Park light storage and hydrogen charging collaborative optimization method and system based on dynamic carbon emission factors

Abstract

The invention discloses a dynamic carbon emission factor-based park light storage and hydrogen charging collaborative optimization method and system. The method comprises the following steps of: obtaining various historical data of a park microgrid; constructing a prediction model and an equipment model based on historical data; based on the prediction model and the equipment model, considering an intra-day electric power dynamic carbon emission factor, taking the minimum carbon dioxide emission of the park microgrid as an objective function, and combining supply and demand balance constraints to establish an optimization model; and solving the model by using an optimization algorithm to obtain a low-carbon operation plan. The system comprises a data acquisition module, a prediction model construction module, an equipment model construction module, an optimization model definition module and an optimization solution module. According to the invention, the method can achieve the optimization of the intra-day optimal operation plan of each energy facility in the park. The method can be widely applied to the field of carbon emission reduction.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission reduction, and particularly to a collaborative optimization method and system for photovoltaic energy storage hydrogen charging in a park based on dynamic carbon emission factors. Background Art

[0002] The large-scale development and utilization of renewable energy, the improvement of energy utilization efficiency, and deep emission reduction have become the basic directions for the development of the energy industry. The application of new energy technologies such as photovoltaic power generation, energy storage, charging stations, and green hydrogen production will be the main players in the clean transformation of energy. The integrated application of the combination of "photovoltaic + energy storage + hydrogen production + charging" has become an inevitable trend in the development of new energy.

[0003] Currently, most projects mainly focus on the demonstration construction of photovoltaic power generation, charging piles, and energy storage facilities, and the application of hydrogen production and hydrogenation equipment is relatively less. This means that hydrogen energy, as an important clean energy carrier, has not been fully emphasized and widely applied. Currently, few parks consider hydrogen production and hydrogenation equipment at the same time, and the independent operation and independent use of various energy elements are relatively common, and the mode of multi-energy complementarity and integrated collaborative operation has not been truly realized. Summary of the Invention

[0004] In view of this, in order to solve the technical problem that the existing low-carbon operation optimization method does not consider the actual park application and cannot achieve integrated collaborative operation according to the specific equipment in the park, in the first aspect, the present invention proposes a collaborative optimization method for photovoltaic energy storage hydrogen charging in a park based on dynamic carbon emission factors. The method includes the following steps:

[0005] Obtain various historical data of the park microgrid, which may include: equipment information: the capacity, efficiency, operating status, etc. of photovoltaic equipment, energy storage equipment, hydrogen production equipment, charging piles, etc. Meteorological data: light intensity, temperature, wind speed, etc., for photovoltaic power output prediction. Generation plan data: historical power generation, grid dispatching plan, etc. Load data: historical data of power load, hydrogenation load, and charging load.

[0006] Based on the historical data, construct the following prediction models: power load prediction model, hydrogenation load prediction model, charging load prediction model, photovoltaic power output prediction model, and grid dynamic carbon emission factor prediction model.

[0007] Based on the historical data, construct the following equipment models: energy storage equipment model and hydrogen production equipment model;

[0008] Taking the minimum carbon dioxide emissions of the park microgrid as the objective function, combined with the supply-demand balance constraint, establish an optimization model;

[0009] Use an optimization algorithm to solve the model to obtain a low-carbon operation plan.

[0010] The present invention also provides a park optical storage hydrogen charging collaborative optimization system based on dynamic carbon emission factors, and the system includes:

[0011] A data acquisition module for acquiring various historical data of the park microgrid;

[0012] A prediction model construction module for constructing a prediction model based on the historical data;

[0013] An equipment model construction module for constructing an equipment model based on the historical data;

[0014] An optimization model definition module for establishing an optimization model with the minimum carbon dioxide emission of the park microgrid as the objective function and combining the supply-demand balance constraint;

[0015] An optimization solution module for solving the model using an optimization algorithm to obtain a low-carbon operation plan.

[0016] Based on the above solution, the present invention provides a park optical storage hydrogen charging collaborative optimization method and system based on dynamic carbon emission factors. Considering the intra-day power dynamic carbon emission factors and aiming at the minimum carbon dioxide emission of the park microgrid, the optimal intra-day operation plans of various energy facilities are obtained under the condition that the photovoltaic system, energy storage system, hydrogen energy system and power consumption system meet the supply-demand balance and constraint conditions. Description of the Drawings

[0017] Figure 1 is a step flow chart of a park optical storage hydrogen charging collaborative optimization method of the present invention;

[0018] Figure 2 is a schematic diagram of the 24-hour dynamic emission factor coefficient of the power grid where the park is located in a specific embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of the 24-hour power load prediction curve of the park in a specific embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of the 24-hour hydrogen consumption load prediction curve of the park in a specific embodiment of the present invention;

[0021] Figure 5 is a schematic diagram of the 24-hour charging load prediction curve of the park in a specific embodiment of the present invention;

[0022] Figure 6 is a schematic diagram of the 24-hour photovoltaic output prediction curve of the park in a specific embodiment of the present invention;

[0023] Figure 7 is a schematic diagram of the 24-hour power supply plan of the park in a specific embodiment of the present invention;

[0024] Figure 8It is a schematic diagram of the 24-hour operation plan of the electrochemical energy storage equipment in the park of a specific embodiment of the present invention;

[0025] Figure 9 It is a schematic diagram of the 24-hour operation plan of the hydrogen production and hydrogenation equipment in the park of a specific embodiment of the present invention;

[0026] Figure 10 It is a schematic diagram of the comparison of the dynamic carbon emission factors between the park and the power grid in a specific embodiment of the present invention. Detailed implementation manner

[0027] In order to achieve the low-carbon operation of the park microgrid, the following is a detailed step framework covering the whole process from data acquisition to optimization solution.

[0028] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0029] It should be noted that for the convenience of description, only the parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0030] It should be understood that the "system", "device" and / or "module" used in the present application is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0031] As shown in the present application and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. An element defined by the statement "comprising one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

[0032] In addition, flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or after do not necessarily need to be executed precisely in order. On the contrary, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0033] Reference Figure 1 , which is a schematic flowchart of an optional example of the park optical storage hydrogen charging collaborative optimization method based on dynamic carbon emission factors proposed by the present invention. This method can be applied to computer devices. The optimization method proposed in this embodiment may include but is not limited to the following steps:

[0034] Step S1: Obtain the device information, meteorological data, and power generation plan data of the grid where the park microgrid is located to obtain historical data;

[0035] Step S2: Construct prediction models according to the historical data, including: power load prediction model, hydrogen refueling load prediction model, charging load prediction model, photovoltaic output prediction model, and grid dynamic carbon emission factor prediction model;

[0036] Step S3: Construct device models according to the historical data, including: energy storage device model and hydrogen production device model;

[0037] Step S4: Combine the models in Step S2 and Step S3, and establish an optimization model with the minimum carbon dioxide emissions of the park microgrid as the objective function under the constraint of the park's supply-demand balance;

[0038] Step S5: Optimize and solve the optimization model to obtain a low-carbon operation plan.

[0039] In some feasible embodiments, Step S1 specifically includes:

[0040] Data access. The telemetry and telecontrol parameter information of distributed photovoltaic power generation systems, energy storage systems, DC charging piles, AC charging piles, hydrogen production loads, various loads, and auxiliary equipment included in the park microgrid system can be directly accessed into the integrated low-carbon operation optimization system of optical storage hydrogen charging through the Internet of Things access service. Standard communication protocols such as Modbus, 104, 103, and 101 are supported. The system provides an external data interface, and external data such as meteorological data, historical power generation conditions of the grid where it is located, and daily power generation plans can be accessed through the API interface of the third-party platform.

[0041] In some feasible embodiments, it further includes:

[0042] Store the data accessed in Step S1 into the system database according to the configured information point numbers, including: various historical data such as device output, load power, meteorological data, and historical power generation conditions of the grid; meteorological data for a future period and grid daily power generation plan data; basic device parameters of photovoltaic, energy storage, charging piles, hydrogen production, etc.

[0043] In some feasible embodiments, Step S2 specifically includes:

[0044] Using the various historical data provided and the meteorological data for a period of time in the future as the input data for the prediction model, methods including but not limited to time series method, regression analysis method, machine learning method, deep learning method, etc. can be adopted to construct prediction models for the park's electricity load, hydrogenation load, charging load, photovoltaic power output, and grid dynamic carbon emission factor.

[0045] 1. Electricity Load Prediction Model

[0046] P power = f1(x1, θ1)

[0047] In the formula, x1 represents the input features of the electricity load prediction model f1; θ1 represents the model parameters of the electricity load prediction model f1; P power According to different time scales, it can be a set of electricity load prediction data for 24 hours a day (per hour), 96 moments a day (every 15 minutes), or divided by any duration.

[0048] 2. Hydrogenation Load Prediction Model

[0049] P hydrogen = f2(x2, θ2)

[0050] In the formula, x2 represents the input features of the hydrogenation load prediction model f2; θ2 represents the model parameters of the hydrogenation load prediction model f2; P hydrogen According to different time scales, it can be a set of hydrogenation load prediction data for 24 hours a day (per hour), 96 moments a day (every 15 minutes), or divided by any duration.

[0051] 3. Charging Load Prediction Model

[0052] P car = f3(x3, θ3)

[0053] In the formula, x3 represents the input features of the charging load prediction model f3, θ3 represents the model parameters of the charging load prediction model f3, P car According to different time scales, it can be a set of charging load prediction data for 24 hours a day (per hour), 96 moments a day (every 15 minutes), or divided by any duration.

[0054] 4. Photovoltaic Power Output Prediction Model

[0055] P solar = f4(x4, θ4)

[0056] In the formula, x4 represents the input features of the photovoltaic power output prediction model f4, θ4 represents the model parameters of the charging load prediction model f4, P solarDepending on the time scale, it can be a set of photovoltaic output forecast data for 24 hours a day (every hour), 96 moments a day (every 15 minutes) or divided by any time length.

[0057] 5. Dynamic carbon emission factor prediction model for power grid

[0058] Based on the historical power generation data of various types of power generation units in the power grid (such as renewable energy, thermal power, hydropower, nuclear power, etc.), combined with meteorological data (especially weather factors that have a greater impact on renewable energy), a deep learning model is used to predict the hourly power generation of the power grid in the future.

[0059] Specifically, the model combines convolutional neural networks (CNN), long short-term memory networks (LSTM), and attention mechanisms (Attention). First, the model processes time series data through the convolutional layers of the convolutional neural network (CNN) to extract local spatiotemporal features in the power generation data. The convolution operation can efficiently capture short-term fluctuations and local changes, especially in renewable energy power generation, where fluctuations in power generation are often closely related to factors such as weather changes, sunshine intensity, and wind speed. By stacking multiple layers of convolutional layers, the model can not only capture local patterns in the time series, but also identify key features in the data at different scales. The goal of this process is to effectively capture short-term trends and provide accurate local feature inputs for subsequent time series forecasts.

[0060] Subsequently, the model introduced the long short-term memory network (LSTM) to model the long-term dependencies in the time series. LSTM is good at processing time series data with long-term dependencies, and can mine long-term trend changes, seasonal fluctuations, and periodic patterns in the historical data of power generation. Through the gating mechanism of LSTM, the model can learn long-term memory, so that the model can more accurately grasp the dynamic trend and periodic characteristics of power generation, and improve the accuracy of prediction.

[0061] In order to further enhance the model's predictive ability, the attention mechanism is introduced into the model. The attention mechanism can dynamically give the model different attention to different time steps when processing time series data. Through this mechanism, the model can pay more attention to key time points (for example, periods of sudden changes in wind speed or periods of drastic temperature fluctuations), thereby improving the ability to capture important information. The attention mechanism not only enhances the interpretability of the model, but also further improves the model's robustness to uncertainty and noisy data, so that the model can still maintain a high prediction accuracy in a complex environment.

[0062] In summary, the model extracts local features through the convolutional layer, the LSTM network captures long-term dependencies, and then the information at critical moments is weighted through the attention mechanism, enabling the entire system to fully consider the short-term fluctuations and long-term trends of time series data when processing new energy power generation forecasts, and at the same time flexibly respond to those key influencing factors, thereby improving the accuracy and stability of the forecasts.

[0063] Next, according to the power generation ratios of various types of units and combined with the unit carbon emission coefficients, the dynamic carbon emission factors for every 15 minutes or every hour are calculated. This process provides precise support for the carbon emission management and energy dispatch of the power grid.

[0064] Dynamic carbon emission factor:

[0065]

[0066] In the formula, γ t represents the dynamic carbon emission factor of the power grid, the subscript i represents various types of power generation units in the power grid, P grid,i represents the predicted power generation of each type of unit every 15 minutes or every hour, and δ i represents the unit carbon emission coefficient of each type of unit.

[0067] In some feasible embodiments, step S3 specifically includes:

[0068] Based on the provided basic equipment parameters, relevant equipment models are constructed according to the characteristics of equipment such as energy storage and hydrogen production.

[0069] 1. Energy storage equipment model

[0070] The energy storage equipment includes two physical processes of charging and discharging. The charging and discharging processes cannot be carried out simultaneously, and the charge and discharge processes need to ensure that the SOC of the energy storage equipment remains within the set safe range.

[0071] Energy storage equipment charging model:

[0072] P charge = η c ·P in

[0073] In the formula, η c represents the charging efficiency, P in represents the input power, and P charge represents the actual charging power of the energy storage equipment.

[0074] Energy storage equipment discharge model:

[0075] P out = η d ·P discharge

[0076] In the formula, ηd Represents the discharge efficiency, P discharge Represents the discharge power, P out Represents the actual output power of the energy storage device.

[0077] The charging and discharging processes cannot be carried out simultaneously.

[0078] P charge ·P discharge =0

[0079] Energy storage device SOC model:

[0080]

[0081] SOC store,lower ≤SOC t+1 ≤SOC store,upper

[0082] In the formula, C store Represents the rated capacity of the energy storage device; t represents the charging and discharging duration; SOC t Represents the capacity ratio of the energy storage device at the current moment, SOC t+1 Represents the capacity ratio of the energy storage device at the next moment, SOC store,lower Represents the set lower limit of the energy storage device capacity ratio, SOC store,upper Represents the set upper limit of the energy storage device capacity ratio.

[0083] 2. Hydrogen production equipment model

[0084] The hydrogen production equipment includes different working conditions such as direct hydrogen production and hydrogenation, hydrogen production and hydrogen storage, and hydrogenation from storage tanks. Only one operating condition can be adopted at the same time.

[0085] Hydrogen production and hydrogenation model

[0086] P hydrogen,inject =P hydrogen,produce

[0087] P produce,power =α·P hydrogen,produce

[0088] In the formula, P hydrogen,produce Is the hydrogen production rate, equal to the hydrogenation rate P hydrogen,inject ; α is the unit hydrogen production power consumption; P produce,power Is the hydrogen production power load.

[0089] Hydrogen production and hydrogen storage model

[0090] P hydrogen,store =P hydrogen,produce

[0091] P store,power =β·P hydrogen,produce

[0092] In the formula, P hydrogen,store is the hydrogen storage rate, which is equal to the hydrogen production rate P hydrogen,produce ; β is the electricity consumption per unit hydrogen storage, which is used to compress hydrogen into the storage tank; P store,power is the electricity load for hydrogen storage.

[0093] Hydrogen tank hydrogenation model

[0094] P hydrogen = P hydrogen,exhaust

[0095] In the formula, P hydrogen,exhaust is the hydrogen release rate, which is equal to the hydrogenation load P hydrogen .

[0096] Hydrogen storage tank SOC model

[0097] During the hydrogen storage and release process, it is necessary to ensure that the SOC of the storage tank remains within the set safe range.

[0098]

[0099]

[0100] In the formula, represents the rated capacity of the hydrogen storage tank; t represents the duration of hydrogen storage and release; represents the capacity ratio of the hydrogen storage tank at the current moment, represents the capacity ratio of the hydrogen storage tank at the next moment, represents the lower limit of the set capacity ratio of the hydrogen storage tank, represents the upper limit of the set capacity ratio of the hydrogen storage tank.

[0101] Because only one of the different working conditions such as hydrogen production and hydrogenation, hydrogen production and hydrogen storage, and tank hydrogenation can exist at the same time, so

[0102] P hydrogen,inject ·P hydrogen,store = 0

[0103] P hydrogen,store ·P hydrogen,exhaust = 0

[0104] P hydrogen,produce ·P hydrogen,exhaust = 0

[0105] In some feasible embodiments, step S4 specifically includes:

[0106] Power supply and demand balance constraint in the park:

[0107] P grid + P solar + P out = Ppower +P car +P in +P produce,power +P store,power

[0108] Hydrogen supply - demand balance constraint in the park:

[0109] P hydrogen =P hydrogen,inject +P hydrogen,exhaust

[0110] Objective function:

[0111]

[0112] In the formula, γ t represents the data of the dynamic carbon emission factor of electricity in the region where it is located; P grid,t represents the electricity consumption of the park microgrid at each time period from the main grid.

[0113] In some feasible embodiments, step S5 specifically includes:

[0114] Call a solver to perform optimization and solution to obtain a low - carbon operation plan for the integrated cooperation of photovoltaic - energy storage - hydrogen - charging. The solver includes but is not limited to Gurobi, CPLEX, MindOpt, etc.

[0115] In some feasible embodiments, it further includes:

[0116] Send the low - carbon operation plan for the integrated cooperation of photovoltaic - energy storage - hydrogen - charging output from the optimization model in step S5 to relevant energy equipment through standard communication protocols such as Modbus, 104, 103, 101, etc. At the same time, the real - time operation data of the equipment is also fed back to the data access in step S1 through the Internet of Things access service, so as to realize the rolling correction of the operation plan within a day.

[0117] Based on the above - mentioned solution, the present invention also gives relevant data examples:

[0118] Taking the operation optimization of a certain park microgrid as an example, the information of relevant energy equipment for "photovoltaic - energy storage - hydrogen - charging" in the park is as follows:

[0119] Table 1 Park energy facility information

[0120]

[0121]

[0122] Under the condition that the photovoltaic system, energy storage system, hydrogen energy system, and power consumption system meet the supply-demand balance and constraint conditions, considering the intra-day power dynamic carbon emission factor, with the goal of minimizing the carbon dioxide emissions of the campus microgrid, the optimal intra-day operation plan of each energy facility is obtained. In this embodiment, taking the hourly operation optimization of the equipment as an example, the 24-hour "photovoltaic-storage-hydrogen-charging" integrated collaborative low-carbon operation plan for the whole day is obtained. The specific steps are as follows:

[0123] According to the historical power generation data of the power grid and combined with characteristic data such as future meteorological data, call the system prediction model to obtain the dynamic emission factor coefficients of the power grid where the campus is located for 24 hours, as Figure 2 shown.

[0124] According to the historical operation data of the campus and combined with characteristic data such as future meteorological data, call the system prediction model to obtain the 24-hour campus power load prediction, hydrogen consumption load prediction, charging load prediction, and photovoltaic power output prediction curves, as Figures 3 - 6 shown.

[0125] Input the relevant technical parameters in Table 1 into the equipment models such as the electrochemical energy storage and hydrogen production and hydrogenation integrated machine built in the system. With the supply-demand balance of campus power consumption and hydrogen consumption as the constraint condition, establish an optimization model with the minimum carbon dioxide emissions of the campus microgrid as the objective function. Call the solver for optimization to obtain the 24-hour "photovoltaic-storage-hydrogen-charging" integrated collaborative low-carbon operation plan for the whole day, as Figure 7 shown.

[0126] Among them, the 24-hour operation plan of the electrochemical energy storage equipment is as Figure 8 shown. Compared with the traditional peak-valley arbitrage operation mode, the optimized energy storage equipment operates more flexibly. On the one hand, it is used to smooth the internal power consumption fluctuations of the campus. On the other hand, it charges during the low-carbon period of the power grid and discharges during the high-carbon period, so as to achieve carbon emission reduction in the campus.

[0127] The 24-hour operation plan of the hydrogen production and hydrogenation integrated equipment is as Figure 9 shown. According to the dynamic carbon emission factor of the power grid and the hydrogen consumption demand of the campus, it flexibly switches among different working conditions such as hydrogen production and hydrogenation, hydrogen production and storage, and tank hydrogenation.

[0128] Finally, compare the dynamic carbon emission factor of the power grid and the actual carbon emission factor of the campus. From Figure 10 it can be seen that the "photovoltaic-storage-hydrogen-charging" integration at the campus level collaboratively considers the changes in the intra-day power carbon emission factor and optimizes the operation plan of energy facilities, which can effectively reduce carbon dioxide emissions, and the daily emission reduction reaches 4657.40 kg.

[0129] A campus photovoltaic-storage-hydrogen-charging collaborative optimization system based on dynamic carbon emission factors includes:

[0130] A data acquisition module that acquires device information, meteorological data, and power generation plan data of the grid where the park microgrid is located to obtain historical data;

[0131] A prediction model construction module that constructs prediction models based on historical data, including: a power load prediction model, a hydrogen refueling load prediction model, a charging load prediction model, a photovoltaic output prediction model, and a grid dynamic carbon emission factor prediction model;

[0132] A device model construction module that constructs device models based on historical data, including: an energy storage device model and a hydrogen production device model;

[0133] An optimization model definition module that establishes an optimization model with the minimum carbon dioxide emissions of the park microgrid as the objective function under the constraint of the park's supply-demand balance;

[0134] An optimization solution module that optimally solves the optimization model to obtain a low-carbon operation plan.

[0135] The content in the above method embodiments is applicable to the present system embodiment. The functions specifically implemented by the present system embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0136] A park optical storage hydrogen charging collaborative optimization device based on dynamic carbon emission factors:

[0137] At least one processor;

[0138] At least one memory for storing at least one program;

[0139] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned park optical storage hydrogen charging collaborative optimization method based on dynamic carbon emission factors.

[0140] The content in the above method embodiments is applicable to the present device embodiment. The functions specifically implemented by the present device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0141] A storage medium storing instructions executable by a processor, where the instructions executable by the processor are used to implement the above-mentioned park optical storage hydrogen charging collaborative optimization method based on dynamic carbon emission factors when executed by the processor.

[0142] The content in the above method embodiments is applicable to the present storage medium embodiment. The functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0143] The above is a specific description of the preferred embodiment of the present invention. However, the present invention is not limited to the described embodiment. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A collaborative optimization method for park optical storage hydrogen charging based on dynamic carbon emission factors, characterized in that It includes the following steps: Obtain the device information, meteorological data of the park microgrid, and the power generation plan data of the grid where it is located to obtain historical data; Construct a power load prediction model, a hydrogenation load prediction model, a charging load prediction model, a photovoltaic power output prediction model, and a grid dynamic carbon emission factor prediction model according to the historical data; Construct a energy storage device model and a hydrogen production device model according to the historical data; Combining the power load prediction model, the hydrogenation load prediction model, the charging load prediction model, the photovoltaic power output prediction model, the grid dynamic carbon emission factor prediction model, the energy storage device model, and the hydrogen production device model, with the balance of supply and demand in the park as the constraint condition, establish an optimization model with the minimum carbon dioxide emissions of the park microgrid as the objective function; Optimize and solve the optimization model to obtain a low-carbon operation plan.

2. The collaborative optimization method for park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 1, characterized in that, The expression of the dynamic emission factor is as follows: Among them, γ t represents the dynamic carbon emission factor of the power grid, and the subscript i represents various types of generating units in the power grid. P grid,i represents the predicted power generation of each type of unit every 15 minutes or every hour, and δ i represents the unit carbon emission coefficient of each type of unit.

3. The collaborative optimization method for park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 2, wherein, The energy storage device model includes: Energy storage device charging model: P charge = η c · P in where η c represents the charging efficiency, P in represents the input power, and P charge represents the actual charging power of the energy storage device; Energy storage device discharging model: P out = η d ·P discharge where η d represents the discharge efficiency, P discharge represents the discharge power, P out represents the actual output power of the energy storage device; Energy storage device SOC model: SOC store,lower ≤SOC t+1 ≤SOC store,upper Where, C store represents the rated capacity of the energy storage device; t represents the charge and discharge duration; SOC t represents the capacity ratio of the energy storage device at the current moment, SOC t+1 represents the capacity ratio of the energy storage device at the next moment, SOC store,lower represents the lower limit of the set capacity ratio of the energy storage device, SOC store,upper represents the upper limit of the set capacity ratio of the energy storage device.

4. The collaborative optimization method of park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 2, wherein The hydrogen production device model includes: Hydrogen production and hydrogenation model: P hydrogen,inject = P hydrogen,produce P produce,power = α · P hydrogen,produce Wherein, P hydrogen,produce is the hydrogen production rate, equal to the hydrogenation rate P hydrogen,inject ; α is the unit power consumption for hydrogen production; P produce,power is the electricity load for hydrogen production; Hydrogen production and hydrogen storage model: P hydrogen,store = P hydrogen,produce P store,power = β · P hydrogen,produce Wherein, P hydrogen,store is the hydrogen storage rate, equal to the hydrogen production rate P hydrogen,produce ; β is the specific electricity consumption for hydrogen storage, used for compressing hydrogen into the storage tank; P store,power is the electricity load for hydrogen storage; Hydrogen tank hydrogenation model: P hydrogen = P hydrogen,exhaust Wherein, P hydrogen,exhaust is the hydrogen release rate, which is equal to the hydrogenation load P hydrogen ; Hydrogen storage tank SOC model: Wherein, represents the rated capacity of the hydrogen storage tank; t represents the duration of hydrogen storage and release; represents the capacity ratio of the hydrogen storage tank at the current moment, represents the capacity ratio of the hydrogen storage tank at the next moment, represents the lower limit of the set capacity ratio of the hydrogen storage tank, represents the upper limit of the set capacity ratio of the hydrogen storage tank.

5. The collaborative optimization method for park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 4, wherein The optimization model is expressed as follows: Park electricity supply and demand balance constraint: P grid +P solar +P out =P power +P car +P in +P produce,power +P store,power ; Park hydrogen supply and demand balance constraint: P hydrogen = P hydrogen,inject + P hydrogen,exhaust ; Objective function: Min(∑ t γ t ·P grid,t ); Among them, γ t represents the data of the dynamic carbon emission factor of electricity in the region where it is located; P grid,t represents the electricity consumption of the park microgrid from the main grid in each period.

6. The collaborative optimization method for park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 1, characterized in that The specific steps for constructing the grid dynamic carbon emission factor prediction model are as follows: Based on the power generation data of various types of generating units in the historical data, combined with meteorological data, use a deep learning model to predict the hourly power generation of the grid in the future preset time to obtain the predicted power generation of each type of unit; According to the predicted power generation of each type of unit, combined with the unit carbon emission coefficient, calculate the dynamic carbon emission factor.

7. The method for collaborative optimization of park optical storage hydrogen charging based on dynamic carbon emission factors according to claim 6, wherein The deep model includes a convolutional neural network, a long short-term memory network, and an attention mechanism, where: Process the time series data through the convolutional layer of the convolutional neural network to extract the local spatio-temporal features in the power generation data; Introduce the long short-term memory network to model the long-term dependence relationship in the time series; Weight the information of the moment based on the attention mechanism.

8. A park optical storage hydrogen charging collaborative optimization system based on dynamic carbon emission factors, characterized in that, It includes: A data acquisition module for obtaining the device information, meteorological data, and power generation plan data of the park microgrid to obtain historical data; A prediction model construction module for constructing a power load prediction model, a hydrogenation load prediction model, a charging load prediction model, a photovoltaic power output prediction model, and a grid dynamic carbon emission factor prediction model according to the historical data; A device model construction module for constructing an energy storage device model and a hydrogen production device model according to the historical data; An optimization model definition module for combining the power load prediction model, the hydrogenation load prediction model, the charging load prediction model, the photovoltaic power output prediction model, the grid dynamic carbon emission factor prediction model, the energy storage device model, and the hydrogen production device model, with the balance of supply and demand in the park as the constraint condition, establish an optimization model with the minimum carbon dioxide emissions of the park microgrid as the objective function; An optimization solution module for optimizing and solving the optimization model to obtain a low-carbon operation plan.

Images