, the power generation control parameter combination in the cluster needs to be updated, and a new cluster may also be formed. When the optimization algorithm reaches a certain number of iterations, or the change in the optimal solution in multiple consecutive iterations is less than the preset threshold, the optimization is considered to have converged. After the optimization converges, the power generation control parameter combination with the highest battery fitness is selected from all clusters as the optimal power generation control parameter.This implementation adopts a clustering and iteration-based optimization strategy. Clustering and iterative optimization can ensure that the algorithm can simultaneously explore new parameter combination areas and utilize known excellent solutions during the search process, thereby achieving the technical effect of improving search efficiency and optimization quality.

[0042] like Figure 2As shown, in a possible implementation, according to the multiple first battery fitnesses, multiple first power generation control parameters are clustered and iteratively optimized, and step S433 further includes step S4331, according to the multiple first battery fitnesses, the first power generation control parameters corresponding to the largest number of first battery fitnesses are divided into several excellent first power generation control parameters. Specifically, according to the calculated multiple first battery fitnesses, the first power generation control parameters are sorted, and from the sorted first power generation control parameters, several parameters with the largest battery fitness are selected as excellent first power generation control parameters. Step S4332, using several excellent first power generation control parameters, the other first power generation control parameters are approximately classified to obtain several power generation control parameter clusters, wherein the approximate classification includes classifying the other first power generation control parameters into the cluster of the closest excellent first power generation control parameters. Specifically, for each non-optimal first power generation control parameter, the distance between it and all the optimal first power generation control parameters is calculated (which can be Euclidean distance, Manhattan distance, etc.), and each non-optimal first power generation control parameter is classified into the cluster of the optimal first power generation control parameter closest to it. Wherein, the power generation control parameter cluster is a set composed of multiple first power generation control parameters, which are relatively close in performance and are classified under the same optimal first power generation control parameter. Step S4333, taking several optimal first power generation control parameters as the adjustment direction, adjusting the other first power generation control parameters in each power generation control parameter cluster, obtaining the second power generation control parameter, and updating several power generation control parameter clusters. Specifically, taking the optimal first power generation control parameter of the cluster as the benchmark, determining the adjustment direction of other power generation control parameters in the cluster, adjusting the other first power generation control parameters in each cluster according to the adjustment strategy (such as linear interpolation, gradient descent, etc.), obtaining the second power generation control parameter, and completing the update of the power generation control parameter cluster at the same time. Step S4334, based on the battery fitness of multiple power generation control parameters in several updated power generation control parameter clusters, the superior power generation control parameters are updated. Specifically, based on the updated power generation control parameter clusters, the battery fitness of all second power generation control parameters in each cluster is recalculated, the second power generation control parameters are reordered according to the new battery fitness, and several power generation control parameters with the largest battery fitness are reselected as new superior first power generation control parameters. Step S4335, continue to adjust and optimize based on the updated superior first power generation control parameters until the converged optimization times are reached, output the power generation control parameter cluster with the largest sum of battery fitness, and obtain the converged power generation control parameter cluster.Specifically, repeat steps S4332 to S4334, continuously iterate and optimize the power generation control parameter cluster, when the number of iterations reaches the preset convergence optimization number, or the change in the superior first power generation control parameter in multiple consecutive iterations is less than a certain threshold, it is considered that the optimization has converged, and the power generation control parameter cluster with the largest sum of battery fitness is output, and the power generation control parameter corresponding to the largest battery fitness in the cluster is the optimal solution. This implementation adopts a cluster-based iterative optimization strategy, by dividing the superior first power generation control parameter, clarifying the direction and scope of the search, forming a power generation control parameter cluster by approximate classification, combining power generation control parameters with similar performance, and adjusting and optimizing the power generation control parameters in each power generation control parameter cluster, which helps to find a better solution faster, and gradually approaches the optimal solution by iteratively updating the superior first power generation control parameter and the power generation control parameter cluster, achieving the technical effect of effectively searching for a power generation control parameter combination with better performance in a huge power generation control parameter space.

[0043] Step S500, using the optimal power generation control parameters, control the fuel cell to generate power for auxiliary power supply and heat supply. Specifically, the optimal power generation control parameters (such as fuel flow, oxygen flow, working pressure, current density, etc.) obtained after optimization are set as the operating parameters of the fuel cell, and these operating parameters are input into the control system of the fuel cell, and the power generation process of the fuel cell is started. According to the set optimal power generation control parameters, the fuel flow, oxygen flow, etc. are adjusted to ensure that the fuel cell operates in a safe and efficient state. During the operation of the fuel cell, its operating state and key parameters, such as battery temperature, voltage, current, power output, etc., are monitored in real time. At the same time, the power load and heat load on the power side and the heat side are also monitored to ensure that the power supply and heat supply of the fuel cell can meet the actual needs. If it is found during the operation that the actual operation effect is inconsistent with expectations or there are abnormal conditions (such as excessive battery temperature, unstable power output, etc.), the power generation control parameters are adjusted in time, and the power generation control parameters are continuously optimized according to the actual needs and changes in operating conditions, so as to improve the power generation efficiency and heat supply efficiency of the fuel cell, and improve the power supply and heat supply. The embodiment of the present application uses real-time collection of the battery temperature of the solid oxide fuel cell and the electricity demand characteristics and heat demand characteristics on the power side and the heat side to perform predictive analysis of the electricity consumption status and the heat consumption status. According to the prediction results, technical means such as adjusting the operating status of the fuel cell in advance and optimizing the power generation control parameters are used to achieve the technical effect of achieving efficient energy utilization and accurate satisfaction of user needs.

[0044] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A fuel cell auxiliary power supply method based on power consumption state prediction, characterized in that: The method comprises: Collecting the battery temperature of the solid oxide fuel cell currently performing cogeneration, and collecting the current electricity demand characteristics and heat demand characteristics of the electricity consumption side and the heat consumption side; According to the electricity demand characteristics and the heat demand characteristics, a power consumption state and a heat consumption state prediction analysis are performed to obtain a power consumption state prediction result and a heat consumption state prediction result, wherein the power consumption state prediction result includes a power consumption continuity parameter and a maximum power load parameter; Analyze and decide on the auxiliary power supply of the fuel cell according to the battery temperature, the power consumption state prediction result and the heat consumption state prediction result, and obtain an auxiliary power supply coefficient. When the auxiliary power supply coefficient is greater than an auxiliary power supply coefficient threshold, use the fuel cell for auxiliary power supply; The fuel cell is heated to an operating temperature, and the power generation control parameters of the fuel cell are optimized according to the power consumption state prediction result and the heat consumption state prediction result to obtain the optimal power generation control parameters, wherein the optimization is performed for the purpose of improving the power supply degree and heat supply degree of the power consumption side and the heat consumption side, and improving the power generation utilization efficiency and heat generation utilization efficiency of the fuel cell; Using the optimal power generation control parameters, controlling the fuel cell to generate power for auxiliary power supply and heat supply; The auxiliary power supply coefficient is obtained by analyzing and deciding the auxiliary power supply of the fuel cell according to the battery temperature, the power consumption state prediction result and the heat consumption state prediction result, including: Inputting the battery temperature into a heating cost coefficient comparison table for indexing to obtain a heating cost coefficient, wherein the heating cost coefficient comparison table includes an index relationship between a plurality of sample battery temperatures and a plurality of sample heating cost coefficients, and the size of the sample battery temperature is negatively correlated with the size of the sample heating cost coefficient; According to the maximum power load parameter in the power consumption state prediction result, the basic power generation utilization efficiency when the power generation power of the fuel cell reaches the maximum power load parameter is analyzed, and according to the power consumption continuity parameter, the basic power generation utilization efficiency is corrected to obtain the corrected power generation utilization efficiency and the power generation utilization coefficient; According to the maximum heat load parameter in the heat state prediction result, the basic heat utilization efficiency when the heat power of the fuel cell reaches the maximum heat load parameter is analyzed, and according to the heat continuity parameter, the basic heat utilization efficiency is corrected to obtain the corrected heat utilization efficiency and the heat utilization coefficient; Performing weighted calculation on the heating cost coefficient, power generation utilization coefficient and heating utilization coefficient to obtain an auxiliary power supply coefficient; When the auxiliary power supply coefficient is greater than the auxiliary power supply coefficient threshold, the fuel cell is used for auxiliary power supply, and when the auxiliary power supply coefficient is not greater than the auxiliary power supply coefficient threshold, the fuel cell is not used for auxiliary power supply.

2. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 1 is characterized in that: Collect the battery temperature of the solid oxide fuel cell currently performing cogeneration, as well as the current electricity demand characteristics and heat demand characteristics of the electricity side and the heat side, including: Collecting the battery temperature of the solid oxide fuel cell currently performing cogeneration; Collect the current timestamp information, as well as the power demand parameters and power user information on the power consumption side; Collect the heat demand parameters and heat user information of the current heat user side; Based on the timestamp information combined with the electricity demand parameters and the electricity user information, the electricity demand characteristics are generated; based on the timestamp information combined with the heat demand parameters and the heat user information, the heat demand characteristics are generated.

3. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 2 is characterized in that: According to the electricity demand characteristics and the heat demand characteristics, a power consumption state and a heat consumption state prediction analysis are performed to obtain a power consumption state prediction result and a heat consumption state prediction result, including: Based on the historical electricity demand data on the electricity consumption side, a sample electricity demand feature set is collected, and the electricity consumption continuity parameters and maximum electricity load parameters of electricity consumption under different sample electricity demand characteristics are obtained to obtain a sample electricity consumption state set; Using the sample power demand feature set and the sample power state set, training a power state prediction path until the training converges; Using the power consumption state prediction path that has converged in training, predicting the power consumption state of the power demand characteristics, and obtaining a power consumption state prediction result; Based on the historical heat demand data on the heat user side, a sample heat demand feature set is collected, and heat continuity parameters and maximum heat load parameters of heat users under different sample heat demand characteristics are obtained to obtain a sample heat state set; Using the sample heat demand feature set and the sample heat state set, training a heat state prediction path until the training converges; The heat usage state prediction path with converged training is adopted to perform heat usage state prediction on the heat usage demand characteristics to obtain a heat usage state prediction result.

4. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 1 is characterized in that: According to the maximum power load parameter in the power consumption state prediction result, analyzing the basic power generation efficiency when the power generation power of the fuel cell reaches the maximum power load parameter, and correcting the basic power generation efficiency according to the power consumption continuity parameter, including: According to the historical working data of the solid oxide fuel cell, a sample power generation efficiency set and a sample power generation utilization efficiency set are collected; Using the sample power generation efficiency set and the sample power generation utilization efficiency set, constructing a power generation utilization efficiency classifier, inputting and classifying the maximum power load parameter, and obtaining a basic power generation utilization efficiency; According to the ratio of the power consumption continuity parameter to the preset power consumption continuity parameter, the basic power generation utilization efficiency is corrected and calculated to obtain the corrected power generation utilization efficiency.

5. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 1 is characterized in that: According to the power consumption state prediction result and the heat consumption state prediction result, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, including: Generate a power generation control parameter space according to a fuel flow rate adjustment range, an air flow rate adjustment range and a temperature adjustment range when the fuel cell generates power; In order to improve the power supply and heat supply of the power and heat sides, and to improve the power generation efficiency and heat generation efficiency of the fuel cell, a fuel cell control function is constructed as follows: ； Among them, FCF is the battery fitness, , , and is the weight, is the ratio of the power consumption continuity parameter to the maximum power consumption continuity parameter, is the ratio of the heat continuity parameter to the maximum heat continuity parameter, and To optimize the power generation control parameters for the fuel cell power generation and heat generation, and are the maximum electrical load parameters and the maximum thermal load parameters, and The fuel input electrical power and the fuel input thermal power for power generation according to the optimized power generation control parameters; In the power generation control parameter space, the power generation control parameters of the fuel cell are optimized according to the fuel cell control function to obtain the optimal power generation control parameters.

6. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 5 is characterized in that: In the power generation control parameter space, according to the fuel cell control function, the power generation control parameters of the fuel cell are optimized to obtain the optimal power generation control parameters, including: In the power generation control parameter space, randomly generating a plurality of first power generation control parameters; According to the fuel flow parameters, air flow parameters and temperature parameters in the plurality of first power generation control parameters, a plurality of first fuel input electric powers and a first fuel input thermal power, as well as a plurality of first power generation powers and a plurality of first heating powers are analyzed and obtained, and in combination with the maximum power load parameter and the maximum thermal load parameter, a plurality of first battery fitness degrees are calculated and obtained; According to the multiple first battery fitnesses, multiple first power generation control parameters are clustered and iteratively optimized. After the optimization converges, the power generation control parameters corresponding to the maximum battery fitness in the converged power generation control parameter cluster are output to obtain the optimal power generation control parameters.

7. The fuel cell auxiliary power supply method based on power consumption state prediction according to claim 6 is characterized in that: According to the plurality of first battery fitnesses, clustering and iterative optimization of a plurality of first power generation control parameters are performed, including: According to the plurality of first battery fitnesses, dividing the first power generation control parameters corresponding to the largest plurality of first battery fitnesses into a plurality of excellent first power generation control parameters; Using a plurality of optimal first power generation control parameters, approximate classification of other first power generation control parameters to obtain a plurality of power generation control parameter clusters, wherein the approximate classification includes classifying the other first power generation control parameters into the cluster of the most adjacent optimal first power generation control parameters; Taking a plurality of excellent first power generation control parameters as adjustment directions, adjusting other first power generation control parameters in each power generation control parameter cluster, obtaining second power generation control parameters, and updating a plurality of power generation control parameter clusters; Based on the battery fitness of multiple power generation control parameters in the updated multiple power generation control parameter clusters, updating the optimal power generation control parameters; Continue to adjust and optimize based on the updated superior first power generation control parameter until the converged optimization times are reached, output the power generation control parameter cluster with the largest total battery fitness, and obtain the converged power generation control parameter cluster.

Images