New energy grid-connected hydrogen production control strategy optimization method, device, equipment and medium

Abstract

The invention relates to the technical field of new energy, and discloses a new energy grid-connected hydrogen production control strategy optimization method and device, equipment and a medium. The method comprises the steps of determining new energy power generation power prediction data and load demand power prediction data based on new energy power generation power historical data, load demand power historical data and a prediction model so as to determine a plurality of hydrogen production scenes; determining a state space model, a multi-objective function and a constraint condition according to the plurality of hydrogen production scenes and the grid-connected bus electric quantity filling and shortage of the new energy grid-connected hydrogen production system, and constructing a rolling optimization scheduling model in combination with a preset rolling optimization scheduling strategy; and according to the new energy power generation power prediction data, the load demand power prediction data and the rated parameters and the real-time state parameters of the new energy grid-connected hydrogen production system, solving the rolling optimization scheduling model to obtain a target control strategy. A control strategy is prevented from being formulated according to artificial experience, so that the comprehensive energy utilization rate is improved, and the economic benefits of the new energy internet are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy, in particular to a new energy grid-connected hydrogen production control strategy optimization method, device, equipment and medium. BACKGROUND

[0002] According to the future energy development direction of China, the proportion of renewable energy power generation in China will become larger and larger, and its large-scale storage, transportation and consumption has gradually become a key problem in China.

[0003] Hydrogen energy is a high-energy-density, green, clean and pollution-free high-quality energy, which has a strong market in the current industrial system and future industrial 4.0. New energy grid-connected hydrogen production not only produces a large amount of clean hydrogen to create economic benefits, but also has unparalleled flexible adjustment capability and energy storage advantage, which can effectively offset the adverse effects of random fluctuations of wind power, solar power and other new energy power generation, and can make a significant contribution to the flexibility and safety of the power system. However, the current control strategy of new energy grid-connected hydrogen production is usually formulated by artificial experience, and new energy power generation has strong randomness. The control strategy of new energy grid-connected hydrogen production formulated according to artificial experience cannot accurately achieve the ideal comprehensive energy utilization rate, the comprehensive energy utilization rate is low, and the economic benefit of the energy internet still has a large space for improvement. SUMMARY

[0004] Therefore, the purpose of the present application is to overcome the deficiencies in the prior art, and to provide a new energy grid-connected hydrogen production control strategy optimization method, which comprises: Obtaining new energy power generation historical data and load demand power historical data of a new energy grid-connected hydrogen production system, and determining new energy power generation power prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data and a prediction model; Determining a plurality of hydrogen production scenarios based on the new energy power generation power prediction data and the load demand power prediction data; Determining a state space model, a multi-objective function and a constraint condition according to a plurality of the hydrogen production scenarios and grid-connected bus power surplus or deficit of the new energy grid-connected hydrogen production system; Constructing a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint condition and a preset rolling optimization scheduling strategy; Solving the rolling optimization scheduling model according to the new energy power generation power prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system, to obtain a target control strategy of the new energy grid-connected hydrogen production system.

[0005] In an embodiment, the new energy power generation prediction data comprises new energy power generation prediction values of a plurality of future time periods, the load demand power prediction data comprises load demand power prediction values of a plurality of future time periods, and the step of determining a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data comprises: combining the load demand power prediction values of a plurality of future time periods and the load demand power prediction values of a plurality of future time periods based on a preset combination rule to determine a plurality of hydrogen production scenarios.

[0006] In an embodiment, the step of determining a state space model, a multi-objective function and a constraint condition according to a plurality of the hydrogen production scenarios and the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system comprises: determining a constraint condition according to a plurality of the hydrogen production scenarios, and determining a multi-objective function according to the constraint condition; determining a scheduling instruction according to the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system, and determining a state space model according to the scheduling instruction.

[0007] In an embodiment, the constraint condition comprises a system power balance constraint, a new energy power generation capacity and load power consumption constraint, an electrolyzer hydrogen production system consumable power interval constraint, an electrolyzer ramp rate constraint and a system grid-connected tie-line transmission power fluctuation constraint.

[0008] In an embodiment, the multi-objective function comprises a new energy curtailment function, a load shedding function in a power grid power deficit state, a minimum system grid-connected tie-line transmission power fluctuation function and a maximum electrolyzer hydrogen production amount function.

[0009] In an embodiment, the step of determining a state space model according to the scheduling instruction comprises: determining a state vector, a control variable and an output vector of the new energy grid-connected hydrogen production system according to the scheduling instruction; determining a state space model based on the state vector, the control variable and the output vector.

[0010] In an embodiment, the step of solving the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain a target control strategy of the new energy grid-connected hydrogen production system comprises: solving the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain an initial control strategy of the new energy grid-connected hydrogen production system; correct the real-time state parameters of the new energy grid-connected hydrogen production system, and update the new energy power generation prediction data and the load demand power prediction data based on the corrected real-time state parameters; According to the updated new energy power generation prediction data, the updated load demand power prediction data, the rated parameters and the corrected real-time state parameters, the rolling optimization scheduling model is solved to obtain the optimization control strategy of the new energy grid-connected hydrogen production system. The optimization control strategy is repeatedly updated and iterated until the optimization control strategy converges, and the target control strategy of the new energy grid-connected hydrogen production system is obtained.

[0011] The application also provides a new energy grid-connected hydrogen production control strategy optimization device, which comprises: A prediction module is configured to obtain new energy power generation historical data and load demand power historical data of a new energy grid-connected hydrogen production system, and determine new energy power generation prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data and a prediction model. A first determination module is configured to determine a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data. A second determination module is configured to determine a state space model, a multi-objective function and a constraint condition according to a plurality of hydrogen production scenarios and grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system. A construction module is configured to construct a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint condition and a preset rolling optimization scheduling strategy. A solving module is configured to solve the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters of the new energy grid-connected hydrogen production system and real-time state parameters to obtain a target control strategy of the new energy grid-connected hydrogen production system.

[0012] The application also provides a computer device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to execute the computer program to implement the new energy grid-connected hydrogen production control strategy optimization method.

[0013] The application also provides a computer readable storage medium storing a computer program, wherein the computer program is configured to execute the new energy grid-connected hydrogen production control strategy optimization method when running on a processor.

[0014] The application has the following beneficial effects: The embodiment of the application obtains new energy power generation historical data and load demand power historical data of a new energy grid-connected hydrogen production system, and determines new energy power generation prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data and a prediction model; determines a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data; determines a state space model, a multi-objective function and a constraint condition according to the plurality of hydrogen production scenarios and power surplus or deficit of a grid-connected bus of the new energy grid-connected hydrogen production system; constructs a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint condition and a preset rolling optimization scheduling strategy; and solves the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system, to obtain a target control strategy of the new energy grid-connected hydrogen production system. By combining various parameters of the new energy grid-connected hydrogen production system and the plurality of hydrogen production scenarios, the target control strategy of the new energy grid-connected hydrogen production system is determined, which avoids formulating the control strategy according to artificial experience, so as to improve comprehensive energy utilization rate and economic benefits of a new energy internet. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope of protection of the present application. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0016] Figure 1 a flowchart of a first embodiment of a new energy grid-connected hydrogen production control strategy optimization method provided by the present application; Figure 2 a topological structure diagram of a new energy grid-connected hydrogen production system provided by the present application; Figure 3 a flowchart of a second embodiment of a new energy grid-connected hydrogen production control strategy optimization method provided by the present application; Figure 4 a flowchart of a third embodiment of a new energy grid-connected hydrogen production control strategy optimization method provided by the present application; Figure 5 a flowchart of a fourth embodiment of a new energy grid-connected hydrogen production control strategy optimization method provided by the present application; Figure 6 a flowchart of a fifth embodiment of a new energy grid-connected hydrogen production control strategy optimization method provided by the present application; Figure 7A structural schematic diagram of a new energy grid-connected hydrogen production control strategy optimization device provided in the application is shown. DETAILED DESCRIPTION

[0017] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application.

[0018] The components of the embodiments of the application generally described and illustrated in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of the application. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the application.

[0019] Hereinafter, the terms "include", "have", and their conjugates used in various embodiments of the application are only intended to denote a certain characteristic, number, step, operation, element, component, or combination of the foregoing, and should not be understood as excluding the presence or addition of one or more other characteristics, numbers, steps, operations, elements, components, or combinations of the foregoing.

[0020] In addition, the terms "first", "second", "third", and the like are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0021] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the application belong. The terms (such as those defined in a generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized or overly formal meaning, unless clearly defined in various embodiments of the application.

[0022] It can be understood that the method of the application is applied to a new energy grid-connected hydrogen production control strategy optimization device, which can be an intelligent terminal, a PC terminal, a mobile terminal, etc., which is not limited here.

[0023] The purpose of the application is to provide a new energy grid-connected hydrogen production system control strategy optimization method, which greatly weakens the influence of uncertain factors in the power grid and ensures the rationality of the short-term rolling scheduling plan of the electrolytic cell hydrogen production system in the new energy grid-connected hydrogen production system and the stability of the system operation.

[0024] The new energy grid-connected hydrogen production system of the application contains wind, light and other renewable energy power generation equipment and electrolyzer hydrogen production equipment. The application mainly uses model predictive control to predict the short-term power generation of new energy and the power consumption of load in the new energy grid-connected hydrogen production system, and obtains the upper and lower limits of power supply and power consumption at different times through interval prediction in the future N period to obtain hydrogen production scenarios under multiple power supply and power consumption power intervals, and obtains the power optimization control sequence of the electrolyzer through multi-objective optimization of the electrolytic hydrogen production system under different power supply and power consumption scenarios, and finally forms the new energy grid-connected hydrogen production system optimization control strategy suitable for multi-scenario optimization.

[0025] Some embodiments of the application will be described in detail below with reference to the accompanying drawings. The following examples and features in the examples can be combined with each other without conflict.

[0026] Please refer to Figure 1 , Figure 1 The flowchart of the first embodiment of the new energy grid-connected hydrogen production control strategy optimization method provided by the application is shown in the figure. The method comprises: Step S101, obtaining the new energy power generation power historical data and load demand power historical data of the new energy grid-connected hydrogen production system, and determining the new energy power generation power prediction data and load demand power prediction data based on the new energy power generation power historical data, the load demand power historical data and the prediction model.

[0027] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device obtains the new energy power generation power historical data and load demand power historical data of the new energy grid-connected hydrogen production system, and determines the new energy power generation power prediction data and load demand power prediction data based on the new energy power generation power historical data, the load demand power historical data and the prediction model. It should be noted that please refer to Figure 2 , Figure 2 The topological structure of the new energy grid-connected hydrogen production system is shown in the figure. The new energy grid-connected hydrogen production system comprises wind, light and other renewable energy power generation equipment, load of power system, electrolyzer hydrogen production equipment and large power grid. The new energy grid-connected hydrogen production system is obtained by connecting the electrolyzer hydrogen production equipment to the new energy power generation power system through grid connection.

[0028] It can be understood that the new energy power generation power historical data is the power generation power historical data of wind, light and other renewable energy power generation equipment, and the load demand power historical data is the power historical data required by the load in the system. The load is the general term of other equipment that needs to be powered in the power system.

[0029] In an embodiment, the new energy grid-connected hydrogen production control strategy optimization device acquires basic data and topology structure information in the new energy grid-connected hydrogen production system; the basic data includes dispatchable power information of a dispatchable new energy power generation system such as a wind power generation system and a photovoltaic power generation system in the system, load demand prediction information of the power system, rated power, rated power and rated operation parameters of an electrolytic cell hydrogen production system, and maximum hydrogen production capacity of the electrolytic cell; and the topology structure information includes system connection mode and power supply bus form. The new energy grid-connected hydrogen production control strategy optimization device judges power supply and use power balance state of the power system based on the topology structure information and the basic data, and performs big data training on a prediction model neural network to obtain the prediction model. The new energy grid-connected hydrogen production control strategy optimization device inputs new energy power generation power historical data and load demand power historical data into the prediction model, and can obtain new energy power generation power prediction data and load demand power prediction data.

[0030] In step S102, a plurality of hydrogen production scenarios are determined based on the new energy power generation power prediction data and the load demand power prediction data.

[0031] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device randomly selects points in the upper and lower limit power matrix of the new energy power generation power prediction data and the load demand power prediction data based on the new energy power generation power prediction data and the load demand power prediction data to form a plurality of hydrogen production scenarios; it should be noted that the number of hydrogen production scenarios can be determined according to a pre-set number threshold, or can be determined by the new energy grid-connected hydrogen production control strategy optimization device according to the state of the new energy grid-connected hydrogen production system. Exemplarily, the plurality of hydrogen production scenarios include a maximum hydrogen production amount scenario formed when a new energy power generation peak time coincides with a load power consumption valley time, a minimum hydrogen production amount scenario formed when a new energy power generation valley time coincides with a load power consumption peak time, a new energy and load opposite fluctuation scenario, a new energy and load synchronous fluctuation scenario, a load sudden increase scenario, and the like. The plurality of hydrogen production scenarios are determined to cover the uncertainty space, thereby improving the robustness and adaptability of the new energy grid-connected hydrogen production system.

[0032] In step S103, a state space model, a multi-objective function, and a constraint condition are determined according to the plurality of hydrogen production scenarios and the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system.

[0033] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device determines a state space model, a multi-objective function, and a constraint condition according to the plurality of hydrogen production scenarios and the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system.

[0034] In step S104, a rolling optimization scheduling model is constructed according to the state space model, the multi-objective function, the constraint condition, and a pre-set rolling optimization scheduling strategy.

[0035] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device constructs a rolling optimization scheduling model according to a state space model, a multi-objective function, a constraint condition and a preset rolling optimization scheduling strategy.

[0036] In step S105, the rolling optimization scheduling model is solved by using a multi-objective swarm intelligent optimization algorithm to solve the optimization model according to the new energy power generation prediction data, the load demand power prediction data, the rated parameters and the real-time state parameters of the new energy grid-connected hydrogen production system, so as to obtain the target control strategy of the new energy grid-connected hydrogen production system.

[0037] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device solves the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, the rated parameters and the real-time state parameters of the new energy grid-connected hydrogen production system, obtains the initial control strategy of the new energy grid-connected hydrogen production system, corrects the current state of each subsystem of the new energy grid-connected hydrogen production system, samples the real-time system state, updates the new energy power generation prediction data and the load demand power prediction data, and continuously updates the initial optimization control strategy until convergence, so as to finally obtain the target control strategy of the new energy grid-connected hydrogen production system.

[0038] The new energy grid-connected hydrogen production control strategy optimization device in this embodiment obtains new energy power generation historical data and load demand power historical data of a new energy grid-connected hydrogen production system, determines new energy power generation prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data and a prediction model, determines a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data, determines a state space model, a multi-objective function and a constraint condition according to the plurality of hydrogen production scenarios and power surplus or deficiency of a grid-connected bus of the new energy grid-connected hydrogen production system, constructs a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint condition and a preset rolling optimization scheduling strategy, and solves the rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system, so as to obtain a target control strategy of the new energy grid-connected hydrogen production system. By combining various parameters of the new energy grid-connected hydrogen production system and a plurality of hydrogen production scenarios, the target control strategy of the new energy grid-connected hydrogen production system is determined, which avoids formulating the control strategy according to artificial experience, improves the comprehensive energy utilization rate and improves the economic benefits of the new energy internet.

[0039] Please refer to Figure 3 , Figure 3A flowchart of a second embodiment of the new energy grid-connected hydrogen production control strategy optimization method provided in the present application is shown in FIG. 2. The second embodiment differs from the first embodiment in that the new energy power generation prediction data includes new energy power generation prediction values for multiple future time periods, the load demand power prediction data includes load demand power prediction values for multiple future time periods, and the step of determining multiple hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data includes the following steps: In step S201, the load demand power prediction values for multiple future time periods and the load demand power prediction values for multiple future time periods are combined based on a preset combination rule to determine multiple hydrogen production scenarios.

[0040] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device obtains new energy power generation historical data and load demand power historical data of the new energy grid-connected hydrogen production system, and determines new energy power generation prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data, and a prediction model.

[0041] In an embodiment, the prediction model is as follows:

[0042] wherein, is the new energy power generation prediction data; is the load demand power prediction data. By analyzing the prediction error, the distribution variance σ of the new energy power generation and load power consumption can be obtained. Based on the new energy power generation prediction data and the variance, the upper and lower limits of the new energy power generation interval prediction power can be determined. Based on the load demand power prediction data and the variance, the upper and lower limits of the load demand power prediction power can be determined.

[0043]

[0044] wherein, is the upper limit of the new energy power generation interval prediction power, is the lower limit of the new energy power generation interval prediction power; is the upper limit of the load power consumption interval prediction power, is the lower limit of the load power consumption interval prediction power. Finally, the prediction power interval data is matrixed to obtain new energy power generation prediction data including new energy power generation prediction values for multiple future time periods, and load demand power prediction data including load demand power prediction values for multiple future time periods as follows:

[0045]

[0046] New energy grid-connected hydrogen production control strategy optimization device randomly selected p-th row m-column combination q-th row m-column combination , scenario two: , scenario one is the maximum hydrogen production scenario formed when the peak of new energy power generation coincides with the low load power consumption time, and scenario two is the minimum hydrogen production scenario formed when the low valley of new energy power generation coincides with the peak of load power consumption. It can be understood that more hydrogen production scenarios can be derived, which will not be illustrated one by one here.

[0047] The new energy grid-connected hydrogen production control strategy optimization device of the embodiment combines the load demand power prediction values of multiple future time periods and the load demand power prediction values of multiple future time periods based on the preset combination rule to determine multiple hydrogen production scenarios. It can cover the uncertainty space of the new energy grid-connected hydrogen production system, help improve the accuracy of subsequent control strategy optimization, and thus improve the robustness and adaptability of the new energy grid-connected hydrogen production system.

[0048] Please refer to Figure 4 , Figure 4 The flowchart of the third embodiment of the new energy grid-connected hydrogen production control strategy optimization method provided in the present application, the third embodiment is different from the first embodiment to the second embodiment in that the step of determining the state space model, the multi-objective function and the constraint condition according to the multiple hydrogen production scenarios and the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system comprises: Step S301, determining the constraint condition according to the multiple hydrogen production scenarios, and determining the multi-objective function according to the constraint condition.

[0049] In the embodiment, after determining the multiple hydrogen production scenarios, the new energy grid-connected hydrogen production control strategy optimization device determines the constraint condition according to the multiple hydrogen production scenarios, and determines the multi-objective function according to the constraint condition.

[0050] In an embodiment, the constraint condition comprises: system power balance constraint, new energy power generation capacity and load power consumption power constraint, electrolytic cell hydrogen production system consumable power interval constraint, electrolytic cell climbing rate constraint and system grid-connected tie line transmission power fluctuation constraint; wherein the system grid-connected tie line transmission power fluctuation constraint is set according to the specific situation of the power system of new energy power generation.

[0051] In an embodiment, the system power balance constraint is:

[0052]

[0053] and Predict the upper and lower power limits of the renewable energy power generation system at time k+i; and Predict the upper and lower power limits for the load power consumption interval at time k+i; N el The number of installed electrolyzer hydrogen production systems; At the k+ith moment l The hydrogen production power of each electrolyzer; and The exchange power of the interconnection line of the new energy grid-connected hydrogen production system under scenario 1 and scenario 2 at the k+i moment. In one embodiment, the renewable energy generation capacity and load power consumption constraints are:

[0054]

[0055]

[0056]

[0057] in, Corresponding predicted power interval matrix Line 2 of List, Corresponding predicted power interval matrix No. 1 Rank Column, where =[1,N], N represents the length of the prediction time; It is the output power of new energy in the first power supply and use scenario. The output power of renewable energy in the second power supply and consumption scenario; is the power consumption of the load in the first power supply and consumption scenario, It is the power consumption of the load in the second power supply and utilization scenario.

[0058] In one embodiment, the power consumption range of the electrolyzer hydrogen production system is constrained as follows:

[0059] in, For the Rated power of each electrolyzer, For the The actual power of an electrolytic cell at time k+i.

[0060] In one embodiment, the electrolyzer hydrogen production power ramp rate constraint is:

[0061] wherein the electrolytic cell hydrogen production process needs to determine a proper ramping rate β to ensure that the electrolytic cell system works in the most operating interval and maintains a stable high-speed hydrogen production process.

[0062] In an embodiment, the multi-objective function includes: a new energy curtailment function, a load shedding function under a power grid deficit state, a minimum transmission power fluctuation function of a system grid-connected tie line, and a maximum electrolytic cell hydrogen production function.

[0063] wherein the multi-objective function is:

[0064] wherein J1 is a new energy curtailment function; J2 is a load shedding function under a power grid deficit state; J3 is a minimum transmission power fluctuation function of a system grid-connected tie line; and J4 is a maximum electrolytic cell hydrogen production function.

[0065] Step S302, determining a scheduling instruction according to the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system, and determining a state space model according to the scheduling instruction.

[0066] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device determines a scheduling instruction according to the grid-connected bus power surplus / deficit of the new energy grid-connected hydrogen production system, and constructs a state space model corresponding to the new energy grid-connected hydrogen production system based on the scheduling instruction and the model predictive control theory.

[0067] The new energy grid-connected hydrogen production control strategy optimization device of this embodiment formulates a set of constraint conditions according to multiple hydrogen production scenarios to ensure that the system operates within resource limits and safety boundaries; at the same time, a multi-objective function is used to jointly optimize multiple targets such as task scheduling time, energy consumption, and load balancing, providing support for subsequent construction of a rolling optimization scheduling model, which helps to improve the accuracy of the rolling optimization scheduling model.

[0068] Please refer to Figure 5 , Figure 5 The fourth embodiment of the new energy grid-connected hydrogen production control strategy optimization method provided in this application is a flowchart, and the fourth embodiment is different from the first to third embodiments in that the step of determining a state space model according to the scheduling instruction includes: Step S401, determining a state vector, a control variable, and an output vector of the new energy grid-connected hydrogen production system according to the scheduling instruction.

[0069] Step S402, determining a state space model based on the state vector, the control variable, and the output vector.

[0070] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device determines a state vector, a control variable and an output vector of the new energy grid-connected hydrogen production system according to a scheduling instruction. The scheduling instruction is issued according to the change of the source-load imbalance in the system. The energy imbalance relationship of the green hydrogen production system at each moment is analyzed through the following process: The power imbalance between the source and the load is required. If , it indicates that the power in the power grid is sufficient and the new energy power generation is surplus. In order to maintain the power balance of the system, the abandoned power needs to be abandoned. At this time, the electrolytic hydrogen production system is connected, and the electrolytic hydrogen production device needs to consume hydrogen production to compensate for the power imbalance and reduce the abandoned power of the new energy as much as possible. If , the load power needs to be prioritized to avoid load shedding in the power grid due to a large amount of hydrogen production, which affects production and life. If , the system is in a balanced state, and there is no need to abandon power and cut off the load to ensure the power balance between the power grid. The electrolytic cell hydrogen production system only needs to produce hydrogen as a normal load or be closed to maintain the power balance of the system and prioritize power supply to the remaining load.

[0071] In actual application, based on the model predictive control theory, a corresponding state space model is constructed in the new energy grid-connected hydrogen production system to solve the multi-objective optimization of the multi-objective function, and a time domain rolling optimization scheduling strategy is established. The model characteristics in the optimization scheduling method include the following input and output information: According to the power balance equation of the system at each period and the electrolytic cell hydrogen production state, the dispatchable new energy output power obtained from the previous prediction data , the electrolytic cell hydrogen production system power consumption , and the microgrid tie line exchange power constitute the state vector:

[0072] The output increment of the dispatchable new energy power generation system , the adjustable load , and the adjustable electrolytic cell system consumption power change constitute the vector as the control variable.

[0073] The vector composed of the ultra-short-term prediction power increment of wind power, photovoltaic power and microgrid load demand as the disturbance input in the time domain rolling optimization process.

[0074] The system output vector is the vector composed of the tie line exchange power between the microgrid and the large power grid and the SOC and SOHR of the energy storage system .

[0075] The new energy grid-connected hydrogen production control strategy optimization device determines the state space model based on the state vector, control variables and output vector. In one embodiment, the state space model is:

[0076]

[0077] in, The state vector is The state of the moment; For new energy power generation systems Power state value at the moment; For electrolysis hydrogen production system Power state value at the moment; Exchange power status values ​​for grid tie lines; Optimize single step duration for scrolling; Increase the dispatchable output of the new energy power generation system; Load demand power change increment; To adjust the amount of power consumed by the electrolytic cell system; Exchange power for the interconnection line of the new energy grid-connected hydrogen production system; It is the system output variable, which is a vector composed of the output of the new energy system, the electrolysis hydrogen production system and the load absorption capacity.

[0078] The new energy grid-connected hydrogen production control strategy optimization device of this embodiment abstracts the internal operating state of the system into a set of state variables by constructing a state space model, and models the dynamic behavior of the system based on the state transfer equation and the observation equation, quantifies the state of the current system, and provides support for the subsequent construction of the rolling optimization scheduling model, which helps to improve the accuracy of the rolling optimization scheduling model.

[0079] Please refer to Figure 6 , Figure 6 This is a flow chart of the fifth embodiment of the new energy grid-connected hydrogen production control strategy optimization method provided in this application. The difference between the fifth embodiment and the first to fourth embodiments is that the step of solving the rolling optimization scheduling model based on the new energy power generation power forecast data, the load demand power forecast data, and the rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain the target control strategy of the new energy grid-connected hydrogen production system includes: Step S401, solving the rolling optimization scheduling model based on the new energy power generation power forecast data, the load demand power forecast data, the rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system, and obtaining the initial control strategy of the new energy grid-connected hydrogen production system.

[0080] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device solves a rolling optimization scheduling model according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system, and obtains an initial control strategy of the new energy grid-connected hydrogen production system. The obtained initial control strategy includes an initial power output value of the new energy grid-connected hydrogen production system, an initial load shedding amount, and an initial electrolyzer hydrogen production power output sequence.

[0081] In an embodiment, the rolling optimization scheduling model is:

[0082] wherein, wherein, is a fusion objective function of a comprehensive multi-objective function; is a vector composed of the optimized output values of each subsystem under the i-th objective function; is a vector composed of the optimized output values of each subsystem under the i-th objective function; is a vector reference value composed of the optimized output values of each subsystem under the i-th objective function; and are obtained by substituting the new energy power generation prediction data, the load demand power prediction data, the rated parameters and the real-time state parameters of the new energy grid-connected hydrogen production system into the fusion objective function of the multi-objective function. Step S402, correcting the real-time state parameters of the new energy grid-connected hydrogen production system, and updating the new energy power generation prediction data and the load demand power prediction data based on the corrected real-time state parameters.

[0083] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device corrects the real-time state parameters of the new energy grid-connected hydrogen production system based on the initial electrolyzer hydrogen production power output sequence in the initial control strategy, and updates the new energy power generation prediction data and the load demand power prediction data based on the corrected real-time state parameters.

[0084] Step S403, solving the rolling optimization scheduling model according to the updated new energy power generation prediction data, the updated load demand power prediction data, the rated parameters and the corrected real-time state parameters, and obtaining an optimized control strategy of the new energy grid-connected hydrogen production system.

[0085] In the embodiment, the new energy grid-connected hydrogen production control strategy optimization device solves a rolling optimization scheduling model according to the updated new energy power generation prediction data, the updated load demand power prediction data, the rated parameters and the corrected real-time state parameters, and obtains an optimized control strategy of the new energy grid-connected hydrogen production system.

[0086]

[0087] ​In step S404, the optimization control strategy is repeatedly updated and iterated until the optimization control strategy converges, and a target control strategy of the new energy grid-connected hydrogen production system is obtained.

[0088] In this embodiment, the new energy grid-connected hydrogen production control strategy optimization device repeatedly updates and iterates the optimization control strategy until the optimization control strategy converges, and a target control strategy of the new energy grid-connected hydrogen production system is obtained. The obtained target control strategy includes a target power output value, a target load shedding amount, and a target electrolyzer hydrogen production power output sequence of the new energy grid-connected hydrogen production system.

[0089] In an embodiment, the target power output value, the target load shedding amount, and the target electrolyzer hydrogen production power output sequence obtained by the new energy grid-connected hydrogen production control strategy optimization device are sequence values of multiple future time periods. The new energy grid-connected hydrogen production control strategy optimization device only uses the target power output value, the target load shedding amount, and the target electrolyzer hydrogen production power output value of the current time period to control the new energy grid-connected hydrogen production system. Alternatively, for the power output values, the target load shedding amounts, and the target electrolyzer hydrogen production power output values of the remaining other future time periods, the new energy grid-connected hydrogen production control strategy optimization device uses them as a reference to perform the next control strategy optimization operation. Alternatively, for the power output values, the target load shedding amounts, and the target electrolyzer hydrogen production power output values of the remaining other future time periods, the new energy grid-connected hydrogen production control strategy optimization device can directly discard them. It should be noted that the process steps of the new energy grid-connected hydrogen production control strategy optimization device performing the next control strategy optimization operation are completely the same as those in the above embodiment, and will not be repeated here.

[0090] The new energy grid-connected hydrogen production control strategy optimization device of this embodiment obtains a target control strategy of the new energy grid-connected hydrogen production system by solving a rolling optimization scheduling model constructed based on constraint conditions, multi-objective functions, and a state space model of multiple hydrogen production scenarios. The target control strategy can reduce the curtailment rate of the new energy power generation system in the microgrid, improve the stability of the new energy power generation system in the grid, improve the power supply capability of the grid to the load, and ensure the rationality of the short-term rolling scheduling plan and the stability of the system operation. This helps to improve the comprehensive energy utilization rate and improve the economic benefits of the new energy internet.

[0091] Reference Figure 7 , Figure 7 is a structural schematic diagram of a new energy grid-connected hydrogen production control strategy optimization device provided by the present application. The new energy grid-connected hydrogen production control strategy optimization device includes: The prediction module 10 is configured to acquire new energy power generation historical data and load demand power historical data of the new energy grid-connected hydrogen production system, and determine new energy power generation prediction data and load demand power prediction data based on the new energy power generation historical data, the load demand power historical data and a prediction model; The first determination module 20 is configured to determine a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data. The second determination module 30 is configured to determine a state space model, a multi-objective function and a constraint condition according to the plurality of hydrogen production scenarios and power surplus / deficit of a grid-connected bus of the new energy grid-connected hydrogen production system. The construction module 40 is configured to construct a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint condition and a preset rolling optimization scheduling strategy. The solution module 50 is configured to solve the rolling optimization scheduling model to obtain a target control strategy of the new energy grid-connected hydrogen production system according to the new energy power generation prediction data, the load demand power prediction data, rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system.

[0092] The application further provides a computer device. Illustratively, the computer device comprises a processor and a memory. The memory stores a computer program. The processor runs the computer program, so that the computer device performs the functions of each module in the new energy grid-connected hydrogen production control strategy optimization method or the new energy grid-connected hydrogen production control strategy optimization device.

[0093] The processor can be an integrated circuit chip with a signal processing capability. The processor can be a general-purpose processor, including a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or at least one of them. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like, which can implement or execute the disclosed methods, steps and logic block diagrams in the embodiments of the application.

[0094] The memory can be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an Electric Erasable Programmable Read-Only Memory (EEPROM), and the like. Among them, the memory is used to store a computer program, and the processor can execute the computer program correspondingly after receiving an execution instruction.

[0095] The application further provides a computer storage medium for storing the computer program used in the computer device. The computer storage medium can be a readable storage medium, a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium can include, but is not limited to, a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk and various program code storage media.

[0096] In several embodiments provided in the application, it should be understood that the disclosed apparatus and method can also be implemented by other manners. The apparatus embodiments described above are only schematic, for example, the flow charts and structural diagrams in the drawings show the possible implementation architectures, functions and operations of the apparatus, method and computer program product according to the embodiments of the application. In this regard, each block in the flow chart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in alternative implementation manners, the functions noted in the blocks can also occur in different orders from that noted in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the structural diagram and / or flow chart, and the combination of blocks in the structural diagram and / or flow chart, can be implemented by a special hardware-based system for executing the specified functions or actions, or can be implemented by a combination of special hardware and computer instructions.

[0097] In addition, each functional module or unit in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0098] The functions, if implemented in the form of software functional modules and sold or used as independent products, can be stored in a readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application.

[0099] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A new energy grid-connected hydrogen production control strategy optimization method, characterized in that: The method comprises: Obtaining historical data on new energy power generation and load demand power of the new energy grid-connected hydrogen production system, and determining new energy power generation prediction data and load demand power prediction data based on the historical data on new energy power generation, the historical data on load demand power, and a prediction model; Determining multiple hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data; Determining a state space model, a multi-objective function, and constraints based on the plurality of hydrogen production scenarios and the grid-connected busbar power surplus or shortage of the new energy grid-connected hydrogen production system; Constructing a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint conditions and a preset rolling optimization scheduling strategy; The rolling optimization scheduling model is solved based on the new energy power generation power forecast data, the load demand power forecast data, and the rated parameters and real-time status parameters of the new energy grid-connected hydrogen production system to obtain the target control strategy of the new energy grid-connected hydrogen production system.

2. The new energy grid-connected hydrogen production control strategy optimization method according to claim 1 is characterized in that: The new energy power generation prediction data includes new energy power generation prediction values ​​for multiple future time periods, and the load demand power prediction data includes load demand power prediction values ​​for multiple future time periods. The step of determining multiple hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data includes: Based on a preset combination rule, the load demand power forecast values ​​of multiple future time periods and the load demand power forecast values ​​of multiple future time periods are combined to determine multiple hydrogen production scenarios.

3. The new energy grid-connected hydrogen production control strategy optimization method according to claim 1 is characterized in that: The step of determining a state space model, a multi-objective function, and constraints based on the plurality of hydrogen production scenarios and the grid-connected busbar power surplus or shortage of the new energy grid-connected hydrogen production system includes: Determining constraints according to the plurality of hydrogen production scenarios, and determining a multi-objective function according to the constraints; A dispatch instruction is determined according to the grid-connected busbar power surplus or shortage of the new energy grid-connected hydrogen production system, and a state space model is determined according to the dispatch instruction.

4. The method for optimizing the control strategy of hydrogen production from grid-connected renewable energy according to claim 3, characterized in that: The constraints include: system power balance constraints, new energy power generation capacity and load power constraints, electrolyzer hydrogen production system power range constraints, electrolyzer ramp rate constraints and system grid-connected interconnection line transmission power fluctuation constraints.

5. The method for optimizing the control strategy of hydrogen production from grid-connected renewable energy according to claim 3, characterized in that: The multi-objective function includes: a new energy power abandonment function, a load shedding function under a power shortage state of the power grid, a function for minimizing the power fluctuation of the system grid-connected interconnection line, and a function for maximizing the hydrogen production of the electrolyzer.

6. The method for optimizing the control strategy of renewable energy grid-connected hydrogen production according to claim 3, characterized in that: The step of determining the state space model according to the scheduling instruction comprises: Determining a state vector, a control variable, and an output vector of the new energy grid-connected hydrogen production system according to the scheduling instruction; A state-space model is determined based on the state vector, the control variables, and the output vector.

7. The method for optimizing the control strategy of hydrogen production from grid-connected renewable energy according to claim 1, characterized in that: The step of solving the rolling optimization scheduling model based on the new energy power generation power forecast data, the load demand power forecast data, and the rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain the target control strategy of the new energy grid-connected hydrogen production system includes: Solving the rolling optimization scheduling model based on the new energy power generation prediction data, the load demand power prediction data, and the rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain an initial control strategy for the new energy grid-connected hydrogen production system; Correcting the real-time status parameters of the new energy grid-connected hydrogen production system, and updating the new energy power generation power forecast data and the load demand power forecast data based on the corrected real-time status parameters; Solving the rolling optimization scheduling model based on the updated new energy power generation forecast data, the updated load demand power forecast data, the rated parameters, and the corrected real-time status parameters to obtain an optimization control strategy for the new energy grid-connected hydrogen production system; The optimization control strategy is repeatedly updated and iterated until the optimization control strategy converges, thereby obtaining a target control strategy for the new energy grid-connected hydrogen production system.

8. A new energy grid-connected hydrogen production control strategy optimization device, characterized in that: The new energy grid-connected hydrogen production control strategy optimization device includes: A prediction module is used to obtain historical data on new energy power generation and load demand power of the new energy grid-connected hydrogen production system, and determine new energy power generation prediction data and load demand power prediction data based on the historical data on new energy power generation, the historical data on load demand power, and a prediction model; A first determination module is configured to determine a plurality of hydrogen production scenarios based on the new energy power generation prediction data and the load demand power prediction data; A second determination module is configured to determine a state space model, a multi-objective function, and constraints based on the plurality of hydrogen production scenarios and the grid-connected bus power surplus or shortage of the new energy grid-connected hydrogen production system; A construction module, configured to construct a rolling optimization scheduling model according to the state space model, the multi-objective function, the constraint conditions and a preset rolling optimization scheduling strategy; A solution module is used to solve the rolling optimization scheduling model based on the new energy power generation power forecast data, the load demand power forecast data, and the rated parameters and real-time state parameters of the new energy grid-connected hydrogen production system to obtain the target control strategy of the new energy grid-connected hydrogen production system.

9. A computer device, characterized in that: The computer device includes a processor and a memory, the memory stores a computer program, and the processor is used to execute the computer program to implement the new energy grid-connected hydrogen production control strategy optimization method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a processor, the method for optimizing a new energy grid-connected hydrogen production control strategy according to any one of claims 1 to 7 is executed.

Images