Coordinated and optimized operation system of electro-hydrogen system

Abstract

The invention relates to the technical field of electric hydrogen system coordination, and provides an electric hydrogen system coordination optimization operation system. The energy input module receives input hydrogen energy and converts the hydrogen energy into electric energy; the energy storage and output module can store energy from the energy input module, and supports electric energy scheduling, electric energy hydrogen production storage and conversion of hydrogen into electric energy for output; the monitoring management module monitors the energy input module and the energy storage and output module in real time and collects power utilization feedback and energy supply feedback; the optimal scheduling module generates a scheduling strategy according to the electricity demand and the energy supply condition; the scheduling strategy is transmitted to the energy storage and output module, and the energy storage and output module adjusts electric energy storage and output according to the scheduling strategy; cooperative cooperation among various energy sources is achieved through the energy input module and the energy storage and output module, the scheduling strategy is generated by the optimization scheduling module, the scheduling unit accurately controls the energy storage and output module to carry out power supply distribution according to the scheduling strategy, and continuity and stability of power supply are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electric-hydrogen system coordination, and in particular to an electric-hydrogen system coordinated optimization operation system. Background Art

[0002] As the world pays more and more attention to environmental protection and sustainable development, traditional fossil energy faces severe challenges such as resource depletion and environmental pollution. Therefore, it is imperative to find clean, efficient and renewable energy alternatives. Hydrogen energy, as a zero-carbon emission energy carrier, has great potential.

[0003] The coordinated optimization operation system of the electric-hydrogen system can convert electricity into hydrogen energy for storage when there is excess renewable energy generation, thus achieving efficient use of excess electricity and promoting the consumption of renewable energy. When the grid load demand is large and renewable energy generation is insufficient, the stored hydrogen energy can be converted into electricity and fed into the grid, thus smoothing out the fluctuations of renewable energy and improving the stability of grid operation.

[0004] At the same time, the extensive use of traditional fossil energy has brought serious environmental problems, and energy transformation is imminent. The coordinated and optimized operation system of the electric hydrogen system uses hydrogen as an energy carrier. The only product of hydrogen combustion is water, which is a zero-carbon energy. The system helps to reduce dependence on traditional fossil energy, reduce carbon emissions, and promote clean and sustainable energy. At the same time, by coupling with other energy systems, multi-energy complementarity is achieved, further improving the reliability of the energy system.

[0005] However, the prior art still has the following shortcomings:

[0006] 1. At present, the electric hydrogen system has obvious deficiencies in the coordination and cooperation with other energy sources. The correlation between them is not strong, and effective complementarity and integration cannot be formed. For example, the integration degree of hydrogen energy with renewable energy such as solar energy and wind energy is low, and their respective advantages cannot be fully utilized, resulting in limited energy utilization efficiency.

[0007] 2. The existing electric-hydrogen system does not coordinate closely enough, and the conversion and scheduling strategies between electricity and hydrogen are not flexible enough. When dealing with complex and changeable electricity consumption scenarios and energy supply conditions, it is impossible to accurately and quickly adjust the scheduling strategies according to actual conditions. For example, it is difficult to make timely and effective responses to sudden peak electricity consumption or fluctuations in energy supply.

[0008] 3. The system has defects in feedback and cannot obtain the actual electricity demand and energy supply in real time and accurately; for example, when there are drastic changes in electricity demand seasonally or periodically, the system cannot perceive it in time and make corresponding adjustments, resulting in a large deviation between the power supply and demand of the electric hydrogen system, affecting the stability and reliability of energy supply. Summary of the invention

[0009] The present invention provides an electric hydrogen system coordinated optimization operation system to solve the problems in the prior art.

[0010] The technical solution of the present invention is as follows:

[0011] A coordinated and optimized operation system for an electric-hydrogen system, comprising:

[0012] An energy input module, wherein the energy input module receives input energy and converts it into electrical energy;

[0013] An energy storage and output module, which is used to store energy from the energy input module and support electric energy dispatching, electric energy hydrogen production storage, and conversion of hydrogen into electric energy output;

[0014] A monitoring and management module, which monitors the input, storage and output of energy of the energy input module and the energy storage and output module in real time and collects power consumption feedback and energy supply feedback;

[0015] The optimization scheduling module is used to generate a scheduling strategy according to the power demand and energy supply situation; and transmit the scheduling strategy to the energy storage and output module, and the energy storage and output module adjusts the power storage and output according to the scheduling strategy.

[0016] Preferably, the energy input module inputs energy types including but not limited to hydrogen energy, wind energy and solar energy, which are converted into electrical energy through relevant electrical energy conversion equipment;

[0017] Preferably, the energy storage and output module includes an energy storage unit and an output unit;

[0018] The energy storage unit can store electrical energy as hydrogen energy through water electrolysis when there is excess electrical energy. The energy storage methods include but are not limited to compressed hydrogen storage tanks for long-term storage and large-scale application, liquid hydrogen storage tanks for low-temperature environments and high-density storage, and solid hydrogen materials for portable transportation and transfer;

[0019] The output unit is used to convert hydrogen into electrical energy for output when there is a shortage of electricity, and can arrange other energy sources for direct output and adjust the output time and output amount according to the scheduling strategy.

[0020] Preferably, the monitoring management module includes a monitoring unit and a feedback unit;

[0021] The monitoring unit monitors the input, output, storage and equipment operation status of the system energy in real time, and predicts the power demand based on the feedback information collected by the feedback unit;

[0022] The feedback unit is used to collect electricity demand feedback and energy input feedback.

[0023] Preferably, the monitoring unit predicts the electricity demand; through the electricity demand feedback, the curve of the electricity demand following the time relationship is calculated in combination with the time series, and the electricity demand and energy input are predicted using the curve smoothing coefficient: the relationship formula of the curve smoothing coefficient is as follows:

[0024] D t+1 =αS t +(1-α)D t

[0025] Among them, t represents a certain period of time, S t represents the power demand value at time t, D t represents the predicted value of electricity consumption at time t, D t+1 It represents the power consumption forecast value in the t+1th time period, α represents the smoothing coefficient. When calculating, the forecast value is first replaced by the actual power demand value to calculate the initial smoothing coefficient α, and then the forecast value and the actual power demand value are used to optimize and correct the smoothing coefficient in combination with the real-time data. When the smoothing coefficient correction optimization no longer changes, the smoothing coefficient is specified and the power consumption forecast value D is calculated. t .

[0026] Preferably, the feedback unit generates an input interface, and relevant staff can input electricity demand feedback and energy input feedback status through the input interface. The electricity demand feedback includes electricity consumption, expected electricity cost and electricity efficiency; the energy input feedback includes power generation, power generation cost and power generation efficiency.

[0027] Preferably, the optimization scheduling module includes a strategy generation unit, a scheduling unit and an optimization unit;

[0028] The strategy generation unit is used to generate a scheduling strategy according to the power demand;

[0029] The dispatching unit is used to control the energy storage and output modules to distribute power according to the dispatching strategy;

[0030] The optimization unit is used to continuously optimize the scheduling strategy based on electricity demand feedback.

[0031] Preferably, the strategy generation unit first generates a scheduling strategy using a random generator, and the solution of the scheduling strategy is set to function F, which is expressed as the scheduling decision optimization value within a specified time t. The function F is expressed as:

[0032]

[0033] Among them, factors affecting function F include but are not limited to energy supply ratio, cost and power generation efficiency;

[0034] P ht P represents the energy supply ratio of hydrogen power generation h within time t; otIt represents the energy supply ratio of other energy sources o at time t, where other energy sources o include solar energy or wind energy;

[0035] C ht represents the unit cost of hydrogen power generation h in time t; C ot represents the unit cost of other energy o at time t;

[0036] B ht represents the efficiency of using hydrogen energy to generate electricity h at time t; B ot represents the efficiency of using other energy o at time t;

[0037] Item 1:

[0038]

[0039] It is used to measure the matching degree between energy supply and electricity demand. The smaller the value, the better the matching.

[0040] Item 2:

[0041]

[0042] It represents the total cost of hydrogen power generation and other energy power generation consumption;

[0043] Item 3:

[0044]

[0045] Represents the total efficiency loss of hydrogen power generation and other energy power generation; this value means the degree of deviation between the actual operating efficiency and the ideal high-efficiency state under the current scheduling strategy, and measures the gap between the actual energy supply and the ideal high-efficiency state;

[0046] After the above scheduling strategy is generated, because the randomness of the random generator determines that the initial solution is uncertain, it is impossible to determine that this scheduling strategy is optimal. Therefore, in the same time period t, a new scheduling strategy is randomly generated to obtain the solution of the new scheduling strategy: function F';

[0047] Calculate the difference ΔF between F and F', ΔF = F'-F. When ΔF is greater than 0, accept the new scheduling strategy with the solution F' as the current scheduling strategy and update the current function F to F'. When ΔF is less than or equal to 0, calculate the probability It means that F' is updated to F with probability Q. The role of probability Q is to avoid falling into the local optimal solution during the calculation process. Among them, e is a natural constant, and Z is the current control parameter, which is a constant;

[0048] Set the initial control parameter to 1000 and the final control parameter to 0.01. The initial control parameter and the final control parameter can be corrected and optimized according to the optimization unit. After selecting the new scheduling strategy, adjust the number of iterative calculations of the scheduling strategy according to the formula Z' = aZ. The value of the control parameter determines the number of iterative calculations for the optimal solution, where a is the control coefficient that determines the reduction speed of the control parameter. The larger the control coefficient, the slower the reduction speed, and the more iterative calculations for the scheduling strategy. The value range of the control coefficient is 0 < a < 1. When a ≥ 1, the control parameter will increase or remain unchanged in each iteration and cannot reach the final control parameter. When a < 0, the new control parameter will be non-positive or zero, resulting in abnormal calculation because the control parameter cannot be negative or zero; Z' is the control parameter for the next iterative calculation.

[0049] During the continuous iterative calculation, when the control parameter Z' for the next iterative calculation is less than or equal to the final control parameter 0.01, the iterative calculation ends, and the current scheduling strategy is output as the optimal scheduling strategy. Otherwise, continue to calculate the new solution.

[0050] During the continuous calculation, when the control parameter Z' for the next iterative calculation is less than or equal to the final control parameter 0.01, the calculation ends, and the current scheduling strategy is output as the optimal scheduling strategy. Otherwise, continue to calculate the new solution.

[0051] Preferably, the optimization unit optimizes the scheduling strategy according to the power consumption feedback.

[0052] Introduce weight coefficients, the weight coefficient w of the energy supply ratio matching value p , the weight coefficient w of the cost C , and the weight coefficient w of the efficiency loss B ; that is, the function F after introducing the weight coefficient w is:

[0053]

[0054] Introduce weight coefficients to adjust the importance of different factors in the scheduling strategy according to the power consumption feedback. According to the comparison between the solution result and the actual situation, adjust the weight coefficients to optimize the scheduling strategy.

[0055] If the power consumption area has a high requirement for the stability of energy supply, the energy supply ratio matching value is particularly important, and the value of w p can be appropriately increased;

[0056] If the energy cost has a great impact on the economy of the power consumption area, such as areas with concentrated high-energy-consuming industries, the value of w C can be appropriately increased;

[0057] If the region has higher requirements for energy efficiency, such as strict environmental protection policies or energy is scarce in the region, w can be appropriately increased. B The value of .

[0058] If it is found in actual situation that a certain item does not meet the expected value, the weight coefficient of the corresponding item is appropriately adjusted to adjust the scheduling strategy; for adjusting the initial control parameters and the final control parameters, the average optimization effect is calculated based on the actual results of multiple tests and historical data, and the value of the control parameter is gradually adjusted according to the expected degree of the effect.

[0059] Compared with the prior art, the present invention has the following beneficial effects:

[0060] 1. The present invention realizes the diversification of energy input and scheduling through energy input modules and energy storage and output modules, and the coordinated use of multiple energy sources. Through the complementarity of hydrogen energy and other energy sources, the reliability and economy of the entire energy system are improved; in the case of energy shortage or instability, hydrogen energy can be used as a reliable backup energy source to ensure the stability and continuity of power supply, reduce energy waste, and improve energy utilization.

[0061] 2. The present invention realizes intelligent and automated energy scheduling and management by optimizing the scheduling module. The strategy generation unit can quickly generate scheduling strategies according to power demand, and the scheduling unit accurately controls the energy storage and output modules to distribute power according to these strategies, ensuring the continuity and stability of power supply. At the same time, the optimization unit continuously optimizes the scheduling strategy through continuous feedback of power demand, so that the scheduling strategy generated by the entire system can continuously approach the optimal, continuously improve the accuracy and adaptability of the system, and provide a guarantee for power supply capacity.

[0062] 3. The present invention realizes real-time monitoring, prediction and feedback collection of energy through the monitoring management module. By collecting and analyzing various energy data, including but not limited to real-time electricity demand, energy supply conditions, equipment operating status, etc., it provides data support for the optimization scheduling module, so that the scheduling strategy is more in line with the actual situation, and the scheduling efficiency and energy utilization rate of the system are improved. The feedback unit optimizes and fine-tunes the scheduling strategy through real-time feedback from users to ensure satisfaction with the power supply service. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a work flow chart of the present invention.

[0064] Figure 2 It is a flow chart of scheduling strategy generation of the present invention. DETAILED DESCRIPTION

[0065] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0066] like Figure 1-2 As shown, the present invention provides a coordinated optimization operation system for an electric hydrogen system, comprising:

[0067] An energy input module, wherein the energy input module receives input energy and converts it into electrical energy;

[0068] An energy storage and output module, which is used to store energy from the energy input module and support electric energy dispatching, electric energy hydrogen production storage, and conversion of hydrogen into electric energy output;

[0069] A monitoring and management module, which monitors the input, storage and output of energy of the energy input module and the energy storage and output module in real time and collects power consumption feedback and energy supply feedback;

[0070] The optimization scheduling module is used to generate a scheduling strategy according to the power demand and energy supply situation; and transmit the scheduling strategy to the energy storage and output module, and the energy storage and output module adjusts the power storage and output according to the scheduling strategy.

[0071] Example: In this example, in a remote area, due to geographical limitations, the connection with the main power grid is relatively weak, but a large number of wind power generation equipment and photovoltaic power generation equipment are installed to meet the electricity needs of residents. However, the intermittent nature of renewable energy makes the power supply unstable, and the electric hydrogen system needs to coordinate and optimize operation to complete the stable power supply to the power-consuming areas.

[0072] The coordinated and optimized operation system of the electric-hydrogen system uses the energy input module to obtain hydrogen energy and convert it into electrical energy, and supports energy such as solar energy or wind energy as auxiliary energy;

[0073] The energy storage and output module includes an energy storage unit and an output unit;

[0074] The energy storage unit can store electricity as hydrogen energy through water electrolysis when there is excess electricity generated by wind or solar energy. The energy storage methods include compressed hydrogen storage tanks and liquid hydrogen storage tanks.

[0075] The output unit can convert hydrogen into electrical energy for output when there is a shortage of electricity generated by solar and wind energy, and can arrange other energy sources for direct output and adjust the output time and output amount according to the scheduling strategy.

[0076] The energy input module and the energy storage and output modules realize the diversification of energy input and scheduling, and the coordinated use of multiple energy sources. The complementarity of hydrogen energy with other energy sources improves the reliability and economy of the entire energy system. In the case of energy shortage or instability, hydrogen energy can be used as a reliable backup energy source to ensure the stability and continuity of power supply.

[0077] The monitoring management module includes a monitoring unit and a feedback unit;

[0078] The monitoring unit monitors the input, output, storage and equipment operation status of the system energy in real time, and predicts the power demand based on the feedback information collected by the feedback unit;

[0079] The feedback unit generates an input interface to receive feedback on power demand values ​​from power consumption areas;

[0080] The monitoring unit predicts the power demand value; through the power demand feedback, combined with the time series, the curve of the power demand following the time relationship is calculated. The time series refers to a series of data points arranged in chronological order, and the data point is the power demand value at each time point.

[0081] The curve smoothing coefficient is used to predict the electricity demand. The relationship of the curve smoothing coefficient is as follows:

[0082] D t+1 =αS t +(1-α)D t

[0083] Among them, t represents a certain period of time, S t represents the power demand value at time t, D t represents the predicted value of electricity consumption at time t, D t+1 It represents the power consumption forecast value in the t+1th time period, α represents the smoothing coefficient. When calculating, the forecast value is first replaced by the actual power demand value to calculate the initial smoothing coefficient α, and then the forecast value and the actual power demand value are used to optimize and correct the smoothing coefficient in combination with the real-time data. When the smoothing coefficient correction optimization no longer changes, the smoothing coefficient is specified and the power consumption forecast value D is calculated. t .

[0084] Energy monitoring and prediction are achieved through the monitoring and management module. By collecting various energy data such as real-time electricity demand and energy supply, electricity demand is predicted, providing data support for the optimization scheduling module, making the scheduling strategy more in line with the actual situation and improving the system's scheduling efficiency and energy utilization.

[0085] After calculating the predicted electricity consumption value for this area, this system supplies electricity to a certain area. The optimization scheduling module generates a scheduling strategy. The optimization unit optimizes the scheduling strategy algorithm in real time to complete the conversion scheduling between electricity and hydrogen energy, and realize the coordinated optimization operation of the electric-hydrogen system for the electricity consumption in this area.

[0086] Among them, the optimization scheduling module includes a strategy generation unit, a scheduling unit and an optimization unit;

[0087] The strategy generation unit is used to generate a scheduling strategy according to the power demand;

[0088] The dispatching unit is used to control the energy storage and output modules to distribute power according to the dispatching strategy;

[0089] The optimization unit is used to continuously optimize the scheduling strategy based on electricity demand feedback.

[0090] The strategy generation unit first generates a scheduling strategy using a random generator. The solution of the scheduling strategy is set to function F, which is expressed as the optimal value of the scheduling strategy within the specified time t. Function F is expressed as:

[0091]

[0092] Among them, factors affecting function F include but are not limited to energy supply ratio, cost and power generation efficiency;

[0093] P ht P represents the energy supply ratio of hydrogen power generation h within time t; ot It represents the energy supply ratio of other energy sources o at time t, where other energy sources o include solar energy or wind energy;

[0094] C ht represents the unit cost of hydrogen power generation h in time t; C ot represents the unit cost of other energy o at time t;

[0095] B ht represents the efficiency of using hydrogen energy to generate electricity h at time t; B ot represents the efficiency of using other energy o at time t;

[0096] Item 1:

[0097]

[0098] It is used to measure the matching degree between energy supply and electricity demand. The smaller the value, the better the matching.

[0099] Item 2:

[0100]

[0101] It represents the total cost of hydrogen power generation and other energy power generation consumption;

[0102] Item 3:

[0103]

[0104] Indicates the total efficiency loss of hydrogen energy power generation and other energy power generation;

[0105] After the above scheduling strategy is generated, due to the randomness of the random generator, the initial solution has uncertainty and it is impossible to determine that this scheduling strategy is optimal. Therefore, within the same time period t, a new scheduling strategy is randomly generated to obtain the solution of the new scheduling strategy: function F';

[0106] Calculate the difference ΔF between F and F', ΔF = F' - F. When ΔF is greater than 0, then accept the new scheduling strategy with the solution F' as the current scheduling strategy and update the current function F to F'; when ΔF is less than or equal to 0, then calculate the probability Indicates that there is a probability Q for F' to be updated to F. The role of probability Q is to avoid falling into a local optimal solution during the calculation process. Among them, e is the natural constant and Z is the current control parameter, which is a constant;

[0107] Set the initial control parameter to 1000 and the final control parameter to 0.01. The initial control parameter and the final control parameter can be corrected and optimized according to the optimization unit. After selecting the new scheduling strategy, adjust the iteration calculation times of the scheduling strategy according to the formula Z' = aZ. The value of the control parameter determines the iteration calculation times of the optimal solution. Among them, a is the control coefficient, which determines the reduction speed of the control parameter. The larger the control coefficient, the slower the reduction speed and the more iteration calculation times of the scheduling strategy. The value range of the control coefficient is 0 < a < 1. When a ≥ 1, the control parameter will increase or remain unchanged in each iteration and cannot reach the final control parameter. When a < 0, the new control parameter will be non-positive or zero, resulting in abnormal calculation because the control parameter cannot be negative or zero; Z' is the control parameter for the next iteration calculation;

[0108] During the continuous iteration calculation, when the control parameter Z' for the next iteration calculation is less than or equal to the final control parameter 0.01, the iteration calculation ends and the current scheduling strategy is output as the optimal scheduling strategy. Otherwise, continue to calculate the new solution.

[0109] Select a control coefficient close to 0 when the calculation data volume is large, and select a control coefficient close to 1 when the calculation data volume is small.

[0110] During the continuous calculation process, when the control parameter Z' for the next iteration calculation is less than or equal to the final control parameter 0.01, the calculation ends and the current scheduling strategy is output as the optimal scheduling strategy. Otherwise, continue to calculate the new solution.

[0111] The optimization unit optimizes the scheduling strategy based on the power consumption feedback;

[0112] Introduce weight coefficient, energy supply ratio matching value weight coefficient w p , cost weight coefficient w C , efficiency loss weight coefficient w B ; That is, the function F that introduces the weight coefficient after optimization w for:

[0113]

[0114] In this embodiment, the proportion of hydrogen power supply per unit time is used to measure the scheduling strategy. In actual calculations, different factors affecting the scheduling strategy also include the proportion of power generation resources, power grid status, energy storage equipment information, power quality information, economic and policy information, etc. By introducing weight coefficients, the importance of different factors in the scheduling strategy is adjusted according to power consumption feedback. According to the comparison between the solution results and the actual situation, the weight coefficients are adjusted through the judgment of power personnel to further optimize the scheduling strategy;

[0115] If it is found in actual situation that a certain item does not meet the expected value, the weight coefficient of the corresponding item is appropriately adjusted to adjust the scheduling strategy; for adjusting the initial control parameters and the final control parameters, the average optimization effect is calculated based on the actual results of multiple tests and historical data, and the value of the control parameter is gradually adjusted according to the expected degree of the effect.

[0116] Intelligent and automated energy dispatch and management are achieved through the optimization dispatch module. The strategy generation unit can quickly generate dispatch strategies according to electricity demand. The dispatch unit accurately controls the proportion of hydrogen power supply in the energy storage and output modules based on these strategies. When there is excess wind or solar power generation, it is converted into hydrogen energy for storage. When there is insufficient solar and wind power generation, the stored hydrogen energy is converted into electricity for output, completing the coordination of the electric hydrogen system and ensuring the continuity and stability of power supply. At the same time, the optimization unit continuously optimizes the dispatch strategy through continuous feedback on electricity demand, so that the dispatch strategy generated by the entire system can continue to approach the optimal. The accuracy and adaptability of the system are continuously improved, providing a guarantee for power supply capacity.

[0117] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A coordinated optimization operation system for an electric hydrogen system, characterized in that: include: An energy input module, wherein the energy input module receives input energy and converts it into electrical energy; An energy storage and output module, which is used to store energy from the energy input module and support electric energy dispatching, electric energy hydrogen production storage, and conversion of hydrogen into electric energy output; A monitoring and management module, which monitors the input, storage and output of energy of the energy input module and the energy storage and output module in real time and collects power consumption feedback and energy supply feedback; An optimization scheduling module, wherein the optimization scheduling module is used to generate a scheduling strategy according to power demand and energy supply conditions; The scheduling strategy is transmitted to the energy storage and output module, and the energy storage and output module adjusts the energy storage and output according to the scheduling strategy; The monitoring management module includes a monitoring unit and a feedback unit; The monitoring unit monitors the input, output, storage and equipment operation status of the system energy in real time, and predicts the power demand based on the feedback information collected by the feedback unit; The feedback unit is used to collect power demand feedback and energy input feedback; The optimization scheduling module includes a strategy generation unit, a scheduling unit and an optimization unit; The strategy generation unit is used to generate a scheduling strategy according to the power demand; The scheduling unit is used to control the energy storage and output modules to distribute power according to the scheduling strategy; The optimization unit is used to continuously optimize the scheduling strategy according to the power demand feedback; The optimization unit optimizes the scheduling strategy according to the power consumption feedback; The strategy generation unit generates a scheduling strategy using a random generator. The solution of the scheduling strategy is set to function F, which represents the scheduling decision optimization value within the specified time t. At the same time, the optimization unit introduces a weight coefficient, and the energy supply ratio matching value weight coefficient w p , cost weight coefficient w C , efficiency loss weight coefficient w B ; That is, the function F that introduces the weight coefficient after optimization w for: Among them, the influence function F w Factors include but are not limited to energy supply ratio, cost and power generation efficiency; D t represents the predicted value of electricity consumption at time t; P ht P represents the energy supply ratio of hydrogen power generation h within time t; ot It represents the energy supply ratio of other energy sources o at time t, where other energy sources o include solar energy or wind energy; C ht represents the unit cost of hydrogen power generation h in time t; C ot represents the unit cost of other energy o at time t; B ht represents the efficiency of using hydrogen energy to generate electricity h at time t; B ot represents the efficiency of using other energy o at time t; Introduce weight coefficients to adjust the importance of different factors in the dispatch strategy based on power consumption feedback. According to the comparison between the solution results and the actual situation, adjust the weight coefficients to optimize the dispatch strategy. If it is found in actual situation that a certain item does not meet the expected value, the weight coefficient of the corresponding item is appropriately adjusted to adjust the scheduling strategy; for adjusting the initial control parameters and the final control parameters, the average optimization effect is calculated based on the actual results of multiple tests and historical data, and the value of the control parameter is gradually adjusted according to the expected degree of the effect.

2. The coordinated optimization operation system of an electric hydrogen system according to claim 1, characterized in that: The energy input module inputs energy types including but not limited to hydrogen energy, wind energy and solar energy, and supports converting them into electrical energy through relevant electrical energy conversion equipment.

3. The coordinated optimization operation system of an electric hydrogen system as claimed in claim 2, characterized in that: The energy storage and output module includes an energy storage unit and an output unit; The energy storage unit can store electrical energy as hydrogen energy through water electrolysis hydrogen production technology when there is excess electrical energy. The energy storage methods include but are not limited to compressed hydrogen storage tanks for long-term storage and large-scale applications, liquid hydrogen storage tanks for low-temperature environments and high-density storage, and solid hydrogen materials for portable transportation and transfer; The output unit is used to convert hydrogen into electrical energy for output when there is a shortage of electrical energy, and can arrange other energy sources for direct output and adjust the output time and output amount according to the scheduling strategy.

4. The coordinated optimization operation system of an electric hydrogen system according to claim 1, characterized in that: The monitoring unit predicts the electricity demand; through the feedback of electricity demand, the curve of the relationship between electricity demand and time is calculated in combination with the time series, and the electricity demand and energy input are predicted using the curve smoothing coefficient: the relationship of the curve smoothing coefficient is as follows: D t+1 =αS t +(1-a)D t Among them, t represents a certain period of time, S t represents the power demand value at time t, D t+1 It represents the power consumption forecast value in the t+1th time period, α represents the smoothing coefficient. When calculating, the forecast value is first replaced by the actual power demand value to calculate the initial smoothing coefficient α, and then the forecast value and the actual power demand value are used to optimize and correct the smoothing coefficient in combination with the real-time data. When the smoothing coefficient correction optimization no longer changes, the smoothing coefficient is specified and the power consumption forecast value D is calculated. t .

5. The coordinated optimization operation system of an electric hydrogen system according to claim 1, characterized in that: The feedback unit generates an input interface through which relevant staff can input electricity demand feedback and energy input feedback status. The electricity demand feedback includes, but is not limited to, electricity consumption, expected electricity cost, and electricity efficiency; the energy input feedback includes, but is not limited to, power generation, power generation cost, and power generation efficiency.

6. The coordinated optimization operation system of an electric hydrogen system according to claim 1, characterized in that: The analysis process of function F in the strategy generation unit is as follows: The first item: represents the degree of matching between energy supply and electricity demand. The smaller the value, the better the matching; The second item: represents the total cost consumed by hydrogen power generation and other energy power generation; The third item: represents the total efficiency loss of hydrogen power generation and other energy power generation; After the above scheduling strategy is generated, due to the randomness of the random generator, the initial solution is uncertain and it is impossible to determine that this scheduling strategy is optimal. Therefore, within the same time period t, a new scheduling strategy is randomly generated to obtain the solution of the new scheduling strategy: function F'; Calculate the difference ΔF between F and F', ΔF = F'-F. When ΔF is greater than 0, accept the new scheduling strategy with the solution F' as the current scheduling strategy and update the current function F to F'. When ΔF is less than or equal to 0, calculate the probability It means that F' is updated to F with probability Q. The role of probability Q is to avoid falling into the local optimal solution during the calculation process. Among them, e is a natural constant, and Z is the current control parameter, which is a constant; Set the initial control parameter to 1000 and the final control parameter to 0.

01. The initial control parameter and the final control parameter can be corrected and optimized according to the optimization unit. After selecting the new scheduling strategy, adjust the number of iterative calculations of the scheduling strategy according to the formula Z' = aZ. The value of the control parameter determines the number of iterative calculations of the optimal solution, where a is the control coefficient that determines the reduction speed of the control parameter. The larger the control coefficient, the slower the reduction speed, and the more the number of iterative calculations of the scheduling strategy. The value range of the control coefficient is 0 < a < 1; Z' is the control parameter for the next iterative calculation; During the continuous iterative calculation process, when the control parameter Z' for the next iterative calculation is less than or equal to the final control parameter 0.01, the iterative calculation ends, and the current scheduling strategy is output as the optimal scheduling strategy. Otherwise, continue to calculate the new solution.

Images