An operation optimization method, device, equipment and medium for a photovoltaic storage coupled hydrogen production system

Abstract

The present application discloses an operation optimization method, device, equipment and medium of a photovoltaic-storage coupled hydrogen production system, which relates to the field of photovoltaic power and hydrogen energy technology, establishes a road resistance calculation model; uses the road resistance calculation model to calculate the road resistance, constructs a decision tree index model, trains the decision tree index model, inputs the road resistance to be predicted into the trained decision tree index model, and outputs a hydrogen consumption prediction value; inputs the hydrogen consumption prediction value into a hydrogen fuel cell vehicle hydrogen consumption model to obtain the vehicle hydrogen refueling demand, and sets operation constraints during the operation of the photovoltaic-storage coupled hydrogen refueling station system; constructs an objective function, based on the operation constraints, inputs the hydrogen consumption prediction value and the vehicle hydrogen refueling demand into the objective function to solve, generates the optimal plan of the system, optimizes the operation of the photovoltaic-storage coupled hydrogen refueling station system, can solve the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic fluctuating power scenarios, and improves the utilization rate of the photovoltaic-storage coupled hydrogen production system.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic power and hydrogen energy technology, and in particular to an operation optimization method, device, equipment and medium for a photovoltaic storage coupled hydrogen production system. Background Art

[0002] Due to the low-carbon, environmentally friendly, and easy-to-transport characteristics of hydrogen energy, the terminal hydrogen market has continued to expand in recent years, and the demand for hydrogen in transportation scenarios such as heavy trucks, ships, and commercial vehicles has continued to increase. However, after the cancellation of hydrogen energy subsidies, the cost of hydrogen remains high, which will affect the development of the hydrogen energy industry. More and more hydrogen refueling stations need to purchase hydrogen sources from other provinces and cities to ensure normal operations, but the high transportation costs have become a constraint on the development of the industry. With the large-scale and over-speed commissioning of photovoltaic power generation projects, the impact of power fluctuations on the power grid has gradually become prominent. Photovoltaic power generation hydrogen production provides a "green electricity" + "green hydrogen" solution. Although it helps to consume photovoltaic power locally, due to the volatility of photovoltaic power generation power, the demand for hydrogen energy in transportation scenarios is highly random, resulting in a low utilization rate of the photovoltaic storage coupled hydrogen production system.

[0003] From the above, it can be seen that how to solve the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under the scenario of fluctuating photovoltaic power, improve the utilization rate of the photovoltaic storage coupled hydrogen production system, and thus effectively coordinate and control the coupling process of each link in the photovoltaic storage coupled hydrogen production system is a problem to be solved in this field. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an operation optimization method, device, equipment and medium for a photovoltaic-storage coupled hydrogen production system, which can solve the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic power fluctuation scenarios, improve the utilization rate of the photovoltaic-storage coupled hydrogen production system, and effectively coordinate and control the coupling process of each link in the photovoltaic-storage coupled hydrogen production system. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses an operation optimization method for a photovoltaic-storage coupled hydrogen production system, comprising:

[0006] Establishing a road resistance calculation model, obtaining historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculating corresponding historical road resistances using the road resistance calculation model, and generating a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistances;

[0007] Using the historical road resistance as a selection feature to construct a decision tree index model, using the historical data set to train the decision tree index model to obtain the trained decision tree index model, and inputting the road resistance to be predicted into the trained decision tree index model to output a predicted value of hydrogen consumption;

[0008] Establishing a hydrogen consumption model for a hydrogen fuel cell vehicle, inputting the predicted hydrogen consumption value into the hydrogen consumption model to obtain the hydrogen refueling demand of the hydrogen fuel cell vehicle, and setting operating constraints during the operation of the photovoltaic-storage coupled hydrogen refueling station system;

[0009] Construct an objective function, based on the operating constraints and input the predicted hydrogen consumption and the vehicle hydrogen refueling demand into the objective function to solve the problem, so as to obtain each power, and optimize the operation of the photovoltaic storage coupled hydrogen refueling station system according to the optimal planning of each power generation system based on the optimal planning of the system.

[0010] Optionally, the road resistance calculation model is:

[0011] ;

[0012] ;

[0013] Among them, ij is the road section, Because the road is blocked, The zero-flow travel time, 、 is the impedance influencing factor, s is the road saturation, c is the signal period, is the green-to-signal ratio, q is the vehicle arrival rate on the road section, is the psychological reaction intensity coefficient, is the arrival rate of vehicles from the stop line of the intersection to the implicit conflict point, K is the traffic density, h is the average length of the vehicle, is the average distance between vehicles when the road is blocked, n is the number of one-way motor vehicle lanes, is the correction factor for non-motor vehicles, is the pedestrian correction coefficient, is the intersection correction coefficient, is the lane correction factor.

[0014] Optionally, obtaining the historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under unit road resistance, calculating the corresponding historical road resistance using the road resistance calculation model, and generating a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistance include:

[0015] Obtaining historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under unit road resistance, and inputting the historical hydrogen consumption per unit distance into the road resistance calculation model to calculate the corresponding historical road resistance;

[0016] Calculating a ratio between the historical hydrogen consumption per unit distance and the historical road resistance, and using the ratio as the historical hydrogen consumption of the hydrogen fuel cell vehicle under unit road resistance;

[0017] A historical data set is generated based on the historical hydrogen consumption and the historical road resistance.

[0018] Optionally, the historical road resistance is used as a selection feature to construct a decision tree index model, and the decision tree index model is trained using the historical data set to obtain the trained decision tree index model, including:

[0019] The historical road resistance is used as a selection feature, and the historical data set is divided into intervals according to the selection feature to obtain intervals, and the corresponding thresholds of each interval are used as the decision tree values ​​of the leaf nodes in the decision tree to construct a decision tree index model;

[0020] The decision tree index model is sorted by hydrogen consumption per unit road resistance using each of the intervals to obtain the trained decision tree index model.

[0021] Optionally, the operating constraints include hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints and power balance constraints.

[0022] Optionally, the hydrogen consumption model of the hydrogen fuel cell vehicle is:

[0023] ;

[0024] ;

[0025] ;

[0026] ;

[0027] in, is the hydrogen consumption of the hydrogen fuel cell vehicle in the cumulative travel distance of A driving calculation sections during period t, Calculate the road resistance to be predicted for A driving sections. Calculate the distance of the road segment for each trip, for The corresponding predicted value of hydrogen fuel cell vehicles, is the hydrogen storage capacity of the hydrogen fuel cell vehicle after the end of period t, is the initial hydrogen storage capacity of the hydrogen fuel cell vehicle at the beginning of period t, is the hydrogen consumption of the vehicle in the cumulative travel distance of B hydrogen refueling calculation sections during period t, The road resistance to be predicted for B hydrogenation calculation sections, The distance of each hydrogenation calculation section, for The corresponding predicted value of hydrogen fuel cell vehicles, Reserve a minimum amount of hydrogen for the vehicle;

[0028] Accordingly, the hydrogen consumption prediction value is input into the hydrogen consumption model of the hydrogen fuel cell vehicle to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, including:

[0029] The predicted hydrogen consumption value is input into the hydrogen consumption model of the hydrogen fuel cell vehicle to output the vehicle's minimum reserved hydrogen storage capacity, and the vehicle's minimum reserved hydrogen storage capacity is used as the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle.

[0030] Optionally, constructing an objective function based on the operating constraints and inputting the predicted hydrogen consumption value and the vehicle hydrogen refueling demand into the objective function for solution includes:

[0031] Construct an objective function with the goal of minimizing system operating costs and minimizing carbon emissions;

[0032] A snow melting optimization algorithm is adopted, based on the operation constraints, and the predicted hydrogen consumption value and the vehicle hydrogen refueling demand are input into the objective function to solve the problem.

[0033] In a second aspect, the present application discloses an operation optimization device for a photovoltaic-storage coupled hydrogen production system, comprising:

[0034] a data set generation module, configured to establish a road resistance calculation model, obtain historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculate corresponding historical road resistances using the road resistance calculation model, and generate a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistances;

[0035] a hydrogen consumption prediction module, configured to use the historical road resistance as a selection feature to construct a decision tree index model, train the decision tree index model using the historical data set to obtain a trained decision tree index model, input the road resistance to be predicted into the trained decision tree index model, and output a predicted hydrogen consumption value;

[0036] A constraint condition construction module is used to establish a hydrogen consumption model for hydrogen fuel cell vehicles, input the predicted hydrogen consumption value into the hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and set the operation constraint conditions during the operation of the photovoltaic storage coupled hydrogen refueling station system;

[0037] The system operation optimization module is used to construct an objective function, based on the operation constraints and inputting the predicted hydrogen consumption value and the vehicle hydrogen refueling demand into the objective function to solve the problem, so as to obtain each power, based on the optimal planning of each power generation system, and optimize the operation of the photovoltaic storage coupled hydrogen refueling station system according to the system optimal planning.

[0038] In a third aspect, the present application discloses an electronic device, comprising:

[0039] Memory, used to store computer programs;

[0040] The processor is used to execute the computer program to implement the operation optimization method of the aforementioned photovoltaic storage coupled hydrogen production system.

[0041] In a fourth aspect, the present application discloses a computer storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the steps of the operation optimization method of the aforementioned photovoltaic storage coupled hydrogen production system are implemented.

[0042] It can be seen that the present application provides an operation optimization method for a photovoltaic storage coupled hydrogen production system, including establishing a road resistance calculation model, obtaining the historical unit distance hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, using the road resistance calculation model to calculate the corresponding historical road resistance, and generating a historical data set based on the historical unit distance hydrogen consumption and the historical road resistance; using the historical road resistance as a selection feature to construct a decision tree index model, using the historical data set to train the decision tree index model to obtain the trained decision tree index model, and inputting the road resistance to be predicted into the trained decision tree index model. A tree index model is established to output a predicted value of hydrogen consumption; a hydrogen fuel cell vehicle hydrogen consumption model is established, and the predicted value of hydrogen consumption is input into the hydrogen fuel cell vehicle hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and operating constraints are set during the operation of the photovoltaic storage coupling hydrogen refueling station system; an objective function is constructed, and based on the operating constraints, the predicted value of hydrogen consumption and the vehicle hydrogen refueling demand are input into the objective function to solve, so as to obtain each power, and based on the optimal planning of each power generation system, the operation of the photovoltaic storage coupling hydrogen refueling station system is optimized according to the optimal planning of the system. This application establishes a road resistance calculation model and constructs a decision tree index model to predict the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, and further obtains the vehicle hydrogen refueling demand of hydrogen fuel cell vehicles, which is conducive to the large-scale and commercial promotion of photovoltaic storage coupled hydrogen production in the transportation field. It sets operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system, solves the objective function, and finally generates the optimal planning of the system to achieve operational optimization of the photovoltaic storage coupled hydrogen refueling station system, effectively solves the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic fluctuating power scenarios, reduces the dependence of hydrogen refueling stations on external hydrogen sources, reduces hydrogen refueling costs, and improves the utilization rate of the photovoltaic storage coupled hydrogen production system, thereby effectively coordinating and controlling the coupling process of each link in the photovoltaic storage coupled hydrogen production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0044] Figure 1 This is a flow chart of an operation optimization method for a photovoltaic-storage coupled hydrogen production system disclosed in this application;

[0045] Figure 2 A flowchart for constructing a tree index model disclosed in this application;

[0046] Figure 3 This is a flow chart of an operation optimization method for a photovoltaic-storage coupled hydrogen production system disclosed in this application;

[0047] Figure 4 A specific flow chart for the operation optimization of a photovoltaic-storage coupled hydrogen production system disclosed in this application;

[0048] Figure 5 This is a schematic diagram of the structure of an operation optimization device for a photovoltaic-storage coupled hydrogen production system disclosed in this application;

[0049] Figure 6 This is a structural diagram of an electronic device provided in this application. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] Due to its low-carbon, environmentally friendly, and easily transportable characteristics, the end-use hydrogen market has continued to expand in recent years, with increasing demand for hydrogen in transportation applications such as heavy trucks, ships, and commercial vehicles. However, even after the removal of hydrogen subsidies, hydrogen costs remain high, hindering the development of the hydrogen energy industry. An increasing number of hydrogen refueling stations need to procure hydrogen from other provinces and cities to ensure normal operations, but high transportation costs are hindering the industry's development. With the rapid commissioning of photovoltaic power generation projects, the impact of power fluctuations on the power grid is becoming increasingly prominent. Photovoltaic power generation (PV-H2) provides a "green electricity + green hydrogen" solution, which helps to locally consume PV power. However, due to the volatility of PV power generation, the demand for hydrogen in transportation applications is highly random, resulting in low utilization rates of PV-storage-coupled hydrogen production systems. Therefore, addressing the challenges of flexibly matching hydrogen demand for hydrogen fuel cell vehicles in fluctuating PV power scenarios, improving the utilization rate of PV-storage-coupled hydrogen production systems, and effectively coordinating and controlling the coupling processes of PV-storage-coupled hydrogen production systems remain unresolved challenges in this field.

[0052] See also Figure 1 As shown, the embodiment of the present invention discloses an operation optimization method for a photovoltaic-storage coupled hydrogen production system, which may specifically include:

[0053] Step S11: Establish a road resistance calculation model, obtain the historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculate the corresponding historical road resistance using the road resistance calculation model, and generate a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistance.

[0054] In this embodiment, since the hydrogen energy consumption of vehicles during driving changes with the road conditions, in order to accurately describe the road structure and traffic network conditions, a graph theory method is used to quantify the road network topology model to extract the key parameter road resistance. The established road resistance calculation model is:

[0055] ;

[0056] ;

[0057] Among them, ij is the road section, Because the road is blocked, The zero-flow travel time, 、 is the impedance influencing factor, s is the road saturation, c is the signal period, is the green-to-signal ratio, q is the vehicle arrival rate on the road section, is the psychological reaction intensity coefficient, is the arrival rate of vehicles from the stop line of the intersection to the implicit conflict point, K is the traffic density, h is the average length of the vehicle, is the average distance between vehicles when the road is blocked, n is the number of one-way motor vehicle lanes, is the correction factor for non-motor vehicles, is the pedestrian correction coefficient, is the intersection correction coefficient, is the lane correction factor.

[0058] In this embodiment, after establishing a road resistance calculation model, the historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under unit road resistance is obtained, and the historical hydrogen consumption per unit distance is input into the road resistance calculation model to calculate the corresponding historical road resistance. The ratio between the historical hydrogen consumption per unit distance and the historical road resistance is calculated, and the ratio is used as the historical hydrogen consumption of the hydrogen fuel cell vehicle under unit road resistance. A historical data set is generated based on the historical hydrogen consumption and the historical road resistance.

[0059] Specifically, as the vehicle travels along the driving route, the hydrogen refueling route between the vehicle and the hydrogen refueling station also changes hourly. The user can divide the route to be calculated during the driving process of the hydrogen fuel cell vehicle in period t according to the driving route and the location of the hydrogen refueling station. The sections to be calculated are marked as ij according to the starting point and the end point. The sections to be calculated include A driving calculation sections and B hydrogen refueling calculation sections: Get the historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle hourly , input the historical hydrogen consumption per unit distance into the road resistance calculation model, and calculate the historical road resistance of the corresponding distance , using the formula , calculate and The ratio between them is used as the historical hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance. , based on the corresponding and A set of historical data is formed to generate a historical data set.

[0060] Step S12: Use the historical road resistance as a selection feature to construct a decision tree index model, use the historical data set to train the decision tree index model to obtain the trained decision tree index model, input the road resistance to be predicted into the trained decision tree index model to output the hydrogen consumption prediction value.

[0061] In this embodiment, the road resistance calculation model is used to calculate the road resistance per unit distance at the current moment, and the historical road resistance is used as a selection feature. The historical data set is divided into intervals according to the selection feature to obtain each interval, and the corresponding threshold value of each interval is used as the decision tree value of the leaf node within the decision tree to construct a decision tree index model. The decision tree index model is sorted by unit resistance hydrogen consumption using each interval to obtain the trained decision tree index model, and the road resistance to be predicted is input into the trained decision tree index model to output the predicted value of hydrogen consumption.

[0062] Among them, the decision tree index model construction process is as follows Figure 2 As shown, As the selection feature of the decision tree index model, the historical data set is divided into 10 intervals, and the threshold of each interval is used as the decision value of the leaf node in the decision tree to construct the decision tree index model. Since there is a correspondence between the unit distance road resistance in a certain period and the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, that is, each historical unit distance road resistance in a certain period of time There is a corresponding collection The learning goal of the decision tree in this application is to sort the collected hourly historical data set into 10 selected feature intervals, and summarize the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance corresponding to these sorting categories. Based on this, after training the decision tree, when a new unit distance is input to predict the road resistance , can output the predicted value of hydrogen consumption of hydrogen fuel cell vehicles under this classification .

[0063] The specific formula for outputting the predicted value of hydrogen consumption is as follows:

[0064] Initialize the prediction function f(x) as:

[0065] ;

[0066] The loss function is:

[0067] ;

[0068] Negative gradient of loss function , that is, the approximate value of the residual is:

[0069] ;

[0070] Sample hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance The mean for:

[0071] ;

[0072] The data obtained in the previous iteration is used as training data, and the iteration is continued to obtain the final prediction function f(x), that is, the trained decision tree index model is:

[0073] ;

[0074] Among them, N is the number of samples, m is the number of iterations, and j is the number of feature intervals selected by the decision tree. Select features for input, namely historical unit distance road resistance, For samples The corresponding historical hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance , is the predicted value of hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance .

[0075] Step S13: Establish a hydrogen consumption model for a hydrogen fuel cell vehicle, input the predicted hydrogen consumption value into the hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and set operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system.

[0076] In this embodiment, the hydrogen consumption model of the hydrogen fuel cell vehicle is:

[0077] ;

[0078] ;

[0079] ;

[0080] ;

[0081] in, is the hydrogen consumption of the hydrogen fuel cell vehicle in the cumulative travel distance of A driving calculation sections during period t, Calculate the road resistance to be predicted for A driving sections. Calculate the distance of the road segment for each trip, for The corresponding predicted value of hydrogen fuel cell vehicles, is the hydrogen storage capacity of the hydrogen fuel cell vehicle after the end of period t, is the initial hydrogen storage capacity of the hydrogen fuel cell vehicle at the beginning of period t, is the hydrogen consumption of the vehicle in the cumulative travel distance of B hydrogen refueling calculation sections during period t, The road resistance to be predicted for B hydrogenation calculation sections, The distance of each hydrogenation calculation section, for The corresponding predicted value of hydrogen fuel cell vehicles, Reserve the minimum hydrogen storage capacity for the vehicle.

[0082] In this embodiment, after establishing a hydrogen fuel cell vehicle hydrogen consumption model, the hydrogen consumption prediction value is input into the hydrogen fuel cell vehicle hydrogen consumption model to output the vehicle's minimum reserved hydrogen storage capacity. The vehicle's minimum reserved hydrogen storage capacity is used as the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and then the operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system are set.

[0083] The specific calculation process is: the road resistance to be predicted According to the corresponding relationship between A driving calculation section and B hydrogenation calculation section, it is divided into and By predicting the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, we can obtain the and Predicted value of hydrogen fuel cell vehicles corresponding to unit road resistance and , a hydrogen fuel cell vehicle hydrogen consumption model is established for the driving process of hydrogen fuel cell vehicles. The specific hydrogen fuel cell vehicle hydrogen consumption model is shown above. During the operation optimization process, if Established, that is, when a vehicle travels to a certain driving calculation section during a certain period of time, the initial hydrogen storage capacity of the hydrogen fuel cell vehicle Subtract the hydrogen consumption of the vehicle to the hydrogen refueling station Less than or equal to the vehicle's minimum reserved hydrogen storage capacity When the vehicle stops driving the calculated route and goes to the hydrogenation station to refuel, the vehicle refueling period begins, and a new round of operation optimization begins after the refueling is completed. The amount of hydrogen refueled each time is the vehicle's rated hydrogen refueling amount. .

[0084] Step S14: Construct an objective function based on the operating constraints and input the predicted hydrogen consumption value and the vehicle hydrogen refueling demand into the objective function to solve the problem, so as to obtain each power. Based on the optimal planning of each power generation system, the operation of the photovoltaic storage coupled hydrogen refueling station system is optimized according to the optimal planning of the system.

[0085] In this embodiment, a road resistance calculation model is established to obtain the historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, the corresponding historical road resistance is calculated using the road resistance calculation model, and a historical data set is generated based on the historical hydrogen consumption per unit distance and the historical road resistance; the historical road resistance is used as a selection feature to construct a decision tree index model, the decision tree index model is trained using the historical data set to obtain the trained decision tree index model, the road resistance to be predicted is input into the trained decision tree index model to output a predicted hydrogen consumption value; a hydrogen fuel cell vehicle hydrogen consumption model is established, the predicted hydrogen consumption value is input into the hydrogen fuel cell vehicle hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and operating constraints are set during the operation of the photovoltaic storage coupled hydrogen refueling station system; an objective function is constructed, and the hydrogen consumption prediction value and the vehicle hydrogen refueling demand are input into the objective function based on the operating constraints to obtain each power, and based on the optimal planning of each power generation system, the operation of the photovoltaic storage coupled hydrogen refueling station system is optimized according to the optimal planning of the system. This application establishes a road resistance calculation model and constructs a decision tree index model to predict the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, and further obtains the vehicle hydrogen refueling demand of hydrogen fuel cell vehicles, which is conducive to the large-scale and commercial promotion of photovoltaic storage coupled hydrogen production in the transportation field. It sets operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system, solves the objective function, and finally generates the optimal planning of the system to achieve operational optimization of the photovoltaic storage coupled hydrogen refueling station system, effectively solves the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic fluctuating power scenarios, reduces the dependence of hydrogen refueling stations on external hydrogen sources, reduces hydrogen refueling costs, and improves the utilization rate of the photovoltaic storage coupled hydrogen production system, thereby effectively coordinating and controlling the coupling process of each link in the photovoltaic storage coupled hydrogen production system.

[0086] See also Figure 3 As shown, the embodiment of the present invention discloses an operation optimization method for a photovoltaic-storage coupled hydrogen production system, which may specifically include:

[0087] Step S21: Establish a road resistance calculation model, obtain the historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculate the corresponding historical road resistance using the road resistance calculation model, and generate a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistance.

[0088] Step S22: Use the historical road resistance as a selection feature to construct a decision tree index model, use the historical data set to train the decision tree index model to obtain the trained decision tree index model, input the road resistance to be predicted into the trained decision tree index model to output the predicted value of hydrogen consumption.

[0089] Step S23: Establish a hydrogen consumption model for a hydrogen fuel cell vehicle, input the predicted hydrogen consumption value into the hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and set operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system; the operating constraints include hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints, and power balance constraints.

[0090] In this embodiment, the constraints of the hydrogen production system of the hydrogen refueling station are:

[0091] ;

[0092] The above formula calculates the hydrogen produced by the hydrogen production system Required electrical power , is the electrical efficiency of the hydrogen production system, Indicates the lower calorific value of hydrogen (kWh / N );

[0093] ;

[0094] ;

[0095] The electric power required by the hydrogen production system is limited between a minimum value and a maximum value, ensuring that the power required by the hydrogen production system is equal to the share of photovoltaic power generation allocated to the hydrogen production system.

[0096] The hydrogen storage constraints are:

[0097] ;

[0098] ;

[0099] The above formula limits the hydrogen storage and desorption processes to occur between the minimum and maximum limits respectively;

[0100] ;

[0101] The above formula indicates that the storage and use processes do not occur at the same time;

[0102] ;

[0103] The above formula relates the amount of hydrogen stored at time t on a certain day to the amount of hydrogen stored at time t-1 on the same day. The efficiency of the hydrogen storage system of the hydrogen refueling station;

[0104] ;

[0105] ;

[0106] in, is the amount of hydrogen stored in the hydrogen storage system during period t, is the amount of hydrogen released by the hydrogen storage system during period t, is the maximum amount of hydrogen stored in the hydrogen storage system, is the maximum amount of hydrogen released by the hydrogen storage system, is the 0-1 state variable of the hydrogen storage system for storing hydrogen in period t, is the 0-1 state variable of the hydrogen storage system for releasing hydrogen during period t.

[0107] The photovoltaic operation constraints are:

[0108] ;

[0109] ;

[0110] in, is the photovoltaic area, is the photovoltaic power generation power during period t, is the total solar irradiance (kW / ), is the photovoltaic power generation efficiency.

[0111] The mathematical model of electrochemical energy storage and its constraints, namely the energy storage operation constraints, include: (1) the energy storage charging and discharging power does not exceed the maximum rated power:

[0112] ;

[0113] ;

[0114] in, is the energy storage discharge power during period t, is the energy storage charging power during period t, is the maximum charge and discharge power;

[0115] (2) Energy storage charging and discharging cannot be performed simultaneously:

[0116] ;

[0117] in, 、 It is a 0-1 state variable to ensure that charging and discharging cannot be performed at the same time;

[0118] (3) Electrochemical energy storage charging and discharging process operating formula:

[0119] ;

[0120] in, is the state of charge of the energy storage battery during period t, is the state of charge of the energy storage battery during period t-1, 、 are the charge and discharge efficiency of ES, is the energy storage capacity.

[0121] The real-time power balance constraint during normal system operation, that is, the power balance constraint condition is:

[0122] ;

[0123] ;

[0124] in, is the purchased power, For the electricity sold, is the photovoltaic output power, To access the remaining load power except the hydrogen production system in the photovoltaic storage coupled hydrogen station system, Charging power for energy storage power station, is the discharge power of the energy storage station.

[0125] Step S24: Construct an objective function with the goal of minimizing system operating costs and minimizing carbon emissions, adopt a snow melting optimization algorithm, based on operating constraints and input the predicted hydrogen consumption value and vehicle hydrogen refueling demand into the objective function to solve, so as to obtain each power, based on the optimal planning of each power generation system, and optimize the operation of the photovoltaic storage coupled hydrogen refueling station system according to the optimal planning of the system.

[0126] In this embodiment, the photovoltaic-storage coupled hydrogen refueling station system can generate revenue through photovoltaic grid access, energy storage peak-valley arbitrage, and hydrogen sales to hydrogen fuel cell vehicles. With the goal of minimizing system operating costs and minimizing carbon emissions, an objective function is established and solved by setting weights for each objective function. The objective function is as follows:

[0127] ;

[0128] ;

[0129] ;

[0130] ;

[0131] in, is the total cost of system operation, is the net electricity purchase cost, The electricity purchase price, is the purchased power, The electricity price is For the electricity sold, For operation and maintenance costs, is the operation and maintenance cost per kilowatt-hour of photovoltaic power generation, is the photovoltaic power generation power, is the operation and maintenance cost per kilowatt-hour of energy storage, 、 are the charging and discharging power of the energy storage station, The maintenance cost of each cubic meter of hydrogen sold at the hydrogen filling station, is the amount of hydrogen sold, To earn revenue from hydrogen sales, is the hydrogen selling price, T is the scheduling period;

[0132] ;

[0133] in, is the total carbon emissions of the system, is the system carbon emission factor, is the purchased power, For the sale of electricity power.

[0134] The specific process of this application is as follows Figure 4 As shown, the energy cost and carbon emission objective functions mentioned above are solved by the snow melting optimization algorithm. When the above hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints and power balance constraints are met, the solution results under the objective function are obtained, and the hourly power of each system is output. The state variables and vehicle hydrogenation time periods are determined based on each power. Finally, the optimal system planning of the photovoltaic-storage coupled hydrogen refueling station system under the two objectives is generated, and the operation of the photovoltaic-storage coupled hydrogen refueling station system is optimized according to the system optimal planning.

[0135] In the snow melting optimization algorithm, the iterative process starts with a randomly generated population. The entire population Z is modeled as a matrix with N rows and D columns, where N is the size of the population and D is the dimension of the solution space:

[0136] ;

[0137] Among them, U is the upper bound of the solution space, L is the lower bound of the solution space, is a randomly generated number in [0, 1].

[0138] Standard Brownian motion is used to simulate the highly dispersed characteristics of the search process data. The step size is obtained by the probability density function based on the normal distribution with a mean of zero and a variance of 1. The mathematical expression is as follows:

[0139] ;

[0140] The position calculation formula during the search process is as follows:

[0141] ;

[0142] in, represents the i-th individual during the t-th iteration, is a vector containing random numbers based on Gaussian distribution, representing Brownian motion, is the convolution operation, represents a number randomly selected from [0, 1], G(t) is the current optimal solution, Elite(t) is the set of individuals randomly selected from the elite group, is the center of mass of the entire swarm.

[0143] ;

[0144] ;

[0145] in, and Represent the second and third best individuals in the current bee colony, is the centroid position of the individuals with the top 50% fitness values. In this algorithm, the individuals with the top 50% fitness values ​​are called leaders.

[0146] ;

[0147] in, is the number of leaders, which is half of the entire swarm, is the i-th optimal leader; therefore, in each iteration, Elite(t) is randomly selected from the set of the current optimal solution, the second-best individual, the third-best individual, and the centroid position of the leader, and the parameter Responsible for controlling the movement of the center of mass of the current optimal individual and leader.

[0148] This application establishes a road resistance calculation model, constructs a decision tree index model to predict the hourly hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, establishes a response relationship between real-time road conditions and vehicle hydrogen consumption, and further calculates the hydrogen refueling demand of hydrogen fuel cell vehicles. Set the operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system, which include hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints, and power balance constraints. Construct an objective function with the goal of minimizing system operating costs and minimizing carbon emissions. Solve the objective function through the snow melting optimization algorithm to obtain the solution under the objective function, that is, the corresponding hourly power of each system. Based on each power, determine the state variables and vehicle hydrogen refueling time period, and finally obtain the system optimal planning of the photovoltaic storage coupled hydrogen refueling station system under the two objectives. According to the system optimal planning, the operation of the photovoltaic storage coupled hydrogen refueling station system is optimized. It effectively solves the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under the scenario of fluctuating photovoltaic power, which is conducive to the large-scale and commercial promotion of photovoltaic storage coupled hydrogen production in the transportation field. The combination of distributed photovoltaics and hydrogen refueling stations promotes the local consumption of new energy electricity, reduces the dependence of hydrogen refueling stations on external hydrogen sources, reduces the cost of hydrogen refueling, promotes the promotion of hydrogen fuel cell vehicles, and achieves the goal of "hydrogen-electricity integration, green hydrogen and carbon reduction".

[0149] In this embodiment, a road resistance calculation model is established to obtain the historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, the corresponding historical road resistance is calculated using the road resistance calculation model, and a historical data set is generated based on the historical hydrogen consumption per unit distance and the historical road resistance; the historical road resistance is used as a selection feature to construct a decision tree index model, the decision tree index model is trained using the historical data set to obtain the trained decision tree index model, the road resistance to be predicted is input into the trained decision tree index model to output a predicted hydrogen consumption value; a hydrogen fuel cell vehicle hydrogen consumption model is established, the predicted hydrogen consumption value is input into the hydrogen fuel cell vehicle hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and operating constraints are set during the operation of the photovoltaic storage coupled hydrogen refueling station system; an objective function is constructed, and the hydrogen consumption prediction value and the vehicle hydrogen refueling demand are input into the objective function based on the operating constraints to obtain each power, and based on the optimal planning of each power generation system, the operation of the photovoltaic storage coupled hydrogen refueling station system is optimized according to the optimal planning of the system. This application establishes a road resistance calculation model and constructs a decision tree index model to predict the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, and further obtains the vehicle hydrogen refueling demand of hydrogen fuel cell vehicles, which is conducive to the large-scale and commercial promotion of photovoltaic storage coupled hydrogen production in the transportation field. It sets operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system, solves the objective function, and finally generates the optimal planning of the system to achieve operational optimization of the photovoltaic storage coupled hydrogen refueling station system, effectively solves the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic fluctuating power scenarios, reduces the dependence of hydrogen refueling stations on external hydrogen sources, reduces hydrogen refueling costs, and improves the utilization rate of the photovoltaic storage coupled hydrogen production system, thereby effectively coordinating and controlling the coupling process of each link in the photovoltaic storage coupled hydrogen production system.

[0150] See also Figure 5 As shown, an embodiment of the present invention discloses an operation optimization device for a photovoltaic-storage coupled hydrogen production system, which may specifically include:

[0151] A data set generation module 11 is configured to establish a road resistance calculation model, obtain historical hydrogen consumption per unit distance of a hydrogen fuel cell vehicle under unit road resistance, calculate corresponding historical road resistances using the road resistance calculation model, and generate a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistances;

[0152] a hydrogen consumption prediction module 12, configured to use the historical road resistance as a selection feature to construct a decision tree index model, train the decision tree index model using the historical data set to obtain a trained decision tree index model, input the road resistance to be predicted into the trained decision tree index model, and output a predicted hydrogen consumption value;

[0153] A constraint condition construction module 13 is used to establish a hydrogen consumption model for hydrogen fuel cell vehicles, input the predicted hydrogen consumption value into the hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and set operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system;

[0154] The system operation optimization module 14 is used to construct an objective function, based on the operation constraints and inputting the hydrogen consumption prediction value and the vehicle hydrogen refueling demand into the objective function to solve, so as to obtain each power, based on the optimal planning of each power generation system, and according to the optimal planning of the system, to optimize the operation of the photovoltaic storage coupled hydrogen refueling station system.

[0155] In this embodiment, a road resistance calculation model is established to obtain the historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, the corresponding historical road resistance is calculated using the road resistance calculation model, and a historical data set is generated based on the historical hydrogen consumption per unit distance and the historical road resistance; the historical road resistance is used as a selection feature to construct a decision tree index model, the decision tree index model is trained using the historical data set to obtain the trained decision tree index model, the road resistance to be predicted is input into the trained decision tree index model to output a predicted hydrogen consumption value; a hydrogen fuel cell vehicle hydrogen consumption model is established, the predicted hydrogen consumption value is input into the hydrogen fuel cell vehicle hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and operating constraints are set during the operation of the photovoltaic storage coupled hydrogen refueling station system; an objective function is constructed, and the hydrogen consumption prediction value and the vehicle hydrogen refueling demand are input into the objective function based on the operating constraints to obtain each power, and based on the optimal planning of each power generation system, the operation of the photovoltaic storage coupled hydrogen refueling station system is optimized according to the optimal planning of the system. This application establishes a road resistance calculation model and constructs a decision tree index model to predict the hydrogen consumption of hydrogen fuel cell vehicles under unit road resistance, and further obtains the vehicle hydrogen refueling demand of hydrogen fuel cell vehicles, which is conducive to the large-scale and commercial promotion of photovoltaic storage coupled hydrogen production in the transportation field. It sets operating constraints during the operation of the photovoltaic storage coupled hydrogen refueling station system, solves the objective function, and finally generates the optimal planning of the system to achieve operational optimization of the photovoltaic storage coupled hydrogen refueling station system, effectively solves the problem of flexibly matching the hydrogen demand of hydrogen fuel cell vehicles under photovoltaic fluctuating power scenarios, reduces the dependence of hydrogen refueling stations on external hydrogen sources, reduces hydrogen refueling costs, and improves the utilization rate of the photovoltaic storage coupled hydrogen production system, thereby effectively coordinating and controlling the coupling process of each link in the photovoltaic storage coupled hydrogen production system.

[0156] In some specific embodiments, the road resistance calculation model is:

[0157] ;

[0158] ;

[0159] Among them, ij is the road section, Because the road is blocked, The zero-flow travel time, 、 is the impedance influencing factor, s is the road saturation, c is the signal period, is the green-to-signal ratio, q is the vehicle arrival rate on the road section, is the psychological reaction intensity coefficient, is the arrival rate of vehicles from the stop line of the intersection to the implicit conflict point, K is the traffic density, h is the average length of the vehicle, is the average distance between vehicles when the road is blocked, n is the number of one-way motor vehicle lanes, is the correction factor for non-motor vehicles, is the pedestrian correction coefficient, is the intersection correction coefficient, is the lane correction factor.

[0160] In some specific embodiments, the data set generation module 11 may specifically include:

[0161] A historical road resistance calculation module is used to obtain the historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under unit road resistance, and input the historical hydrogen consumption per unit distance into the road resistance calculation model to calculate the corresponding historical road resistance;

[0162] a ratio calculation module, configured to calculate a ratio between the historical hydrogen consumption per unit distance and the historical road resistance, and use the ratio as the historical hydrogen consumption of the hydrogen fuel cell vehicle under unit road resistance;

[0163] A historical data set generation module is used to generate a historical data set based on the historical hydrogen consumption and the historical road resistance.

[0164] In some specific embodiments, the hydrogen consumption prediction module 12 may specifically include:

[0165] An interval division module is used to use the historical road resistance as a selection feature, divide the historical data set into intervals according to the selection feature to obtain intervals, and use the corresponding threshold of each interval as the leaf node decision tree value within the decision tree to construct a decision tree index model;

[0166] The model training module is used to use each of the intervals to sort the hydrogen consumption per unit road resistance of the decision tree index model to obtain the trained decision tree index model.

[0167] In some specific embodiments, the operating constraints include hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints, and power balance constraints.

[0168] In some specific embodiments, the hydrogen consumption model of the hydrogen fuel cell vehicle is:

[0169] ;

[0170] ;

[0171] ;

[0172] ;

[0173] in, is the hydrogen consumption of the hydrogen fuel cell vehicle in the cumulative travel distance of A driving calculation sections during period t, Calculate the road resistance to be predicted for A driving sections. Calculate the distance of the road segment for each trip, for The corresponding predicted value of hydrogen fuel cell vehicles, is the hydrogen storage capacity of the hydrogen fuel cell vehicle after the end of period t, is the initial hydrogen storage capacity of the hydrogen fuel cell vehicle at the beginning of period t, is the hydrogen consumption of the vehicle in the cumulative travel distance of B hydrogen refueling calculation sections during period t, The road resistance to be predicted for B hydrogenation calculation sections, The distance of each hydrogenation calculation section, for The corresponding predicted value of hydrogen fuel cell vehicles, Reserve the minimum hydrogen storage capacity for the vehicle.

[0174] In some specific embodiments, the constraint condition construction module 13 may specifically include:

[0175] The minimum reserved hydrogen storage capacity calculation module is used to input the hydrogen consumption prediction value into the hydrogen consumption model of the hydrogen fuel cell vehicle to output the vehicle's minimum reserved hydrogen storage capacity, and use the vehicle's minimum reserved hydrogen storage capacity as the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle.

[0176] In some specific embodiments, the system operation optimization module 14 may specifically include:

[0177] An objective function building module is used to build an objective function with the goal of minimizing system operating costs and minimizing carbon emissions;

[0178] The objective function solving module is used to adopt the snow melting optimization algorithm, based on the operation constraints, and input the hydrogen consumption prediction value and the vehicle hydrogen refueling demand into the objective function for solving.

[0179] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps of the operation optimization method for a photovoltaic-storage-coupled hydrogen production system performed by the electronic device as disclosed in any of the aforementioned embodiments.

[0180] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device. The communication protocol it follows is any communication protocol that can be applied to the technical solution of this application and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world. Its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0181] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or CD, etc. The resources stored thereon include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0182] Among them, the operating system 221 is used to manage and control the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to calculate and process the data 223 in the memory 22. It can be Windows, Unix, Linux, etc. In addition to including computer programs that can be used to complete the operation optimization method of the photovoltaic storage coupled hydrogen production system performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include computer programs that can be used to complete other specific tasks. In addition to including data transmitted from external devices and received by the operation optimization device of the photovoltaic storage coupled hydrogen production system, the data 223 can also include data collected by its own input and output interface 25.

[0183] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0184] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the operation optimization method steps of the photovoltaic storage coupled hydrogen production system disclosed in any of the aforementioned embodiments are implemented.

[0185] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or device comprising the element.

[0186] The above is a detailed introduction to the operation optimization method, device, equipment and storage medium of a photo-storage coupled hydrogen production system provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An operation optimization method for a photovoltaic-storage coupled hydrogen production system, characterized in that: include: Establishing a road resistance calculation model, obtaining historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculating corresponding historical road resistances using the road resistance calculation model, and generating a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistances; Using the historical road resistance as a selection feature to construct a decision tree index model, using the historical data set to train the decision tree index model to obtain the trained decision tree index model, and inputting the road resistance to be predicted into the trained decision tree index model to output a predicted value of hydrogen consumption; Establishing a hydrogen consumption model for a hydrogen fuel cell vehicle, inputting the predicted hydrogen consumption value into the hydrogen consumption model to obtain the hydrogen refueling demand of the hydrogen fuel cell vehicle, and setting operating constraints during the operation of the photovoltaic-storage coupled hydrogen refueling station system; Construct an objective function, based on the operating constraints and input the predicted hydrogen consumption and the vehicle hydrogen refueling demand into the objective function to solve the problem, so as to obtain each power, and optimize the operation of the photovoltaic storage coupled hydrogen refueling station system according to the optimal planning of each power generation system based on the optimal planning of the system.

2. The operation optimization method of the photovoltaic storage coupled hydrogen production system according to claim 1 is characterized in that: The road resistance calculation model is: ； ； Among them, ij is the road section, Because the road is blocked, The zero-flow travel time, 、 is the impedance influencing factor, s is the road saturation, c is the signal period, is the green-to-signal ratio, q is the vehicle arrival rate on the road section, is the psychological reaction intensity coefficient, is the arrival rate of vehicles from the stop line of the intersection to the implicit conflict point, K is the traffic density, h is the average length of the vehicle, is the average distance between vehicles when the road is blocked, n is the number of one-way motor vehicle lanes, is the correction factor for non-motor vehicles, is the pedestrian correction coefficient, is the intersection correction coefficient, is the lane correction factor.

3. The operation optimization method of the photovoltaic storage coupled hydrogen production system according to claim 1 is characterized in that: The method of obtaining the historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under the unit road resistance, calculating the corresponding historical road resistance using the road resistance calculation model, and generating a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistance includes: Obtaining historical hydrogen consumption per unit distance of the hydrogen fuel cell vehicle under unit road resistance, and inputting the historical hydrogen consumption per unit distance into the road resistance calculation model to calculate the corresponding historical road resistance; Calculating a ratio between the historical hydrogen consumption per unit distance and the historical road resistance, and using the ratio as the historical hydrogen consumption of the hydrogen fuel cell vehicle under unit road resistance; A historical data set is generated based on the historical hydrogen consumption and the historical road resistance.

4. The operation optimization method of the photovoltaic storage coupled hydrogen production system according to claim 1 is characterized in that: The method of using the historical road resistance as a selection feature to construct a decision tree index model and using the historical data set to train the decision tree index model to obtain the trained decision tree index model includes: The historical road resistance is used as a selection feature, and the historical data set is divided into intervals according to the selection feature to obtain intervals. The corresponding thresholds of each interval are used as the decision tree values ​​of the leaf nodes in the decision tree to construct a decision tree index model; The decision tree index model is sorted by hydrogen consumption per unit road resistance using each of the intervals to obtain the trained decision tree index model.

5. The operation optimization method of the photovoltaic storage coupled hydrogen production system according to claim 1 is characterized in that: The operation constraints include hydrogen production system constraints, hydrogen storage constraints, photovoltaic operation constraints, energy storage operation constraints and power balance constraints.

6. The operation optimization method of the photovoltaic storage coupled hydrogen production system according to claim 1 is characterized in that: The hydrogen consumption model of the hydrogen fuel cell vehicle is: ； ； ； ； in, is the hydrogen consumption of the hydrogen fuel cell vehicle in the cumulative travel distance of A driving calculation sections during period t, Calculate the road resistance to be predicted for A driving sections. Calculate the distance of the road segment for each trip, for The corresponding predicted value of hydrogen fuel cell vehicles, is the hydrogen storage capacity of the hydrogen fuel cell vehicle after the end of period t, is the initial hydrogen storage capacity of the hydrogen fuel cell vehicle at the beginning of period t, is the hydrogen consumption of the vehicle in the cumulative travel distance of B hydrogen refueling calculation sections during period t, The road resistance to be predicted for B hydrogenation calculation sections, The distance of each hydrogenation calculation section, for The corresponding predicted value of hydrogen fuel cell vehicles, Reserve a minimum amount of hydrogen for the vehicle; Accordingly, the hydrogen consumption prediction value is input into the hydrogen consumption model of the hydrogen fuel cell vehicle to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, including: The predicted hydrogen consumption value is input into the hydrogen consumption model of the hydrogen fuel cell vehicle to output the vehicle's minimum reserved hydrogen storage capacity, and the vehicle's minimum reserved hydrogen storage capacity is used as the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle.

7. The operation optimization method of the photovoltaic-storage coupled hydrogen production system according to any one of claims 1 to 6, characterized in that: The constructing of the objective function, based on the operating constraints and inputting the predicted hydrogen consumption value and the vehicle hydrogen refueling demand into the objective function for solving, includes: Construct an objective function with the goal of minimizing system operating costs and minimizing carbon emissions; A snow melting optimization algorithm is adopted, based on the operation constraints, and the predicted hydrogen consumption value and the vehicle hydrogen refueling demand are input into the objective function to solve the problem.

8. An operation optimization device for a photovoltaic-storage coupled hydrogen production system, characterized in that: include: a data set generation module, configured to establish a road resistance calculation model, obtain historical hydrogen consumption per unit distance of hydrogen fuel cell vehicles under unit road resistance, calculate corresponding historical road resistances using the road resistance calculation model, and generate a historical data set based on the historical hydrogen consumption per unit distance and the historical road resistances; a hydrogen consumption prediction module, configured to use the historical road resistance as a selection feature to construct a decision tree index model, train the decision tree index model using the historical data set to obtain a trained decision tree index model, input the road resistance to be predicted into the trained decision tree index model, and output a predicted hydrogen consumption value; A constraint condition construction module is used to establish a hydrogen consumption model for hydrogen fuel cell vehicles, input the predicted hydrogen consumption value into the hydrogen consumption model to obtain the vehicle hydrogen refueling demand of the hydrogen fuel cell vehicle, and set the operation constraint conditions during the operation of the photovoltaic storage coupled hydrogen refueling station system; The system operation optimization module is used to construct an objective function, based on the operation constraints and inputting the predicted hydrogen consumption value and the vehicle hydrogen refueling demand into the objective function to solve the problem, so as to obtain each power, based on the optimal planning of each power generation system, and optimize the operation of the photovoltaic storage coupled hydrogen refueling station system according to the system optimal planning.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the operation optimization method of the photovoltaic storage coupled hydrogen production system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program; wherein, when the computer program is executed by a processor, the operation optimization method of the photovoltaic storage coupled hydrogen production system according to any one of claims 1 to 7 is implemented.

Images