Hydrogen production and storage system planning method based on integrated learning mode
Through the integrated learning model hydrogen storage system planning method, the uncertainty of new energy power generation and load electricity use is optimized, the resource utilization rate of new energy electrolytic hydrogen storage system is improved, and the low resource utilization rate in the existing technology is solved and the problem of idle resources have achieved a more efficient new energy electrolytic water-making and hydrogen storage model.
Patent Information
- Application Number
- CN202411038676.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-15
AI Technical Summary
Under the multiple influences of uncertainty in new energy power generation, uncertainty in electricity load and uncertainty in hydrogen load, the existing technology is difficult to effectively improve the utilization rate of new energy and hydrogen production and storage equipment, resulting in hydrogen production and storage. The rated power of the electrolytic cell and the volume of the hydrogen storage tank in the system are insufficiently planned, the resource utilization rate is low, and there are problems of idle and waste of resources.
Adopting the hydrogen storage system planning method based on the integrated learning model, through data information collection, system modeling, planning evaluation and iterative optimization, considering the uncertainty of new energy power generation, load power and load hydrogen, and establishing random sampling scenarios and Iterative optimization method of statistical analysis, optimize the rated power of the hydrogen production electrolytic cell and the capacity configuration of the hydrogen storage tank.
The resource utilization rate and application rationality of the hydrogen storage system are improved, the idle and waste of resources caused by excessive construction is avoided, and the economic and efficient nature of the new energy electrolytic water-based hydrogen storage model is enhanced.
Smart Images

Figure CN118966682A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of hydrogen production and storage, and in particular to a method for planning a hydrogen production and storage system based on an integrated learning model under hydrogen production by electrolysis of water using new energy. Background Art
[0002] Using new energy to generate electricity and electrolyze water to produce hydrogen will gradually become an important way to produce hydrogen. Under the multiple influences of uncertainty in new energy generation, electricity load uncertainty, and hydrogen load uncertainty, how to maximize the utilization rate of new energy and hydrogen production and storage equipment while meeting the needs of load users has become a key issue in the scientific and rational development of the new energy electrolysis water hydrogen production model.
[0003] In the current actual engineering applications of new energy hydrogen production and storage by electrolysis of water, the rated power of the hydrogen production electrolyzer and the volume of the hydrogen storage tank of the hydrogen storage equipment in the hydrogen production and storage system are generally calculated by calculating the net power through the local total installed capacity of new energy and the peak load power consumption, and then combining the total local hydrogen load to plan the installed capacity of the hydrogen production electrolyzer and hydrogen storage tank. This method is relatively simple and lacks in-depth analysis of the laws of new energy power generation and load power consumption, making it difficult to make full use of new energy and hydrogen production and storage equipment.
[0004] In existing research, some experts and scholars have analyzed renewable energy power generation, load electricity and hydrogen consumption, used scenario generation technology, and clustered typical scenarios to analyze and optimize the planning of hydrogen production and storage systems. This approach focuses on the differences in renewable energy power generation and load electricity and hydrogen consumption in different scenarios, and better describes the operating conditions of hydrogen production and storage systems, but the analysis of scenario uncertainty is insufficient and lacks recognition of statistical laws. For example, in the reference (Yang Zijuan, Tian Xueqin, Wu Weili, et al. Optimal configuration of wind power-hydrogen energy-HCNG coupled network capacity considering electrolyzer combined operation [J]. Automation of Electric Power Systems, 2023, 47(12): 76-85.), it is necessary to solve the hydrogen blending ratio control problem during pipeline hydrogen blending and the hydrogen production equipment capacity configuration problem. A wind power-hydrogen energy-HCNG (hybrid hydrogen natural gas) coupled network was established. With the goal of maximizing system benefits, the power and hydrogen balance in the system and the operating constraints of each equipment were considered, and a hydrogen energy system capacity configuration model that can meet the hydrogen blending demand was established. In the simulation example, 12 typical days of wind, electricity and gas loads in spring, summer, autumn and winter in a certain region were selected to calculate the electrolyzer capacity configuration. However, the representativeness of the typical day selected in this scheme is questionable. Considering that it cannot represent all possible operating conditions of the new energy power generation and hydrogen production system, it does not have wide applicability. Therefore, whether the electrolyzer capacity data calculated by selecting the typical day can be applied to actual applications will be questionable, and whether the configuration result can achieve the desired benefits is also uncertain. Summary of the invention
[0005] In order to solve the problem of optimizing the rated power of the electrolyzer and the volume of the hydrogen storage tank in the hydrogen production and storage system under uncertain scenarios of renewable energy power generation, load electricity and hydrogen consumption, so as to improve the resource utilization rate of renewable energy power generation and hydrogen production and storage systems, avoid idleness and waste caused by excessive construction, and maximize the economy and efficiency of the hydrogen production and storage mode by electrolysis of water from renewable energy, the present invention provides a hydrogen production and storage system planning method based on an integrated learning model. By establishing an integrated learning method including random sampling scenarios, statistical analysis and iterative optimization, it is applied to the renewable energy hydrogen production and storage system, and the influence of the uncertainty of renewable energy power generation, load electricity consumption and load hydrogen consumption on the planning scheme of the hydrogen production and storage system is considered to the greatest extent, thereby improving the rationality of the practical application of the hydrogen production and storage system.
[0006] The present invention provides a hydrogen production and storage system planning method based on an integrated learning mode, which implements a data information collection unit, a hydrogen production and storage system modeling unit, a hydrogen production and storage system planning evaluation unit, and a hydrogen production and storage system planning calculation unit through a computer program. Based on the units, the photovoltaic-battery-hydrogen production and storage system to be investigated is subjected to the following steps:
[0007] Step 1: The data information collection unit obtains the historical data of photovoltaic power generation, power load and hydrogen load in the planned area of the hydrogen production and storage system and constructs three sample sets: photovoltaic power generation sample set, power load power sample set and hydrogen consumption sample set; at the same time, the data information collection unit obtains the parameters of the hydrogen production electrolyzer, hydrogen storage tank and auxiliary equipment in the hydrogen production and storage system according to the selection results of the hydrogen production and storage system equipment;
[0008] Step 2: The hydrogen production and storage system modeling unit establishes a mathematical model of hydrogen production under off-grid conditions that takes into account the maximum utilization of photovoltaic power generation and hydrogen production and storage systems based on the process of photovoltaic water electrolysis to produce hydrogen and load hydrogen use;
[0009] Step 3: The hydrogen production and storage system planning and evaluation unit evaluates the currently input hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration based on the historical data and parameters of the photovoltaic-battery-hydrogen production and storage system under off-grid conditions collected in step 1 and the hydrogen production mathematical model established in step 2;
[0010] The hydrogen production and storage system planning and evaluation unit randomly extracts a sample from the three sample sets to form an operation scenario, constructs multiple operation scenario subsets, and each operation scenario subset includes multiple operation scenarios; solves the hydrogen production mathematical model for each operation scenario subset to obtain the optimization target value under the preset confidence level under the corresponding operation scenario subset, and the optimization target includes the photovoltaic power generation utilization rate and the hydrogen production and storage system utilization rate; and then counts the optimization target values under the preset confidence level under all operation scenario subsets as the evaluation result of the current hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan.
[0011] Step 4: The hydrogen production and storage system planning calculation unit sets the hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan, calculates the evaluation result of the configuration plan based on the hydrogen production and storage system planning evaluation unit described in step 3, and iteratively updates the configuration plan until the maximum number of iterations is reached, and obtains the final hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan;
[0012] The hydrogen production and storage system planning calculation unit presets the iterative update step of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank. During each iteration, the configuration plan is updated according to the current iterative update step, the evaluation result of the updated configuration plan is calculated, and the evaluation results of the configuration plans before and after the update are compared. The iterative update step of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank is updated, and then the next iteration is entered.
[0013] Compared with the prior art, the advantages and positive effects of the present invention are:
[0014] (1) The following problems exist in the planning of hydrogen production and storage systems in current technologies: In practical applications, the rated power of the electrolyzer and the volume of the hydrogen storage equipment in the hydrogen production and storage system are calculated based on the total installed capacity of local new energy sources, the power consumption of important loads, and other information. This method is relatively simple and crude, and lacks optimization of resource utilization. At present, from the perspective of the time change of new energy power generation and load power consumption, through statistical analysis or artificial intelligence technology, the typical operating conditions of the hydrogen production and storage system are established, and the solution of planning the hydrogen production and storage system under the probability of occurrence of different working conditions is considered. Studies have shown that by establishing typical working conditions and optimizing the objective function method, the utilization rate of new energy and hydrogen production and storage equipment can be improved, and the impact of the differences in different typical scenarios on the planning results of the hydrogen production and storage system can be reduced. However, the uncertainty of typical scenarios and the integrity of the statistical laws shown between different scenarios need to be improved. The method of the present invention introduces the idea of integrated learning into the planning of the hydrogen production and storage system of new energy electrolysis water, and comprehensively describes the operating conditions of the hydrogen production and storage system by randomly extracting a large number of scenarios to form a scenario set, thereby enhancing the applicability of the hydrogen production and storage system planning scheme. In addition, the method of the present invention strengthens the statistical laws of hydrogen production and storage schemes in different scenarios by statistically analyzing the utilization rates of new energy and hydrogen production and storage systems under multiple scenario sets. Finally, the method of the present invention achieves directional optimization of hydrogen production and storage systems through perturbation observation iterative learning, which is conducive to the configuration of the optimal electrolyzer rated power and hydrogen storage tank volume in the hydrogen production and storage system.
[0015] (2) The method of the present invention takes into account the impact of the uncertainty of new energy power generation, load electricity consumption and load hydrogen consumption on the hydrogen production and storage system to the greatest extent, improves the rationality and applicability of the practical application of the hydrogen production and storage system, and is conducive to avoiding the idle resources of the hydrogen production and storage system caused by excessive planning. At the same time, it reduces the waste of resources caused by the abandonment of the new energy power generation system, which will help the rapid development of the new energy hydrogen production mode and is of great significance for the in-depth application of the new energy hydrogen production mode. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 It is a structural schematic diagram of a wind power-photovoltaic-battery hydrogen production system under off-grid conditions in an embodiment of the present invention;
[0017] Figure 2 It is a functional unit structure diagram of the hydrogen production and storage system planning method based on the integrated learning mode of the present invention;
[0018] Figure 3 It is an implementation flow chart of the hydrogen production and storage system planning method based on the integrated learning mode of the present invention;
[0019] Figure 4 It is a schematic diagram of the evaluation process of hydrogen production and storage system planning according to an embodiment of the present invention. DETAILED DESCRIPTION
[0020] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention is clearly and completely described below in conjunction with the accompanying drawings of the embodiment of the present invention.
[0021] The present invention provides a method for planning a hydrogen production and storage system based on an integrated learning model, which mainly includes: first, collecting the operating parameters of the hydrogen production and storage system and the historical data of the local renewable energy power generation, load power consumption and load hydrogen consumption; then, establishing an operation optimization mathematical model of the renewable energy water electrolysis hydrogen production and storage system, including system operation constraints and optimization objective functions; then, calculating the utilization rate of new energy and the utilization rate of the hydrogen production and storage system in the process of renewable energy hydrogen production and storage under a large number of random scenarios, and evaluating the planning effect of the hydrogen production and storage system; finally, continuously updating the rated power of the heavy electrolyzer of the hydrogen production and storage system and the capacity of the hydrogen storage tank to obtain the optimal planning scheme of the hydrogen production and storage system. The method of the present invention takes into account the impact of the uncertainty of renewable energy power generation, load power consumption and load hydrogen consumption on the planning scheme of the hydrogen production and storage system to the greatest extent, and will help promote the in-depth application and sustainable development of renewable energy water electrolysis hydrogen production.
[0022] like Figure 1As shown, the embodiment of the present invention takes the photovoltaic-battery-hydrogen production and storage system under off-grid conditions as an example to illustrate the method of the present invention. The hydrogen production and storage system includes: a photovoltaic power generation unit, which provides green energy for loads and hydrogen production; a battery energy storage unit, which can balance the time contradiction between photovoltaic power generation and load electricity consumption; electricity load; a hydrogen production electrolyzer, which is an electricity load; a hydrogen storage tank for storing hydrogen; and a hydrogen consumption unit as a hydrogen load in the hydrogen sales link.
[0023] like Figure 2 As shown, the embodiment of the present invention implements four functional modules through a computer program: a data information collection unit, a hydrogen production and storage system modeling unit, a hydrogen production and storage system planning evaluation unit, and a hydrogen production and storage system planning calculation unit; then the four functional modules are used to execute the following Figure 3 The process described above, specifically, the implementation process of the method in this embodiment includes the following four steps.
[0024] Step 1: The data information collection unit obtains the historical data of photovoltaic power generation, power load and hydrogen load in the planned area of the hydrogen production and storage system, and obtains the parameters of the hydrogen production and storage system such as the hydrogen production electrolyzer, hydrogen storage tank and auxiliary equipment according to the selection results of the hydrogen production and storage system equipment. Step 1 of the embodiment of the present invention includes the following steps 1.1-1.4:
[0025] Step 1.1: Collect the historical data of photovoltaic power generation in the planned area of the hydrogen production and storage system, and divide the historical data into multiple samples in units of days after cleaning the data. Assume that the photovoltaic power generation sample set is M1; one photovoltaic power generation sample corresponds to recording the photovoltaic power generation information of one day. For example, taking a sampling interval of 1 hour, one photovoltaic power generation sample is a vector composed of 24 photovoltaic power values sampled for 24 hours a day.
[0026] Step 1.2: Collect the historical data of power consumption of the electric load in the planning area of the hydrogen production and storage system, and divide the historical data into multiple samples in units of days after cleaning the data. Assume that the power load power sample set is M2; one power load power sample corresponds to recording the power consumption information of the power load for one day. For example, taking a sampling interval of 1 hour, one power load power sample is a vector composed of 24 power load power values sampled for 24 hours a day.
[0027] Step 1.3: Collect historical data on hydrogen consumption by hydrogen load in the planned area of hydrogen production and storage system, and divide the historical data into multiple samples by day after cleaning the data. Assume that the set of hydrogen consumption by hydrogen load is M3; one hydrogen consumption by hydrogen load sample corresponds to recording one day's hydrogen consumption information. Taking the sampling interval of 1 hour as an example, one hydrogen consumption by hydrogen load sample is a vector composed of 24 hydrogen consumption values sampled for 24 hours a day.
[0028] Step 1.4: Based on the selection results of the photovoltaic-battery-hydrogen production and storage system equipment, obtain the parameters of the hydrogen production and storage system, such as the charging and discharging efficiency, rated power and capacity of the battery energy storage, the hydrogen production electrolyzer, the hydrogen storage tank and auxiliary equipment.
[0029] Step 2: The hydrogen production and storage system modeling unit establishes a mathematical model for hydrogen production under off-grid conditions that takes into account the maximum utilization of photovoltaic power generation and hydrogen production and storage systems based on the process of photovoltaic water electrolysis to produce hydrogen and load hydrogen use, including the following steps 2.1-2.2.
[0030] Step 2.1: When the photovoltaic-battery-hydrogen production and storage system is in operation under off-grid conditions, the system needs to meet constraints such as electric power balance, hydrogen balance, photovoltaic power generation output power, battery energy storage unit output power and energy state.
[0031] Step 2.1.1: Establish the power balance constraint of the system, as shown in formula (1):
[0032]
[0033] Among them, P PV (k) represents the actual output power of the photovoltaic power generation unit at time k, represents the battery energy storage discharge power at time k, represents the battery energy storage charging power at time k, P L (k) represents the power load power at time k, P EL (k) represents the hydrogen production power of the hydrogen production electrolyzer at time k.
[0034] Step 2.1.2: Establish the operating constraints of the output power of the photovoltaic power generation unit in the system, as shown in formula (2):
[0035]
[0036] in, Represents the maximum output power of the photovoltaic power generation unit at time k.
[0037] Step 2.1.3: Establish the operating constraints of the battery energy storage unit in the system, as shown in formula (3):
[0038]
[0039] Among them, C SOE (k) represents the energy state of the battery energy storage at time k; Δk represents the sampling time interval within the day, and T represents the end time of the system operation within the day; η d and η cRespectively represent the rated power, rated capacity, discharge efficiency and charging efficiency of battery energy storage; as well as They respectively represent the initial energy state, lower limit value and upper limit value of the battery energy storage; It is an indicator of the battery energy storage discharge state. It is an indicator of the battery energy storage charging status. and It is a binary optimization variable representing 0-1.
[0040] Step 2.1.4: Establish the hydrogen energy balance constraint in the system, as shown in formula (4). EL (k) represents the hydrogen production volume of the hydrogen production electrolyzer at time k; η EL and λ EL They represent the hydrogen production efficiency and electricity-to-hydrogen ratio of the hydrogen production electrolyzer respectively; Indicates the density of hydrogen; C SOH (k) represents the hydrogen storage state in the hydrogen storage tank at time k; V SELL (k) represents the hydrogen sales volume at time k; Indicates the rated volume of the hydrogen storage tank; Indicates the initial storage state of hydrogen in the hydrogen storage tank; and Respectively represent the lower limit and upper limit of the hydrogen state in the hydrogen storage tank; Indicates the volume limit of hydrogen sold per unit time; δ EL Indicates the allowable variation range of the power of the hydrogen production electrolyzer per unit time; and Respectively represent the rated power, minimum power and maximum power of the hydrogen production electrolyzer; ΔP EL (k) is the change in hydrogen production power of the electrolyzer at time k.
[0041]
[0042] Step 2.2: Establish the optimization objective function J of the photovoltaic-battery-hydrogen production and storage system under off-grid conditions. In order to make full use of the utilization rate of photovoltaic power generation and hydrogen production and storage system, two optimization objectives are defined: the optimization objective J1 is the photovoltaic power generation utilization rate, as shown in formula (5), and the optimization objective J2 is the hydrogen production and storage system utilization rate, as shown in formula (6).
[0043]
[0044]
[0045] J=ω1J1+ω2J2 (7)
[0046] in, represents the maximum output power of the photovoltaic power generation unit at time k; ω1 and ω2 represent the weights of the two optimization objectives, and the default value is 0.5.
[0047] Step 3: The hydrogen production and storage system planning evaluation unit establishes an evaluation method for the rated hydrogen power of the electrolyzer and the hydrogen storage tank capacity configuration in the hydrogen production and storage system based on the data and parameters of the photovoltaic-battery-hydrogen production and storage system under off-grid conditions collected in step 1 and the mathematical model described in step 2. Figure 4 As shown, the planning and evaluation process of the hydrogen production and storage system of the present invention includes steps 3.1-3.6.
[0048] Step 3.1: Get the given rated power of the hydrogen production electrolyzer and hydrogen storage tank capacity The confidence level parameters of photovoltaic power generation utilization rate and hydrogen production and storage system utilization rate are set to α and β respectively, the ensemble learning scale is N, and the initial ensemble number n=1.
[0049] Step 3.2: From the photovoltaic power generation power sample set M1, the power load power sample set M2, and the hydrogen consumption load hydrogen consumption sample set M3 described in steps 1.1, 1.2, and 1.3, randomly select once each to form an operation scenario. In this way, a total of M random samplings are performed to form an off-grid photovoltaic-battery-hydrogen production and storage system operation scenario subset S consisting of M photovoltaic power generation samples, M power load power samples, and M hydrogen consumption load hydrogen consumption samples. n .
[0050] Step 3.3: The scene subset S described in step 3.2 n The mathematical model of photovoltaic-battery-hydrogen production and storage system under off-grid conditions with J as the optimization objective function is solved in step 2 to obtain the scenario subset S n Under the M group of samples, the optimization objective functions of photovoltaic power generation utilization and hydrogen production and storage system utilization are {(J1(m),J2(m))|S n ,m=1,2,…,M}.
[0051] Step 3.4: Based on step 3.3, n The optimization results of the M groups of samples are statistically analyzed to calculate the optimization target value under the confidence level α of photovoltaic power generation utilization and the confidence level β of hydrogen production and storage system utilization, that is, in Through statistics Calculated by Through statistics It is calculated by this method, and pr(·) represents the function for calculating the probability value.
[0052] Step 3.5: Determine whether the integration number n is greater than the integration learning scale N. If so, proceed to step 3.6. If not, n is incremented by 1, that is, n=n+1, and return to step 3.2 to execute.
[0053] The present invention executes step 3.2 N times to generate N running scenario subsets S n , n=1,2,…,N. In view of the uncertainty of typical scenarios in current technology, the method of the present invention avoids the limitation brought by only considering data samples of typical scenarios, adopts an integrated learning mode, randomly extracts scenarios, and constructs several subsets of running scenarios to obtain the statistical laws shown between different scenarios, so as to improve the applicability to different scenarios.
[0054] Step 3.6: Statistical analysis ensemble learning scale N subsets S n Photovoltaic power generation utilization rate and hydrogen production and storage system utilization rate under Calculate the optimization target value under the confidence level α of photovoltaic power generation utilization and the confidence level β of hydrogen production and storage system utilization, that is, in Through statistics Calculated by Through statistics Obtained by calculation. The rated power of the hydrogen production electrolyzer is characterized as The hydrogen storage tank capacity is When the planning effect of the hydrogen production and storage system in the photovoltaic-battery-hydrogen production and storage system under off-grid conditions is calculated, the total optimization target value can be further obtained by weighted summation, forming an overall evaluation of the hydrogen production and storage system planning.
[0055] The method of the present invention forms a large number of possible scenarios through a large number of extraction combinations, and then performs statistical analysis to complete the configuration of the rated power of the electrolyzer and the capacity of the hydrogen storage tank, so that the configuration result has greater applicability.
[0056] Step 4: The hydrogen production and storage system planning calculation unit establishes an updated calculation method for the rated hydrogen production power and hydrogen storage tank capacity of the electrolyzer in the hydrogen production and storage system based on the hydrogen production and storage system planning evaluation method described in step 3, including steps 4.1-4.4.
[0057] Step 4.1: According to the installed capacity of the photovoltaic power generation system, the rated power of the battery energy storage and the peak power of the load, set the initial values of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank. Initially, let the number of update iterations iter = 1, then the rated power of the hydrogen production electrolyzer is and hydrogen storage tank capacity At the same time, the maximum number of iterations is itermax. In addition, the iterative update step size of the hydrogen electrolyzer rated power and hydrogen storage tank capacity is set to ΔP EL and ΔVHESS , and ΔP EL >0,ΔV HESS >0.
[0058] Step 4.2: Set the rated power of the hydrogen production electrolyzer of the hydrogen production and storage system and hydrogen storage tank capacity Input the hydrogen production and storage system planning evaluation unit to obtain the evaluation value of the hydrogen production and storage system planning result:
[0059] Indicates the rated power of the hydrogen production electrolyzer in the hydrogen storage system and hydrogen storage tank capacity Planning effect of hydrogen production and storage system under certain conditions.
[0060] Step 4.3: Iteratively update the step size ΔP with the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank EL and ΔV HESS , update the planning results of the hydrogen production and storage system, as shown in formula (8).
[0061]
[0062] The updated hydrogen production electrolyzer rated power and hydrogen storage tank capacity Enter the hydrogen production and storage system planning evaluation unit to obtain the evaluation value of the updated configuration plan:
[0063]
[0064] Step 4.4: According to the changes in the evaluation values of the configuration schemes before and after the update in Steps 4.2 and 4.3, the iterative update step length of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank is modified. The update process is as follows:
[0065] Step 4.4.1: If the utilization rate of photovoltaic power generation increases, that is, And the utilization rate of hydrogen production and storage system increases, that is, Then the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank increase, maintaining ΔP EL and ΔV HESS constant;
[0066] Step 4.4.2: If the utilization rate of photovoltaic power generation increases, that is, And the utilization rate of hydrogen production and storage system decreases, that is, Then the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank decrease slowly, and the iteration step size is updated at a rate of -0.5, that is, ΔP EL (new) = -0.5*ΔPEL , ΔV HESS (new) = -0.5*ΔV HESS ;
[0067] Step 4.4.3: If the photovoltaic power generation utilization rate decreases, that is, And the utilization rate of hydrogen production and storage system increases, that is, The rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank increase rapidly, and the iteration step is updated at a rate of 2, that is, the new iteration step ΔP EL (new) = 2*ΔP EL , ΔV HESS (new) = 2*ΔV HESS .
[0068] Step 4.4.4: If the photovoltaic power generation utilization rate decreases, that is, And the utilization rate of hydrogen production and storage system decreases, that is, Then the rated power of the hydrogen electrolyzer and the capacity of the hydrogen storage tank increase slowly, and the iteration step is updated at a rate of 0.5, that is, the new iteration step ΔP EL (new) = 0.5*ΔP EL , ΔV HESS (new) = 0.5 * ΔV HESS .
[0069] Step 4.5: Determine whether the update iteration number iter is greater than or equal to the maximum iteration number itermax; if so, the hydrogen production and storage system planning is completed, and the planning result is the rated power of the hydrogen production electrolyzer and hydrogen storage tank capacity If not, the number of iterations is updated, iter is incremented by 1, and the process returns to step 4.3 to continue updating the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank.
[0070] Except for the technical features described in the specification, all other technical features are known technologies to those skilled in the art. The present invention omits the description of known components and known technologies to avoid redundancy and unnecessary limitation of the present invention. Obviously, the embodiments described above are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present invention.
Claims
1. A hydrogen production and storage system planning method based on an integrated learning model, characterized in that: The following steps are performed for the photovoltaic-battery-hydrogen production and storage system to obtain the optimally configured hydrogen production electrolyzer rated power and hydrogen storage tank capacity; the method comprises the following steps: Step 1: The data information collection unit obtains the historical data of photovoltaic power generation, power load and hydrogen load in the planned area of the hydrogen production and storage system and constructs three sample sets: photovoltaic power generation sample set, power load power sample set and hydrogen consumption sample set; at the same time, the data information collection unit obtains the parameters of the hydrogen production electrolyzer, hydrogen storage tank and auxiliary equipment in the hydrogen production and storage system according to the selection results of the hydrogen production and storage system equipment; Step 2: The hydrogen production and storage system modeling unit establishes a hydrogen production mathematical model under off-grid conditions that takes into account the maximum utilization rate of photovoltaic power generation and the utilization rate of the hydrogen production and storage system based on the process of producing hydrogen by photovoltaic water electrolysis and the use of hydrogen by load; Step 3: The hydrogen production and storage system planning and evaluation unit uses the sample set obtained in step 1 and the established hydrogen production mathematical model to evaluate the input hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan; The hydrogen production and storage system planning and evaluation unit randomly extracts a sample from the three sample sets to form an operation scenario, and constructs multiple operation scenario subsets, each operation scenario subset containing multiple operation scenarios; Solving the hydrogen production mathematical model for each subset of operation scenarios to obtain an optimization target value at a preset confidence level under the corresponding subset of operation scenarios, wherein the optimization target includes a photovoltaic power generation utilization rate and a hydrogen production and storage system utilization rate; Then, the optimization target values under the preset confidence level in all the subsets of operation scenarios are counted as the evaluation results of the current configuration scheme of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank; Step 4: The hydrogen production and storage system planning calculation unit sets the hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan, uses the hydrogen production and storage system planning evaluation unit to calculate the evaluation result of the configuration plan, and iteratively updates the configuration plan until the maximum number of iterations is reached, and obtains the final hydrogen production electrolyzer rated power and hydrogen storage tank capacity configuration plan; The hydrogen production and storage system planning calculation unit presets the iterative update step of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank. During each iteration, the configuration plan is updated according to the current iterative update step, the evaluation result of the updated configuration plan is calculated, and the evaluation results of the configuration plans before and after the update are compared. The iterative update step of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank is updated, and then the next iteration is entered.
2. The method according to claim 1, characterized in that In the step 1, the data information collection unit collects historical data on photovoltaic power generation, historical data on electric load power consumption, and historical data on hydrogen consumption by hydrogen load in the planned area of the hydrogen production and storage system, and after cleaning the data, divides the samples into days to obtain a sample set of photovoltaic power generation, a sample set of electric load power consumption, and a sample set of hydrogen consumption by hydrogen load, respectively.
3. The method according to claim 1, characterized in that: In step 2, a hydrogen production mathematical model is established for the photovoltaic-battery-hydrogen production and storage system under off-grid conditions as follows: Considering the two optimization objectives of photovoltaic power generation utilization rate J1 and hydrogen production and storage system utilization rate J2, the optimization objective function J of the hydrogen production and storage system is established as follows: Among them, ω1 and ω2 represent the weights of the two optimization objectives; T represents the end time of the intraday system operation; P PV (k) represents the actual output power of the photovoltaic power generation unit at time k; represents the maximum output power of the photovoltaic power generation unit at time k; P EL (k) represents the hydrogen production power of the electrolyzer at time k; Indicates the rated power of the hydrogen production electrolyzer; Indicates the upper limit of the hydrogen state in the hydrogen storage tank; C SOH (k) represents the hydrogen storage state in the hydrogen storage tank at time k; The hydrogen production and storage system needs to meet the following constraints during operation: Power balance constraints: Operational constraints on the output power of photovoltaic power generation units: Battery storage unit operating constraints: Hydrogen energy balance constraints: in, represents the battery energy storage discharge power at time k, represents the battery energy storage charging power at time k, P L (k) represents the power load power at time k; Δk represents the sampling time interval within the day; C SOE (k) represents the energy state of the battery storage at time k; η d and η c Respectively represent the rated power, rated capacity, discharge efficiency and charging efficiency of battery energy storage; as well as They respectively represent the initial energy state, lower limit value and upper limit value of the battery energy storage; It is the indicator of the discharge state of the battery energy storage at time k, and its value is 0 or 1; It is the symbol of the battery energy storage charging state at time k, and its value is 0 or 1; V EL (k) represents the hydrogen production volume of the hydrogen production electrolyzer at time k; η EL and λ EL They represent the hydrogen production efficiency and electricity-to-hydrogen ratio of the hydrogen production electrolyzer respectively; Indicates the density of hydrogen; V SELL (k) represents the hydrogen sales volume at time k; Indicates the rated volume of the hydrogen storage tank; Indicates the initial storage state of hydrogen in the hydrogen storage tank; and Respectively represent the lower limit and upper limit of the hydrogen state in the hydrogen storage tank; and are the minimum and maximum powers of the hydrogen production electrolyzer, respectively; Indicates the volume limit of hydrogen sold per unit time; δ EL Indicates the allowable variation range of the hydrogen production electrolyzer power per unit time; ΔP EL (k) is the change in hydrogen production power of the electrolyzer at time k.
4. The method according to claim 1 or 3, characterized in that: In step 3, the hydrogen production and storage system planning and evaluation unit performs the following steps: Step 3.1: Determine the rated power of the hydrogen production electrolyzer and hydrogen storage tank capacity Set the confidence level α of the photovoltaic power generation utilization rate and the confidence level β of the hydrogen production and storage system utilization rate, set the ensemble learning scale N, and the initial ensemble number n = 1; Step 3.2: Extract one sample from each of the photovoltaic power generation sample set, the power load power sample set, and the hydrogen consumption load hydrogen consumption sample set to form an operation scenario, and randomly select M operation scenarios to form an operation scenario subset S n ; Step 3.3: In the current running scene subset S n Under the optimization, we solve the hydrogen production mathematical model and obtain n The optimization target value for all operating scenarios; Let subset S n The photovoltaic power generation utilization rate of scenario m is J1(m), and the hydrogen production and storage system utilization rate is J2(m), m = 1, 2, ..., M; Step 3.4: For subset S n Perform statistical analysis on the optimization target values of the M groups of samples in the set, and calculate the optimization target values under the confidence levels α and β; n The optimization target value is expressed as in, By statistics pr(·) is the function for calculating the probability value; By statistics Obtained by calculation; Step 3.5: Determine whether the integration number n is greater than the integration learning scale N. If so, proceed to step 3.
6. If not, the integration number n is incremented by 1, and then go to step 3.2 for execution; Step 3.6: Statistical calculation of N subsets S n (n=1,2,…,N) The optimization target value under the confidence level α and β; Suppose we obtain N subsets S n The optimization objective value at confidence levels α and β is in, By statistics Calculated by By statistics Obtained by calculation; Optimization target value Characterizes the off-grid photovoltaic-battery-hydrogen production and storage system at the current rated power of the hydrogen production electrolyzer and hydrogen storage tank capacity The planning effect under the configuration scheme.
5. The method according to claim 1, characterized in that In step 4, the hydrogen production and storage system planning calculation unit updates the configuration scheme according to the current iteration update step in each iteration, and then compares the evaluation result of the updated configuration scheme with the evaluation result of the configuration scheme before the update, and adjusts the iterative update step of the hydrogen electrolyzer rated power and the hydrogen storage tank capacity as follows: (1) If the utilization rate of photovoltaic power generation increases and the utilization rate of the hydrogen production and storage system increases, it means that the rated power of the hydrogen electrolyzer and the capacity of the hydrogen storage tank need to be increased, and the iterative update step size remains unchanged; (2) If the utilization rate of photovoltaic power generation increases and the utilization rate of the hydrogen production and storage system decreases, it means that the rated power of the hydrogen electrolyzer and the capacity of the hydrogen storage tank need to be slowly reduced, and the iterative update step size is updated at a rate of -0.5; (3) If the utilization rate of photovoltaic power generation decreases and the utilization rate of the hydrogen production and storage system increases, it means that the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank need to be increased rapidly, and the iterative update step size is updated at a rate of 2; (4) If the utilization rate of photovoltaic power generation decreases and the utilization rate of the hydrogen production and storage system decreases, it means that the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank need to be slowly increased, and the iterative update step size is updated at a rate of 0.
5.
6. The method according to claim 5, characterized in that The step 4 comprises the following steps: Step 4.1: According to the installed capacity of the photovoltaic power generation system, the rated power of the battery energy storage and the peak power of the load, set the initial values of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank, set the number of iterations iter to 1, and set the rated power of the hydrogen production electrolyzer to The hydrogen storage tank capacity is Set the maximum number of iterations itermax and the iterative update step size ΔP of the rated power of the hydrogen electrolyzer EL and the iterative update step size ΔV of the hydrogen storage tank capacity HESS , ΔP EL >0,ΔV HESS >0; Step 4.2: Convert the current hydrogen electrolyzer rated power and hydrogen storage tank capacity Input the hydrogen production and storage system planning evaluation unit to obtain the evaluation results of the corresponding configuration scheme Step 4.3: Iterate and update the step size ΔP EL and ΔV HESS The rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank are updated as follows: in, and They represent the updated rated power of the hydrogen electrolyzer and the capacity of the hydrogen storage tank respectively; Input the updated rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank into the hydrogen production and storage system planning evaluation unit to obtain the evaluation results of the corresponding configuration scheme Step 4.4: Compare the evaluation results of the configuration schemes before and after the update, and adjust the iterative update step size ΔP of the rated power of the hydrogen production electrolyzer and the capacity of the hydrogen storage tank EL and ΔV HESS ; Step 4.5: Determine whether the number of iterations iter is greater than or equal to the maximum number of iterations itermax; if so, complete the hydrogen production and storage system planning and output the rated power of the hydrogen production electrolyzer and hydrogen storage tank capacity as the final configuration solution; if not, the number of iterations iter increases by 1 and returns to step 4.3 to continue execution.
