Optimal scheduling method and device for fuel cell integrated energy system

Abstract

The application relates to a fuel cell comprehensive energy system optimization scheduling method and device, which establishes a fuel cell comprehensive energy system optimization scheduling model and operation coupling constraints; the optimization scheduling model comprises a day-ahead scheduling model and an adjustment model suitable for an uncertain scenario; the day-ahead scheduling model takes the minimum operation economic cost of the fuel cell comprehensive energy system as a target; a game mechanism is constructed based on a supply-demand two-side benefit optimization target, and a layered iteration mode is adopted to solve the optimization scheduling model, combined with the operation coupling constraints, to determine a target scheduling strategy. The fuel cell comprehensive energy system optimization scheduling method provided by the application can improve the ability of the fuel cell comprehensive energy system to cope with uncertain disturbances while realizing the collaborative and efficient operation of multiple energies.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to an optimized scheduling method and apparatus for a fuel cell integrated energy system. Background Technology

[0002] With the rapid development of new energy technologies and the advancement of the "dual carbon" goal, integrated energy systems are gaining significant value in engineering applications due to their ability to synergistically utilize multiple energy forms such as electricity, heat, and hydrogen. Especially under off-grid operation conditions, integrated energy systems do not rely on the public power grid and can achieve independent and reliable supply of multiple energy sources to the user side through local multi-energy coupling and energy storage configuration.

[0003] For the optimal scheduling of off-grid integrated energy systems, such as fuel cell integrated energy systems, traditional technologies often focus on single energy sources or deterministic load conditions, making it difficult to simultaneously consider factors such as multi-energy coupling, uncertainty modeling, and equipment performance degradation. Traditional methods for handling uncertainty rely on known or assumed probability distributions, but the true distribution of uncertain variables is often difficult to accurately obtain. Therefore, there is an urgent need for a scheduling method that can improve the ability of integrated energy systems to cope with uncertainty disturbances while achieving efficient and coordinated operation of multiple energy sources. Summary of the Invention

[0004] Therefore, it is necessary to provide an optimized scheduling method and apparatus for a fuel cell integrated energy system that can improve the ability of the fuel cell integrated energy system to cope with uncertain disturbances and achieve efficient operation of multiple energy sources, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides an optimized scheduling method for a fuel cell integrated energy system, the method comprising:

[0006] An optimal scheduling model for a fuel cell integrated energy system and its operational coupling constraints are established. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system.

[0007] A game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy.

[0008] In one embodiment, an optimal scheduling model for the fuel cell integrated energy system and operational coupling constraints for the fuel cell integrated energy system are established, including:

[0009] Based on the basic output of the fuel cell integrated energy system, and with the goal of minimizing the operating economic cost of the fuel cell integrated energy system, a day-ahead scheduling model is constructed.

[0010] Based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, an adjustment model is constructed with the optimization objective of optimizing the adjustment cost under the worst operating scenario.

[0011] Based on the current forecast baseline power demand and energy demand under uncertain scenarios, operational coupling constraints are constructed.

[0012] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell unit, a hydrogen storage unit, a lithium battery unit, and a thermal storage unit. Based on the basic output of the fuel cell integrated energy system, and with the objective of minimizing the operating economic cost of the fuel cell integrated energy system, a day-ahead scheduling model is constructed, including:

[0013] The total hydrogen consumption cost of the integrated fuel cell energy system is determined based on the basic output of the multi-unit fuel cell equipment and the lithium battery equipment.

[0014] The first loss cost of the multi-unit fuel cell equipment is determined based on its basic output and start / stop status; the second loss cost of the lithium battery equipment is determined based on its basic output.

[0015] The thermal energy output cost of the thermal storage equipment is determined based on its supplementary heating output capacity.

[0016] Based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the heat output cost, the economic operating cost is determined; and with the goal of minimizing the economic operating cost, a day-ahead scheduling model is constructed.

[0017] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell unit, a lithium battery unit, a thermal storage unit, and a hydrogen storage unit. Based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, an adjustment model is constructed with the optimization objective of optimizing the adjustment cost under the worst-case operating scenario. The model includes:

[0018] The initial optimization model is determined based on the adjustment parameters of the basic output of the multi-engine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario.

[0019] Based on historical data of the fuel cell integrated energy system, a probability distribution fuzzy set is constructed. Based on the probability distribution fuzzy set and the initial optimization model, an adjustment model is constructed with the optimization objective of optimizing the adjustment cost under the worst operating scenario in all operating scenarios.

[0020] In one embodiment, the prediction bias of the uncertainty scenario includes a first uncertainty of the multi-machine fuel cell device and the lithium battery device, a second uncertainty of the thermal storage device, and a third uncertainty of the hydrogen storage device; the method further includes:

[0021] Based on the coupling relationship between the multi-machine fuel cell equipment, lithium battery equipment, thermal storage equipment and hydrogen storage equipment, the coupling relationship between the first uncertainty, the second uncertainty and the third uncertainty is constructed.

[0022] In one embodiment, a probability distribution fuzzy set is constructed based on historical data of the fuel cell integrated energy system, including:

[0023] Determine the initial probability distribution under uncertain scenarios based on historical data;

[0024] A fuzzy set of probability distribution is constructed using the probability distribution difference index and the initial probability distribution.

[0025] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0026] In one embodiment, a game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides, including:

[0027] Based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, a game mechanism is constructed with the goal of optimizing the benefits on both the supply and demand sides.

[0028] In one embodiment, a game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy, including:

[0029] Obtain input data for the fuel cell integrated energy system, including the inherent intrinsic parameters of the fuel cell integrated energy system, initial health status, historical data, and initial unit cost.

[0030] Based on the input data and combined with the operational coupling constraints, the optimization scheduling model is solved to obtain the initial scheduling strategy;

[0031] Based on the initial scheduling strategy and game mechanism, the initial cost unit price is iteratively updated until the supply and demand sides meet the equilibrium convergence condition, thus obtaining the target scheduling strategy.

[0032] Secondly, one embodiment of this application provides an optimized scheduling device for a fuel cell integrated energy system, the device comprising:

[0033] A module is established to build an optimal scheduling model for the integrated fuel cell energy system, as well as the operational coupling constraints of the integrated fuel cell energy system. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the integrated fuel cell energy system.

[0034] The determination module is used to construct a game mechanism based on the goal of optimizing the benefits on both the supply and demand sides, and, in conjunction with the operational coupling constraints, to solve the optimization scheduling model in a hierarchical iterative manner to determine the target scheduling strategy.

[0035] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method provided in the first aspect above.

[0036] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0037] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0038] The aforementioned optimization scheduling method and apparatus for a fuel cell integrated energy system establishes an optimization scheduling model for the fuel cell integrated energy system, along with operational coupling constraints. The optimization scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system. A game mechanism is constructed based on the optimal benefits on both the supply and demand sides, and combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy. In this embodiment, the optimization scheduling model includes a day-ahead scheduling model corresponding to the fuel cell integrated energy system and an adjustment model suitable for uncertain scenarios. Since it is specifically designed for the fuel cell integrated energy system, it can take into account factors such as multi-energy coupling and uncertain scenarios within the fuel cell integrated energy system, thereby improving the fuel cell integrated energy system's ability to cope with uncertain disturbances and enabling efficient collaborative operation of multiple energy sources within the fuel cell integrated energy system. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram of the structure of a fuel cell integrated energy system in one embodiment;

[0041] Figure 2 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in one embodiment.

[0042] Figure 3 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment;

[0043] Figure 4 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment;

[0044] Figure 5 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment;

[0045] Figure 6 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment;

[0046] Figure 7 This is a schematic diagram illustrating the probability distribution under the worst-case operating scenario in one embodiment.

[0047] Figure 8 This is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment;

[0048] Figure 9 is a flowchart illustrating the steps of an optimized scheduling method for a fuel cell integrated energy system in another embodiment.

[0049] Figure 10 This is a schematic diagram of the efficiency curves of a multi-unit fuel cell device in one embodiment;

[0050] Figure 11 This is a schematic diagram of the structure of the optimization scheduling device of a fuel cell integrated energy system in one embodiment;

[0051] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion.

[0054] Before detailing the technical solutions of the embodiments disclosed in this application, the background technology or technological evolution on which the embodiments of this application are based will be introduced first. With the rapid development of new energy technologies and the advancement of the "dual carbon" goal, integrated energy systems have received widespread attention in application scenarios such as industrial parks, remote areas, and microgrids because they can achieve the synergistic effect of multiple energy forms such as electricity, heat, and hydrogen. Especially under off-grid operation conditions, integrated energy systems do not rely on the public power grid and can achieve independent and reliable supply of multiple energy sources to the user side through local multi-energy coupling and energy storage configuration, which has important engineering application value. Fuel cells, due to their advantages such as high energy conversion efficiency, low pollution emissions, and the ability to simultaneously output electrical and thermal energy, have gradually become the core power generation unit in off-grid integrated energy systems. Through the coordinated operation of multi-fuel cells with lithium batteries, hydrogen storage systems, thermal storage systems, and other equipment, the flexibility and reliability of the system can be improved to a certain extent. However, in actual operation, this type of off-grid fuel cell integrated energy system still faces many challenges. On the one hand, user-side electrical load, thermal load, and system hydrogen supply conditions generally exhibit significant uncertainties, influenced by various factors such as climate change, user behavior, equipment status, and fluctuations in renewable energy output, making them difficult to accurately characterize using deterministic models. On the other hand, multi-unit fuel cells and lithium batteries experience performance degradation during long-term operation, and their start-up and shutdown strategies, output allocation methods, and frequent adjustments significantly impact system lifespan and operating costs. Existing scheduling methods mostly focus on single energy sources or deterministic load conditions, making it difficult to simultaneously consider factors such as multi-energy coupling, uncertainty modeling, and equipment performance degradation. Traditional stochastic optimization methods for handling uncertainty typically rely on known or assumed probability distributions. However, in off-grid fuel cell integrated energy systems, the true distribution of uncertain variables is often difficult to obtain accurately, and directly using stochastic models may lead to insufficient robustness of scheduling results in actual operation. Furthermore, while some robust optimization methods can handle worst-case scenarios, they are often overly conservative, resulting in increased system operating costs and decreased equipment utilization efficiency. Therefore, there is an urgent need for a scheduling method that can improve the integrated energy system's ability to cope with uncertain disturbances while achieving efficient operation of multi-energy systems.

[0055] The optimized scheduling method for a fuel cell integrated energy system provided in this application embodiment is applied to a fuel cell integrated energy system. For example... Figure 1As shown, the integrated fuel cell energy system includes a multi-fuel cell unit 100, a lithium battery unit 110, a thermal storage unit 120, a hydrogen storage unit 130, a user-side unit 140, and a control unit 150. The control unit 150 is communicatively connected to the multi-fuel cell unit 100, the lithium battery unit 110, the thermal storage unit 120, the hydrogen storage unit 130, and the user-side unit 140, enabling the user to coordinate control of the integrated fuel cell energy system. The multi-fuel cell unit 100 integrates two or more independent fuel cell stacks in parallel or series, serving as the core combined power and heat generation unit, simultaneously outputting electrical energy and waste heat energy. The hydrogen storage unit 130 includes a hydrogen supply cylinder group and a buffer cylinder group. Hydrogen is replenished to the hydrogen storage unit 130 via external hydrogen supply. The buffer cylinder group provides pressure stabilization, while the hydrogen supply cylinder group provides a stable and continuous gas supply, serving as the long-term energy source for the integrated fuel cell energy system. It is bidirectionally compatible with the multi-fuel cell unit 100, dynamically supplying fuel on demand. The lithium battery device 110 is used for rapid energy storage, responsible for instantaneous power support and load fluctuation smoothing. The thermal storage device 120 includes a heat pump and a hot water tank, allowing users to recover waste heat from the multi-unit fuel cell device 100's power generation, achieving thermal energy storage and inter-period allocation. For example... Figure 1 As shown, the integrated fuel cell energy system includes a common energy bus (electrical bus, hydrogen bus, and thermal bus). User-side 140 consumes electrical and thermal energy. The basic operating principle of the integrated fuel cell energy system includes: the hydrogen storage tanks in the hydrogen storage device 130 continuously supply hydrogen to the multi-unit fuel cell device 100; the multi-unit fuel cell device 100 operates stably, prioritizing the delivery of basic electrical energy to the electrical bus, directly supplying the electrical load of user-side 140. A large amount of waste heat generated during the power generation process of the multi-unit fuel cell device 100 is sent to the thermal storage device 120 via the thermal bus; the heat pump upgrades the heat and stores it in a hot water tank, with a portion directly supplying the user-side heat load and a portion stored for later use. The lithium battery device is in float charge standby mode, only compensating for minor power fluctuations.

[0056] The technical solution of this application and how the technical solution of this application solves the technical problem are described in detail below with specific embodiments.

[0057] In one embodiment, such as Figure 2 As shown, an optimized scheduling method for a fuel cell integrated energy system is provided, which can be applied to applications such as... Figure 1 The control device shown is used as an example for illustration. In this embodiment, the method includes the following steps:

[0058] Step 200: Establish an optimal scheduling model for the integrated fuel cell energy system and the operational coupling constraints of the integrated fuel cell energy system; the optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios; the day-ahead scheduling model aims to minimize the operating economic cost of the integrated fuel cell energy system.

[0059] The day-ahead scheduling model aims to minimize the overall economic cost of operation for all devices in a fuel cell integrated energy system. It identifies the pre-decision variables in each device that cannot be frequently modified in real-time. The adjustment model, suitable for uncertain scenarios, addresses the uncertain parameters of the fuel cell integrated energy system under uncertain conditions. Under the worst-case probability distribution, it calculates the penalty cost of real-time parameter adjustments in the fuel cell integrated energy system based on the pre-decision variables in the day-ahead scheduling model. The optimal scheduling model for the fuel cell integrated energy system is the sum of the day-ahead scheduling model and the adjustment model.

[0060] Operational coupling constraints of a fuel cell integrated energy system refer to the boundary conditions and linkage balance relationships used to limit the coordinated operation of various devices in the system during operation. These constraints standardize the coupling matching logic and operational limits of each device to ensure the physical feasibility of the fuel cell integrated energy system. This embodiment does not limit the specific content of the operational coupling constraints, as long as their function is achieved.

[0061] The control equipment establishes an optimal scheduling model for the integrated energy system of the fuel cell and sets operational coupling constraints for the integrated energy system of the fuel cell.

[0062] Step 210: Construct a game mechanism based on the goal of optimizing benefits on both the supply and demand sides, and combine it with the operational coupling constraints to solve the optimization scheduling model in a hierarchical iterative manner to determine the target scheduling strategy.

[0063] The supply side refers to the side of the fuel cell integrated energy system where multiple fuel cell devices, lithium battery devices, thermal storage devices, and hydrogen storage devices are located, while the demand side refers to the user side. The game theory mechanism refers to a collaborative decision-making mechanism guided by different optimization objectives on both the supply and demand sides, with energy prices in the fuel cell integrated energy system serving as the regulatory link. This mechanism involves independent optimization, mutual constraints, and dynamic iterative adjustments on both sides, ultimately converging to a stable operating state where the benefits of supply and demand are balanced. This embodiment does not limit the specific method for constructing the game theory mechanism, as long as its function can be achieved.

[0064] After acquiring the optimal scheduling model and operational coupling constraints, the control equipment first iteratively solves the two-stage optimal scheduling model based on the operational coupling constraints, and then determines the final target scheduling strategy according to the game mechanism. In other words, it first solves the day-ahead scheduling model based on the operational coupling constraints to obtain the pre-decision variables, then solves the adjustment model to adjust the pre-decision variables; finally, it dynamically adjusts energy prices based on the game mechanism until the equilibrium convergence condition is met, thus obtaining the final target scheduling strategy.

[0065] The optimized scheduling method for a fuel cell integrated energy system provided in this application establishes an optimized scheduling model for the fuel cell integrated energy system and operational coupling constraints. The optimized scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system. A game mechanism is constructed based on the optimal benefits on both the supply and demand sides, and combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimized scheduling model and determine the target scheduling strategy. In this embodiment, the optimized scheduling model includes a day-ahead scheduling model corresponding to the fuel cell integrated energy system and an adjustment model suitable for uncertain scenarios. Since it is specifically designed for the fuel cell integrated energy system, it can take into account factors such as multi-energy coupling and uncertain scenarios within the fuel cell integrated energy system, thereby improving the fuel cell integrated energy system's ability to cope with uncertain disturbances and enabling efficient collaborative operation of multiple energy sources within the fuel cell integrated energy system.

[0066] In one embodiment, such as Figure 3 As shown, this involves establishing an optimal scheduling model for a fuel cell integrated energy system and an implementation method for the operational coupling constraints of the fuel cell integrated energy system. The steps of this implementation method include:

[0067] Step 300: Based on the basic output of the fuel cell integrated energy system, construct a day-ahead scheduling model with the goal of minimizing the operating economic cost of the fuel cell integrated energy system.

[0068] The base output of a fuel cell integrated energy system refers to the fixed daily reference power of each device in the system. Based on the base output of the fuel cell integrated energy system, the control equipment can determine the economic cost of the system during operation, and a day-ahead scheduling model is constructed with the goal of minimizing this economic cost.

[0069] Step 310: Based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, construct an adjustment model with the optimization objective of optimizing the adjustment cost under the worst operating scenario.

[0070] The adjustment parameters for the base output of the fuel cell integrated energy system refer to the parameters used to adjust the daily fixed reference power of each device in the fuel cell integrated energy system; these adjustment parameters include power up-adjustment parameters and power down-adjustment parameters. Based on the adjustment parameters for the base output of the fuel cell integrated energy system, and considering the prediction deviation under uncertain scenarios (i.e., the uncertain energy demand of the load), the control equipment constructs an adjustment model with the optimization objective of minimizing the penalty cost incurred by real-time parameter adjustments in the fuel cell integrated energy system under the worst-case probability distribution.

[0071] In an optional embodiment, the optimal scheduling model of the fuel cell integrated energy system can be expressed as follows: .in, This represents the day-ahead scheduling model. This represents the pre-decision decision variables, namely the base output of each device in the fuel cell integrated energy system. Indicates the economic cost of operation. This indicates an adjustment to the model. This refers to the real-time adjustment parameters, specifically the adjustment parameters of the basic output of each device in the fuel cell integrated energy system. Indicates prediction bias. It refers to the set of all probability distributions.

[0072] Step 320: Based on the day-ahead forecast baseline demand power and energy demand under uncertain scenarios, construct operational coupling constraints.

[0073] During operation, the control equipment fuel cell integrated energy system constructs operational coupling constraints for the day-ahead predicted baseline power demand and the energy demand under uncertain scenarios.

[0074] In this embodiment, a day-ahead scheduling model is constructed based on the base output of the fuel cell integrated energy system, with the goal of minimizing the operating economic cost of the fuel cell integrated energy system. An adjustment model is constructed based on the adjustment parameters of the base output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, with the optimization goal of maximizing the adjustment cost under the worst-case operating scenario. Operating coupling constraints are constructed based on the day-ahead predicted baseline demand power and the energy demand under uncertain scenarios. This method of constructing the day-ahead scheduling model, adjustment model, and operating coupling constraints is easy to implement and can improve the practicality of the optimization scheduling method for the fuel cell integrated energy system.

[0075] In one embodiment, such as Figure 4 As shown, this involves an implementation method for constructing a day-ahead scheduling model based on the base output of the fuel cell integrated energy system, with the objective of minimizing the operating economic cost of the fuel cell integrated energy system. The steps of this implementation method include:

[0076] Step 400: Determine the total hydrogen consumption cost of the integrated fuel cell energy system based on the basic output of the multi-unit fuel cell equipment and the lithium battery equipment.

[0077] A fuel cell integrated energy system includes multi-unit fuel cell equipment, lithium battery equipment, hydrogen storage equipment, and thermal storage equipment. Total hydrogen cost refers to the cost of using hydrogen, which is the conversion of hydrogen consumption into the power generation of the multi-unit fuel cell equipment and the equivalent hydrogen consumption of the lithium battery. For both the multi-unit fuel cell equipment and the lithium battery equipment, the total hydrogen cost can be determined based on their respective base output capacities.

[0078] In an optional embodiment, at time t, the total hydrogen consumption cost of the j-th fuel cell and lithium battery in the multi-engine fuel cell system can be expressed as: ,in, This indicates the unit price of hydrogen. This indicates the hydrogen consumption per unit time of a multi-unit fuel cell. This indicates the amount of hydrogen consumed by the lithium battery per unit of time. Indicates the duration, here representing the unit interval T for scheduling optimization. DRO .

[0079] Step 410: Determine the first loss cost of the multi-unit fuel cell equipment based on its basic output and start / stop status; determine the second loss cost of the lithium battery equipment based on its basic output.

[0080] During the operation of a multi-unit fuel cell device, losses occur. The start-up and shutdown states of a multi-unit fuel cell device include the start-up operating state and the shutdown state. The start-up operating state indicates that the multi-unit fuel cell device is operational and can generate basic output power. The shutdown state indicates that the multi-unit fuel cell device is not operational, has no power output, and does not participate in the power supply of the fuel cell integrated energy system. Based on the basic output power and the start-up and shutdown states of the multi-unit fuel cell device, the control equipment can determine the first loss cost of the multi-unit fuel cell device. During the operation of a lithium battery device, losses also occur. The control equipment can determine the second loss cost of the lithium battery device based on its basic output power.

[0081] In an optional embodiment, the first loss cost of the multi-machine fuel cell device can be determined based on the purchase price and health status of the multi-machine fuel cell device. Similarly, the second loss cost of the lithium battery device can be determined based on the purchase price and health status of the lithium battery device. Specifically, the first loss cost... Second loss cost It can be represented as:

[0082]

[0083] in, This represents the start-up / shutdown state of the i-th fuel cell in a multi-fuel cell system at time t. 0 indicates that the i-th fuel cell is in the shutdown state at time t, and 1 indicates that the i-th fuel cell is in the start-up state at time t. This represents the base output of the i-th fuel cell at time t. This indicates the basic output of the lithium battery equipment. This indicates the purchase price of a multi-unit fuel cell system. This indicates the purchase price of lithium battery equipment. This represents the health status of the i-th fuel cell at time t. This indicates the health status of lithium battery devices.

[0084] Step 420: Determine the thermal energy output cost of the thermal storage equipment based on its supplementary heat output capacity.

[0085] Thermal storage equipment refers to energy storage devices that pre-store waste heat and release it to compensate for the heating gap when the fuel cell integrated energy system has insufficient energy or a heat load deficit. Control equipment determines the thermal energy output cost of the thermal storage equipment based on its supplementary heating output.

[0086] In an optional embodiment, the thermal energy output cost can be determined based on the unit price of thermal energy produced by the thermal storage device and the output capacity of the thermal storage device. Specifically, the thermal energy output cost... It can be represented as .

[0087] Step 430: Determine the economic operating cost based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and construct a day-ahead scheduling model with the goal of minimizing the economic operating cost.

[0088] Once the control equipment obtains the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal output cost, it can determine the economic operating cost. Specifically, by calculating the sum of these costs, the economic operating cost of the fuel cell integrated energy system can be obtained. Minimizing this economic operating cost allows for the development of a day-ahead scheduling model.

[0089] In an optional embodiment, the operating economic cost can be expressed as:

[0090]

[0091] in, Represents the decision variables in the day-ahead scheduling model. .

[0092] In this embodiment, the calculated operating economic cost includes the total hydrogen consumption cost and loss cost (first loss cost and second loss cost) of the multi-machine fuel cell equipment and lithium battery equipment, as well as the thermal energy output cost. This not only takes into account the total hydrogen consumption cost of the fuel cell integrated energy system, but also the performance loss generated by the fuel cell integrated energy system during operation. This can improve the accuracy of the determined operating economic cost, improve the accuracy of the constructed day-ahead scheduling model, and further improve the scheduling accuracy of the optimization scheduling method of the fuel cell integrated energy system.

[0093] In one embodiment, such as Figure 5 As shown, this involves an implementation method for constructing an adjustment model based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, with the optimization objective of optimizing the adjustment cost under the worst operating scenario. The steps of this implementation method include:

[0094] Step 500: Determine the initial optimization model based on the adjustment parameters of the basic output of the multi-unit fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario.

[0095] By using a day-ahead scheduling model, the adjustment model constructed by the integrated fuel cell energy system should be robust after meeting the user's predicted future electricity and heat load. This model should adjust the power output of the integrated fuel cell energy system based on the day-ahead scheduling model to cope with the probability distribution results under the worst-case scenario in an uncertain field.

[0096] Based on this, when constructing the adjustment model, the control device can construct an initial optimization model based on the adjustment parameters of the basic output of the multi-machine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario.

[0097] Step 510: Construct a probability distribution fuzzy set based on historical data of the fuel cell integrated energy system. Based on the probability distribution fuzzy set and the initial optimization model, construct an adjustment model with the optimization objective of optimizing the adjustment cost under the worst operating scenario in all operating scenarios.

[0098] The adjustment parameters for the base output of multi-unit fuel cell equipment and lithium battery equipment need to meet the uncertainty of user-side energy demand. The prediction deviation in uncertain scenarios has an unknown probability distribution. Historical data of the integrated fuel cell energy system can be pre-acquired and stored in the control equipment, which then constructs a fuzzy set of probability distributions using this historical data. This embodiment does not limit the specific method for constructing the fuzzy set of probability distributions from historical data, as long as the function can be achieved.

[0099] After obtaining the probability distribution simulation set, the control device constructs an adjustment model based on the fuzzy set of the probability distribution and the initial optimization model, with the optimization objective being the optimal adjustment cost under the worst-case operating scenario. In other words, it defines the probability distribution range of the uncertainty set in all operating scenarios based on the fuzzy set of the probability distribution, traverses the probability distribution range of the uncertainty set corresponding to all operating scenarios, and constructs an adjustment model with the optimization objective being the optimal adjustment cost under the worst-case operating scenario.

[0100] In this embodiment, an initial optimization model is determined based on the adjustment parameters of the basic output of the multi-unit fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of uncertain scenarios. A probability distribution fuzzy set is constructed based on the historical data of the fuel cell integrated energy system. Based on the probability distribution fuzzy set and the initial optimization model, an adjustment model is constructed in all operating scenarios with the optimization objective of optimizing the adjustment cost under the worst operating scenario. In this way, the influence of uncertain factors under uncertain scenarios is taken into account during the construction of the adjustment model, and it can cope with multiple uncertain scenarios, making the constructed adjustment model robust. This improves the practicality and reliability of the optimization scheduling method of the fuel cell integrated energy system.

[0101] In one embodiment, such as Figure 6 As shown, this involves an implementation method for constructing a fuzzy set of probability distributions based on historical data of a fuel cell integrated energy system. The steps of this implementation method include:

[0102] Step 600: Determine the initial probability distribution under uncertain scenarios based on historical data.

[0103] After acquiring historical data, the control device obtains the nominal probability distribution (the set of uncertainties) under uncertain scenarios, i.e., the initial probability distribution, based on the historical data. .

[0104] Step 610: Construct a fuzzy set of probability distribution based on the probability distribution difference index and the initial probability distribution.

[0105] The probability distribution difference index refers to the degree of deviation between the initial probability distribution and the true probability distribution of uncertainties during the operation of a fuel cell integrated energy system. Based on the probability distribution difference index and the initial probability distribution, the control equipment can construct a fuzzy set of probability distributions.

[0106] In uncertain scenarios, the prediction bias is unknown due to the unknown probability distribution of the scenario. In this embodiment, the initial probability distribution under uncertain scenarios is determined based on historical data. A fuzzy set of probability distribution is constructed using the probability distribution difference index and the initial probability distribution. The adjustment model formed by this fuzzy set can be transformed into an equivalent (mixed integer) convex optimization problem through the dual transformation of the fuzzy set. This facilitates the use of commercial solvers (such as CPLEX / Gurobi) for solving the problem, thereby improving the practicality and reliability of the optimization scheduling method for fuel cell integrated energy systems. A schematic diagram of obtaining the probability distribution under the worst-case operating scenario is shown below. Figure 7 As shown. Figure 7 The paper describes a general algorithm paradigm for hybrid integer convex optimization that combines adaptive polyhedral approximation and iterative interactive solution. Figure 7 The left side of the middle section represents the adaptive polyhedral approximation. The conical aggregate represents the complex feasible region, i.e. the fuzzy set of probability distribution. The complex feasible region is wrapped and fitted by continuously updating the linear plane (the gray cross-section on the side in the diagram), and the nonlinear and non-convex constraints are transformed into a linear polyhedron. Figure 7 The key scenario on the right is the worst-case scenario. Through each iteration, a new cutting plane is added, the polyhedron approximation boundary is updated, the worst-case scenario is accurately captured, and the upper and lower bounds of the feasible region are continuously tightened until the termination condition is reached.

[0107] In an optional embodiment, the probability distribution dissimilarity index is the Wasserstein distance. The fuzzy set of the probability distribution can be represented as: ,in, Distance representing probability distributions This indicates a region centered at P0 with a radius of... The Wasserstein sphere. The fuzzy set of probability distributions is used as the feasible region of the distribution in the initial optimization model, that is, the feasible value space of the unknown probability distribution, which allows traversal and filtering of the constraint boundary range under the worst-case operating scenario.

[0108] Specifically, the initial optimization model can be expressed as: ,in, Represents a fuzzy set of probability distributions, i.e. , Let these represent the upper and lower adjustment parameters, respectively, of the base output of the i-th fuel cell at time t. These represent the upper and lower adjustment parameters of the basic output of the lithium battery equipment, respectively.

[0109] To minimize the cost of corrective actions, the cost changes caused by the upward and downward adjustment parameters are minimized under each uncertainty scenario. A dynamic programming algorithm is used to optimize the adjustment model, completing the start-up and shutdown decisions for multi-unit fuel cell equipment and optimizing the power trajectories among the devices in the integrated fuel cell energy system.

[0110]

[0111] In one embodiment, the prediction bias in an uncertain scenario includes a first uncertainty for the multi-unit fuel cell device and the lithium battery device, a second uncertainty for the thermal storage device, and a third uncertainty for the hydrogen storage device. That is, in an uncertain scenario, the multi-unit fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device in the integrated fuel cell energy system all have uncertainties. The first uncertainty for the multi-unit fuel cell device and the lithium battery device can be expressed as... This refers to the uncertainty in predicting electricity within the fuel cell integrated energy system. The second uncertainty corresponding to the thermal storage device can be expressed as... This refers to the uncertainty in predicting thermal energy within the fuel cell integrated energy system. The third uncertainty related to the hydrogen storage device can be expressed as... The boundaries of the first, second, and third uncertainties can be expressed as follows:

[0112]

[0113] in, and Let represent the constraint boundaries of the first uncertainty, respectively. and Let represent the constraint boundaries of the first and second uncertainties, respectively. and These represent the constraint boundaries for the third uncertainty. These boundary constraints can be obtained from the historical residuals corresponding to historical data.

[0114] Based on this, the optimal scheduling method for fuel cell integrated energy systems also includes:

[0115] Based on the coupling relationship between the multi-machine fuel cell equipment, lithium battery equipment, thermal storage equipment and hydrogen storage equipment, the coupling relationship between the first uncertainty, the second uncertainty and the third uncertainty is constructed.

[0116] After determining the prediction bias of the uncertain scenario in the fuel cell integrated energy system, including the first uncertainty, the second uncertainty, and the third uncertainty, the control equipment can determine the coupling relationship between the first uncertainty, the second uncertainty, and the third uncertainty based on the channel relationship between the multi-machine fuel cell equipment, lithium battery equipment, thermal storage equipment, and hydrogen storage equipment.

[0117] In an optional embodiment, the coupling relationship between the first uncertainty, the second uncertainty, and the third uncertainty can be expressed as follows: .in, These represent the degree of shortage of electricity, heat, and hydrogen energy, respectively. Focusing solely on the degree of shortage is because "hydrogen deficiency is ≥ a linear combination of electrical deficit + thermal deficit." In practical coupling, insufficient hydrogen will cause electrical / thermal deficits, and these deficits are determined by the power generation of multi-unit fuel cell equipment. The power generation efficiency of multiple fuel cell devices can be set separately. Heat recovery efficiency of thermal storage equipment The lower calorific value (LHV) of hydrogen in hydrogen storage devices H2 .

[0118] The deviation (dt) between electrical energy and thermal energy under the same operating scenario is: ,in, These represent the standard deviations of electrical load and thermal load at time t, respectively. The deviations under the same operating scenario must not deviate from the actual values, i.e. , This allows for deviations from the threshold at all times, representing the tightness of the coupling. To ensure that at least 95% of historical data satisfies this coupling relationship, the standard deviations of electrical and thermal energy are calculated based on the historical data, and then the quantiles are used to calculate... : .

[0119] For coupled energy demand constraints in uncertain scenarios, the uncertainty lies in adjusting parameters to meet the user-side energy demand.

[0120]

[0121] in, These respectively indicate that insufficient hydrogen energy storage leads to a shortage of electrical and thermal energy at the user level.

[0122] In this embodiment, to address the prediction bias of uncertain scenarios in the adjustment model, the coupling relationship between the uncertainties of each device in the fuel cell integrated energy system is established based on the coupling relationship between the devices. This improves the robustness of the constructed adjustment model and enhances the practicality of the optimization scheduling method for the fuel cell integrated energy system.

[0123] In an optional embodiment, the optimized scheduling model can be expressed as:

[0124]

[0125] One embodiment involves an implementation of a game theory mechanism based on the goal of optimizing benefits on both the supply and demand sides, including:

[0126] Based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, a game mechanism is constructed with the goal of optimizing the benefits on both the supply and demand sides.

[0127] The unit price of hydrogen and the time-of-use electricity price can be input by the user into the control device in real time, or they can be obtained periodically by the control device. This embodiment does not limit the specific method for obtaining the unit price of hydrogen and the time-of-use electricity price, as long as the function can be achieved.

[0128] The price of hydrogen is variable, and the electricity price needs to be customized based on the energy demand of the user side. The control equipment can construct a game mechanism based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system. This game mechanism aims to optimize the benefits on both the supply and demand sides. A description of the game mechanism can be found in the specific description of the above embodiments, and will not be repeated here.

[0129] In an optional embodiment, the game mechanism can be represented as:

[0130]

[0131] In this embodiment, based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic processing of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, a game mechanism is constructed with the goal of optimizing the benefits on both the supply and demand sides. This mechanism aims to achieve a game between maximizing the unit revenue cost on the power supply side and minimizing the consumption cost on the user side, thereby improving the practicality of the optimization scheduling method for the fuel cell integrated energy system.

[0132] In one embodiment, such as Figure 8 As shown, this involves constructing a game mechanism based on the goal of optimizing benefits on both the supply and demand sides, and combining operational coupling constraints to solve the optimization scheduling model using a hierarchical iterative approach to determine the target scheduling strategy. The steps of this implementation method include:

[0133] Step 800: Obtain the input data of the fuel cell integrated energy system; the input data includes the inherent physical parameters of the fuel cell integrated energy system, the initial health status, historical data, and the initial cost per unit.

[0134] The inherent intrinsic parameters of a fuel cell integrated energy system refer to the fixed rated parameters and operational boundary constraints of each device within the system. The initial health state of the fuel cell integrated energy system refers to the real-time health and remaining lifespan of each device within the system. Historical data refers to the multi-dimensional measured statistical data accumulated during the early stages of operation of the fuel cell integrated energy system, providing a data foundation for adjusting the model. The initial unit cost refers to the initial hydrogen unit price and the initial time-of-use electricity price.

[0135] The input data for the fuel cell integrated energy system can be input by the user into the control device in real time, or it can be acquired by the control device in real time. This embodiment does not limit the specific method for acquiring the input data of the fuel cell integrated energy system, as long as it can achieve its function.

[0136] Step 810: Based on the input data and combined with the running coupling constraints, solve the optimization scheduling model to obtain the initial scheduling strategy.

[0137] After acquiring input data, the control equipment substitutes this input data into the optimization scheduling model and, in conjunction with operational coupling constraints, solves the optimization scheduling model to obtain the initial scheduling strategy. It can be understood that inputting input data into the day-ahead scheduling model within the optimization scheduling model yields the day-ahead decision variables; solving the scheduling model based on these day-ahead decision variables provides the initial scheduling strategy.

[0138] Step 820: Based on the initial scheduling strategy and game mechanism, iteratively update the initial cost unit price until the supply and demand sides meet the equilibrium convergence condition to obtain the target scheduling strategy.

[0139] After obtaining the initial scheduling strategy, the control device updates the initial cost unit price according to the initial scheduling strategy and the game mechanism, and determines whether the game pricing meets the equilibrium convergence condition. If it does not meet the condition, the updated initial cost unit price is used as the new initial cost unit price, and the process returns to steps 700-710. If the condition is met, the target scheduling strategy is obtained.

[0140] After obtaining the target scheduling strategy, the control equipment controls each device in the fuel cell integrated energy system based on the target scheduling strategy to achieve efficient operation of multiple energy sources in the fuel cell integrated energy system.

[0141] In an optional embodiment, the control device can employ the Benders solution method combined with operational coupling constraints to solve the optimal scheduling model and obtain an initial scheduling strategy. Specifically, as shown below... Figure 9As shown, the control device acquires input data, preprocesses the input data, and determines relevant parameters (such as probability distribution fuzzy sets) in the optimization scheduling model based on the input data; initialization is performed first, i.e., setting an upper bound. The lower realm The number of iterations k=0, and the threshold is Based on the base output of each device in the fuel cell integrated energy system and the start-stop status of the multi-unit fuel cell devices, the first stage of the day-ahead scheduling model in the optimization scheduling model is solved to obtain the day-ahead decision variables; the lower bound is updated based on the day-ahead policy variables. ,in, This represents the operating economic cost obtained based on the decision variables of the previous day. This represents the variables (adjustment parameters and prediction bias) in the scheduling model; the adjustment model is solved based on the day-ahead decision variables to obtain the optimal adjustment parameters and the worst-case expected cost. Update the upper bound based on the worst-case expected cost. To obtain the initial scheduling strategy Extracting the dual solution of the second stage yields the optimal cut. Determine the updated upper and lower bounds, and determine whether the convergence condition is met. If the convergence condition is not met, then k = k + 1, and return to the initialization step; if the convergence condition is met, then based on the initial scheduling strategy and game mechanism, determine whether the pricing strategies for the power supply side and the user side meet the equilibrium convergence condition. If the conditions are not met, the hydrogen unit price in the initial cost unit price is updated, and the initialization step is returned; if the conditions are met, the target initial cost unit price and the target scheduling strategy are obtained.

[0142] In one embodiment, the operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0143] The supply-demand balance constraint of a fuel cell integrated energy system characterizes the constraint that the energy supply side and energy demand side of the fuel cell integrated energy system need to maintain a match (energy balance or power balance). The state of charge constraint of lithium batteries refers to the constraint on the operating range of the remaining charge of the lithium batteries in the lithium battery device. The thermal energy constraint of thermal storage equipment refers to the upper and lower limits of the power for heat storage and release, and the boundary constraints of the thermal energy storage capacity. The capacity state constraint of a fuel cell integrated energy system refers to the capacity state constraint of each device in the fuel cell integrated energy system. The coupled energy demand constraint under uncertain scenarios refers to the fluctuation boundary constraints set for the uncertain loads of each device in the fuel cell integrated energy system.

[0144] Specifically, operational coupling constraints may include: the total output level of the fuel cell integrated energy system at time t needs to meet the electricity and heat demand of the user side. In this context, since the actual power demand of each user is unknown during the day-ahead scheduling phase, power prediction for each user at time t is required. These represent the predicted values ​​of electrical load and thermal load on the user side, respectively. Let represent the hydrogen storage capacity that the hydrogen storage tank in the hydrogen storage device should store at time t, and the hydrogen consumption capacity of the multi-machine fuel cell device, respectively. This represents the maximum predicted deviation of hydrogen consumption, i.e. Based on the discrepancy between hydrogen storage and consumption in historical data, insufficient hydrogen storage capacity can be preemptively allocated (hydrogen allocation takes a certain amount of time and cannot be responded to in a timely manner).

[0145] When a multi-unit fuel cell device outputs electrical energy, it often generates heat energy. Equipping this waste heat with a heat recovery and storage device allows its energy to be supplied to the load side. The heat energy generated by the multi-unit fuel cell device is as follows: ,in, This represents the thermal energy output provided by the i-th fuel cell at time t. This represents the output of thermal energy provided by an auxiliary heat source (such as an electric boiler or heat pump) at time t. Energy storage devices are typically used to supplement the heat load demand that stacked fuel cell equipment cannot meet. This represents the heat released by the thermal storage device at time t; this can balance the thermal energy fluctuations in the fuel cell integrated energy system. This represents the amount of heat consumed when the thermal storage device is charged at time t, thus storing excess heat.

[0146] Operational coupling constraints also include: ,in, This indicates the maximum output of the fuel cell integrated energy system. This indicates the maximum power that the fuel cell integrated energy system can output. This indicates the maximum amount of electricity that a lithium battery can absorb.

[0147] The model for multi-unit fuel cell equipment considers issues such as losses and power distribution under actual operating conditions, including the power demand during power generation, lithium battery state of charge (SOC), degradation, durability, and efficiency of the multi-unit fuel cell equipment. The state of charge constraint of the lithium battery can be represented by an internal resistance model. Specifically, the internal resistance model used in the lithium battery equipment is as follows: ,in, This indicates the state of charge of the lithium battery. This indicates the nominal capacity of the lithium battery. This indicates the lithium battery power (negative for charging, positive for discharging). Indicates the efficiency of lithium batteries. This indicates the current of the lithium battery. This indicates the output voltage of the lithium battery. This indicates the open-circuit voltage of the lithium battery. This indicates the internal resistance of the lithium battery.

[0148] The output power of a multi-unit fuel cell system must meet the power requirements of all auxiliary equipment, such as air compressors and water circulation pumps. Among the auxiliary equipment, the air compressor has the highest power requirement; therefore, the power requirements of subsequent auxiliary equipment are represented by the air compressor. The remaining deliverable power is called the net power of the multi-unit fuel cell system, denoted as [missing information]. The efficiency curves of the multi-engine fuel cell device studied are as follows: Figure 10 As shown. Figure 10 The horizontal axis represents the net power of the multi-unit fuel cell system, and the vertical axis represents its efficiency. The multi-unit fuel cell system reaches its maximum efficiency point. The power at that time is The range in which a multi-unit fuel cell device operates at high efficiency is defined as follows: At this point, the efficiency of the multi-unit fuel cell equipment remains above 45%, that is... To improve the overall efficiency of the fuel cell integrated energy system, the operating point of multi-unit fuel cell equipment should be tilted towards this region. When multi-unit fuel cell equipment cannot meet the required power... At that time, it is allowed to exceed But it cannot exceed .

[0149] Assuming that the efficiency of a multi-unit fuel cell device, specifically a proton exchange membrane fuel cell (PEMFC), has a certain functional relationship with its output power, offline data fitting analysis shows that a fourth-order polynomial can be used to determine this relationship. This characterizes the curve properties. The overall efficiency of a multi-machine fuel cell system is: The total number of fuel cells in a multi-fuel cell system is Ns. The basic output of the multi-fuel cell system is the product of the total output power and total efficiency of the multi-fuel cell system.

[0150] The attrition costs of multi-unit fuel cell equipment and lithium battery equipment are related to their current degradation state. The degradation model for fuel cell systems and lithium batteries is as follows:

[0151]

[0152] Among them, FT fc and FTbat These represent the fault thresholds at the end of the lifespan of multi-unit fuel cell equipment and lithium battery equipment, respectively. Let represent the health performance indicators of the i-th fuel cell and lithium battery device at time t, respectively. The health performance values ​​of each device can be obtained through impedance spectroscopy testing, but real-time measurements have significant deviations. Therefore, a degradation model for each device in the integrated fuel cell energy system is constructed based on historical measurement data.

[0153]

[0154] The degradation of multi-unit fuel cell equipment is correspondingly categorized into start-stop cycle degradation, load variation cycle degradation, idling degradation, and high-power load degradation, as follows:

[0155]

[0156] in, The increase in resistance attenuation is caused by the inherent attenuation phenomenon related to the load. It is the attenuation increment caused by load changes. This represents the increment of the decay during start-stop operations. k represents the decay increment during idling. cal E is the calendar decay factor (empirical constant). a Let R be the apparent activation energy, R be the gas constant, and T be the absolute temperature. For time power-law terms, The value is 0.5. This indicates the impact of each charge-discharge cycle on the lifespan of a multi-unit fuel cell device.

[0157] The state of charge (SOC) of hydrogen storage devices, lithium batteries, and thermal storage devices are as follows:

[0158]

[0159] in, These represent the capacity of externally injected hydrogen and the capacity of hydrogen consumed by the multi-unit fuel cell device, respectively. These represent the charging efficiency and discharging efficiency of lithium battery devices, respectively. These represent the charging power and discharging power of the lithium battery device, respectively.

[0160] Lithium battery devices operate in two modes: charging and discharging, which correspond to different output power. It can be divided into positive and negative. In order to accurately establish the adjustment model, positive and negative values ​​will be used. Split into two positive values However, the actual output power of the lithium battery device remains: .

[0161] Furthermore, to ensure smooth energy supply and maximize economic efficiency across the entire power generation area, strict and rigorous conditions do not need to be set for energy shortages. Therefore, introducing opportunity constraints allows the energy determination problem to be scaled up, i.e. ,in, These represent the probabilities of recombination of electrical energy and thermal energy, respectively.

[0162] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0163] Based on the same inventive concept, this application also provides an optimization scheduling device for a fuel cell integrated energy system to implement the optimization scheduling method for the fuel cell integrated energy system described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the optimization scheduling device for a fuel cell integrated energy system provided below can be found in the limitations of the optimization scheduling method for the fuel cell integrated energy system described above, and will not be repeated here.

[0164] In one embodiment, such as Figure 11 As shown, an optimized scheduling device for a fuel cell integrated energy system is provided, comprising: an establishment module 11 and a determination module 12, wherein:

[0165] Module 11 is used to establish an optimal scheduling model for the integrated fuel cell energy system, as well as the operational coupling constraints of the integrated fuel cell energy system. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the integrated fuel cell energy system.

[0166] The determination module 12 is used to construct a game mechanism based on the goal of optimizing the benefits on both the supply and demand sides, and combined with the operational coupling constraints, it uses a hierarchical iterative approach to solve the optimization scheduling model and determine the target scheduling strategy.

[0167] In one embodiment, the establishment module 11 includes a first building unit, a second building unit, and a third building unit. The first building unit constructs a day-ahead scheduling model based on the base output of the fuel cell integrated energy system, with the goal of minimizing the operating economic cost of the fuel cell integrated energy system. The second building unit is used to construct an adjustment model based on the adjustment parameters of the base output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, with the goal of optimizing the adjustment cost under the worst operating scenario. The third building unit is used to construct operating coupling constraints based on the day-ahead predicted baseline demand power and the energy demand under uncertain scenarios.

[0168] In one embodiment, the first building unit is specifically used to determine the total hydrogen consumption cost of the integrated fuel cell energy system based on the base output of the multi-unit fuel cell equipment and the lithium battery equipment; determine the first loss cost of the multi-unit fuel cell equipment based on its base output and start-stop status; determine the second loss cost of the lithium battery equipment based on its base output; determine the thermal energy output cost of the thermal storage equipment based on its supplementary heat output; determine the operating economic cost based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and construct a day-ahead scheduling model with the goal of minimizing the operating economic cost.

[0169] In one embodiment, the second building unit is specifically used to determine an initial optimization model based on the adjustment parameters of the basic output of the multi-machine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario; construct a probability distribution fuzzy set based on the historical data of the fuel cell integrated energy system; and construct an adjustment model based on the probability distribution fuzzy set and the initial optimization model, with the optimization objective being the optimal adjustment cost under the worst operating scenario among all operating scenarios.

[0170] In one embodiment, the establishment module 11 is further configured to construct the coupling relationship between the first uncertainty, the second uncertainty, and the third uncertainty based on the coupling relationship between the multi-machine fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device.

[0171] In one embodiment, the second building unit is further configured to determine the initial probability distribution under uncertain scenarios based on historical data; and to construct a fuzzy set of probability distributions using the probability distribution difference index and the initial probability distribution.

[0172] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0173] In one embodiment, the determining module 12 is specifically used to construct a game mechanism with the goal of optimizing the benefits on both the supply and demand sides, based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system.

[0174] In one embodiment, the determining module 12 is further configured to acquire input data of the fuel cell integrated energy system, including the inherent ontological parameters, initial health state, historical data, and initial cost unit price of the fuel cell integrated energy system; based on the input data and combined with the operational coupling constraints, solve the optimization scheduling model to obtain the initial scheduling strategy; and iteratively update the initial cost unit price based on the initial scheduling strategy and the game mechanism until the supply and demand sides meet the equilibrium convergence conditions to obtain the target scheduling strategy.

[0175] Each module in the aforementioned fuel cell integrated energy system's optimization scheduling device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0176] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an optimized scheduling method for a fuel cell integrated energy system. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0177] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0178] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0179] An optimal scheduling model for a fuel cell integrated energy system and its operational coupling constraints are established. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system.

[0180] A game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy.

[0181] In one embodiment, when the processor executes the computer program, it also performs the following steps: based on the base output of the fuel cell integrated energy system, constructing a day-ahead scheduling model with the goal of minimizing the operating economic cost of the fuel cell integrated energy system; based on the adjustment parameters of the base output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, constructing an adjustment model with the goal of optimizing the adjustment cost under the worst operating scenario; and constructing operating coupling constraints based on the day-ahead predicted baseline demand power and the energy demand under uncertain scenarios.

[0182] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the total hydrogen consumption cost of the integrated fuel cell energy system based on the base output of the multi-unit fuel cell equipment and the lithium battery equipment; determining the first loss cost of the multi-unit fuel cell equipment based on its base output and start / stop status; determining the second loss cost of the lithium battery equipment based on its base output; determining the thermal energy output cost of the thermal storage equipment based on its supplementary heat output; determining the operating economic cost based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and constructing a day-ahead scheduling model with the goal of minimizing the operating economic cost.

[0183] In one embodiment, when the processor executes the computer program, it also performs the following steps: determining an initial optimization model based on the adjustment parameters of the basic output of the multi-machine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario; constructing a probability distribution fuzzy set based on the historical data of the fuel cell integrated energy system; and constructing an adjustment model based on the probability distribution fuzzy set and the initial optimization model, with the optimization objective being the optimal adjustment cost under the worst operating scenario among all operating scenarios.

[0184] In one embodiment, when the processor executes the computer program, it also performs the following steps: constructing the coupling relationship between a first uncertainty, a second uncertainty, and a third uncertainty based on the coupling relationship between the multi-machine fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device.

[0185] In one embodiment, when the processor executes the computer program, it also performs the following steps: determining the initial probability distribution under uncertain scenarios based on historical data; and constructing a fuzzy set of probability distributions using a probability distribution difference index and the initial probability distribution.

[0186] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0187] In one embodiment, when the processor executes the computer program, it also performs the following steps: based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, a game mechanism is constructed with the goal of optimizing the benefits on both the supply and demand sides.

[0188] In one embodiment, when the processor executes the computer program, it further performs the following steps: acquiring input data of the fuel cell integrated energy system, including the inherent ontological parameters, initial health state, historical data, and initial unit cost of the fuel cell integrated energy system; solving the optimization scheduling model based on the input data and combined with the operational coupling constraints to obtain the initial scheduling strategy; iteratively updating the initial unit cost based on the initial scheduling strategy and the game mechanism until the supply and demand sides meet the equilibrium convergence conditions to obtain the target scheduling strategy.

[0189] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0190] An optimal scheduling model for a fuel cell integrated energy system and its operational coupling constraints are established. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system.

[0191] A game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy.

[0192] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing a day-ahead scheduling model based on the base output of the fuel cell integrated energy system, with the goal of minimizing the operating economic cost of the fuel cell integrated energy system; constructing an adjustment model based on the adjustment parameters of the base output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, with the goal of optimizing the adjustment cost under the worst operating scenario; and constructing operating coupling constraints based on the day-ahead predicted baseline demand power and the energy demand under uncertain scenarios.

[0193] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the total hydrogen consumption cost of the integrated fuel cell energy system based on the base output of the multi-unit fuel cell equipment and the lithium battery equipment; determining the first loss cost of the multi-unit fuel cell equipment based on its base output and start-stop status; determining the second loss cost of the lithium battery equipment based on its base output; determining the thermal energy output cost of the thermal storage equipment based on its supplementary heat output; determining the operating economic cost based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and constructing a day-ahead scheduling model with the goal of minimizing the operating economic cost.

[0194] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining an initial optimization model based on the adjustment parameters of the basic output of the multi-machine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario; constructing a probability distribution fuzzy set based on the historical data of the fuel cell integrated energy system; and constructing an adjustment model based on the probability distribution fuzzy set and the initial optimization model, with the optimization objective being the optimal adjustment cost under the worst operating scenario among all operating scenarios.

[0195] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing the coupling relationship between a first uncertainty, a second uncertainty, and a third uncertainty based on the coupling relationship between the multi-machine fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device.

[0196] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the initial probability distribution under uncertain scenarios based on historical data; and constructing a fuzzy set of probability distributions using a probability distribution difference index and the initial probability distribution.

[0197] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0198] In one embodiment, when the computer program is executed by the processor, it also performs the following steps: based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, constructing a game mechanism with the goal of optimizing the benefits on both the supply and demand sides.

[0199] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring input data of the fuel cell integrated energy system, including the inherent ontological parameters of the fuel cell integrated energy system, initial health state, historical data, and initial cost per unit; solving the optimization scheduling model based on the input data and combined with operational coupling constraints to obtain an initial scheduling strategy; iteratively updating the initial cost per unit based on the initial scheduling strategy and the game mechanism until the supply and demand sides meet the equilibrium convergence conditions to obtain the target scheduling strategy.

[0200] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0201] An optimal scheduling model for a fuel cell integrated energy system and its operational coupling constraints are established. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system.

[0202] A game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with operational coupling constraints, a hierarchical iterative approach is used to solve the optimization scheduling model and determine the target scheduling strategy.

[0203] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing a day-ahead scheduling model based on the base output of the fuel cell integrated energy system, with the goal of minimizing the operating economic cost of the fuel cell integrated energy system; constructing an adjustment model based on the adjustment parameters of the base output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, with the goal of optimizing the adjustment cost under the worst operating scenario; and constructing operating coupling constraints based on the day-ahead predicted baseline demand power and the energy demand under uncertain scenarios.

[0204] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the total hydrogen consumption cost of the integrated fuel cell energy system based on the base output of the multi-unit fuel cell equipment and the lithium battery equipment; determining the first loss cost of the multi-unit fuel cell equipment based on its base output and start-stop status; determining the second loss cost of the lithium battery equipment based on its base output; determining the thermal energy output cost of the thermal storage equipment based on its supplementary heat output; determining the operating economic cost based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and constructing a day-ahead scheduling model with the goal of minimizing the operating economic cost.

[0205] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining an initial optimization model based on the adjustment parameters of the basic output of the multi-machine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario; constructing a probability distribution fuzzy set based on the historical data of the fuel cell integrated energy system; and constructing an adjustment model based on the probability distribution fuzzy set and the initial optimization model, with the optimization objective being the optimal adjustment cost under the worst operating scenario among all operating scenarios.

[0206] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing the coupling relationship between a first uncertainty, a second uncertainty, and a third uncertainty based on the coupling relationship between the multi-machine fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device.

[0207] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: determining the initial probability distribution under uncertain scenarios based on historical data; and constructing a fuzzy set of probability distributions using a probability distribution difference index and the initial probability distribution.

[0208] In one embodiment, the fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

[0209] In one embodiment, when the computer program is executed by the processor, it also performs the following steps: based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, constructing a game mechanism with the goal of optimizing the benefits on both the supply and demand sides.

[0210] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: acquiring input data of the fuel cell integrated energy system, including the inherent ontological parameters of the fuel cell integrated energy system, initial health state, historical data, and initial cost per unit; solving the optimization scheduling model based on the input data and combined with operational coupling constraints to obtain an initial scheduling strategy; iteratively updating the initial cost per unit based on the initial scheduling strategy and the game mechanism until the supply and demand sides meet the equilibrium convergence conditions to obtain the target scheduling strategy.

[0211] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0212] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0213] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An optimized scheduling method for a fuel cell integrated energy system, characterized in that, The method includes: An optimal scheduling model for a fuel cell integrated energy system is established, along with the operational coupling constraints of the fuel cell integrated energy system. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the fuel cell integrated energy system. A game theory mechanism is constructed based on the goal of optimizing benefits on both the supply and demand sides. Combined with the aforementioned operational coupling constraints, the optimization scheduling model is solved using a hierarchical iterative approach to determine the target scheduling strategy.

2. The method according to claim 1, characterized in that, The establishment of the optimized scheduling model for the integrated fuel cell energy system, and the operational coupling constraints of the integrated fuel cell energy system, include: Based on the basic output of the fuel cell integrated energy system, and with the goal of minimizing the operating economic cost of the fuel cell integrated energy system, the day-ahead scheduling model is constructed. Based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, the adjustment model is constructed with the optimization objective of optimizing the adjustment cost under the worst operating scenario. The operational coupling constraints are constructed based on the day-ahead forecast baseline power demand and the energy demand under uncertain scenarios.

3. The method according to claim 2, characterized in that, The fuel cell integrated energy system includes multi-fuel cell equipment, hydrogen storage equipment, lithium battery equipment, and thermal storage equipment. Based on the basic output of the fuel cell integrated energy system, and with the objective of minimizing the operating economic cost of the fuel cell integrated energy system, the day-ahead scheduling model is constructed, including: The total hydrogen consumption cost of the fuel cell integrated energy system is determined based on the basic output of the multi-engine fuel cell equipment and the lithium battery equipment. Based on the base output and start / stop status of the multi-machine fuel cell equipment, determine the first loss cost of the multi-machine fuel cell equipment; based on the base output of the lithium battery equipment, determine the second loss cost of the lithium battery equipment. The thermal energy output cost of the thermal storage device is determined based on its supplementary heat output capacity. The operating economic cost is determined based on the total hydrogen consumption cost, the first loss cost, the second loss cost, and the thermal energy output cost; and the day-ahead scheduling model is constructed with the goal of minimizing the operating economic cost.

4. The method according to claim 2, characterized in that, The fuel cell integrated energy system includes a multi-fuel cell unit, a lithium battery unit, a thermal storage unit, and a hydrogen storage unit. Based on the adjustment parameters of the basic output of the fuel cell integrated energy system and the prediction deviation under uncertain scenarios, the adjustment model is constructed with the optimization objective of minimizing the adjustment cost under the worst-case operating scenario. The model includes: The initial optimization model is determined based on the adjustment parameters of the basic output of the multi-engine fuel cell equipment, the adjustment parameters of the basic output of the lithium battery equipment, and the prediction deviation of the uncertainty scenario. Based on the historical data of the fuel cell integrated energy system, a probability distribution fuzzy set is constructed. Based on the probability distribution fuzzy set and the initial optimization model, the adjustment model is constructed with the optimization objective of optimizing the adjustment cost under the worst operating scenario in all operating scenarios.

5. The method according to claim 4, characterized in that, The prediction bias in the uncertainty scenario includes a first uncertainty of the multi-machine fuel cell device and the lithium battery device, a second uncertainty of the thermal storage device, and a third uncertainty of the hydrogen storage device; the method further includes: Based on the coupling relationship between the multi-machine fuel cell device, the lithium battery device, the thermal storage device, and the hydrogen storage device, the coupling relationship between the first uncertainty, the second uncertainty, and the third uncertainty is constructed.

6. The method according to claim 4, characterized in that, The construction of a probability distribution fuzzy set based on historical data of the fuel cell integrated energy system includes: Based on the historical data, determine the initial probability distribution under the uncertainty scenario; The probability distribution fuzzy set is constructed using the probability distribution difference index and the initial probability distribution.

7. The method according to claim 2, characterized in that, The fuel cell integrated energy system includes a multi-fuel cell device, a lithium battery device, and a thermal storage device. The operational coupling constraints include the supply and demand balance constraints of the fuel cell integrated energy system, the state of charge constraints of the lithium battery, the thermal energy constraints of the thermal storage device, the capacity state constraints of the fuel cell integrated energy system, and the coupled energy demand constraints under uncertain scenarios.

8. The method according to claim 1, characterized in that, The game-theoretic mechanism constructed based on the goal of optimizing benefits on both the supply and demand sides includes: Based on the unit price of hydrogen, the time-of-use electricity price, the hydrogen consumption and basic output of the fuel cell integrated energy system, and the loss cost of the fuel cell integrated energy system, a game mechanism is constructed with the goal of optimizing the benefits on both the supply and demand sides.

9. The method according to claim 8, characterized in that, The game mechanism, based on the goal of optimizing benefits on both the supply and demand sides, and combined with the operational coupling constraints, employs a hierarchical iterative approach to solve the optimization scheduling model and determine the target scheduling strategy, including: The input data of the fuel cell integrated energy system is obtained, including the inherent physical parameters, initial health status, historical data and initial unit cost of the fuel cell integrated energy system. Based on the input data and the operational coupling constraints, the optimized scheduling model is solved to obtain the initial scheduling strategy. Based on the initial scheduling strategy and the game mechanism, the initial cost unit price is iteratively updated until the supply and demand sides meet the equilibrium convergence condition, thus obtaining the target scheduling strategy.

10. An optimized scheduling device for a fuel cell integrated energy system, characterized in that, The device includes: A module is established to build an optimal scheduling model for the integrated fuel cell energy system, as well as the operational coupling constraints of the integrated fuel cell energy system. The optimal scheduling model includes a day-ahead scheduling model and an adjustment model suitable for uncertain scenarios. The day-ahead scheduling model aims to minimize the operating economic cost of the integrated fuel cell energy system. The determination module is used to construct a game mechanism based on the goal of optimizing the benefits on both the supply and demand sides, and, in conjunction with the aforementioned operational coupling constraints, to solve the optimization scheduling model in a hierarchical iterative manner to determine the target scheduling strategy.

Images