Direct-current off-grid renewable energy hydrogen production energy management method and system

Abstract

The invention discloses a direct-current off-grid renewable energy hydrogen production energy management method and system, and relates to the technical field of renewable energy management, and the method comprises the steps: constructing a hydrogen production energy management module of a direct-current voltage network; carrying out load characteristic analysis, obtaining the energy demand of the hydrogen production facility, and identifying a high demand time period and a low demand time period; collecting wind power and sunlight data, and evaluating potential output capability of wind power generation and photovoltaic power generation; and determining a wind turbine, a photovoltaic panel and energy storage equipment based on an analysis result of the energy demand and the output capability, determining a hydrogen production operation mode, and performing energy management. According to the direct-current off-grid type renewable energy hydrogen production energy management method, the energy utilization efficiency is improved, energy waste in off-peak periods is reduced, adaptability and stability are enhanced, and different situations of energy peak and valley are dealt with. Energy storage and output strategies are optimized, operation cost is reduced, economic benefits are improved, and energy requirements are met.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of renewable energy management, in particular to a direct current off-grid renewable energy hydrogen production energy management method and system. BACKGROUND

[0002] In the scenario of high penetration of new energy access or with new energy as the main power source, it is necessary to strengthen the multi-element direct utilization of renewable energy, utilize new energy direct power supply, wind-solar-hydrogen storage coupling, flexible load and other technologies, promote the integration of new energy development, transmission and terminal consumption through development and utilization mode innovation, and build a batch of new energy supply and utilization of high proportion of wind-solar-hydrogen integrated projects, which has become a new way of large-scale consumption of new energy. Under the condition of new energy and hydrogen production load fluctuation, there are problems of insufficient power supply reliability, voltage instability risk and power failure and network collapse when the tie-in channel is disconnected, especially under the restriction of new energy high proportion of self-generation and self-use project, it is necessary to improve the stability and reliability of wind-solar-hydrogen integrated system, and reduce the disturbance of large power grid.

[0003] According to the different sources of electric energy, the renewable energy hydrogen production technology can be divided into grid-connected hydrogen production and off-grid hydrogen production. Grid-connected hydrogen production is to connect the electric energy generated by wind-solar units to the power grid or partially connect to the power grid, and then take electric energy from the power grid. It is mainly applied to large-scale abandoned light and wind consumption and energy storage. Off-grid hydrogen production refers to directly providing electric energy generated by wind-solar units to the hydrogen production equipment for electrolysis of water to produce hydrogen, which is mainly applied to distributed hydrogen production. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is that the existing grid-connected and off-grid hydrogen production methods have the problems of low energy utilization efficiency and poor grid stability, and how to realize the efficient direct utilization and optimization of storage of new energy.

[0006] To solve the above technical problems, the present application provides the following technical scheme: a direct current off-grid renewable energy hydrogen production energy management method, comprising: A hydrogen production energy management module of direct current voltage networking is constructed. Load characteristics are analyzed to obtain the energy demand of hydrogen production facilities and identify high demand and low demand periods. Wind and sunlight data are collected to evaluate the potential output capacity of wind power generation and photovoltaic power generation. Based on the analysis results of energy demand and output capacity, the wind turbine, photovoltaic panel and energy storage device are determined, the hydrogen production operation mode is determined, and energy management is performed.

[0007] As a preferred scheme of the direct current off-grid renewable energy hydrogen production energy management method of the present application, wherein: the hydrogen production energy management module of direct current voltage networking comprises an upper layer, a middle layer and a lower layer. The upper layer is a scheduling management system for operation management / scheduling / optimization / prediction, and issues operation instructions and operation constraints to the lower layer micro source / load and its local controller; the middle layer is an energy management module that determines the operation mode of hydrogen production according to the upper layer instructions and the lower layer state, and manages and schedules the lower layer equipment; and the lower layer is a micro source / load and its local controller for renewable energy / energy storage / load data measurement / operation control / state feedback.

[0008] As a preferred scheme of the direct off-grid type renewable energy hydrogen production energy management method, wherein: the load characteristic analysis includes collecting energy consumption data of the hydrogen production facility recorded by hours in the past preset time period; collecting environmental data in the same period, including temperature, humidity, wind speed; recording equipment state data, including maintenance history and efficiency change; The energy demand of the hydrogen production facility is obtained by constructing an energy consumption prediction model. Collect historical energy consumption data, collect environmental data, record operation mode and maintenance data of the hydrogen production facility, explain energy consumption fluctuation, and perform data preprocessing on the collected data; perform Fourier analysis on the historical energy consumption data; select and fit the parameters of the ARIMA model through the Akaike information criterion AIC; use linear regression method to determine the influence coefficient of environmental factors on energy consumption; calculate the energy consumption prediction value according to the determined parameters and real-time environmental data; compare the prediction result with the actual energy consumption data to verify the model accuracy, adjust the model parameters according to the actual situation, optimize the prediction performance, and re-predict according to the adjusted model parameters; calculate the average value and standard deviation using historical prediction results, and set high demand threshold and low demand threshold.

[0009] As a preferred scheme of the direct off-grid type renewable energy hydrogen production energy management method, wherein: the evaluation of the potential output capacity of wind power generation and photovoltaic power generation includes constructing an output capacity evaluation model; Install an anemometer and a pyranometer at the location of the hydrogen production facility to collect wind speed and solar radiation intensity, and perform data preprocessing on the collected data; Calculate the integral of the square of the wind speed in a preset time window to quantify the continuous contribution of the wind speed to energy output, and apply logarithmic transformation to process the solar radiation data to improve the sensitivity and response of the model to changes in light intensity; Select a prediction model based on data characteristics, train the model, and set initial parameters of the neural network, including the number of layers, the number of neurons in each layer, and the type of activation function; Use historical data sets to train the model, and optimize the model parameters through the back propagation algorithm to minimize the prediction error; Use cross-validation techniques to evaluate model performance; The prediction accuracy of the model is evaluated by indexes such as mean square error and coefficient of determination; The real-time collected wind speed and sunshine intensity data are input into the model to obtain instant energy output prediction.

[0010] As a preferred scheme of the direct current off-grid type renewable energy hydrogen production energy management method, wherein: the determination of the wind turbine, photovoltaic panel and energy storage device includes identifying the time period combination, which includes high demand and sufficient energy supply, high demand and energy shortage, low demand and sufficient energy supply and low demand and energy shortage; For each time period combination, configuration analysis is performed, a configuration scheme is formulated, device requirements are determined, and the matching degree of the existing device configuration and the predicted demand is evaluated; For the wind turbine and photovoltaic panel, for the high demand and energy shortage period, the number of wind turbines and photovoltaic panels required to be increased is calculated to make up for the energy gap; for the low demand and sufficient energy supply period, the surplus energy is managed by adjusting the operation strategy instead of increasing the device; in the high demand and sufficient energy supply period and the low demand and energy shortage period, the device is ensured to operate effectively; The energy storage device is determined, and the required energy storage capacity is determined according to the changes of energy supply and demand in each time period. When in the high demand period or the energy shortage risk period, the energy storage device is configured to ensure energy supply; When in the low demand period or the energy supply sufficient period, the energy storage strategy is executed to maximize energy capture.

[0011] As a preferred scheme of the direct current off-grid type renewable energy hydrogen production energy management method, wherein: the determination of the operation mode of hydrogen production includes analyzing the matching degree of device configuration and predicted demand in each time period combination, determining the operation mode based on the matching degree, and the operation mode includes maximizing output mode, energy saving mode, balance mode and emergency mode.

[0012] As a preferred scheme of the direct current off-grid type renewable energy hydrogen production energy management method, wherein: the energy management includes increasing the discharge rate of the energy storage device when the operation mode is the maximum output mode, monitoring and adjusting the energy output in real time to not exceed the maximum carrying capacity of the facility, and automatically transferring the energy exceeding the instant demand to the energy storage system for storage; When the operation mode is the energy saving mode, the charge and discharge behavior of the energy storage device is dynamically adjusted to smooth the instantaneous energy fluctuation, and the energy flow is automatically balanced to hydrogen production activities or energy storage to maintain the stability of system operation; When the operation mode is the balance mode, the operation frequency of the hydrogen production facility is reduced to reduce energy consumption, the energy storage preparation is increased, and the energy distribution is optimized by reducing or temporarily shutting down the power use of non-critical devices to ensure the energy supply of critical operations; When the operation mode is the emergency mode, a preset emergency energy management strategy is started, a backup energy system is immediately enabled, and an energy storage device is preferentially dispatched to support the operation of a critical facility.

[0013] Another object of the present application is to provide a DC off-grid renewable energy hydrogen production energy management system, which can effectively dispatch and optimize energy resources in a DC off-grid environment by constructing a DC off-grid renewable energy hydrogen production energy management system, enhance adaptability to environmental changes, improve hydrogen production efficiency, reduce energy waste, and achieve the goal of improving overall energy management efficiency and system reliability.

[0014] To solve the above technical problems, the present application provides the following technical solution: a DC off-grid renewable energy hydrogen production energy management system, comprising: an energy management module, a demand analysis module, a potential assessment module, and an energy management module; the energy management module is used to construct a hydrogen production energy management module of DC voltage networking; the demand analysis module is used to perform load characteristic analysis, obtain energy demand of hydrogen production facilities, and identify high demand and low demand periods; the potential assessment module is used to collect wind power and solar radiation data, and assess potential output capacity of wind power generation and photovoltaic power generation; the energy management module is used to determine wind turbines, photovoltaic panels and energy storage devices based on the analysis results of energy demand and output capacity, determine the hydrogen production operation mode, and perform energy management.

[0015] A computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the DC off-grid renewable energy hydrogen production energy management method as described above when executing the computer program.

[0016] A computer readable storage medium stores a computer program, and the computer program implements the steps of the DC off-grid renewable energy hydrogen production energy management method as described above when executed by a processor.

[0017] The present application has the following advantages: the DC off-grid renewable energy hydrogen production energy management method provided by the present application optimizes energy distribution through load characteristic analysis, improves energy utilization efficiency, and reduces energy waste during non-peak periods. The potential output capacity of wind power generation and photovoltaic power generation is predicted to optimize energy production and storage, and adapt to the variability of wind and sunlight conditions.

[0018] By precisely matching the supply and demand configuration of appropriate energy equipment, adaptability and stability are enhanced to cope with different situations of energy peaks and troughs. The energy storage and output strategy is optimized to reduce operating costs, improve economic benefits, and meet energy demand. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0020] Figure 1 A flow chart of a direct current off-grid type renewable energy hydrogen production energy management method is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort should be within the scope of protection of the present application.

[0022] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from the description, and those skilled in the art can make similar generalizations without departing from the concept of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0023] Embodiment 1

[0024] Reference Figure 1 For an embodiment of the present application, a direct current off-grid type renewable energy hydrogen production energy management method is provided, comprising: A hydrogen production energy management module of direct current voltage networking is constructed; load characteristic analysis is performed to obtain the energy demand of hydrogen production facilities, identify high demand and low demand periods; wind and sunlight data are collected to evaluate the potential output capacity of wind power generation and photovoltaic power generation; based on the analysis results of energy demand and output capacity, wind turbines, photovoltaic panels and energy storage devices are determined, the hydrogen production operation mode is determined, and energy management is performed.

[0025] The hydrogen production energy management module of direct current voltage networking includes upper, middle and lower layers; the upper layer is a dispatching management system for operation management / dispatching / optimization / prediction, and issues operation instructions and operation constraints to the lower layer micro source / load and its local controller; the middle layer is an energy management module that determines the operation mode of hydrogen production according to the upper layer instructions and the lower layer state, and manages and dispatches the lower layer devices; the lower layer is a micro source / load and its local controller for data measurement / operation control / state feedback of renewable energy / energy storage / load.

[0026] The upper layer is responsible for load characteristic analysis and wind and sunlight data collection and evaluation. This layer mainly processes large amounts of data for analysis and prediction, including but not limited to energy demand analysis, weather conditions, and energy production potential. The upper layer scheduling management system processes this information and generates energy supply forecasts and demand models based on this data, forming operational strategies and instructions.

[0027] The middle layer receives analysis results and strategy instructions from the upper layer and determines the optimal configuration and layout of wind turbines, photovoltaic panels, and energy storage devices based on this information. Ensure that all device configurations meet the optimal mode of energy output and demand forecasts. The middle layer makes decisions on the configuration and operation strategy of energy equipment by analyzing the data received from the upper layer to achieve the best energy utilization efficiency and cost-effectiveness.

[0028] The lower layer is responsible for actually implementing the strategies formulated by the middle and upper layers. This includes actually operating wind turbines, photovoltaic panels, and managing energy storage devices.

[0029] Load characteristic analysis includes collecting hourly energy consumption data of the hydrogen production facility for a predetermined period in the past; collecting environmental data for the same period, including temperature, humidity, and wind speed; recording equipment status data, including maintenance history and efficiency changes.

[0030] Obtaining the energy demand of the hydrogen production facility includes constructing an energy consumption prediction model, represented as: , where, represents the predicted energy consumption at time , and represent the coefficients of the Fourier series, quantifying the amplitude of periodic fluctuations in energy consumption data at different frequencies, obtained by Fourier transform of historical energy consumption data, represents the period, represents the number of periodic terms, determined according to the seasonal characteristics of the data, and the present invention determines the seasonal changes throughout the year, represents the period length, represents the autoregressive integrated moving average model, which predicts the trend and non-periodic fluctuations of energy consumption data, is the historical energy consumption data, is the order of the autoregressive term, is the difference order, is the order of the moving average term, represents the regression coefficient of the environmental variable, represents the data vector of the environmental variable, including temperature, humidity, and real-time data obtained from environmental monitoring equipment.

[0031] Collect historical energy consumption data , collect environmental data , record the operating mode and maintenance data of hydrogen production facilities, explain energy consumption fluctuations, and perform data preprocessing on the collected data; use historical energy consumption data to perform Fourier analysis to determine and ; Select and fit the parameters of the ARIMA model using the Akaike Information Criterion AIC ; Use linear regression method to determine the influence coefficient of environmental factors on energy consumption ; Based on determined parameters and real-time environmental data , calculation time Energy consumption forecast ; Compare the predicted results with the actual energy consumption data to verify the accuracy of the model, adjust the model parameters according to the actual situation, optimize the prediction performance, and re-predict based on the adjusted model parameters ;use Calculate the average of historical forecast results and standard deviation , set the high demand threshold to , the low demand threshold is set to ,in, Determined by historical data analysis; if High demand threshold, judged as high demand period, if Low demand threshold, judged as low demand period, otherwise, regarded as regular demand period.

[0032] The rationale behind combining these three components lies in their ability to account for different aspects of energy consumption. The Fourier series addresses inherent cyclical variations, the ARIMA model addresses random fluctuations and trends, and the exogenous variables account for variations caused by environmental factors. Together, they provide energy consumption forecasts.

[0033] Traditional energy consumption analysis methods typically involve simple historical averages or use basic linear trend forecasting. These methods suffer from the following drawbacks: They fail to effectively handle seasonal and diurnal variations in data; and they neglect random fluctuations and external influences: Simple historical averages or linear models cannot adapt to the randomness and external environmental variations in energy consumption forecasting.

[0034] Evaluating the potential output capacity of wind power and photovoltaic power generation includes constructing an output capacity evaluation model, which is expressed as: , in, Indicates time The total predicted energy output, Indicates time wind speed, representing the solar intensity at time representing the model parameters, representing the integral of the square of the wind speed over a period representing the persistent effect of wind, representing the logarithmic transformation of the solar intensity, used to smooth the solar data and enhance the non-linear representation capacity of the model, representing the environmental impact function, is a coefficient obtained through experimental data, representing the exponential function, representing the normalized value, converting the linear regression output to a number between 0 and 1.

[0035] In the actual energy model, the cumulative effect of wind speed and the immediate effect of solar radiation are combined, allowing the model to capture both the long-term cumulative effect of wind energy and the short-term change effect of solar energy.

[0036] By processing wind speed and solar intensity separately, it can be more flexible to adapt to different environmental conditions and changes, increasing the accuracy and applicability of the prediction. For example, on a cloudy and windy day, the model can accurately calculate the high energy output due to the persistent existence of wind, while handling the fluctuation of photovoltaic output caused by the change of cloud layer.

[0037] Using wind speed as the integral variable and solar intensity as the immediate variable, the model can effectively predict energy output at different time scales. It increases the adaptability to complex environmental changes.

[0038] Install anemometers and pyranometers at the location of the hydrogen production facility to collect wind speed and solar intensity, and perform data preprocessing on the collected data; data preprocessing includes data cleaning: outlier processing, checking data through automated scripts, identifying and removing outliers such as data during equipment failure.

[0039] Missing value processing: for missing data points, time series interpolation methods can be used to fill in, ensuring the integrity of the data.

[0040] Data normalization: standardization processing, normalize or standardize wind speed and solar intensity data, convert data to a unified scale (e.g. between 0 and 1) to eliminate the impact of different measurement units.

[0041] ​The integral of the square of the wind speed in a preset time window is calculated to quantify the continuous contribution of the wind speed to the energy output, the sunlight data is processed by a logarithmic transformation to improve the sensitivity and response of the model to changes in light intensity, and a prediction model is selected based on the characteristics of the data. The present application uses a multi-layer perception (MLP) to handle nonlinear relationships and high-dimensional data, trains the model, sets the initial parameters of the neural network, including the number of layers, the number of neurons in each layer, and the type of activation function, and uses historical data sets to train the model, optimize the model parameters through a backpropagation algorithm, and minimize the prediction error. The model performance is evaluated using cross-validation techniques, and the prediction accuracy of the model is evaluated using indicators such as mean squared error (MSE) and coefficient of determination (R²). Real-time wind speed and sunlight intensity data are input into the model to obtain an instant energy output prediction. When ≥ the first output capacity threshold, it is determined that it is an energy supply sufficient period, and when < the second output capacity threshold, it is determined that it is an energy shortage risk period.

[0042] Determining the wind turbine, photovoltaic panel and energy storage device includes identifying the period combination, including high demand and energy supply sufficient, high demand and energy shortage, low demand and energy supply sufficient and low demand and energy shortage; performing configuration analysis on each period combination, developing a configuration scheme, determining device requirements, and evaluating the matching degree of the existing device configuration and the predicted demand; determining the wind turbine and photovoltaic panel, for the high demand and energy shortage period, calculating the number of wind turbines and photovoltaic panels needed to be increased to make up for the energy gap; for the low demand and energy supply sufficient period, managing excess energy by adjusting the operation strategy rather than increasing the device; ensuring the effective operation of the device in the high demand and energy supply sufficient period and the low demand and energy shortage period; determining the energy storage device, determining the required energy storage capacity according to the changes in energy supply and demand in each period, configuring the energy storage device to ensure energy supply when in the high demand period or the energy shortage risk period; when in the low demand period or the energy supply sufficient period, performing an energy storage strategy to maximize energy capture. If both conditions are met, configure the energy storage device to ensure energy supply and perform the energy storage strategy to maximize energy capture.

[0043] Configuring the energy storage device to ensure energy supply includes extracting energy from the device and ensuring that these devices are fully charged before this period. The output of the energy storage device is dynamically adjusted according to the real-time energy demand and supply situation. Machine learning algorithms are used to optimize the charge and discharge cycle of the energy storage device, reduce energy loss and improve response speed, automatically start the backup power system when energy shortage is about to occur, and ensure that all control systems and sensors operate normally in extreme weather or other adverse conditions.

[0044] The energy storage strategy maximizes energy capture, including storing excess energy in energy storage devices during high sunlight or wind speed, using high-frequency pulse charging or progressive charging techniques to improve energy conversion efficiency and reduce heat loss, adjusting the charging strategy of the energy storage device according to the predicted data of energy output, and starting slow charging after the peak of the sun to prolong the service life of the battery. According to the predicted weather changes, the energy collection and storage strategy is automatically adjusted.

[0045] The determination of the operation mode of hydrogen production includes analyzing the matching degree of device configuration and predicted demand in each time period combination, analyzing whether the number and capacity of wind turbines, photovoltaic panels and energy storage devices meet the current and predicted energy demand, determining the operation mode based on the matching degree, and the operation mode includes maximizing output mode, energy saving mode, balance mode and emergency mode.

[0046] When the wind turbines, photovoltaic panels and energy storage devices are determined, the data is re-collected to update the execution adjustment strategy And The obtained values are preprocessed, and the difference value .

[0047] , Among them, The difference value is represented.

[0048] Based on historical data analysis, considering seasonal changes, weather forecasts and possible changes in device efficiency, set energy management thresholds, including energy surplus threshold Energy balance threshold And energy shortage threshold .

[0049] In the present application Set to 0, indicating that the energy is exactly balanced; Set to 3%; Set to -3%, indicating a significant energy supply shortage.

[0050] The maximum output mode satisfies when , indicating that there is enough energy for efficient hydrogen production.

[0051] The energy saving mode satisfies when , indicating that the energy is relatively tight and energy saving measures need to be taken.

[0052] The balance mode satisfies when , the energy supply and demand are basically balanced, and normal operation is suitable.

[0053] The emergency mode satisfies when , the energy is severely insufficient, and the standby system needs to be started or emergency measures need to be taken.

[0054] Adjust thresholds and operating modes dynamically based on actual energy usage and forecast data, continuously optimize using machine learning and pattern recognition techniques And The calculation improves the accuracy of the prediction.

[0055] Energy management includes actively increasing the discharge rate of energy storage devices in maximum output mode to provide the maximum amount of energy to the hydrogen production facility, supporting efficient hydrogen production operations. Automatically activated when monitoring sufficient energy supply. To prevent equipment overload, monitor energy output in real time and ensure it does not exceed the maximum carrying capacity of the facility. At the same time, the energy exceeding the immediate demand will be automatically transferred to the energy storage system for storage, or sold to other users through smart grid technology, thereby optimizing the use of energy.

[0056] In the balance mode, the goal is to maintain the balance between energy supply and demand, ensuring the stability of the system operation. Perform adjustment strategies to smooth out transient energy fluctuations by adjusting the charge and discharge behavior of energy storage devices. Based on real-time monitoring of energy production and consumption data, automatically balance energy flow to hydrogen production activities or energy storage to achieve optimal system efficiency and response.

[0057] In the energy saving mode, measures are taken to reduce energy consumption, reduce the operating frequency of the hydrogen production facility to reduce energy consumption, and increase the storage of energy to optimize energy distribution. By reducing the power usage of non-critical equipment or temporarily shutting down, ensure the energy supply of critical operations.

[0058] In the emergency mode, the preset emergency energy management strategy is started, including immediately enabling the backup energy system (such as diesel generators, etc.) to quickly supplement the energy required for critical operations. In addition, energy storage devices will be preferentially scheduled to support the operation of critical facilities such as hydrogen production lines. Automatically disconnect non-critical loads to ensure the endurance and safety of critical operations.

[0059] Embodiment 2

[0060] One embodiment of the present application provides a direct current off-grid renewable energy hydrogen production energy management system, comprising: an energy management module, a demand analysis module, a potential assessment module, and an energy management module.

[0061] The energy management module is used to construct a direct current voltage network hydrogen energy management module.

[0062] The demand analysis module is used to analyze the load characteristics and obtain the energy demand of the hydrogen production facility to identify high demand and low demand periods.

[0063] The potential assessment module is used to collect wind and sunlight data to assess the potential output capacity of wind power and photovoltaic power generation.

[0064] The energy management module is used to determine the wind turbines, photovoltaic panels and energy storage equipment based on the analysis results of energy demand and output capacity, determine the hydrogen production operation mode, and perform energy management.

[0065] Example 3

[0066] An embodiment of the present invention is different from the previous two embodiments in that:

[0067] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0068] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0069] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0070] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or combinations thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, implementation can be with any or a combination of the following technologies, which are all well known in the art: a discrete logic circuit having logic gates for implementing logic functions upon an application of data signals, an application specific integrated circuit having appropriate combinational logic gates, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0071] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A DC off-grid type renewable energy hydrogen production energy management method, characterized by, The application relates to a hydrogen production energy management module based on direct current voltage networking. Load characteristic analysis is performed to obtain energy demand of the hydrogen production facility, and high-demand and low-demand time periods are identified. Wind power and solar radiation data are collected to evaluate potential output capacity of wind power generation and photovoltaic power generation. Based on the analysis results of the energy demand and the output capacity, a wind turbine, a photovoltaic panel and an energy storage device are determined, a hydrogen production operation mode is determined, and energy management is performed. The hydrogen production energy management module based on direct current voltage networking comprises an upper layer, a middle layer and a lower layer.

2. The DC off-grid renewable energy hydrogen generation energy management method of claim 1, wherein: The upper layer is a scheduling management system used for operation management / scheduling / optimization / prediction, and issues operation instructions and operation constraint conditions to the lower layer micro source / load and the local controller thereof. The middle layer is an energy management module used for determining the operation mode of hydrogen production according to the upper layer instructions and the lower layer state, and managing and scheduling the lower layer device. The lower layer is a micro source / load and a local controller thereof used for renewable energy / energy storage / load data measurement / operation control / state feedback. The load characteristic analysis comprises collecting hourly energy consumption data of the hydrogen production facility in a preset time period in the past, collecting environmental data in the same period, including temperature, humidity and wind speed.

3. The DC off-grid renewable energy hydrogen generation energy management method of claim 2, wherein: Device state data, including maintenance history and efficiency change, are recorded. The energy demand of the hydrogen production facility is obtained by constructing an energy consumption prediction model. Historical energy consumption data are collected, environmental data are collected, operation mode and maintenance data of the hydrogen production facility are recorded, energy consumption fluctuation is explained, the collected data are preprocessed, historical energy consumption data are used for Fourier analysis, Akaike information criterion (AIC) is used to select and fit the parameters of an ARIMA model, a linear regression method is used to determine the influence coefficient of environmental factors on energy consumption, the energy consumption prediction value of a time period is calculated according to the determined parameters and real-time environmental data, the prediction result is compared with the actual energy consumption data to verify the model accuracy, the model parameters are adjusted according to the actual situation to optimize the prediction performance, and the model parameters are re-predicted according to the adjusted model parameters; the average value and the standard deviation of the historical prediction results are calculated, and high-demand and low-demand threshold values are set. The potential output capacity of wind power generation and photovoltaic power generation is evaluated by constructing an output capacity evaluation model.

4. The DC off-grid renewable energy hydrogen generation energy management method of claim 3, wherein: A wind speed meter and a solar radiation meter are installed at the location of the hydrogen production facility to collect wind speed and solar radiation intensity, and the collected data are preprocessed. The integral of the square of the wind speed in a preset time window is calculated to quantify the continuous contribution of the wind speed to energy output, and the solar radiation data are processed by logarithmic transformation to improve the sensitivity and response of the model to the change of the solar radiation intensity. A prediction model is selected based on the data characteristics, the model is trained, and the initial parameters of the neural network are set, including the number of layers, the number of neurons in each layer and the type of activation function. The model is trained by using a historical data set, and the model parameters are optimized by using a back propagation algorithm to minimize the prediction error. The model performance is evaluated by using a cross-validation technique. The prediction accuracy of the model is evaluated by using indexes such as mean square error and determination coefficient. Real-time collected wind speed and solar radiation intensity data are input into the model to obtain instant energy output prediction. ​ 5. The DC off-grid renewable energy hydrogen generation energy management method of claim 4, wherein: The determining of the wind turbine, photovoltaic panel and energy storage device includes identifying time period combinations including high demand and sufficient energy supply, high demand and energy shortage, low demand and sufficient energy supply and low demand and energy shortage; For each time period combination, a configuration analysis is performed to develop a configuration scheme, determine device requirements and evaluate the matching degree of existing device configuration and predicted demand; The wind turbine and photovoltaic panel are determined, the number of wind turbines and photovoltaic panels required to be increased is calculated to make up for the energy gap during the high demand and energy shortage period, and the operation strategy is adjusted to manage the surplus energy instead of increasing the device during the low demand and sufficient energy supply period, so as to ensure the effective operation of the device during the high demand and sufficient energy supply period and the low demand and energy shortage period; The energy storage device is determined, and the required energy storage capacity is determined according to the changes of energy supply and demand in each time period, and the energy storage device is configured to ensure energy supply when in the high demand period or the energy shortage risk period; When in the low demand period or the energy supply sufficient period, an energy storage strategy is executed to maximize energy capture.

6. The DC off-grid renewable energy hydrogen generation energy management method of claim 5, wherein: The determination of the operation mode of hydrogen production includes analyzing the matching degree of device configuration and predicted demand in each time period combination, and determining the operation mode based on the matching degree, wherein the operation mode includes a maximum output mode, an energy saving mode, a balance mode and an emergency mode.

7. The DC off-grid renewable energy hydrogen generation energy management method of claim 6, wherein: The energy management includes increasing the discharge rate of the energy storage device when the operation mode is the maximum output mode, monitoring and adjusting the energy output in real time to not exceed the maximum carrying capacity of the facility, and automatically transferring the energy exceeding the immediate demand to the energy storage system for storage; When the operation mode is the energy saving mode, the charge and discharge behavior of the energy storage device is dynamically adjusted to smooth the instantaneous energy fluctuation, and the energy flow is automatically balanced to the hydrogen production activity or the energy storage to maintain the stability of the system operation; When the operation mode is the balance mode, the operation frequency of the hydrogen production facility is reduced to reduce energy consumption, the energy storage preparation is increased, and the energy distribution is optimized by reducing or temporarily shutting down the power use of non-critical devices to ensure the energy supply of critical operations; When the operation mode is the emergency mode, a preset emergency energy management strategy is started, the standby energy system is immediately enabled, and the energy storage device is preferentially dispatched to support the operation of the critical facility.

8. A system for employing the direct current off-grid type renewable energy hydrogen generation energy management method according to any one of claims 1 to 7, characterized in that, It comprises: an energy management module, a demand analysis module, a potential evaluation module and an energy management module; The energy management module is used to build a direct current voltage networking hydrogen energy management module; The demand analysis module is used to perform load characteristic analysis, obtain the energy demand of the hydrogen production facility, and identify high demand and low demand periods; The potential evaluation module is used to collect wind power and sunlight data, and evaluate the potential output capacity of wind power generation and photovoltaic power generation; The energy management module is used to determine the wind turbine, photovoltaic panel and energy storage device based on the analysis results of energy demand and output capacity, determine the operation mode of hydrogen production, and perform energy management. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to realize the steps of the direct current off-grid type renewable energy hydrogen production energy management method in any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, when executed by a processor, implements the steps of the direct current off-grid type renewable energy hydrogen production energy management method of any one of claims 1-7.

Images