A method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction

Abstract

This invention belongs to the field of optimized operation and multi-energy collaborative control technology of new energy power hydrogen production systems. It discloses a feedforward compensation method for hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction. The feedforward compensation method includes: based on the traditional 15-minute wind-solar-hydrogen-storage scheduling, if the accuracy of the current second-level power prediction meets the requirements, if so, further determining whether there is a sudden change in predicted power; if so, considering factors such as whether the current system can absorb the sudden power change, whether the total hydrogen production power after the execution of the hydrogen production power plan compensation value will cause the energy storage charging / discharging and grid connection power limits to exceed the upper and lower limits, and whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle, a feedforward compensation value for the 15-minute hydrogen production plan is given. This improves the overall scheduling accuracy and compensates for the lack of wind and solar power prediction values ​​within 15 minutes.

Description

Technical Field

[0001] This invention belongs to the field of optimized operation and multi-energy coordinated control technology of new energy power hydrogen production system. Specifically, it relates to a method for feedforward compensation of hydrogen production power in wind-solar-hydrogen storage system based on second-level wind and solar power prediction. Background Technology

[0002] Combining renewable energy generation with hydrogen energy is one of the important ways to achieve the goals of "carbon peaking" and "carbon neutrality". Due to the intermittency and uncertainty of renewable energy generation such as wind power and photovoltaic power generation, variable power hydrogen production is currently the main method of hydrogen production.

[0003] Actual measurement data shows that when wind speed changes exceed 3 m / s or irradiance changes exceed 200 W / m², 2 At the same time, existing variable-power hydrogen production methods can have a maximum instantaneous error of up to 25% within a 30-second time window; meanwhile, power fluctuations on the order of seconds caused by cloud movement (change rate > 10% / s) can lead to a power tracking deviation of 1.2-1.8 MW / min in existing dispatching systems, and this deviation is even more severe in some wind and solar hydrogen production projects. Existing variable-power hydrogen production methods suffer from prominent problems of mismatch and lag in control, while there are few solutions available in the field to address these issues.

[0004] Therefore, there is an urgent need to provide a feedforward compensation method for hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, which has high accuracy and rapid and timely regulation, in order to solve the above problems.

[0005] In view of the above, this application is hereby submitted. Summary of the Invention

[0006] The technical problem to be solved by this invention is to overcome the shortcomings of existing technologies such as mismatch and lag in regulation. The purpose is to provide a method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, which has high regulation accuracy and is fast and timely.

[0007] To solve the above-mentioned technical problems, the basic concept of the technical solution adopted by this invention is: a method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, comprising the following steps:

[0008] S1. Taking the current unit power prediction cycle as a node, determine whether the accuracy of the second-level power prediction value in the previous several unit power prediction cycles meets the preset standard.

[0009] S2. If the preset criteria are met, then a prediction power mutation judgment is performed.

[0010] S3. If a sharp rise or fall in the predicted power is detected within a prediction period and the accumulation of the mutation reaches a predetermined value, then it is determined whether the current grid connection, hydrogen production and energy storage system can absorb the mutation power within the prediction period.

[0011] S4. If it is detected that the current grid connection, hydrogen production and energy storage system cannot absorb the sudden power, then in combination with the power limits of energy storage, electrolyzer and grid connection, calculate the feedforward compensation value of hydrogen production power according to the dynamic response model of electrolyzer, and determine whether the total hydrogen production power calculated based on the compensation value will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits.

[0012] S5. If the change in total hydrogen production power after the compensation value is executed does not cause the energy storage charging and discharging or grid connection power limit to exceed the upper and lower limits, then determine whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle.

[0013] S6. If the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle, the compensated total hydrogen production power is set to the adjustable upper and lower limits. It is then determined whether there is a power increase / decrease lockout in the current total hydrogen production power control. If there is no lockout, the compensated total hydrogen production power is allocated and distributed. Using the current unit power prediction cycle as a node, it is determined whether the accuracy of the second-level power prediction value in the previous several unit power prediction cycles meets the preset standard. If a power increase / decrease lockout is detected in the current total hydrogen production power, it is then determined whether the accuracy of the second-level power prediction value in the previous several unit power prediction cycles meets the preset standard, using the current unit power prediction cycle as a node.

[0014] According to one embodiment of the present invention, the second-level power prediction data update interval is 30s, and the interval between two adjacent power prediction values ​​is 5s.

[0015] According to one embodiment of the present invention, step S3 further includes: if the predicted power within a prediction period is detected to have no sharp rise or fall and the accumulation of mutations reaches a predetermined value, then the prediction power mutation judgment is performed again.

[0016] According to one embodiment of the present invention, the steep rise threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≥ +15% / 5s; where ΔP / Δt = (P i+1 -P i ) / 5;

[0017] The steep drop threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≤ -15% / 5s;

[0018] Cumulative mutation amount definition: |ΔP 15s |≥0.3P rated ;

[0019] Among them, |ΔP 15s | represents the absolute value of the power change within 15 seconds, 0.3P rated This indicates 30% of the rated power.

[0020] According to one embodiment of the present invention, step S4 further includes: if it is detected that the current power surge can be absorbed by the grid connection, hydrogen production and energy storage system, then the predicted power surge judgment is performed again.

[0021] According to one embodiment of the present invention, step S5 further includes: if it is detected that the change in the total hydrogen production power after the compensation value is executed will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits, then the upper and lower limit margins of the preset standard are retained to calculate the total hydrogen production power after compensation, and it is determined whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle.

[0022] According to one embodiment of the present invention, step S6 further includes: if it is detected that the calculated total hydrogen production power does not exceed the adjustable upper and lower limits of the total hydrogen production power within the cycle, then it is detected whether the current total hydrogen production power is locked.

[0023] According to one embodiment of the present invention, if it is detected that the current total hydrogen production power is not locked, the compensated total hydrogen production power allocation is issued, and it is determined whether the accuracy of the power prediction value meets the standard within the previous several unit power prediction cycles.

[0024] According to one embodiment of the present invention, if a rise / fall lockout is detected in the current total hydrogen production power, then the accuracy of the second-level power prediction value in the previous several unit power prediction cycles is determined using the current unit power prediction cycle as a node, and whether the accuracy of the second-level power prediction value meets a preset standard.

[0025] After adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art: by applying the hydrogen production power feedforward compensation method in the wind-solar-hydrogen storage system based on second-level wind and solar power prediction provided in this application, the predicted power value and the actual value in the previous several unit detection cycles are compared, and the predicted power value, the actual value and the system capacity are compared, providing feedforward compensation correction for subsequent power prediction, thereby improving the accuracy and timeliness of regulation.

[0026] The specific embodiments of the present invention will now be described in further detail with reference to the accompanying drawings. Attached Figure Description

[0027] The accompanying drawings, as part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments and descriptions of the invention are used to explain the invention, but do not constitute an undue limitation of the invention. Obviously, the drawings described below are merely some embodiments, and those skilled in the art can obtain other drawings based on these drawings without creative effort. In the drawings:

[0028] Figure 1 This is a flowchart illustrating the steps of a hydrogen production power feedforward compensation method in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in an embodiment of the present invention.

[0029] It should be noted that these accompanying drawings and textual descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art by referring to specific embodiments. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below with reference to the accompanying drawings. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0031] In the description of this invention, it should be noted that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0032] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0033] like Figure 1 As shown, the present invention discloses a method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction. This method is applicable to coupled systems of wind and solar power generation, water electrolysis for hydrogen production, energy storage, and the power grid. The hydrogen production power feedforward compensation method includes the following steps:

[0034] S1. Taking the current unit power prediction cycle as a node, determine whether the accuracy of the second-level power prediction value in the previous several unit power prediction cycles meets the preset standard.

[0035] S2. If the preset criteria are met, then a prediction power mutation judgment is performed.

[0036] S3. If a sharp rise or fall in the predicted power is detected within a prediction period and the accumulation of the mutation reaches a predetermined value, then it is determined whether the current grid connection, hydrogen production and energy storage system can absorb the mutation power within the prediction period.

[0037] S4. If it is detected that the current grid connection, hydrogen production and energy storage system cannot absorb the sudden power, then in combination with the power limits of energy storage, electrolyzer and grid connection, calculate the feedforward compensation value of hydrogen production power according to the dynamic response model of electrolyzer, and determine whether the total hydrogen production power calculated based on the compensation value will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits.

[0038] S5. If the change in total hydrogen production power after the compensation value is executed does not cause the energy storage charging and discharging or grid connection power limit to exceed the upper and lower limits, then determine whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle.

[0039] S6. If the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle, the compensated total hydrogen production power is set to the adjustable upper and lower limits, and it is determined whether there is an increase / decrease lockout in the current total hydrogen production power increase / decrease control. If there is no increase / decrease lockout in the current total hydrogen production power increase / decrease control, the compensated total hydrogen production power is allocated and distributed, and (S1 is executed repeatedly) the accuracy of the second-level power prediction value in the previous several unit power prediction cycles is determined using the current unit power prediction cycle as the node. If there is an increase / decrease lockout in the current total hydrogen production power, (S1 is executed repeatedly) the accuracy of the second-level power prediction value in the previous several unit power prediction cycles is determined using the current unit power prediction cycle as the node.

[0040] In this invention, in step S1, the accuracy of the second-level power prediction values ​​within several previous unit power prediction cycles is judged to meet a preset standard. If the standard is met, the current prediction data is considered to have a high accuracy and can be used as a feedforward correction for the total hydrogen production power. Only after meeting the standard does the subsequent steps such as abrupt change judgment proceed, ensuring the accuracy of the subsequent hydrogen production power feedforward compensation calculation and avoiding control deviations caused by inaccurate power predictions. This effectively solves the problem of mismatch in the control of existing variable power hydrogen production methods. In subsequent steps, the hydrogen production power feedforward compensation value is calculated by combining the power limits of energy storage, electrolyzer, grid connection, and the dynamic response model of the electrolyzer. This fully considers the actual operating parameters and limitations of each part of the system, making the control of hydrogen production power more precise. It can better match the intermittency and uncertainty of wind and solar power generation, improve the synergy between the hydrogen production system and new energy power generation, and thus improve the control accuracy of the entire system.

[0041] In step S2, if the accuracy of the power prediction value meets the standard, a sudden change in predicted power is immediately judged. When a sharp rise or fall in predicted power is detected and the accumulation of the change reaches a predetermined value (step S3), subsequent countermeasures are initiated. The entire process is closely linked, greatly shortening the time from detecting power changes to making a control response. Compared with existing methods, it can react to fluctuations in wind and solar power more promptly, effectively solving the problem of control lag in existing variable power hydrogen production methods, and filling the scheduling gap between the 15-minute scheduling cycle and the second-level control cycle in the current hydrogen production cluster control.

[0042] In step S3, it is determined whether the current grid connection, hydrogen production, and energy storage systems can absorb sudden power surges. If the system cannot absorb the surges (step S4), power allocation is optimized by calculating the hydrogen production power feedforward compensation value. This process fully considers the power limits of energy storage, electrolyzers, and grid connection, enabling the system to rationally allocate power when faced with sudden power surges. This ensures that all parts of the system operate safely and stably, avoiding system failures or inefficiencies caused by unreasonable power allocation. It improves the system's ability to absorb sudden power surges and enhances the stability and reliability of the entire wind-solar-hydrogen-storage system.

[0043] In one specific implementation of this embodiment, several unit power prediction cycles refer to one or more unit power prediction cycles adjacent to the current unit power prediction cycle.

[0044] In one specific implementation of this embodiment, the second-level power prediction data update interval is 30s, that is: the hydrogen production power feedforward compensation method updates the prediction data every 30s and outputs the power prediction value within 15 minutes at 5s intervals (15 minutes corresponds to 180 power prediction points).

[0045] The unit power prediction period includes 6 adjacent power prediction points (intervald in 5s).

[0046] In one specific implementation of this embodiment, whether the accuracy of the second-level power prediction value meets the preset standard refers to the fact that the accuracy of the 6 power prediction points included in the unit power prediction cycle is 95% or higher (with an allowable error value within 5%).

[0047] The accuracy refers to Y∈(1±0.05)X; where Y represents the predicted power value and X represents the actual power value.

[0048] In one specific implementation of this embodiment, if the accuracy of any one or more of the six power prediction points included in the unit power prediction cycle does not meet the preset standard, then the judgment is repeated for several previous unit power prediction cycles to determine whether the accuracy of the second-level power prediction value meets the preset standard.

[0049] Please see the appendix Figure 1 In one specific implementation of this embodiment, step S3 further includes: if the predicted power within a prediction period is detected to have no sharp rise or fall and the accumulation of mutations reaches a predetermined value, then the prediction power mutation judgment is performed again.

[0050] This invention uses second-level prediction data to predict unexpected wind and solar power surges / dips in advance. Combined with the load rate constraints of hydrogen production equipment, it dynamically generates feedforward correction commands, effectively avoiding the risks of frequent charging and discharging of energy storage and grid over-limits caused by power surges. This significantly improves the hydrogen production system's ability to actively adapt to wind and solar power fluctuations.

[0051] In one specific implementation of this embodiment, the steep rise threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≥ +15% / 5s; where ΔP / Δt = (P i+1 -P i ) / 5, i equals 1 or 2, correspondingly, P i This indicates the first (power prediction point) sampling point or the second (power prediction point) sampling point;

[0052] The steep drop threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≤ -15% / 5s;

[0053] Cumulative mutation amount definition: |ΔP 15s |≥0.3P rated ;

[0054] Among them, |ΔP 15s | represents the absolute value of the power change within 15 seconds, P rated This indicates the rated power, 0.3P. ratedThis indicates 30% of the rated power.

[0055] Please see the appendix Figure 1 In one specific implementation of this embodiment, step S4 further includes: if the current power surge can be absorbed by the grid connection, hydrogen production and energy storage system, then the predicted power surge judgment is performed again.

[0056] In one specific implementation of this embodiment, step S5 further includes: if it is detected that the change in the total hydrogen production power after the compensation value is executed will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits, then the upper and lower limit margins of the preset standard are retained to calculate the total hydrogen production power after compensation, and it is determined whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle.

[0057] In one specific implementation of this embodiment, the upper and lower margins of the preset standard refer to a numerical standard that allows values ​​to exceed or fall below the upper or lower limits by 20%.

[0058] In one specific implementation of this embodiment, step S6 further includes: if it is detected that the calculated total hydrogen production power does not exceed the adjustable upper and lower limits of the total hydrogen production power within the cycle, then it is detected whether the current total hydrogen production power is locked.

[0059] The hydrogen production total power increase / decrease interlock refers to a control measure that limits or prohibits the increase or decrease of the total power in the hydrogen production system, while ensuring the safe and stable operation of the hydrogen production system.

[0060] Please see the appendix Figure 1 In one specific implementation of this embodiment, if it is detected that the current total hydrogen production power is not locked, the compensated total hydrogen production power allocation will be issued, and it will be determined whether the accuracy of the power prediction value in the previous several unit power prediction cycles has met the standard.

[0061] Please see the appendix Figure 1 In one specific implementation of this embodiment, if the current total hydrogen production power rise / fall lockout is detected, then the current unit power prediction cycle is used as a node to determine whether the accuracy of the power prediction value in the previous several unit power prediction cycles meets the preset standard.

[0062] Existing variable power hydrogen production methods typically use power prediction data at the ten-minute or hourly level. Due to the time span, the control matching rate is low and the control response time is long.

[0063] The hydrogen production power feedforward compensation method provided in this application employs second-level power prediction, improving the dynamic tracking capability of hydrogen production load by more than three times. When wind and solar power experience second-level abrupt changes, the system can generate control commands 30-60 seconds in advance, reducing the wind and solar curtailment rate from the industry average of 12% to below 5%, significantly improving the local consumption level of renewable energy. Based on second-level prediction data, the feedforward compensation mechanism can reduce the energy storage system's need to smooth power discrepancies by more than 40%, directly reducing energy storage capacity investment by approximately 25%. Simultaneously, through a predictive electrolyzer group control strategy, the frequency of equipment start-up and shutdown is reduced, the lifespan of core electrolyzer components is extended, and annual maintenance costs are saved. The risk of grid ramp rate exceeding limits due to power fluctuations is reduced by 90%, ensuring 100% compliance with the grid-connected power deviation control standards required by the power grid. In scenarios of second-level power surges caused by extreme weather, the system can maintain the continuity of hydrogen production load, avoiding hydrogen supply interruptions caused by emergency load shedding.

[0064] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-described technical content to create equivalent embodiments without departing from the scope of the present invention. The implementation schemes in the above embodiments can also be further combined or replaced. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, characterized in that, The hydrogen production power feedforward compensation method includes: S1. Using the current unit power prediction cycle as a node, determine whether the accuracy of the second-level power prediction value in the previous several unit prediction cycles meets the preset standard. S2. If the preset criteria are met, then a prediction power mutation judgment is performed. S3. If a sharp rise or fall in the predicted power is detected within a prediction period and the accumulation of the mutation reaches a predetermined value, then it is determined whether the current grid connection, hydrogen production and energy storage system can absorb the mutation power within the prediction period. S4. If it is detected that the current grid connection, hydrogen production and energy storage system cannot absorb the sudden power, then in combination with the power limits of energy storage, electrolyzer and grid connection, calculate the feedforward compensation value of hydrogen production power according to the dynamic response model of electrolyzer, and determine whether the total hydrogen production power calculated based on the compensation value will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits. S5. If the change in total hydrogen production power after the compensation value is executed does not cause the energy storage charging and discharging or grid connection power limit to exceed the upper and lower limits, then determine whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle. S6. If the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle, the compensated total hydrogen production power is set to the adjustable upper and lower limits, and it is determined whether there is a lockout in the current hydrogen production power increase / decrease control. If there is no lockout, the compensated total hydrogen production power is allocated and distributed, and S1 is executed repeatedly. If there is a lockout, S1 is executed repeatedly.

2. The method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... The power prediction data is updated every 30 seconds, and there is a 5-second interval between two adjacent power prediction values.

3. The method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... Step S3 further includes: if the predicted power within a prediction period is detected to have no sharp rise or fall and the accumulation of mutations reaches a predetermined value, then the prediction power mutation judgment is performed again.

4. The method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... The steep rise threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≥ +15% / 5s; where ΔP / Δt = (P i+1 -P i ) / 5; The steep drop threshold is defined as follows: three consecutive 5-second sampling points satisfy ΔP / Δt ≤ -15% / 5s; Cumulative mutation amount definition: |ΔP 15s |≥0.3P rated ; Among them, |ΔP 15s | represents the absolute value of the power change within 15 seconds, 0.3P rated This indicates 30% of the rated power.

5. The method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... Step S4 further includes: if the current power surge can be absorbed by the current grid connection, hydrogen production and energy storage system, then the predicted power surge judgment is performed again.

6. The method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... Step S5 further includes: if it is detected that the change in the total hydrogen production power after the compensation value is executed will cause the energy storage charging and discharging and grid connection power limits to exceed the upper and lower limits, then the upper and lower limit margins of the preset standard are retained to calculate the total hydrogen production power after compensation, and it is determined whether the calculated total hydrogen production power exceeds the adjustable upper and lower limits of the total hydrogen production power within the cycle.

7. The method for hydrogen production power feedforward compensation in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 1, is characterized in that... Step S6 further includes: if it is detected that the calculated total hydrogen production power does not exceed the adjustable upper and lower limits of the total hydrogen production power within the cycle, then it is detected whether the current total hydrogen production power is locked.

8. A method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 7, is characterized in that... If it is detected that there is no increase / decrease lockout for the current total hydrogen production power, the compensated total hydrogen production power allocation will be issued, and it will be determined whether the accuracy of the power prediction value has met the standard in the previous several unit power prediction cycles.

9. A method for feedforward compensation of hydrogen production power in a wind-solar-hydrogen storage system based on second-level wind and solar power prediction, as described in claim 7, is characterized in that... If a rise / fall lockout is detected in the current total hydrogen production power, then the current unit power prediction cycle is used as a node to determine whether the accuracy of the second-level power prediction value in the previous several unit power prediction cycles meets the preset standard.

Images