Adjustable load management method and device based on multi-target random modeling

Abstract

The invention relates to the technical field related to load scheduling, in particular to an adjustable load management method and device based on multi-target random modeling. The method comprises the following steps: based on the structure and characteristics of an energy hub, establishing an operation model of energy hub equipment; according to system operation characteristics, an uncertain model of loads and prices based on an adjustable load management strategy is established; establishing a multi-target random model, converting a plurality of preset targets into a single target, and optimizing a load management strategy by taking the maximum single target as a target based on the uncertain model and the operation model of the load and the price; wherein the plurality of preset targets comprise operation cost reduction and carbon emission reduction.

Description

Technical Field

[0001] This application relates to the technical field of load scheduling, and specifically relates to an adjustable load management method and device based on multi-objective stochastic modeling. Background Art

[0002] With the continuous growth of global energy demand and the increasingly severe environmental problems, traditional power systems are facing major challenges. These systems are typically characterized by centralized power generation and unidirectional power flow, and have problems such as high emissions, high power losses, low power quality, and low reliability. To address these challenges, the energy industry is gradually developing towards a more flexible, efficient, and environmentally friendly direction.

[0003] In this transformation process, the concept of distributed energy resources (DERs) has emerged. These resources include small, decentralized power generation facilities such as photovoltaic panels, wind turbines, integrated heat and power storage devices, etc. They can provide a more flexible energy supply and help improve the reliability of the system and reduce dependence on traditional energy sources.

[0004] However, the integration and management of distributed energy resources bring new technical challenges. In particular, how to effectively manage and schedule these resources to meet the changing power demand, while optimizing the energy utilization efficiency and reducing the environmental impact, has become a key issue. Summary of the Invention

[0005] In view of this, embodiments of this application are committed to providing an adjustable load management method and device based on multi-objective stochastic modeling to more comprehensively and effectively analyze load scheduling.

[0006] This application provides an adjustable load management method based on multi-objective stochastic modeling, including:

[0007] Based on the structure and characteristics of the energy hub, establish an operation model of the energy hub equipment;

[0008] According to the system operation characteristics, establish an uncertain model of load and price based on the adjustable load management strategy;

[0009] Establish a multi-objective stochastic model and convert a plurality of preset objectives into a single objective, and optimize the load management strategy with the maximum of the single objective as the goal based on the uncertain model of load and price and the operation model.

[0010] Among them, the plurality of preset objectives include: reducing operating costs and reducing carbon emissions.

[0011] In some embodiments, the energy hub includes: renewable energy, combined heat and power generator, plug-in hybrid vehicle, hydrogen equipment system.

[0012] In some embodiments, the operation model of the plug-in hybrid vehicle includes:

[0013]

[0014] wherein, within a specific time period t ∈ [p, q] of a day, the electric vehicle is working outside and cannot be connected to the hub system; is the state of charge of the electric vehicle at time t; and are the initial and final state of charge of the electric vehicle; μ PHEV，c and μ PHEV，d are the charge and discharge efficiencies of the electric vehicle; and P PHEV,d are the charge and discharge powers of the electric vehicle; and are the upper and lower limits of the capacity of the electric vehicle; and are binary variables representing the charge and discharge states.

[0015] In some embodiments, the operation model of the hydrogen equipment system includes:

[0016] Electric energy is consumed by the electrolyzer to produce hydrogen, and its power utilization degree is as follows:

[0017]

[0018]

[0019] In the formula, is the amount of electricity input to the electrolyzer; is a binary variable of the operating state of the electrolyzer; and are the upper and lower limits of the electrolyzer power;

[0020] The maximum limit of hydrogen mole count is calculated by the following formula:

[0021]

[0022] In the formula, is the amount of hydrogen moles produced by the electrolyzer; is the upper limit of the hydrogen mole amount of the electrolyzer;

[0023] The formula for hydrogen produced by using the electrolyzer power is as follows:

[0024]

[0025] In the formula, η EL is the electrolyzer efficiency; LHV H2 is the calorific value of hydrogen;

[0026] When the load in the energy hub exceeds the supply capacity of other devices, power is supplied by generating electricity through a hydrogen fuel cell; it is expressed by the following formula:

[0027]

[0028] In the formula, is the molar amount of hydrogen generated by the fuel cell; is the upper limit of the molar amount of hydrogen in the fuel cell; is a binary variable representing the operating state of the fuel cell;

[0029] The power generated by the fuel cell can be expressed as a function of the number of moles of hydrogen used:

[0030]

[0031] In the formula, is the electric power generated by the fuel cell; η FC is the efficiency of the fuel cell;

[0032] The constraints for supplying power through the fuel cell are as follows:

[0033]

[0034] In the formula, and are the upper and lower limits of the fuel cell power;

[0035] In the hydrogen system, the electrolyzer and the fuel cell cannot consume or generate hydrogen energy simultaneously; this limitation is reflected in the following formula:

[0036]

[0037] The pressure limit of the hydrogen storage tank is modeled as follows:

[0038]

[0039] In the formula, is the pressure of the hydrogen storage tank at time t; is the pressure of the hydrogen storage tank at the initial time; and are the upper and lower limits of the pressure of the hydrogen storage tank;

[0040] Due to the presence of the electrolyzer and the fuel cell, the hydrogen in the hydrogen storage tank will be replenished and consumed; the pressure of the hydrogen storage tank at non-initial times is calculated as follows:

[0041]

[0042] In the formula, is the air pressure coefficient; T H2is the average temperature of hydrogen; V H2 is the volume of the hydrogen storage tank.

[0043] In some embodiments, the uncertainty model of the load and price is as follows:

[0044]

[0045] In the formula, and are the power of the up / down transfer of electricity; and are the ratio of the up / down transfer of demand response; and are binary variables indicating whether demand response is performed;

[0046]

[0047] In the formula, L d is the load; is the load mean value; is the load variance; pr is the market price; pr mean is the market price mean value; σ pr is the market price variance.

[0048] In some embodiments, the multi-objective stochastic model is as follows:

[0049]

[0050] In the formula, W i is the weight vector; f i is a single objective function; is the optimal solution obtained by single-objective optimization; the value of 1 / p determines the decision maker's preference for the target distance.

[0051] In some embodiments, p takes the value of ∞.

[0052] This application provides an electronic device, including:

[0053] a processor, and a memory for storing the executable program of the processor;

[0054] The processor is configured to implement the adjustable load management method based on multi-objective stochastic modeling as described above by running the program in the memory.

[0055] This application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the processor is caused to execute the adjustable load management method based on multi-objective stochastic modeling as described above.

[0056] The present application provides a computer program product, including a computer program which, when executed by a processor, implements the above-mentioned adjustable load management method based on multi-objective stochastic modeling.

[0057] An adjustable load management method based on multi-objective stochastic modeling provided by the present application first establishes an operation model of energy hub devices based on the structure and characteristics of the energy hub; establishes an uncertain model of load and price based on an adjustable load management strategy according to the system operation characteristics; establishes a multi-objective stochastic model and converts a plurality of preset objectives into a single objective, and optimizes the load management strategy with the maximum of the single objective as the target based on the uncertain model of load and price and the operation model; wherein, the plurality of preset objectives include: reducing operation costs and reducing carbon emissions. Thus, taking reducing operation costs and reducing carbon emissions as preset objectives, establishing a multi-objective stochastic model and converting it into a single objective for optimization can comprehensively consider the economic and environmental performance of the system. Optimizing the load management strategy with the maximum of the single objective as the target can find the optimal solution of the system, maximize the energy utilization efficiency, reduce energy waste, and reduce environmental pollution. At the same time, by optimizing based on the uncertain model of load and price and the operation model, the load management strategy can be made more in line with the actual situation, improving the overall performance and sustainability of the system. Description of the Drawings

[0058] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0059] Figure 1 is a schematic flowchart of an adjustable load management method based on multi-objective stochastic modeling provided by an embodiment of the present application.

[0060] Figure 2 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed Embodiments

[0061] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0062] Application Overview

[0063] With the continuous growth of global energy demand and the increasingly severe environmental problems, traditional power systems are facing major challenges. These systems are typically characterized by centralized power generation and unidirectional power flow, suffering from problems such as high emissions, high power losses, low power quality, and low reliability. To address these challenges, the energy industry is gradually evolving towards a more flexible, efficient, and environmentally friendly direction.

[0064] In this transformation process, the concept of distributed energy resources (DERs) has emerged. These resources include small, decentralized power generation facilities such as photovoltaic panels, wind turbines, integrated thermal and power storage devices, etc. They can provide a more flexible energy supply, contribute to improving system reliability, and reduce dependence on traditional energy sources.

[0065] However, the integration and management of distributed energy resources bring new technical challenges. In particular, how to effectively manage and schedule these resources to meet the changing power demand while optimizing energy utilization efficiency and reducing environmental impact has become a key issue. In addition, existing power systems often lack sufficient flexibility to cope with peak and trough demands, which limits the effective utilization of renewable energy and may lead to energy waste.

[0066] To improve the flexibility and efficiency of power systems, the concept of an energy hub has been proposed. An energy hub is a system that integrates multiple energy forms and conversion technologies, enabling the mutual conversion and optimal scheduling of multiple energies such as electricity, heat, and gas. Such a system can better respond to demand changes, improve energy utilization efficiency, and promote the wider application of renewable energy.

[0067] Although the concept of an energy hub provides new solutions for power systems, in actual operation, how to establish an effective model to simultaneously handle the daily planning of different energy forms and how to optimize system operation while considering economic and environmental benefits remains an urgent problem to be solved. In addition, existing research often evaluates the performance of energy hubs from a single perspective (such as economy), ignoring the interactions and comprehensive benefits between different energy forms.

[0068] Therefore, a new type of load management method needs to be developed, which can not only handle the multi - energy characteristics in power systems but also optimize economic and environmental objectives under uncertain conditions. This requires an adjustable load management method based on multi - objective stochastic modeling to achieve the efficient, flexible, and sustainable operation of the energy system.

[0069] After introducing the basic principles of this application, various non - restrictive embodiments of this application will be specifically introduced with reference to the accompanying drawings.

[0070] Exemplary Method

[0071] Figure 1 It is a schematic flowchart of an adjustable load management method based on multi-objective stochastic modeling provided by an embodiment of the present application. As Figure 1 shown, the method includes the following contents.

[0072] Step S110: Based on the structure and characteristics of the energy hub, establish an operation model of the energy hub equipment;

[0073] By constructing an equipment operation model based on the structure and characteristics of the energy hub, the operation state of the energy hub can be accurately simulated and predicted. This helps to achieve an in-depth understanding and effective control of the energy production, conversion, and distribution processes.

[0074] Step S120: According to the system operation characteristics, establish an uncertain model of load and price based on the adjustable load management strategy;

[0075] Creating a model considering the uncertainty of load and price can enhance the system's adaptability to market fluctuations and demand changes. Such a model helps to formulate flexible load management strategies to cope with unpredictable market conditions.

[0076] Step S130: Establish a multi-objective stochastic model and convert a plurality of preset objectives into a single objective, and optimize the load management strategy with the maximum of the single objective as the target; wherein, the plurality of preset objectives include: reducing the operating cost and reducing the carbon emission.

[0077] With such settings, in the solution provided by the present application, reducing the operating cost and reducing the carbon emission are used as preset objectives, a multi-objective stochastic model is established and converted into a single objective for optimization, so that the economic and environmental performance of the system can be comprehensively considered. Optimizing the load management strategy with the maximum of the single objective as the target can find the optimal solution of the system, maximize the energy utilization efficiency, reduce energy waste, and reduce environmental pollution. At the same time, by optimizing based on the uncertain model of load and price and the operation model, the load management strategy can be made more in line with the actual situation, improving the overall performance and sustainability of the system.

[0078] Specifically, the energy hub includes renewable energy, combined heat and power generators, plug-in hybrid electric vehicles, and hydrogen equipment systems, etc.

[0079] The modeling of electric vehicles is as follows. It is assumed that within a specific time period of a day, \(t\in[p,q]\), when the electric vehicle is working outside and cannot be connected to the hub system, it cannot be charged or discharged. Equation (1) represents the state of charge of the electric vehicle connected to the system. Equation (2) represents the capacity range of the state of charge of the electric vehicle. Equations (3) and (4) represent that the state of charge of the electric vehicle at the initial and final moments is the same, and it is fully charged before going out. Equations (5) and (6) represent the numerical limits of the charge and discharge of the electric vehicle. Equation (7) represents that the electric vehicle cannot be charged and discharged simultaneously.

[0080]

[0081]

[0082] In the formula, is the state of charge of the electric vehicle at time \(t\); and are the state of charge of the electric vehicle at the initial and final moments; \(\mu\) PHEV，c and \(\mu\) PHEV，d are the charge and discharge efficiency of the electric vehicle; and \(P\) PHEV,d are the charge and discharge power of the electric vehicle; and are the upper and lower limits of the capacity of the electric vehicle; and are binary variables representing the charge and discharge states.

[0083] The hydrogen system includes an electrolyzer, a hydrogen fuel cell, and a hydrogen storage tank, and the modeling is as follows.

[0084] Electric energy is consumed by the electrolyzer to produce hydrogen, and the power utilization degree is as follows:

[0085]

[0086] In the formula, is the amount of electricity input to the electrolyzer; is a binary variable representing the operating state of the electrolyzer; and are the upper and lower limits of the electrolyzer power.

[0087] The maximum limit of hydrogen mole count is calculated by the following formula:

[0088]

[0089] In the formula, is the amount of hydrogen moles produced by the electrolyzer; is the upper limit of the hydrogen mole amount of the electrolyzer.

[0090] The formula for the hydrogen produced by using the electrolyzer power is as follows:

[0091]

[0092] In the formula, η EL is the electrolyzer efficiency; LHV H2 is the calorific value of hydrogen.

[0093] When the load in the energy hub exceeds the supply capacity of other devices, power is supplied by generating electricity through a hydrogen fuel cell. It is expressed by the following formula:

[0094]

[0095] In the formula, is the molar amount of hydrogen generated by the fuel cell; is the upper limit of the molar amount of hydrogen in the fuel cell; is a binary variable representing the operating state of the fuel cell.

[0096] The power generated by the fuel cell can be expressed as a function of the number of moles of hydrogen used:

[0097]

[0098] In the formula, is the electric power generated by the fuel cell; η FC is the efficiency of the fuel cell.

[0099] The constraints for power supply by the fuel cell are as follows:

[0100]

[0101] In the formula, and are the upper and lower limits of the fuel cell power.

[0102] In the hydrogen system, the electrolyzer and the fuel cell cannot consume or produce hydrogen energy simultaneously. This limitation is reflected in the following formula:

[0103]

[0104] The pressure limit of the hydrogen storage tank is modeled as follows:

[0105]

[0106] In the formula, is the pressure of the hydrogen storage tank at time t; is the pressure of the hydrogen storage tank at the initial time; and are the upper and lower limits of the pressure of the hydrogen storage tank.

[0107] Due to the existence of the electrolyzer and fuel cell, hydrogen in the hydrogen storage tank will be supplemented and consumed. The pressure of the hydrogen storage tank at a non-initial moment is calculated as follows:

[0108]

[0109] In the formula, is the air pressure coefficient; T H2 is the average temperature of hydrogen; V H2 is the volume of the hydrogen storage tank.

[0110] The modeling of devices such as renewable energy and combined heat and power generators is conventional and will not be elaborated here.

[0111] The uncertain model of the load and price can also be called establishing an adjustable load management strategy and an uncertain model:

[0112] Adjustable load response is related to activities that actively affect power consumption during scheduling, execution, and control. Participants consciously decide their power consumption behaviors through demand response programs. Demand response allows for changing the original power consumption plan, thereby changing the load curve and achieving peak shifting. Its modeling is as follows:

[0113]

[0114] In the formula, and are the power of upward / downward transfer of electricity; and are the ratios of upward / downward transfer of demand response; and are binary variables indicating whether demand response is carried out.

[0115] Probability modeling of load and price.

[0116] The present invention considers the uncertainties of load and price. For the random variables of these two, they are represented by the following distribution functions and simulated using point estimation:

[0117]

[0118] In the formula, L d is the load; is the load mean; is the load variance; pr is the market price; pr mean is the market price mean; σ pr is the market price variance.

[0119] Furthermore, the object of the present invention is to reduce operating costs and carbon emissions:

[0120]

[0121]

[0122] Wherein, is the natural gas price; is the volume of gas purchased from the main grid; the electricity price; is the volume of electricity purchased from the main grid; the charge-discharge price of electric energy storage; and is the charge-discharge volume of electric energy storage; is the price of electricity demand response; is the price of hydrogen energy storage; and is the power of the fuel cell and electrolyzer; β e is the electricity emission factor; β g is the gas emission factor.

[0123] The balance condition is as follows:

[0124]

[0125] Wherein, is the photovoltaic electricity volume of the j-th energy hub; is the wind power electricity volume of the j-th energy hub; is the electricity volume transferred from the n-th energy hub to the j-th energy hub.

[0126] Multi-objective decision-making is multi-criteria decision-making with heterogeneous objective functions. In the multi-objective improvement method of the present invention, the original multi-objective problem is transferred to an individual objective problem that has been solved once or several times. The overall structure is as follows:

[0127]

[0128] Wherein, W i is the weight vector; f i is a single objective function; is the optimal solution obtained by single-objective optimization; the value of 1 / p determines the decision maker's preference for the objective distance.

[0129] If p = ∞, the above formula becomes

[0130]

[0131] The two objectives of the present invention can be redefined as

[0132]

[0133] The above formula can be further transformed by linear programming into:

[0134]

[0135] In the formula, ξ is an auxiliary variable.

[0136] In summary, due to the above technical solutions adopted by the present invention, it has the following advantages: By considering various energy resources such as electric vehicles, wind turbines, and photovoltaic power generation from the perspectives of the economy of the energy hub and environmental pollution, the present invention models and plans energy management. Considering the uncertainties of energy prices and loads, the system operation can be optimized according to the fluctuations of energy prices, reducing the total cost, reducing environmental pollution, and improving the reliability of the system. The demand response strategy and storage system can provide better load distribution and better optimization of the operation of renewable resources. Therefore, the present invention can be widely applied to the field of adjustable load management.

[0137] Exemplary Electronic Device

[0138] Next, refer to Figure 2 to describe the electronic device according to an embodiment of the present application. Figure 2 The block diagram of the electronic device according to an embodiment of the present application is illustrated.

[0139] As Figure 2 shown, the electronic device 200 includes one or more processors 210 and a memory 220.

[0140] The processor 210 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 200 to perform desired functions.

[0141] The memory 220 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 210 may run the program instructions to implement the adjustable load management method based on multi-objective stochastic modeling and / or other desired functions of the various embodiments of the present application described above. Various contents such as category correspondence relationships may also be stored in the computer-readable storage media.

[0142] In one example, the electronic device 200 may further include: an input device 230 and an output device 240, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0143] In addition, the input device 230 may further include, for example, a keyboard, a mouse, an interface, and the like. The output device 240 may output various information to the outside, including analysis results and the like. The output device 240 may include, for example, a display, a speaker, a printer, a communication network, and a remote output device connected thereto, and the like.

[0144] Of course, for simplicity, Figure 2 only some of the components related to the present application in the electronic device are shown, and components such as a bus, an input / output interface, and the like are omitted. In addition, according to specific application scenarios, the electronic device may further include any other appropriate components.

[0145] Exemplary Computer Program Product and Computer Readable Storage Medium

[0146] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps in the adjustable load management method based on multi-objective stochastic modeling according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0147] The computer program product may be written in any combination of one or more programming languages to write program code for performing the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0148] In addition, an embodiment of the present application may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when run by a processor, cause the processor to execute the steps in the adjustable load management method based on multi-objective stochastic modeling according to various embodiments of the present application described in the above "Exemplary Method" section of this specification.

[0149] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0150] The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although several example aspects and embodiments have been discussed above, those skilled in the art will recognize some of their variations, modifications, alterations, additions, and sub-combinations.

Claims

1. An adjustable load management method based on multi-objective stochastic modeling, characterized in that: include: Based on the structure and characteristics of the energy hub, establish the operation model of the energy hub equipment; According to the system operation characteristics, an uncertain model of load and price based on adjustable load management strategy is established; Establish a multi-objective stochastic model and convert the preset multiple objectives into a single objective, and optimize the load management strategy with the maximum of the single objective as the goal based on the uncertainty model and operation model of the load and price; Among them, the preset goals include: reducing operating costs and reducing carbon emissions.

2. The adjustable load management method based on multi-objective stochastic modeling according to claim 1 is characterized in that: The energy hub includes: renewable energy, cogeneration generators, plug-in hybrid vehicles, and hydrogen equipment systems.

3. The adjustable load management method based on multi-objective stochastic modeling according to claim 2 is characterized in that: The operation model of the plug-in hybrid electric vehicle includes: Among them, during a specific time of the day t∈[p,q], electric vehicles are working outside and cannot access the hub system; is the state of charge of the electric vehicle at time t; and is the charge state of the electric vehicle at the initial and final moments; μ PHEV，c and μ PHEV，d is the charging and discharging efficiency of the electric vehicle; and is the charging and discharging power of the electric vehicle; and are the upper and lower limits of electric vehicle capacity; and is a binary variable representing the charge and discharge state.

4. The adjustable load management method based on multi-objective stochastic modeling according to claim 2 is characterized in that: The operation model of the hydrogen equipment system includes: The electrolyzer consumes electricity to produce hydrogen, and its power utilization is as follows: In the formula, is the amount of electricity fed into the electrolytic cell; is a binary variable of the electrolyzer operating status; and The upper and lower limits of the electrolyzer power; The maximum limit on hydrogen mole count is calculated by the following formula: In the formula, is the molar amount of hydrogen produced by the electrolyzer; is the upper limit of the molar amount of hydrogen in the electrolyzer; The formula for hydrogen produced using electrolyser power is as follows: Where η EL is the electrolyzer efficiency; LHV H2 is the calorific value of hydrogen; When the load in the energy hub exceeds the supply capacity of other equipment, electricity is generated by hydrogen fuel cells for supply; this is expressed by the following formula: In the formula, is the molar amount of hydrogen produced by the fuel cell; It is the upper limit of the molar amount of hydrogen in the fuel cell; A binary variable representing the operating status of the fuel cell; The power generated by a fuel cell can be expressed as a function of the number of moles of hydrogen used: In the formula, is the electrical power generated by the fuel cell; η FC is the efficiency of the fuel cell; The constraints for providing power via fuel cells are as follows: In the formula, and are the upper and lower limits of the fuel cell power; In a hydrogen system, the electrolyzer and fuel cell cannot consume or produce hydrogen energy at the same time; this limitation is reflected in the following equation: The pressure limitation of the hydrogen storage tank is modeled as follows: In the formula, is the hydrogen storage tank pressure at time t; is the hydrogen storage tank pressure at the initial moment; and are the upper and lower limits of the hydrogen storage tank pressure; Due to the presence of the electrolyzer and fuel cell, the hydrogen in the hydrogen storage tank will be replenished and consumed; the calculation of the hydrogen storage tank pressure at non-initial moments is as follows: In the formula, is the pressure coefficient; T H2 is the average temperature of hydrogen; V H2 is the volume of the hydrogen storage tank.

5. The adjustable load management method based on multi-objective stochastic modeling according to claim 1 is characterized in that: The load and price uncertainty model is as follows: In the formula, and is the power of the up / down transfer of electricity; and is the ratio of demand response up and down shifts; and is a binary variable indicating whether demand response is performed; Where, L d is the load; is the load mean; is the load variance; pr is the market price; pr mean is the market price mean; σ pr is the market price variance.

6. The adjustable load management method based on multi-objective stochastic modeling according to claim 1 is characterized in that: The multi-objective stochastic model is as follows: Where W i is the weight vector; f i is a single objective function; It is the optimal solution obtained by single-objective optimization; the value of 1 / p determines the decision maker's inclination towards the target distance.

7. The adjustable load management method based on multi-objective stochastic modeling according to claim 1 is characterized in that: The value of p is ∞.

8. An electronic device, characterized in that: include: A processor, and a memory for storing a program executable by the processor; The processor is used to implement the adjustable load management method based on multi-objective stochastic modeling as described in any one of claims 1 to 7 by running the program in the memory.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, enables the processor to execute the adjustable load management method based on multi-objective stochastic modeling according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the adjustable load management method based on multi-objective stochastic modeling according to any one of claims 1 to 7.

Images