A capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines

Abstract

The present invention discloses a capacity planning method for an offshore hydrogen production platform with integrated offshore wind turbines, which belongs to the technical field of offshore wind farm engineering planning, and the steps are as follows: input an annual wind speed curve with a planned sea area for more than one year; obtain an annual power curve using a wind speed-power conversion curve; classify by quarter, cluster the curve of each quarter according to the mean and variance using the k-means method to obtain an initial typical weekly curve; adjust the correction parameters to make the corrected curve consistent with the characteristic parameters of the original curve; set the planning model objective function and constraints, and solve the planning model to obtain the optimal capacity result. The present invention can accurately evaluate the power generation capacity of wind turbines in the sea area to be planned and efficiently handle the variability and seasonality of renewable energy power generation, ensuring that the offshore hydrogen production platform can effectively meet the hydrogen demand of the area to be planned, promote the comprehensive utilization of renewable energy, reduce the equipment loss of the energy storage system, and improve the economy of the system.

Description

Technical Field

[0001] The present invention belongs to the technical field of offshore wind farm engineering planning, and in particular relates to a capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines. Background Art

[0002] In recent years, my country's offshore wind power installed capacity has continued to grow. According to statistics from the Global Wind Energy Council (GWEC), in 2023, my country's newly connected offshore wind power capacity reached 6.3GW, a year-on-year increase of 25%, accounting for 58% of the world's newly installed capacity, maintaining its leading position in the world's newly installed capacity and cumulative installed capacity of offshore wind power.

[0003] Although my country's offshore wind power has developed rapidly, the large-scale access to offshore wind power has posed a more severe challenge to the voltage stability and power balance of coastal power grids. Due to the limitation of the capacity of onshore transmission channels, offshore wind power and onshore wind power may also face regional power congestion problems, and the current offshore wind farms are saturated, while the long-distance transmission technology of offshore wind farms is not yet fully mature. In response to the above problems, offshore hydrogen production platforms integrating several offshore wind turbines have received attention. Offshore hydrogen production can realize the local consumption of offshore wind power, solving the problem of difficulties in long-distance offshore power transmission. At the same time, it can take water locally to produce green hydrogen through electrolyzers, which has significant advantages in production costs. Therefore, it is necessary to rationally plan the capacity of offshore hydrogen production equipment integrated with offshore wind turbines. Summary of the invention

[0004] Based on the above shortcomings, the present invention provides a capacity planning method for an offshore hydrogen production platform integrating offshore wind turbines, which can accurately evaluate the power generation capacity of wind turbines in the sea area to be planned and efficiently handle the variability and seasonality of renewable energy power generation, ensuring that the offshore hydrogen production platform can effectively meet the hydrogen demand in the area to be planned, and providing effective support for the development of the coastal green hydrogen industrial system.

[0005] The technical solution adopted by the present invention is as follows: A capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines, comprising the following steps:

[0006] S1: Construct a new energy typical cycle generation method considering characteristic parameter correction:

[0007] S11: Obtain the annual wind speed data of the sea area to be planned. Using the wind speed data provided by the Copernicus Climate Change Service Center, obtain two mutually perpendicular crosswind speed data u and v at an altitude of 100m at a certain coordinate point, and then calculate the absolute wind speed at an altitude of 100m in the area to be planned. If the tower height of the wind turbine to be planned is h, in meters, then the wind speed s at the tower height is obtained using formula (1): wt , unit: m / s,

[0008]

[0009] Where z0 is the sea surface roughness coefficient, which depends on the actual sea surface conditions, including wave height and depth factors, and is obtained through the existing geographic database;

[0010] S12: Convert the wind speed data into the expected output at the corresponding wind speed according to the wind speed-power curve. The curve is provided by the wind turbine manufacturer or obtained by fitting the actual output curve and wind speed data. Formula (2) is a fitting curve obtained according to a certain type of wind turbine.

[0011]

[0012] In the formula, P(s wt ) is the wind speed in s wt The power output of the fan at that time, unit: MW; P rated is the rated output power of the fan; s in ,s out ,s rated are the cut-in wind speed, cut-out wind speed and rated working wind speed of the fan, in m / s; α, β, γ and δ are the constants obtained by fitting;

[0013] S13: The power curve P of each season w1 ,P w2 ,P w3 ,P w4 Typical circle curve compressed into a circle length For each season, the k-means method is used to select a representative weekly scenario. The mean and variance of the power daily curve are used as clustering feature parameters. The power curve closest to the center point is selected as the typical power curve through the Euclidean distance, as shown in formula (3). The 7 power curves generated by the 7 clusters constitute the preliminary typical representative weekly power of a quarter;

[0014]

[0015] Where P i is the wind power daily power curve on the ith day; E ij P i and P j The Euclidean distance between them; var(·), mean(·) represent the calculation of variance and mean respectively;

[0016] S14: After obtaining the uncorrected basic typical representative weekly power of each quarter, due to the differences in the maximum, minimum and total characteristic indicators between the basic typical weekly curve and the original seasonal curve, it is necessary to adjust the weekly curve and introduce variables and Represent the original and adjusted weekly curves respectively. The conversion function is used as shown in formula (4) to adjust the correction parameters a, b, k to ensure that the characteristic indexes of the adjusted weekly scenario: maximum, minimum and mean value match the characteristic indexes of the seasonal curve;

[0017]

[0018] S2: Construct a collaborative planning model for offshore hydrogen production systems based on:

[0019] S21: The objective function is set to maximize the comprehensive annual revenue of the offshore hydrogen production system, and the decision variable is the rated power of the hydrogen production electrolyzer Total rated power of fan Electrochemical energy storage rated capacity S b , supporting hydrogen storage tank S h , as shown in formulas (5) and (6),

[0020]

[0021] Where: R H is the annual hydrogen sales revenue, unit: 10,000 yuan; W H is the annual green hydrogen production, unit: kg; P H , T H are the green hydrogen price and equivalent transportation cost, respectively, unit: kg / 10,000 yuan; C inv is the equivalent annual investment cost, unit: 10,000 yuan; CPR is the capital recovery rate; τ is the annual interest rate; T is the designed service life, unit: year; The total rated power of all offshore wind turbines integrated into the hydrogen production platform, unit: MW; is the rated power of the electrolyzer, unit: MW; S b is the rated capacity of electrochemical energy storage, unit: MWh; S h is the rated capacity of the hydrogen storage tank, unit: kg; S cable , L cable are the total capacity and total length of the cables connecting the hydrogen production platform and the supporting offshore wind turbines, in MW and km respectively; γ w is the unit capacity cost of offshore wind turbines, unit: MW / 10,000 yuan; γ H is the unit capacity cost of the electrolyzer, unit: MW / 10,000 yuan; γ cable is the construction cost per unit length of submarine cable, unit: 10,000 yuan / km; γ b is the unit capacity cost of electrochemical energy storage, unit: MWh / 10,000 yuan; γ h is the unit capacity cost of hydrogen storage tank, unit: MW / kg; C OM is the annual operation and maintenance cost, unit: 10,000 yuan; δ w , δ H , δcable , δ b ,δ h They are the average annual operation and maintenance rates for offshore wind turbines, hydrogen production equipment, submarine cables, electrochemical energy storage and hydrogen storage tanks;

[0022] S22: Setting model constraints: including the electrolyzer hydrogen production model as shown in formulas (7) and (8), the power balance equation as shown in formula (10), the wind turbine output constraint as shown in formula (9), the energy storage charge state constraint as shown in formula (11), and the energy storage power constraint as shown in formula (12).

[0023]

[0024]

[0025] P H,t =P w,t +P b,t (10)

[0026]

[0027] Where, κ1 and κ2 are the maximum and minimum load adjustment ratios of the hydrogen production electrolyzer, alkaline electrolyzer: κ1 = 25%, κ2 = 120%, PEM electrolyzer: κ1 = 10%, κ2 = 110%; H t is the hydrogen produced at time t, unit: kg; LHV H is the lower calorific value of hydrogen, unit: WM / kg; η H is the efficiency of hydrogen production equipment; P H,t , P w,t , P b,t They are the power consumed by the electrolyzer at time t, the power consumed by the fan, and the power generated by the electrochemical energy storage, in MW; is the value corresponding to time t in the typical weekly curve, unit: pu; SoC t is the state of charge of the electrochemical energy storage at time t; c ,λ d They are respectively the charging efficiency and discharging efficiency of energy storage; SoC min , SoC max are the upper and lower limits of the state of charge of the energy storage, respectively; Δt is the simulation time interval of the planning model, which is set to 1h; P b max is the maximum discharge power of energy storage, unit: MW;

[0028] S23: Real-time hydrogen reserves are modeled at time intervals of days to calculate hydrogen reserves at different times, as shown in formulas (13) and (14), where subscript d = 1, 2, ..., T / 24, where T is the total simulation time.

[0029]

[0030] 0≤H d ≤S h (14) In the formula, H d is the hydrogen reserve at time d, unit: kg; H out is the average daily consumption of hydrogen in the planned area,

[0031] Unit: kg;

[0032] S24: Based on the above constraints, the model is formed into a linear function and solved using the existing commercial solver to finally obtain the optimal hydrogen production equipment capacity for the current planned area. and optimal fan capacity

[0033] Another object of the present invention is to provide a capacity planning system for an offshore hydrogen production platform integrated with offshore wind turbines, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the method for capacity planning of an offshore hydrogen production platform integrated with offshore wind turbines as described above is implemented.

[0034] Another object of the present invention is to provide a computer-readable storage medium, on which is stored an implementation program for information transmission, and when the program is executed by a processor, the steps of the above-mentioned method for capacity planning of an offshore hydrogen production platform integrated with offshore wind turbines are implemented.

[0035] Advantages and beneficial effects of the present invention: Under the premise of significantly reducing the computing cost, the present invention captures the variability and seasonality of offshore wind power generation by considering the typical weekly curve arranged in chronological order, while considering the matching with the original scene, and promotes the comprehensive utilization of renewable energy. The present invention effectively reduces the complexity of model solution by modeling the different time intervals of operation and hydrogen storage. Through the coordinated planning of various forms of energy storage devices, it ensures that the offshore hydrogen production platform can effectively meet the hydrogen demand of the planned area, obtain the best wind power energy storage capacity ratio, reduce the equipment loss of the energy storage system, improve the economy and robustness of the system, and provide effective support for the development of the coastal green hydrogen industrial system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a complete flow chart of the technical solution of the present invention.

[0037] Figure 2 This is a simulation result analysis diagram of the present invention. DETAILED DESCRIPTION

[0038] The present invention first obtains the crosswind speed data at an altitude of 100m at a certain coordinate point in the planned sea area, and calculates the absolute wind speed at an altitude of 100m in the area. If the wind turbine to be planned has a specific tower height, the wind speed at the tower height at the tower height is obtained according to the conversion formula and the sea surface roughness coefficient obtained from the existing geographic database. Then, according to the wind speed-power curve, the wind speed data is converted into the expected output of the wind turbine under the corresponding wind speed, and the power curve of each season is compressed into a typical weekly curve of one week in length. The k-means method is used, and the mean and variance of the power daily curve are used as clustering feature parameters to select a representative weekly scenario. The power curve closest to the center point is determined by the Euclidean distance as the typical power curve to form a preliminary typical representative weekly power for a quarter. After obtaining the uncorrected basic typical representative weekly power of each quarter, due to the difference in characteristic indicators between it and the original seasonal curve, A conversion function is introduced to adjust the correction parameters to ensure that the characteristic indexes of the adjusted weekly scenarios: maximum value, minimum value and mean value match the characteristic indexes of the seasonal curve, and then a collaborative planning model of the offshore hydrogen production system based on is constructed: wherein the objective function includes: setting the objective function to maximize the comprehensive annual revenue of the offshore hydrogen production system, the decision variables include the rated power of the hydrogen production electrolyzer, the total rated power of the wind turbine, the rated capacity of the electrochemical energy storage and the supporting hydrogen storage tanks, and the calculation formula of the objective function comprehensively considers the annual hydrogen sales revenue, annual green hydrogen production, green hydrogen price and equivalent transportation cost, equivalent annual investment cost, capital recovery rate, annual interest rate, design service life, and the cost and operation and maintenance cost of offshore wind turbines, electrolyzers, electrochemical energy storage, hydrogen storage tanks and other equipment integrated in the hydrogen production platform. Among them, the constraints include: an electrolyzer hydrogen production model, which limits the maximum and minimum load adjustment ratios of the hydrogen production electrolyzer, and takes into account the amount of hydrogen produced at different times, the low calorific value of hydrogen, the efficiency of the hydrogen production equipment, and the power consumed by the electrolyzer at different times, the power of the wind fan consumed, and the power emitted by the electrochemical energy storage, to construct a power balance equation to ensure the balance of system power; construct a fan output constraint to limit the output power of the fan; construct an energy storage charge state constraint to stipulate the upper and lower limits of the charge state of the electrochemical energy storage; construct an energy storage power constraint to limit the maximum discharge power of the energy storage, and then use the real-time hydrogen reserves to model the time on a daily basis. By calculating the hydrogen reserves at different times and the average daily consumption of hydrogen in the area to be planned, the above constraints are solved using existing commercial solvers, and finally the optimal hydrogen production equipment capacity and the optimal wind fan capacity in the current area to be planned are obtained; the present invention is described in detail below with reference to the accompanying drawings.

[0039] Example 1

[0040] like Figure 1 As shown, a capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines comprises the following steps:

[0041] S1: Construct a new energy typical cycle generation method considering characteristic parameter correction:

[0042] S11: Obtain the annual wind speed data of the sea area to be planned. Using the wind speed data provided by the Copernicus Climate Change Service Climate Data Store, obtain two mutually perpendicular crosswind speed data u and v at an altitude of 100m at a certain coordinate point, and then calculate the absolute wind speed at an altitude of 100m in the area to be planned. If the tower height of the wind turbine to be planned is h, in meters, then the wind speed s at the tower height is obtained using formula (1): wt , unit: m / s,

[0043]

[0044] Where z0 is the sea surface roughness coefficient, which depends on the actual sea surface conditions, including wave height and depth factors, and is obtained through the existing geographic database;

[0045] S12: Convert the wind speed data into the expected output at the corresponding wind speed according to the wind speed-power curve. The curve is provided by the wind turbine manufacturer or obtained by fitting the actual output curve and wind speed data. Formula (2) is a fitting curve obtained according to a certain type of wind turbine.

[0046]

[0047] In the formula, P(s wt ) is the wind speed in s wt The power output of the fan at that time, unit: MW; P rated is the rated output power of the fan; s in ,s out ,s rated are the cut-in wind speed, cut-out wind speed and rated working wind speed of the fan, in m / s; α, β, γ and δ are the constants obtained by fitting;

[0048] S13: In order to capture the variability and seasonality of renewable energy generation, it is necessary to consider the renewable energy curves arranged in chronological order. However, since 8760 hours of the whole year need to be analyzed, this approach will bring a great computational burden to the subsequent planning model. In this embodiment, the power curve P of each season is w1 ,P w2 ,P w3 ,P w4 Typical circle curve compressed into a circle length For each season, the k-means method is used to select a representative weekly scenario, and the mean and variance of the power daily curve are used as clustering feature parameters (the simulation analysis results refer to Figure 2 ), through the Euclidean distance, as shown in formula (3), the power curve closest to the center point is selected as the typical power curve. The 7 power curves generated by the 7 clusters constitute the preliminary typical representative weekly power of a quarter;

[0049]

[0050] Where P i is the wind power daily power curve on the ith day; E ij P i and P j The Euclidean distance between them; var(·), mean(·) represent the calculation of variance and mean respectively;

[0051] S14: After obtaining the uncorrected basic typical representative weekly power of each quarter, due to the differences in the maximum, minimum and total characteristic indicators between the basic typical weekly curve and the original seasonal curve, it is necessary to adjust the weekly curve and introduce variables and Represent the original and adjusted weekly curves respectively. The conversion function is used as shown in formula (4) to adjust the correction parameters a, b, k to ensure that the characteristic indexes of the adjusted weekly scenario: maximum, minimum and mean value match the characteristic indexes of the seasonal curve;

[0052]

[0053] S2: Construct a collaborative planning model for offshore hydrogen production systems based on:

[0054] S21: The objective function is set to maximize the comprehensive annual revenue of the offshore hydrogen production system, and the decision variable is the rated power of the hydrogen production electrolyzer Total rated power of fan Electrochemical energy storage rated capacity S b , supporting hydrogen storage tank S h , as shown in formulas (5) and (6),

[0055]

[0056] Where: R H is the annual hydrogen sales revenue, unit: 10,000 yuan; W H is the annual green hydrogen production, unit: kg; P H , T H are the green hydrogen price and equivalent transportation cost, respectively, unit: kg / 10,000 yuan; C invis the equivalent annual investment cost, unit: 10,000 yuan; CPR is the capital recovery rate; τ is the annual interest rate; T is the designed service life, unit: year; The total rated power of all offshore wind turbines integrated into the hydrogen production platform, unit: MW; is the rated power of the electrolyzer, unit: MW; S b is the rated capacity of electrochemical energy storage, unit: MWh; S h is the rated capacity of the hydrogen storage tank, unit: kg; S cable , L cable are the total capacity and total length of the cables connecting the hydrogen production platform and the supporting offshore wind turbines, in MW and km respectively; γ w is the unit capacity cost of offshore wind turbines, unit: MW / 10,000 yuan; γ H is the unit capacity cost of the electrolyzer, unit: MW / 10,000 yuan; γ cable is the construction cost per unit length of submarine cable, unit: 10,000 yuan / km; γ b is the unit capacity cost of electrochemical energy storage, unit: MWh / 10,000 yuan; γ h is the unit capacity cost of hydrogen storage tank, unit: MW / kg; C OM is the annual operation and maintenance cost, unit: 10,000 yuan; δ w , δ H , δ cable , δ b ,δ h They are the average annual operation and maintenance rates for offshore wind turbines, hydrogen production equipment, submarine cables, electrochemical energy storage and hydrogen storage tanks;

[0057] S22: Setting model constraints: including the electrolyzer hydrogen production model as shown in formulas (7) and (8), the power balance equation as shown in formula (10), the wind turbine output constraint as shown in formula (9), the energy storage charge state constraint as shown in formula (11), and the energy storage power constraint as shown in formula (12).

[0058]

[0059] P H,t =P w,t +P b,t (10)

[0060]

[0061] Where, κ1 and κ2 are the maximum and minimum load adjustment ratios of the hydrogen production electrolyzer, alkaline electrolyzer: κ1 = 25%, κ2 = 120%, PEM electrolyzer: κ1 = 10%, κ2 = 110%; H t is the hydrogen produced at time t, unit: kg; LHV His the lower calorific value of hydrogen, unit: WM / kg; η H is the efficiency of hydrogen production equipment; P H,t , P w,t , P b,t They are the power consumed by the electrolyzer at time t, the power consumed by the fan, and the power generated by the electrochemical energy storage, in MW; is the value corresponding to time t in the typical weekly curve, unit: pu; SoC t is the state of charge of the electrochemical energy storage at time t; c ,λ d They are respectively the charging efficiency and discharging efficiency of energy storage; SoC min , SoC max are the upper and lower limits of the state of charge of the energy storage, respectively; Δt is the simulation time interval of the planning model, which is set to 1h; P b max is the maximum discharge power of energy storage, unit: MW;

[0062] S23: The supply and demand relationship of hydrogen energy does not need to meet the real-time balance requirement like electric energy. In order to reduce the computational complexity, the real-time hydrogen reserves are modeled at time intervals of days to calculate the hydrogen reserves at different times, as shown in formulas (13) and (14), where subscript d = 1, 2, ..., T / 24, where T is the total simulation time.

[0063]

[0064] 0≤H d ≤S h (14) In the formula, H d is the hydrogen reserve at time d, unit: kg; H out is the average daily consumption of hydrogen in the planned area,

[0065] Unit: kg;

[0066] S24: Based on the above constraints, the model is formed into a linear function and solved using the existing commercial solver to finally obtain the optimal hydrogen production equipment capacity for the current planned area. and optimal fan capacity

[0067] The present invention is described by some embodiments, and it is known to those skilled in the art that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines, characterized in that: The following steps are involved: S1: Construct a new energy typical cycle generation method considering characteristic parameter correction: S11: Obtain the annual wind speed data of the sea area to be planned. Using the wind speed data provided by the Copernicus Climate Change Service Center, obtain two mutually perpendicular crosswind speed data u and v at an altitude of 100m at a certain coordinate point, and then calculate the absolute wind speed at an altitude of 100m in the area to be planned. If the tower height of the wind turbine to be planned is h, in meters, then the wind speed s at the tower height is obtained using formula (1): wt , unit: m / s, Where z0 is the sea surface roughness coefficient, which depends on the actual sea surface conditions, including wave height and depth factors, and is obtained through the existing geographic database; S12: Convert the wind speed data into the expected output at the corresponding wind speed according to the wind speed-power curve. The curve is provided by the wind turbine manufacturer or obtained by fitting the actual output curve and wind speed data. Formula (2) is a fitting curve obtained according to a certain type of wind turbine. In the formula, P(s wt ) is the wind speed in s wt The power output of the wind turbine at that time, unit: MW; P rated is the rated output power of the fan; s in ,s out ,s rated are the cut-in wind speed, cut-out wind speed and rated working wind speed of the fan, in m / s; α, β, γ and δ are the constants obtained by fitting; S13: The power curve P of each season w1 ,P w2 ,P w3 ,P w4 Typical circle curve compressed into a circle length For each season, the k-means method is used to select a representative weekly scenario. The mean and variance of the power daily curve are used as clustering feature parameters. The power curve closest to the center point is selected as the typical power curve through the Euclidean distance, as shown in formula (3). The 7 power curves generated by the 7 clusters constitute the preliminary typical representative weekly power of a quarter; Where P i is the wind power daily power curve on the ith day; E ij P i and P j The Euclidean distance between them; var(·), mean(·) represent the calculation of variance and mean respectively; S14: After obtaining the uncorrected basic typical representative weekly power of each quarter, due to the differences in the maximum, minimum and total characteristic indicators between the basic typical weekly curve and the original seasonal curve, it is necessary to adjust the weekly curve and introduce variables and Represent the original and adjusted weekly curves respectively. The conversion function is used as shown in formula (4) to adjust the correction parameters a, b, k to ensure that the characteristic indexes of the adjusted weekly scenario: maximum, minimum and mean value match the characteristic indexes of the seasonal curve; S2: Construct a collaborative planning model for offshore hydrogen production systems based on: S21: The objective function is set to maximize the comprehensive annual revenue of the offshore hydrogen production system, and the decision variable is the rated power of the hydrogen production electrolyzer Total rated power of fan Electrochemical energy storage rated capacity S b , supporting hydrogen storage tank S h , as shown in formulas (5) and (6), Where: R H is the annual hydrogen sales revenue, unit: 10,000 yuan; W H is the annual green hydrogen production, unit: kg; P H , T H are the green hydrogen price and equivalent transportation cost, respectively, unit: kg / 10,000 yuan; C inv is the equivalent annual investment cost, unit: 10,000 yuan; CPR is the capital recovery rate; τ is the annual interest rate; T is the designed service life, unit: year; The total rated power of all offshore wind turbines integrated into the hydrogen production platform, unit: MW; is the rated power of the electrolyzer, unit: MW; S b is the rated capacity of electrochemical energy storage, unit: MWh; S h is the rated capacity of the hydrogen storage tank, unit: kg; S cable , L cable are the total capacity and total length of the cables connecting the hydrogen production platform and the supporting offshore wind turbines, in MW and km respectively; γ w is the unit capacity cost of offshore wind turbines, unit: MW / 10,000 yuan; γ H is the unit capacity cost of the electrolyzer, unit: MW / 10,000 yuan; γ cable is the construction cost per unit length of submarine cable, unit: 10,000 yuan / km; γ b is the unit capacity cost of electrochemical energy storage, unit: MWh / 10,000 yuan; γ h is the unit capacity cost of hydrogen storage tank, unit: MW / kg; C OM is the annual operation and maintenance cost, unit: ten thousand yuan; δ w , δ H , δ cable , δ b ,δ h They are the average annual operation and maintenance rates for offshore wind turbines, hydrogen production equipment, submarine cables, electrochemical energy storage and hydrogen storage tanks; S22: Setting model constraints: including the electrolyzer hydrogen production model as shown in formulas (7) and (8), the power balance equation as shown in formula (10), the wind turbine output constraint as shown in formula (9), the energy storage charge state constraint as shown in formula (11), and the energy storage power constraint as shown in formula (12). P H,t =P w,t +P b,t (10) Where, κ1 and κ2 are the maximum and minimum load adjustment ratios of the hydrogen production cell, respectively, and the alkaline electrolyzer: κ1=25%, κ2=120%, PEM electrolyzer: κ1=10%, κ2=110%; H t is the hydrogen produced at time t, unit: kg; LHV H is the lower calorific value of hydrogen, unit: WM / kg; η H is the efficiency of hydrogen production equipment; P H,t , P w,t , P b,t They are the power consumed by the electrolyzer at time t, the power consumed by the fan, and the power generated by the electrochemical energy storage, in MW; is the value corresponding to time t in the typical weekly curve, unit: pu; SoC t is the state of charge of the electrochemical energy storage at time t; c ,λ d They are respectively the charging efficiency and discharging efficiency of energy storage; SoC min , SoC max are the upper and lower limits of the state of charge of the energy storage, respectively; Δt is the simulation time interval of the planning model, which is set to 1h; is the maximum discharge power of energy storage, unit: MW; S23: Real-time hydrogen reserves are modeled at time intervals of days to calculate hydrogen reserves at different times, as shown in formulas (13) and (14), where subscript d = 1, 2, ..., T / 24, where T is the total simulation time. 0≤H d ≤S h (14) In the formula, H d is the hydrogen reserve at time d, unit: kg; H out is the average daily consumption of hydrogen in the area to be planned, unit: kg; S24: Based on the above constraints, the model is formed into a linear function and solved using the existing commercial solver to finally obtain the optimal hydrogen production equipment capacity for the current planned area. and optimal fan capacity 2. A capacity planning system for an offshore hydrogen production platform integrated with offshore wind turbines, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements a capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines as claimed in claim 1.

3. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an implementation program for information transmission, and when the program is executed by the processor, the steps of the capacity planning method for an offshore hydrogen production platform integrated with offshore wind turbines as claimed in claim 1 are implemented.

Images