A multi-objective scheduling optimization method and system for methane generation

Abstract

The present disclosure provides a multi-objective scheduling optimization method and system for methane generation, and relates to the technical field of chemical process optimization. The method comprises: obtaining running state data corresponding to the i-th moment of a methane generation system, determining a methane coupling variable set based on the running state data; determining renewable energy fluctuation parameters corresponding to the i+1-th moment, when it is predicted that the renewable energy fluctuation parameters exceed a preset energy fluctuation threshold, inputting the methane coupling variable set into a preset multi-objective scheduling optimization model for scheduling solution, and outputting a scheduling response parameter interval; and determining a methane scheduling scheme under a corresponding running scenario based on the scheduling response parameter interval. Through the above method, the renewable energy fluctuation parameters can be predicted in real time, the prediction of renewable energy fluctuation can be realized, and when the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the system will automatically trigger the methane scheduling scheme, so that the adjustment of the methane generation system can be completed before the renewable energy fluctuation intensifies.

Description

Technical Field

[0001] This disclosure relates to the field of chemical process optimization technology, and in particular to a multi-objective scheduling optimization method and system for methane generation. Background Technology

[0002] Using renewable electricity to electrolyze water to produce hydrogen, and then catalytically synthesizing methane with captured carbon dioxide, is an important technological pathway for achieving carbon recycling and chemical energy storage. However, the front-end energy input of methane generation systems is highly dependent on renewable energy sources such as wind power and photovoltaics, which are highly intermittent and fluctuating.

[0003] Such fluctuations in renewable energy directly impact the electrolysis hydrogen production unit, leading to unstable hydrogen production power. This, in turn, disrupts the stable material ratios necessary for the subsequent methanation reaction, causing drastic changes in reaction conditions and frequent system start-ups and shutdowns. To mitigate the impact of external energy fluctuations, power-following strategies or large-scale buffer storage are typically employed to smooth the input. However, power-following strategies are prone to causing frequent reactor overruns, catalyst lifetime degradation, and unstable product quality. Large-scale buffer storage significantly increases the investment and operating costs of the methane generation system.

[0004] Furthermore, existing scheduling methods focus on local optimization of a single unit within the methane generation system, or offline planning with steady-state economic efficiency as the sole objective. Under external energy fluctuations, they cannot guarantee the global optimization of multiple key aspects such as dynamic material matching, reaction heat balance, and energy storage state coordination. This leads to problems such as decreased operating efficiency, high adjustment costs, and even increased safety risks for the methane generation system when dealing with severe power fluctuations.

[0005] Therefore, in the context of fluctuating external energy levels, how to achieve coordinated scheduling optimization of multiple process units has become a major problem to be solved. Summary of the Invention

[0006] To overcome the problems existing in related technologies, this disclosure provides a multi-objective scheduling optimization method and system for methane generation.

[0007] According to a first aspect of the present disclosure, a multi-objective scheduling optimization method for methane generation is provided, the method comprising: Obtain the operating status data of the methane generation system at time i, where i is a positive integer; Based on the aforementioned operational status data, a set of methane coupling variables is determined; Determine the renewable energy fluctuation parameters corresponding to time i+1. When it is predicted that the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, input the methane coupling variable set into the preset multi-objective scheduling optimization model for scheduling solution and output the scheduling response parameter range. Based on the aforementioned scheduling response parameter range, a methane scheduling scheme is determined for the corresponding operating scenario.

[0008] In one possible design, determining the set of methane coupling variables based on the operational status data includes: The operating status data is analyzed to obtain the real-time methane generation rate, real-time energy input power, and operating load of the electroconversion unit; The ratio between the real-time methane generation rate and the real-time energy input power is determined as the energy supply coupling variable; The ratio between the operating load and the rated load of the power conversion unit is determined as the load response coupling variable; The ratio of real-time renewable energy generation to total system demand is defined as the power fluctuation coupling variable. The methane coupling variable set is generated based on the energy supply coupling variable, the load response coupling variable, and the power fluctuation coupling variable.

[0009] In one possible design, determining the renewable energy fluctuation parameters corresponding to time i+1 includes: Acquire historical renewable energy fluctuation time-series data and historical meteorological data, as well as forecast meteorological data; The historical renewable energy fluctuation time series data and the historical meteorological data are input into a preset fluctuation model for iterative training, and the energy fluctuation prediction parameters corresponding to each training are output. Based on each energy fluctuation prediction parameter and the corresponding actual energy fluctuation parameter, the prediction accuracy of the preset fluctuation model is calculated. If the prediction accuracy is greater than the prediction accuracy threshold, the current preset fluctuation model is determined as the target fluctuation model, and the predicted meteorological data is input into the target fluctuation model to output the renewable energy fluctuation parameters corresponding to the (i+1)th time.

[0010] In one possible design, the preset energy fluctuation threshold is determined based on the load capacity of the power conversion unit and the load capacity coefficient, which is adjusted based on the type of renewable energy.

[0011] In one possible design, the step of inputting the methane coupling variable set into a preset multi-objective scheduling optimization model for scheduling solution and outputting a scheduling response parameter range includes: Determine the energy fluctuation absorption function and the methane formation continuity function; Based on the energy fluctuation absorption function and the methane generation continuity function, a target scheduling function set is constructed; The target scheduling function set is iteratively solved to generate the scheduling response parameter range that conforms to the current running scenario.

[0012] In one possible design, the iterative solution of the target scheduling function set to generate the scheduling response parameter range that conforms to the current operating scenario includes: Determine the energy fluctuation weight value corresponding to the energy fluctuation absorption function, and the continuous weight value corresponding to the methane generation continuity function; The target scheduling function set is weighted based on the energy fluctuation weight value and the continuous weight value to obtain the target scheduling solution set. Extract the target solution that matches the current operating scenario from the target scheduling solution set, and determine the range of variable values ​​corresponding to the target solution as the scheduling response parameter range.

[0013] In one possible design, after determining the methane scheduling scheme for the corresponding operating scenario based on the scheduling response parameter range, the method further includes: Determine the actual scheduling response parameter range corresponding to each methane coupling variable in the methane coupling variable set; If the actual scheduling response parameter range deviates from the target scheduling response parameter range, the deviation value between the actual scheduling response parameter range and the target scheduling response parameter range is determined, and the methane scheduling scheme is adjusted based on the deviation value.

[0014] According to a second aspect of the present disclosure, a multi-objective scheduling optimization system for methane generation is provided, comprising: The data acquisition module is used to acquire the operating status data of the methane generation system at time i, where i is a positive integer; The variable acquisition module is used to determine the set of methane coupling variables based on the operating status data; The prediction response module is used to determine the renewable energy fluctuation parameters corresponding to time i+1. When the predicted renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the methane coupling variable set is input into the preset multi-objective scheduling optimization model for scheduling solution, and the scheduling response parameter range is output. The scheme determination module is used to determine the methane scheduling scheme under the corresponding operating scenario based on the scheduling response parameter range.

[0015] In one possible design, the variable acquisition module is specifically used to parse the operating status data to obtain the real-time methane generation rate, real-time energy input power, and operating load of the power conversion unit. The ratio between the real-time methane generation rate and the real-time energy input power is determined as the energy supply coupling variable, the ratio between the operating load of the power conversion unit and the rated load is determined as the load response coupling variable, and the ratio between the real-time renewable energy power generation and the total system demand power is determined as the power fluctuation coupling variable. Based on the energy supply coupling variable, the load response coupling variable, and the power fluctuation coupling variable, the methane coupling variable set is generated.

[0016] In one possible design, the prediction response module is specifically used to acquire historical renewable energy fluctuation time-series data and historical meteorological data, as well as predictive meteorological data. The historical renewable energy fluctuation time-series data and the historical meteorological data are input into a preset fluctuation model for iterative training. The module outputs energy fluctuation prediction parameters corresponding to each training iteration. Based on each energy fluctuation prediction parameter and the corresponding actual energy fluctuation parameter, the prediction accuracy of the preset fluctuation model is calculated. If the prediction accuracy is greater than a prediction accuracy threshold, the current preset fluctuation model is determined as the target fluctuation model, and the predictive meteorological data is input into the target fluctuation model. The renewable energy fluctuation parameters corresponding to the (i+1)th time are then output.

[0017] In one possible design, the predictive response module includes: a preset energy fluctuation threshold determined based on the load capacity of the power conversion unit and the load capacity coefficient, wherein the load capacity coefficient is adjusted based on the type of renewable energy.

[0018] In one possible design, the predictive response module is further configured to determine the energy fluctuation absorption function and the methane generation continuity function, construct a target scheduling function set based on the energy fluctuation absorption function and the methane generation continuity function, iteratively solve the target scheduling function set, and generate the scheduling response parameter range that conforms to the current operating scenario.

[0019] In one possible design, the prediction response module is further configured to determine the energy fluctuation weight value corresponding to the energy fluctuation absorption function and the continuous weight value corresponding to the methane generation continuity function, perform weighted processing on the target scheduling function group based on the energy fluctuation weight value and the continuous weight value to obtain the target scheduling solution set, extract the target solution that conforms to the current operating scenario from the target scheduling solution set, and determine the variable value range corresponding to the target solution as the scheduling response parameter interval.

[0020] In one possible design, the scheme determination module is specifically used to determine the actual scheduling response parameter range corresponding to each methane coupling variable in the methane coupling variable set. If the actual scheduling response parameter range deviates from the target scheduling response parameter range, the deviation value between the actual scheduling response parameter range and the target scheduling response parameter range is determined, and the methane scheduling scheme is adjusted based on the deviation value.

[0021] According to a third aspect of the present disclosure, a computer device is provided, comprising: A memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the method of the first or second aspect described above.

[0022] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when the computer program is executed by a processor, the method of the first or second aspect described above is implemented.

[0023] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: In this embodiment of the disclosure, under the condition of renewable energy fluctuations, the renewable energy fluctuation parameters can be predicted in real time, thereby achieving the prediction of renewable energy fluctuations. When the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the system will automatically trigger the methane scheduling scheme, thereby completing the adjustment of the methane generation system before the renewable energy fluctuations intensify, avoiding production interruption in the methane generation process due to renewable energy fluctuations, reducing the waste of renewable energy, realizing the coordinated scheduling optimization of multiple process units, and improving the methane generation efficiency.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this disclosure, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0026] Figure 1 This is a flowchart illustrating a multi-objective scheduling optimization method for methane generation according to an exemplary embodiment of the present disclosure; Figure 2 This is a schematic diagram of the system structure of a methane generation system according to an exemplary embodiment of the present disclosure; Figure 3 This disclosure is a schematic diagram illustrating the structure of a multi-objective scheduling optimization system for methane generation according to an exemplary embodiment; Figure 4This is a schematic diagram of the structure of a computer device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0028] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The singular forms “a,” “the,” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0029] It should be understood that although the terms first, second, third, etc., may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are used only to distinguish information of the same type from one another. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0030] In related technologies, fluctuations in renewable energy can lead to unstable hydrogen production power, which in turn disrupts the stable material ratios necessary for subsequent methanation reactions, causing drastic changes in reaction conditions and frequent system start-ups and shutdowns. Simultaneously, under conditions of external energy fluctuations, existing scheduling methods cannot guarantee the global optimization of multiple key aspects such as dynamic material matching, reaction heat balance, and energy storage status coordination. This results in methane generation systems facing reduced operating efficiency, high adjustment costs, and even increased safety risks when dealing with severe power fluctuations. Therefore, how to achieve coordinated scheduling optimization of multiple process units under external energy fluctuation environments has become a major problem to be solved.

[0031] The multi-objective scheduling optimization method for methane generation in this example embodiment will now be described in detail.

[0032] like Figure 1 As shown, Figure 1 This disclosure is a flowchart illustrating a multi-objective scheduling optimization method for methane generation according to an exemplary embodiment, comprising the following steps: Step S110: Obtain the operating status data corresponding to the methane generation system.

[0033] In practical applications, a methane generation system typically consists of a renewable energy power generation unit, a water electrolysis hydrogen production unit, a biomass treatment unit, a gas treatment unit, and a methane synthesis unit. A system structure diagram of a methane generation system is shown below. Figure 2 As shown, in Figure 2 In this system, the renewable energy power generation unit converts renewable energy into electricity and stores the electricity; renewable energy can be solar energy, wind energy, etc.; the renewable energy power generation unit supplies electricity to the water electrolysis hydrogen production unit, whose electrolyzer can electrolyze water to produce hydrogen and oxygen based on electricity, and then store the hydrogen in a hydrogen storage tank; the biomass treatment unit is used to gasify biomass to obtain syngas containing carbon monoxide and hydrogen; the gas treatment unit is used to purify carbon dioxide from the syngas and store the carbon dioxide in a carbon dioxide storage tank; the methane synthesis unit is used to mix hydrogen and carbon dioxide in a 4:1 ratio, pressurize the mixture to 3.0~5.0 MPa in the feed gas compressor, and then heat it to 200~250℃ in the preheater before feeding it into the methanation reactor. Under the action of a catalyst, the mixed gas undergoes a methanation reaction, i.e.: CO2 + 4H2 = CH4 + 2H2O, to produce methane.

[0034] In order to ensure the stable operation of the methane generation system during external energy fluctuations, this application embodiment requires real-time monitoring of the corresponding operating status data of the methane generation system. The operating status data includes at least: biomass feed data, power conversion unit operating load data, and feed gas status data of the methane synthesis unit. The power conversion unit is located within the renewable energy power generation unit. The operating status data and renewable energy fluctuation parameters are monitored based on their respective sensors, which can be: weighing sensors, current sensors, voltage sensors, gas concentration sensors, etc.

[0035] Obtaining the operating status data of the methane generation system using the above methods helps to avoid equipment overload or waste of biomass feed.

[0036] Step S120: Determine the set of methane coupling variables based on the operating status data.

[0037] The operating status data is analyzed to obtain the real-time methane generation rate, real-time energy input power, and operating load of the power conversion unit. The ratio between the real-time methane generation rate and the real-time energy input power is then calculated and determined as the energy supply coupling variable. The rated load corresponding to the power conversion unit is determined, for example, if the rated load is 50 kilowatts (kW), and the ratio between the operating load of the power conversion unit and the rated load is calculated and determined as the load response coupling variable. The real-time renewable energy power generation can be determined directly from the monitoring interface on the photovoltaic inverter. The ratio between the real-time renewable energy power generation and the total system demand power is calculated and determined as the power fluctuation coupling variable. The total system demand power is the total power of the electrical energy consumed by the methane generation system.

[0038] Specifically, the calculation formula for the energy supply coupling variables is as follows: The above For energy supply coupling variables, Let be the methane production rate at time t, where t is a positive integer. Let be the real-time energy input power at time t. The real-time energy input power can be the input power of the water electrolysis hydrogen production and methane synthesis unit. The energy supply coupling variable is used to characterize the methane production efficiency corresponding to a unit energy input. The higher the methane production efficiency, the higher the energy utilization rate.

[0039] Will , Before substituting the energy supply coupling variables into the calculation formula, it is necessary to... , All parameters are normalized so that each parameter is converted into a dimensionless value in the range of 0 to 1.

[0040] The specific calculation formula for the load response coupling variable is as follows: The above For load response coupling variables, Let be the real-time operating power at time t. The rated power is used to characterize the equipment's operating intensity and load regulation capability.

[0041] Will , Before substituting the load response coupling variable into the calculation formula, it is necessary to... , All parameters are normalized so that each parameter is converted into a dimensionless value in the range of 0 to 1.

[0042] The specific calculation formula for the power fluctuation coupling variable is as follows: The above For power fluctuation coupling variables, Let t be the renewable energy output power at time t. Let be the total power demand of the system at time t; the power fluctuation coupling variable represents the degree of energy supply and demand matching and the intensity of fluctuation impact.

[0043] Will , Before substituting the power fluctuation coupling variable into the calculation formula, it is necessary to... , All parameters are normalized so that each parameter is converted into a dimensionless value in the range of 0 to 1.

[0044] Energy supply coupling variables, load response coupling variables, and power fluctuation coupling variables are stored in a methane coupling variable set. The methane coupling variable set represents the coupling relationship between energy output fluctuations, changes in the load of the power conversion unit, and the methane generation rate.

[0045] Using the methods described above, the relationship between various parameters within the methane generation system can be described more accurately based on the methane coupling variable set.

[0046] Step S130: Determine the renewable energy fluctuation parameters corresponding to time i+1. When it is predicted that the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, input the methane coupling variable set into the preset multi-objective scheduling optimization model for scheduling solution and output the scheduling response parameter range.

[0047] To prevent the methane generation rate from becoming unstable due to renewable energy fluctuations, this application embodiment requires the construction of a target fluctuation model. At time i, where i is a positive integer, the renewable energy fluctuation parameters of the methane generation system at time i+1 are output based on the target fluctuation model. This enables the methane generation system to determine at time i whether the renewable energy fluctuation parameters at time i+1 exceed a preset energy fluctuation threshold, which helps to reduce the impact of renewable energy fluctuations on the methane generation process and thus ensures the stability of the methane generation system.

[0048] Specifically, the process of constructing the target volatility model is as follows: First, it is necessary to obtain historical renewable energy time-series data and historical meteorological data. Historical renewable energy time-series data includes: the output power of renewable energy power generation end, and actual energy fluctuation parameters. This application takes photovoltaic power generation as an example for illustration. Historical meteorological data includes solar irradiance, sunshine duration, ambient temperature, and cloud coverage, etc. Historical meteorological data can be extracted from photovoltaic power station monitoring equipment or from the China Meteorological Data Network.

[0049] Then, historical renewable energy fluctuation time-series data and historical meteorological data are input into a preset fluctuation model for training. The preset fluctuation model aligns the historical renewable energy fluctuation time-series data and historical meteorological data based on the same timestamp, generating one-to-one training samples based on the historical renewable energy fluctuation time-series data and historical meteorological data. For example, at one time, the solar irradiance is 800 watts per square meter, the temperature is 25°C, and the output power is 80 kilowatts; at another time, the solar irradiance is 500 watts per square meter, the temperature is 20°C, and the output power is 50 kilowatts. The preset fluctuation model learns from all training samples to find the relationship between meteorological data and output power.

[0050] Furthermore, the preset fluctuation model will output the corresponding energy fluctuation prediction parameters in each iteration of training. Based on each energy fluctuation prediction parameter and the corresponding actual energy fluctuation parameter, the prediction accuracy of the preset fluctuation model can be calculated. If the prediction accuracy is less than the prediction accuracy threshold, the current preset fluctuation model will continue to be iteratively trained; if the prediction accuracy is greater than the prediction accuracy threshold, the current preset fluctuation model will be determined as the target fluctuation model.

[0051] It should be noted that, in order to ensure the accuracy of the target volatility model, validation samples need to be obtained. Validation samples include validation meteorological data and validation renewable energy volatility time series data. The validation samples are then input into the target volatility model for prediction, and the validation accuracy of the validation sample pairs is obtained. If the validation accuracy is less than the prediction accuracy threshold, the model parameters of the target volatility model are adjusted. The model parameters can be the number of hidden layers, the number of neurons, etc., until the validation accuracy is greater than the prediction accuracy threshold. If the validation accuracy is greater than the prediction accuracy threshold, the target volatility model is determined to be up to standard.

[0052] After determining the target fluctuation model, predictive meteorological data is obtained. The predictive meteorological data can be obtained from a meteorological data platform. The predictive meteorological data can be the meteorological data at time i+1. The predictive meteorological data is input into the target fluctuation model, and the renewable energy fluctuation parameters corresponding to time i+1 are output. The renewable energy fluctuation parameters can be: solar irradiance, photovoltaic panel temperature, wind speed, wind direction, etc. The renewable energy fluctuation parameters will affect the input power of the power conversion unit, thereby running the scheduling of the entire methane generation system.

[0053] The preset fluctuation model can be a Long Short-Term Memory (LSTM) network model or a Gated Recurrent Neural Network (GRNN) model. Since the training process of LSTM and GRNN is a well-known technique in the art, it will not be elaborated on here.

[0054] When the renewable energy fluctuation parameters do not exceed the preset energy fluctuation threshold, the methane generation system continues to be monitored in real time; when the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the preset energy fluctuation threshold is determined based on the load capacity and load capacity coefficient of the power conversion unit. The load capacity coefficient can be 0.8. For example, if the load capacity of the power conversion unit is 100 kW and the load capacity coefficient is 0.8, then the preset energy fluctuation threshold is 80 kW.

[0055] It should be noted that different types of renewable energy have different impacts on the methane generation process. When the renewable energy is photovoltaic, the power output of photovoltaic power generation is significantly affected by the intensity of sunlight and is prone to rapid and large fluctuations. Therefore, in order to avoid impacting the methane generation system, the load capacity factor can be set to 0.6. When the renewable energy is wind power, the power output of wind power is affected by wind speed and fluctuates relatively slowly. Therefore, the load capacity factor can be set to 0.8.

[0056] At this point, if the predicted renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, this embodiment of the application needs to input the methane coupling variable set into the preset multi-objective scheduling optimization model for scheduling solution, and output the scheduling response parameter range, which can effectively match the fluctuation of renewable energy.

[0057] Specifically, the above multi-objective scheduling optimization model is constructed with energy fluctuation response as a constraint, and the specific construction process is as follows: The constraints corresponding to energy fluctuation response include: power upper limit constraint, fluctuation rate constraint, and energy prediction error constraint.

[0058] The above power limit constraint is that the actual output power of renewable energy + the input power of other auxiliary energy sources < the rated power of the power conversion unit.

[0059] The above fluctuation rate constraint is that within a unit of time, the change in the power generation of renewable energy is less than the maximum power change that the power conversion unit can withstand. For example, when the power of a photovoltaic panel drops from 80 kW to 50 kW in one second due to cloud cover, the change in the power generation of renewable energy reaches 30 kW. The power conversion unit can withstand a power fluctuation of 36 kW per second. 30 kW < 36 kW means that the power change rate of renewable energy is within the range that the power conversion unit can withstand, thereby avoiding overload of the power conversion unit.

[0060] The above-mentioned energy prediction error constraint is that the ratio of the actual measured power fluctuation of renewable energy to the predicted power fluctuation is between [0.9, 1.1], thereby preventing the power conversion unit from being overloaded due to excessive prediction error, and preventing the methane generation system from being frequently adjusted due to small fluctuations, thus affecting the stability of the methane generation process.

[0061] Furthermore, to ensure the stability of the methane generation process under energy fluctuations, this application embodiment also needs to determine stoichiometric constraints, equipment load constraints, energy storage balance constraints, and renewable energy constraints. The specific process is as follows: The above stoichiometric constraints are the reaction ratio constraints in the methane synthesis process, namely: ∈[3.96, 4.04], The reaction ratio of H2 and CO is constrained.

[0062] The above-mentioned equipment load constraints are that the load rate of each device in the methane generation system does not exceed the rated power of each device, and is not less than 10% of the rated power of each device, i.e., 0.1. ≤ ≤ , Let i be the load rate of the i-th device. Let be the rated power of the i-th device, to avoid the device operating under too low a load, which would affect the methane generation rate.

[0063] The above energy storage balance constraint is that the real-time capacity of the hydrogen storage tank, battery, and CO2 storage tank is maintained between 0 and the rated capacity, i.e.: 0 ≤ ≤ j = H2, E, CO2 Let j be the real-time capacity of the device corresponding to j. The rated capacity of the corresponding equipment is j, which ensures that the energy flow of the methane generation system remains balanced and stabilizes the fluctuations of renewable energy, providing a continuous and stable energy supply for the methane generation system.

[0064] The above renewable energy constraints are for photovoltaic power. Wind power ≤ ,in, This refers to photovoltaic installed capacity, expressed in megawatts (MW). This refers to the installed capacity of wind power, measured in MW.

[0065] The formula for calculating the photovoltaic power mentioned above is as follows: in, Photovoltaic power, measured in megawatts (MW). This represents the actual solar irradiance. The unit for both actual solar irradiance and standard test condition irradiance is megawatts per square meter (MW / m²). For photovoltaic module conversion efficiency, For temperature coefficient, It can be -0.004 / ℃. This refers to the actual ambient temperature. The standard test temperature can be 25℃. , It is a dimensionless numerical value.

[0066] The formula for calculating wind power is as follows: in, For wind power, This refers to the actual wind speed. This refers to the fan cut-in velocity, which can be 3 m / s. The cutoff velocity for the fan can be 25 m / s. The rated wind speed of the fan is 12 m / s. The ratio is a dimensionless value.

[0067] To address the fluctuations in renewable energy, it is also necessary to set model decision variables. These model decision variables are adjustable parameters for dealing with the fluctuations in renewable energy. The model decision variables should include at least the following: renewable energy installed capacity, water electrolysis hydrogen production capacity, biomass oxygen-enriched combustion capacity, CO2 capture capacity, methanation treatment capacity, and gas and electricity storage capacity.

[0068] Specifically, the aforementioned renewable energy installed capacity includes: photovoltaic installed capacity range and wind power installed capacity range, with photovoltaic installed capacity range being [5MW, 300MW], and wind power installed capacity range being [5MW, 300MW]; the aforementioned water electrolysis hydrogen production capacity includes: electrolyzer rated power range, which can be [2MW, 150MW]; the aforementioned biomass oxygen-enriched combustion capacity is the heat output power range under oxygen-enriched combustion conditions, with heat output power range being [300kW, 600kW]; the aforementioned CO2 capture capacity is the range of carbon dioxide captured daily by the CO2 capture device, with carbon dioxide range being [300 tons (t), 600t]; the aforementioned methanation treatment capacity is the range of methane synthesized daily, with methane weight range being [5t, 300t]; the aforementioned gas and electrical energy storage capacity includes: hydrogen storage tank capacity range [0.5t, 50t], battery capacity range [2t, 150t], and storage... Tank capacity range [0.5t, 50t].

[0069] In addition, the energy fluctuation absorption function and the methane formation continuity function are determined. The specific expression for the energy fluctuation absorption function is as follows: The above This represents the value of the energy fluctuation absorption function. The time period is measured in hours (h). Let t be the renewable energy output power at time t. Let be the real-time operating power at time t; the energy fluctuation absorption function value is used to measure the methane generation system's ability to absorb fluctuations in renewable energy output. The smaller the value, the less wind and solar power are wasted, and the higher the energy utilization rate of the methane generation system.

[0070] The specific expression for the methane formation continuity function is as follows: The above For methane generation, a continuous function value, The length of the time period. Let be the methane production rate at time t. The average methane formation rate over time T is given. To ensure dimensionless measurement, it is necessary to... The unit is converted from hours to seconds, and at the same time, The unit is converted from kg / h to kg / s. The methane formation continuity function value is used to measure the stability and continuity of the methane formation process. The smaller the value, the smaller the fluctuation in methane production and the more stable the operation.

[0071] Furthermore, a target scheduling function set is constructed based on the energy fluctuation absorption function and the methane generation continuity function.

[0072] Based on the above, a historical set of methane coupling variables and a historical dispatch response parameter range are obtained. Then, based on the constraints corresponding to energy fluctuation response, stoichiometric constraints, equipment load constraints, energy storage balance constraints, renewable energy constraints, model decision variables, historical set of methane coupling variables, and historical dispatch response parameter range, a preset multi-objective dispatch optimization model is constructed. The historical set of methane coupling variables and the historical dispatch response parameter range are used to iteratively optimize the preset multi-objective dispatch optimization model, thereby ensuring the accuracy of the preset multi-objective dispatch optimization model.

[0073] The aforementioned pre-defined multi-objective scheduling optimization model can be an error back-propagation neural network (BPNN) model. Since the construction of the BPNN model is a well-known technique to those skilled in the art, it will not be described in detail here.

[0074] After determining the preset multi-objective scheduling model, the methane coupling variable set is input into the preset multi-objective scheduling optimization model for scheduling solution. The solution process is as follows: Determine the energy fluctuation weight value corresponding to the energy fluctuation absorption function and the continuous weight value corresponding to the methane generation continuity function. Based on the energy fluctuation weight value and the continuous weight value, perform weighted processing on the target scheduling function group to obtain the scheduling solution set. Then adjust the energy fluctuation weight value and the continuous weight value to achieve iterative optimization of the scheduling solution set of the target scheduling function group. When the number of iterations reaches the optimal number of iterations, output the target scheduling solution set.

[0075] The energy fluctuation absorption function in the aforementioned pre-defined multi-objective scheduling model is used to measure the ability of the methane generation system to cope with the fluctuations of renewable energy. The smaller the value of the energy fluctuation absorption function, the stronger the ability of the methane generation system to absorb energy fluctuations. The methane generation continuity function is used to measure the stability of the methane generation process. The larger the value of the methane generation continuity function, the more continuous and stable the methane production.

[0076] For example, when the output power of a photovoltaic panel suddenly drops, the energy fluctuation absorption function value determines whether the methane generation system can quickly mobilize the hydrogen in the storage tank or switch to other energy sources to make up for the energy gap and keep the energy input of the entire methane generation system stable.

[0077] Extract the target solution that matches the current operating scenario from the target scheduling solution set, and determine the range of variable values ​​corresponding to the target solution as the scheduling response parameter range.

[0078] For example, in the current operating scenario: when the output power of the photovoltaic panel fluctuates greatly but the methane demand is stable, the target solution with a larger energy fluctuation absorption function value can be selected first; in the current operating scenario: when the output power of the photovoltaic panel is stable but the methane demand suddenly increases, the target solution with a larger methane generation continuity function value can be selected first.

[0079] Using the above method, when the system predicts that the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the methane coupling variable set is input into the preset multi-objective scheduling optimization model for scheduling solution, and the scheduling response parameter range is output. This allows the system to determine the scheduling response parameter range in advance based on the predicted renewable energy fluctuation parameters, thereby avoiding methane production interruptions caused by renewable energy fluctuations or resource waste caused by excess renewable energy output, and ensuring that the methane generation rate matches the external energy fluctuation state.

[0080] Step S140: Based on the scheduling response parameter range, determine the methane scheduling scheme for the corresponding operating scenario.

[0081] Once the scheduling response parameter range is determined, since the scheduling response parameter range represents the range of parameters within which the methane generation system can operate stably under renewable energy fluctuations, a methane scheduling scheme for the corresponding operating scenario can be generated based on the scheduling response parameter range.

[0082] Furthermore, embodiments of this application can adjust the operating parameters of the methane generation system based on a methane scheduling scheme, as detailed below: Based on the scheduling response parameter range, load adjustment instructions and operating parameter adjustment instructions are generated. The load adjustment instructions are used to adjust the instantaneous power of the electrolytic hydrogen production unit, and the operating parameter adjustment instructions are used to adjust the reaction load of the methane synthesis unit, such as the feed rate of hydrogen and carbon dioxide in the reactor, so that the methane generation process can form a buffer response to external energy fluctuations.

[0083] To ensure the stability of the methane generation process under renewable energy fluctuations, it is also necessary to determine the actual dispatch response parameter range corresponding to each methane coupling variable in the methane coupling variable set. If the actual dispatch response parameter range deviates from the target dispatch response parameter range, the deviation value between the actual dispatch response parameter range and the target dispatch response parameter range is determined, and the methane dispatch scheme is adjusted based on the deviation value to obtain a new methane dispatch scheme.

[0084] Using the methods described above, the system can predict renewable energy fluctuation parameters in real time under conditions of renewable energy fluctuations. When the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the system will automatically trigger a methane scheduling scheme. This allows the methane generation system to be adjusted before renewable energy fluctuations intensify, preventing production interruptions in the methane generation process due to renewable energy fluctuations, reducing renewable energy waste, achieving coordinated scheduling optimization of multiple process units, and improving methane generation efficiency.

[0085] like Figure 3 The diagram shown is a schematic representation of a multi-objective scheduling optimization system for methane generation according to an exemplary embodiment, comprising the following modules: Data acquisition module 301 is used to acquire the operating status data of the methane generation system at time i, where i is a positive integer; The variable acquisition module 302 is used to determine the methane coupling variable set based on the operating status data; The prediction response module 303 is used to determine the renewable energy fluctuation parameters corresponding to the (i+1)th time. When the predicted renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the methane coupling variable set is input into the preset multi-objective scheduling optimization model for scheduling solution, and the scheduling response parameter range is output. The scheme determination module 304 is used to determine the methane scheduling scheme under the corresponding operating scenario based on the scheduling response parameter range.

[0086] In one possible design, the variable acquisition module 302 is specifically used to parse the operating status data to obtain the real-time methane generation rate, real-time energy input power, and operating load of the power conversion unit. The ratio between the real-time methane generation rate and the real-time energy input power is determined as the energy supply coupling variable, the ratio between the operating load of the power conversion unit and the rated load is determined as the load response coupling variable, and the ratio between the real-time renewable energy power generation and the total system demand power is determined as the power fluctuation coupling variable. Based on the energy supply coupling variable, the load response coupling variable, and the power fluctuation coupling variable, the methane coupling variable set is generated.

[0087] In one possible design, the prediction response module 303 is specifically used to acquire historical renewable energy fluctuation time-series data and historical meteorological data, as well as predictive meteorological data. The historical renewable energy fluctuation time-series data and the historical meteorological data are input into a preset fluctuation model for iterative training. The energy fluctuation prediction parameters corresponding to each training iteration are output. Based on each energy fluctuation prediction parameter and the corresponding actual energy fluctuation parameter, the prediction accuracy of the preset fluctuation model is calculated. If the prediction accuracy is greater than the prediction accuracy threshold, the current preset fluctuation model is determined as the target fluctuation model, and the predictive meteorological data is input into the target fluctuation model to output the renewable energy fluctuation parameters corresponding to the (i+1)th time.

[0088] In one possible design, the predictive response module 303 includes: a preset energy fluctuation threshold determined based on the load capacity of the power conversion unit and the load capacity coefficient, wherein the load capacity coefficient is adjusted based on the type of renewable energy.

[0089] In one possible design, the prediction response module 303 is further configured to determine the energy fluctuation absorption function and the methane generation continuity function, construct a target scheduling function set based on the energy fluctuation absorption function and the methane generation continuity function, iteratively solve the target scheduling function set, and generate the scheduling response parameter range that conforms to the current operating scenario.

[0090] In one possible design, the prediction response module 303 is further configured to determine the energy fluctuation weight value corresponding to the energy fluctuation absorption function and the continuous weight value corresponding to the methane generation continuity function, perform weighted processing on the target scheduling function group based on the energy fluctuation weight value and the continuous weight value to obtain the target scheduling solution set, extract the target solution that conforms to the current operating scenario from the target scheduling solution set, and determine the variable value range corresponding to the target solution as the scheduling response parameter interval.

[0091] In one possible design, the scheme determination module 304 is specifically used to determine the actual scheduling response parameter range corresponding to each methane coupling variable in the methane coupling variable set. If the actual scheduling response parameter range deviates from the target scheduling response parameter range, the deviation value between the actual scheduling response parameter range and the target scheduling response parameter range is determined, and the methane scheduling scheme is adjusted based on the deviation value.

[0092] This disclosure provides a computer device, including: A memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the method of any of the above embodiments.

[0093] This specification describes an embodiment of a multi-objective scheduling optimization method for methane generation, which can be applied to computer devices, such as servers or terminal devices. The device embodiment can be implemented through software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor responsible for the multi-objective scheduling optimization of methane generation loading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 4 The diagram shown is a structural schematic of a computer device used in an embodiment of this specification for a multi-objective scheduling optimization method for methane generation. Except for... Figure 4 In addition to the processor 410, memory 430, network interface 420, and non-volatile memory 440 shown, the server or electronic device where the multi-objective scheduling optimization system 431 for methane generation is located may also include other hardware depending on the actual function, which will not be described in detail here.

[0094] This disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the methods of any of the above embodiments. The execution method and beneficial effects are similar, and will not be described again here.

[0095] The aforementioned computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0096] The computer program described above can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer device, partially on the user's device, as a standalone software package, partially on the user's computer device and partially on a remote computer device, or entirely on a remote computer device or server.

[0097] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0098] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0099] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-objective scheduling optimization method for methane generation, characterized in that, include: Obtain the operating status data of the methane generation system at time i, where i is a positive integer; Based on the aforementioned operational status data, a set of methane coupling variables is determined; Determine the renewable energy fluctuation parameters corresponding to time i+1. When it is predicted that the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, input the methane coupling variable set into the preset multi-objective scheduling optimization model for scheduling solution and output the scheduling response parameter range. Based on the aforementioned scheduling response parameter range, a methane scheduling scheme is determined for the corresponding operating scenario.

2. The method according to claim 1, characterized in that, The determination of the methane coupling variable set based on the operational status data includes: The operating status data is analyzed to obtain the real-time methane generation rate, real-time energy input power, and operating load of the electroconversion unit; The ratio between the real-time methane generation rate and the real-time energy input power is determined as the energy supply coupling variable; The ratio between the operating load and the rated load of the power conversion unit is determined as the load response coupling variable; The ratio of real-time renewable energy generation to total system demand is defined as the power fluctuation coupling variable. The methane coupling variable set is generated based on the energy supply coupling variable, the load response coupling variable, and the power fluctuation coupling variable.

3. The method according to claim 1, characterized in that, Determining the renewable energy fluctuation parameters corresponding to time i+1 includes: Acquire historical renewable energy fluctuation time-series data and historical meteorological data, as well as forecast meteorological data; The historical renewable energy fluctuation time series data and the historical meteorological data are input into a preset fluctuation model for iterative training, and the energy fluctuation prediction parameters corresponding to each training are output. Based on each energy fluctuation prediction parameter and the corresponding actual energy fluctuation parameter, the prediction accuracy of the preset fluctuation model is calculated. If the prediction accuracy is greater than the prediction accuracy threshold, the current preset fluctuation model is determined as the target fluctuation model, and the predicted meteorological data is input into the target fluctuation model to output the renewable energy fluctuation parameters corresponding to the (i+1)th time.

4. The method according to claim 1, characterized in that, The preset energy fluctuation threshold is determined based on the load capacity of the power conversion unit and the load capacity coefficient, and the load capacity coefficient is adjusted based on the type of renewable energy.

5. The method according to claim 1, characterized in that, The step of inputting the methane coupling variable set into a preset multi-objective scheduling optimization model for scheduling solution and outputting a scheduling response parameter range includes: Determine the energy fluctuation absorption function and the methane formation continuity function; Based on the energy fluctuation absorption function and the methane generation continuity function, a target scheduling function set is constructed; The target scheduling function set is iteratively solved to generate the scheduling response parameter range that conforms to the current running scenario.

6. The method according to claim 5, characterized in that, The iterative solution of the target scheduling function set to generate the scheduling response parameter range that conforms to the current operating scenario includes: Determine the energy fluctuation weight value corresponding to the energy fluctuation absorption function, and the continuous weight value corresponding to the methane generation continuity function; The target scheduling function set is weighted based on the energy fluctuation weight value and the continuous weight value to obtain the target scheduling solution set. Extract the target solution that matches the current operating scenario from the target scheduling solution set, and determine the range of variable values ​​corresponding to the target solution as the scheduling response parameter range.

7. The method according to claim 1, characterized in that, After determining the methane scheduling scheme for the corresponding operating scenario based on the scheduling response parameter range, the process further includes: Determine the actual scheduling response parameter range corresponding to each methane coupling variable in the methane coupling variable set; If the actual scheduling response parameter range deviates from the target scheduling response parameter range, the deviation value between the actual scheduling response parameter range and the target scheduling response parameter range is determined, and the methane scheduling scheme is adjusted based on the deviation value.

8. A multi-objective scheduling optimization system for methane generation, characterized in that, The system includes: The data acquisition module is used to acquire the operating status data of the methane generation system at time i, where i is a positive integer; The variable acquisition module is used to determine the set of methane coupling variables based on the operating status data; The prediction response module is used to determine the renewable energy fluctuation parameters corresponding to time i+1. When the predicted renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, the methane coupling variable set is input into the preset multi-objective scheduling optimization model for scheduling solution, and the scheduling response parameter range is output. The scheme determination module is used to determine the methane scheduling scheme under the corresponding operating scenario based on the scheduling response parameter range.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-7.

10. A computer device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the following method: Obtain the operating status data of the methane generation system at time i, where i is a positive integer; Based on the aforementioned operational status data, a set of methane coupling variables is determined; Determine the renewable energy fluctuation parameters corresponding to time i+1. When it is predicted that the renewable energy fluctuation parameters exceed the preset energy fluctuation threshold, input the methane coupling variable set into the preset multi-objective scheduling optimization model for scheduling solution and output the scheduling response parameter range. Based on the aforementioned scheduling response parameter range, a methane scheduling scheme is determined for the corresponding operating scenario.

Images