Building fuel cell integrated energy system optimal configuration method based on multi-objective optimization

Abstract

The invention relates to a multi-objective optimization-based optimal configuration method for a building fuel cell integrated energy system. The method comprises the following steps of S1, performing modeling aiming at the processes of realizing energy consumption, responding to a power demand and responding to a hot water demand of the building fuel cell integrated energy system; s2, with the purpose of minimizing the carbon emission objective function and the economic objective function, performing iterative optimization on the capacity configuration of the building fuel cell integrated energy system by using NSGA II to obtain a Pareto frontier solution set; and S3, based on the Pareto frontier solution set, obtaining the optimized capacity configuration of the building fuel cell integrated energy system by approaching the sorting of ideal solutions based on an entropy weight method. Compared with the prior art, the building fuel cell comprehensive energy system integrated optimization configuration based on multi-objective optimization is achieved.

Description

Technical Field

[0001] The present invention relates to the field of comprehensive energy system configuration optimization, and in particular to a building fuel cell comprehensive energy system optimization configuration method based on multi-objective optimization. Background Art

[0002] At present, the integrated energy system based on clean energy and traditional power grid provides a transformation model for the transformation of zero-carbon energy system. However, due to the complexity of the system, the design of this integrated energy system faces many difficulties. First, the coupling mechanism between various power generation facilities and demand-side power equipment loads will affect the overall efficiency of the energy system. Second, the high cost of new energy systems and the volatility of their own power generation make it difficult to implement actual integrated energy station projects. Compared with traditional power systems, the cost of photovoltaic, wind power, and fuel cell systems is much higher than that of using existing traditional power supply systems. In addition, photovoltaic and wind power, as the most mature clean energy power generation devices, are subject to weather and environmental factors, have high volatility and intermittency, and it is difficult to achieve a balance between supply and demand at every moment, which brings challenges to the resilience and frequency control of the power system.

[0003] Most existing energy system optimization models are based on single-objective optimization algorithms or lack decision-making support models. The biggest problem with single-objective optimization models for the current integrated energy system optimization is the setting of the objective function. In the initial stage of increasing the proportion of clean energy power generation, economic benefits are the main evaluation target, and a single objective function can be set as the evaluation criterion. With the increasing importance of carbon reduction in future power systems, environmental factors are also one of the factors that cannot be ignored. However, due to the conflict between the optimal solutions of economic and environmental goals, there will be problems with function setting when combining the two evaluation criteria for a single objective. In addition, although there have been some attempts at multi-objective optimization methods, it is difficult for decision makers to make an objective optimal choice, resulting in poor performance of the system in practice.

[0004] Therefore, it is necessary to develop a design method for the integrated optimization configuration of the hydrogen fuel cell comprehensive energy system based on multi-objective optimization, to achieve objective decision-making of multi-objective weights, and to improve the carbon reduction, economy and stability of the energy system. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide an optimization configuration method for a building fuel cell integrated energy system based on multi-objective optimization, so as to solve or partially solve the problem of the current lack of an integrated optimization configuration scheme for a building fuel cell integrated energy system based on multi-objective optimization.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] One aspect of the present invention provides a method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization, comprising the following steps:

[0008] Step S1, modeling the process of realizing energy consumption, responding to electricity demand, and responding to hot water demand for the building fuel cell integrated energy system;

[0009] Step S2, with the purpose of minimizing the carbon emission objective function and the economic objective function, the capacity configuration of the building fuel cell integrated energy system is iteratively optimized using NSGA II to obtain a Pareto frontier solution set;

[0010] Step S3, based on the Pareto front solution set, by sorting the ideal solution based on the entropy weight method, the capacity configuration of the optimized building fuel cell integrated energy system is obtained.

[0011] As a preferred technical solution, the modeling process in step S1 includes the following steps:

[0012] Step S101, determine whether the photovoltaic and wind power generation can meet the power demand at the time. If the power generation is greater than the power demand at the time, use lithium batteries to store the power generation surplus and execute step S108. If the power generation is less than the power demand at the time, use lithium batteries to meet the remaining load and execute step S102.

[0013] Step S102, determining whether the power reserve of the lithium battery is greater than the remaining power demand, if so, executing step S103, if not, using the fuel cell to meet the remaining load demand, executing step S106;

[0014] Step S103, determining whether the hot water in the hot water tank meets the hot water demand, if so, ending the calculation, if not, using the lithium battery to meet the remaining hot water demand, and executing step S104;

[0015] Step S104, determining whether the power reserve of the lithium battery is greater than the remaining hot water demand, if so, ending the calculation, if not, executing step S105;

[0016] Step S105, purchasing electricity from the power grid to heat hot water to meet the remaining hot water demand, and then the calculation ends;

[0017] Step S106, start the fuel cell system to meet the remaining power load demand, use the waste heat from power generation to produce hot water and store it in a hot water tank, and determine whether the fuel cell power generation can meet the remaining power load. If so, execute step S103, if not, execute step S107;

[0018] Step S107, purchasing electricity from the power grid to meet the remaining load demand, and executing step S103;

[0019] Step S108, determining whether the surplus power generation can be fully stored in the lithium battery, if so, executing step S103, if not, using the surplus power generation in the electrolytic water tank to produce hydrogen, executing step S109;

[0020] Step S109, determining whether the hydrogen generated by electrolyzing water using the remaining clean energy surplus electricity can be fully stored in the hydrogen storage container, if so, executing step S103, if not, executing step S110;

[0021] Step S110, selling the remaining energy surplus electricity to the power grid, and executing step S103.

[0022] As a preferred technical solution, the step S2 includes:

[0023] Step S201, modeling photovoltaic and wind power generation processes under different weather conditions;

[0024] Step S202, constructing a carbon emission objective function that takes into account electricity sales, electricity purchases and electricity storage;

[0025] Step S203, constructing a carbon emission objective function that takes into account electricity sales, electricity purchases and electricity storage;

[0026] Step S204, under the consideration of capacity optimization boundary conditions, using NSGAII based on hypercube sampling, mutation and crossover, iteratively optimize the economic objective function and the carbon emission objective function to obtain a Pareto frontier solution set, wherein the boundary conditions include site space restrictions and building specifications.

[0027] As a preferred technical solution, the photovoltaic and wind power generation processes under different weather conditions are modeled as follows:

[0028] G PV =I A ×A PV ×N PV ×η PV

[0029]

[0030] Among them, G PV , G Wind are photovoltaic power generation and wind power generation, I A is the solar radiation intensity, A PV is the area of ​​each photovoltaic panel, N PV is the number of photovoltaic panels, η PV is the photoelectric conversion efficiency of each photovoltaic panel, G rated is the rated power of the wind power system, V Z is the wind speed at the height of the wind turbine, V rated is the rated power generation wind speed of the wind turbine, V cut-inis the wind turbine cut-in wind speed, V cut-out is the cut-out wind speed of the wind turbine, and k is a parameter used to adjust the relationship between wind speed and power output based on a specific wind turbine.

[0031] As a preferred technical solution, the economic objective function is:

[0032]

[0033] Among them, SC IES is the economic objective function, CAP i For the capacity of each component, Unic i and Unimc i Unigb provides the initial investment cost and maintenance unit cost for each component. i and Unigs i is the unit electricity purchase price and electricity sales price, E G_in and E G_out is the amount of electricity purchased and sold at each moment, T is the life cycle of each component, I is the number of subsystems optimally configured in the integrated energy system, and AO is the total operating time of the system. G_in and E G_out The calculation is based on the difference between the electricity that clean energy can provide and the load data for 8760 hours. The unmet load or surplus power generation at each moment needs to be purchased from the grid or sold back to the grid.

[0034] As a preferred technical solution, the carbon emission objective function is:

[0035]

[0036] Among them, Emit IES is the carbon emission objective function, Emit G_in and Emit G_out For the amount of electricity purchased and sold at each moment, is the carbon emission factor, and AO is the total operating time of the system. The calculation of electricity purchase and sales at each moment is based on the difference between the electricity that can be provided by clean energy and the load data of 8760 hours.

[0037] As a preferred technical solution, the step S3 includes:

[0038] Step S301, standardizing the results obtained for the economic target and the carbon emission target in the Pareto front solution set, calculating the median, the first quartile and the third quartile for the results of the economic target and the results of the carbon emission target respectively, to achieve standardization of the economic and carbon emission target values ​​in the optimization scheme;

[0039] Step S302, calculating the entropy value and entropy weight of the economic objective function and the carbon emission objective function, and assigning the entropy weight to the two function objectives in each optimization solution set to obtain a decision matrix;

[0040] Step S303, for each optimization scheme, searching for a positive ideal solution including a minimum value in the objective function and a negative ideal solution including a maximum value in the objective function, and calculating the approximation between each optimization scheme and the positive ideal solution and the negative ideal solution;

[0041] Step S304, sorting the optimization schemes according to the approximation to obtain the optimized capacity configuration of the building fuel cell integrated energy system.

[0042] As a preferred technical solution, the standardization of the optimization solution is implemented by the following formula:

[0043]

[0044] As a preferred technical solution, the approximation is calculated using the following formula:

[0045]

[0046] Among them, C i Proximity, are positive ideal solution and negative ideal solution respectively.

[0047] As a preferred technical solution, the building fuel cell integrated energy system includes:

[0048] Clean energy generation modules, including photovoltaic panels and wind turbines;

[0049] The electrolyzer and the electrical load are connected to the clean energy power generation module, wherein the electrical load includes an air source heat pump and building electrical equipment;

[0050] A hydrogen storage container connected to the electrolyzer;

[0051] A hot water tank connected to the hot water load used;

[0052] A fuel cell is connected to the hydrogen storage container, the electrical load and the hot water tank respectively;

[0053] A battery energy storage subsystem, connected to the clean energy power generation module and the power load respectively;

[0054] A power grid, connected to the clean energy power generation module, the fuel cell and the power load respectively;

[0055] The air source heat pump is connected to the power grid and the hot water tank respectively.

[0056] Another aspect of the present invention provides an electronic device, comprising: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the aforementioned method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization.

[0057] Another aspect of the present invention provides a computer-readable storage medium comprising one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the aforementioned method for optimizing configuration of a building fuel cell integrated energy system based on multi-objective optimization.

[0058] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0059] (1) Realize the integrated optimization configuration of the hydrogen fuel cell comprehensive energy system based on multi-objective optimization: In the integrated design of the comprehensive energy system based on fuel cells, the present invention uses the coupling of multi-source clean energy power generation subsystems and the power grid, and configures on-site water electrolysis hydrogen production and storage equipment and fuel cell power generation systems. The capacity configuration of the energy storage devices including various clean energy power generation devices, lithium batteries and hydrogen storage tanks is optimized based on economic and environmental multi-objectives, and a recommended hourly optimization operation strategy for 8760 hours throughout the year is provided as a reference for the later project operation.

[0060] (2) Taking into account both economy and environmental friendliness: Compared with the traditional energy system design that uses the annual design load and calculates based on design experience and mathematical formulas, the present invention optimizes the configuration of the energy system by combining the hourly load data throughout the year with the optimization algorithm. While avoiding waste caused by excessive system configuration, it also provides the most environmentally and economically optimal configuration plan for the energy system.

[0061] (3) Strong objectivity: The present invention combines the multi-objective optimization based on the non-dominated sorting genetic algorithm II (NSGA II) with the Pareto solution set decision based on the entropy weight method to approximate the ideal solution sorting technology, and applies it to the optimal configuration of the hydrogen fuel cell integrated energy system. It avoids the interference of human factors on the selection of weight coefficients of each target in the multi-objective to a large extent. By eliminating the subjective influence of people on the decision of weight coefficients, the objectivity of the optimal configuration is guaranteed, and a clear integrated energy system configuration plan can be quickly provided to decision makers. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 It is a flow chart of the method for optimizing configuration of a building fuel cell integrated energy system based on multi-objective optimization in an embodiment;

[0063] Figure 2 A schematic diagram of a building fuel cell integrated energy system in an embodiment;

[0064] Figure 3 A schematic diagram of the process of energy consumption, responding to electricity demand, and responding to hot water demand in the embodiment;

[0065] Figure 4 It is a flow chart for solving the Pareto front solution set and optimizing the configuration in the embodiment. DETAILED DESCRIPTION

[0066] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0067] Example 1

[0068] In view of the problems existing in the above-mentioned prior art, this embodiment provides a multi-objective optimization design method based on the integration of hydrogen fuel cell integrated energy system. The method is divided into three parts: the construction of hydrogen fuel cell integrated energy system mechanism, the multi-objective optimization energy system capacity configuration method with environmental and economic goals, and the decision-making method for the multi-objective Pareto front solution set. Through the above methods, combined with 8760 hours of power load and weather data throughout the year, the optimal configuration scheme of the integrated energy system with fuel cells as the core is determined, including system configuration, capacity optimization, energy storage priority and annual operation strategy recommendations.

[0069] The hydrogen fuel cell integrated energy system of this embodiment is mainly used in residential areas and other places where there is a demand for hot water supply. Figure 2 , which mainly include:

[0070] Clean energy generation modules, including photovoltaic panels and wind turbines;

[0071] The electrolyzer and the electrical load are connected to the clean energy power generation module, wherein the electrical load includes an air source heat pump and building electrical equipment;

[0072] A hydrogen storage container connected to the electrolyzer;

[0073] A hot water tank connected to the hot water load used;

[0074] The fuel cell is connected to the hydrogen storage container, the electrical load and the hot water tank respectively;

[0075] The battery energy storage subsystem is connected to the clean energy power generation module and the power load respectively;

[0076] A power grid, connected to the clean energy power generation module, the fuel cell and the power load respectively;

[0077] The air source heat pump is connected to the power grid and the hot water tank respectively.

[0078] In the application scenario of this embodiment, hydrogen is prepared by photovoltaic and wind power rather than obtained through external transportation. The system is connected to the power grid. When clean energy power is insufficient, power is provided by the power grid. When clean energy is in surplus, clean power enters the power grid.

[0079] Figure 2 As shown in the figure, the integrated energy system includes three clean energy power generation devices, photovoltaic, wind power and hydrogen fuel cells. The hydrogen energy to start the fuel cell is obtained only by the electrolysis of water by the wind and solar power generation devices in the system. Similarly, the lithium battery is only charged by the wind and solar power generation devices. The power grid, as a power generation source to maintain the stability of the integrated energy system, meets all the needs that are not met by the clean energy devices at all times. The hot water demand is met by two mechanisms, heating hot water through an air source heat pump or providing it through a hot water tank that absorbs the waste heat of the fuel cell, or both.

[0080] In addition to this application scenario, the integrated energy system can also be applied to other scenarios. For example, if the system is not connected to the power grid, hydrogen can be obtained through external transportation. In this case, when the power is insufficient, it can be obtained through hydrogen power generation. Another application scenario is that the system is connected to the power grid and hydrogen can also be obtained through external transportation. In this case, when the power is insufficient, it can be obtained from the power grid, from hydrogen fuel cell power generation, or from wind and solar power generation devices according to economic efficiency.

[0081] See also Figure 1 , the specific steps of this method include:

[0082] Step S1, building a comprehensive energy system model with fuel cells as the core.

[0083] See also Figure 3 , step S1 may include the following sub-steps:

[0084] Step S101, import 8760 hours of load data of building simulation into the python model (i.e., hourly load data throughout the year, obtained by software simulation), and start looping from the first moment data. Determine whether the clean energy power generation meets the power demand within the moment under the first random capacity configuration. If it does, use lithium batteries to store the power generation surplus and execute step S108. If not, use lithium batteries to meet the remaining load and execute step S102.

[0085] Step S102, determine whether the lithium battery power reserve is greater than the remaining power demand load, considering the lithium battery charging and discharging efficiency (95%) and the maximum power limit, the domestic hot water heating equipment is an air source heat pump, and the COP is 3. If it is satisfied, execute step S103, if not, use the fuel cell to meet the remaining load, and execute step S106;

[0086] Step S103, determine whether the remaining amount in the hot water tank meets the hot water demand, calculate the relationship between the demand and the water volume according to the water specific heat capacity formula, and the water temperature change between the water inlet and the water outlet is 45 degrees Celsius. If it meets the requirement, the calculation ends at this moment. If not, use the lithium battery to meet the remaining hot water demand, and execute step S104;

[0087] Step S104, determine whether the lithium battery power reserve is greater than the remaining power demand for heating hot water, consider the lithium battery charging and discharging efficiency (95%) and the maximum power limit, heat the hot water through the air source heat pump, and set the COP to 3. If it is satisfied, the calculation ends at this moment. If not, execute step S105;

[0088] Step S105, purchasing electricity from the power grid and heating hot water through an air source heat pump to meet the remaining hot water demand, and the COP is set to 3;

[0089] Step S106, start the fuel cell system to determine whether the amount of electricity generated by the fuel cell can meet the remaining power demand at the time: check the power generation capacity of the fuel cell at the time, that is, the hydrogen storage capacity of the hydrogen tank. In the model, the hydrogen consumption is set to 4.56 liters per hour per kilowatt of rated power, and the hydrogen storage environment is set to a fixed state of 25 degrees Celsius and an atmospheric pressure of 30 MPa. The fuel cell is subject to the maximum power generation limit. At the same time, the hot water tank absorbs the waste heat of the fuel cell module, and the waste heat efficiency is 40%. If the power generated by the fuel cell meets the requirements, the calculation ends at this moment and step S103 is executed. If not, step S107 is executed;

[0090] Step S107, the grid purchases electricity to meet the remaining power demand: the remaining power demand includes hot water heating equipment and other electrical equipment in the building, the hot water heating equipment includes an air source heat pump, the COP is 3, and step S103 is executed;

[0091] Step S108, determine whether the surplus clean energy power generation can be fully stored in the lithium battery system, considering the lithium battery charging and discharging efficiency (95%) and the maximum power limit. If satisfied, execute step S103; if not, use the electrolytic water tank to produce hydrogen and execute step S109;

[0092] Step S109, check whether the hydrogen tank can store the remaining excess clean energy surplus electricity electrolyzed hydrogen: produce hydrogen through the electrolytic water tank and store it, and judge whether the hydrogen storage tank can be fully stored with hydrogen. The efficiency of the electrolytic water tank is 85%, the hydrogen production volume is calculated by the ideal gas equation, and the hydrogen combustion calorific value is set to 285.83kJ / m 3 If satisfied, the calculation ends at this moment and step S103 is executed; if not, step S110 is executed.

[0093] Step S110, selling the remaining clean energy and electricity to the power grid, and then executing step S103.

[0094] Step S2, multi-objective optimization based on non-dominated sorting genetic algorithm II (NSGAII).

[0095] See also Figure 4 , step S2 may include the following sub-steps:

[0096] Step S201, construct photovoltaic and wind power generation models based on weather data. The photovoltaic power generation model is

[0097] G PV =I A ×A PV ×N PV ×η PV

[0098] Among them I A is the solar radiation intensity, A PV is the area of ​​each photovoltaic panel, N PV is the number of photovoltaic panels, η PV is the photoelectric conversion efficiency of each photovoltaic panel. The wind power generation model is as follows, where G rated is the rated power of the wind power system, V Z is the wind speed at the height of the wind turbine, V rated is the rated power generation wind speed of the wind turbine, V cut-in is the wind turbine cut-in wind speed, V cut-out Cut out wind speed for the fan;

[0099]

[0100] Step S202, establish an economic objective function, which consists of the annual investment cost and annual maintenance cost. For different system components, a simple annual investment cost is calculated. Except for the fuel cell system, which has a life cycle of 5 years, all other components have a life cycle of 20 years. The maintenance cost is similar, consisting of the cost of each component. The annual electricity purchase cost and electricity sales revenue of the power grid are included as system maintenance costs. The cost is based on the introduction of existing mainstream products in the market. The specific function is:

[0101]

[0102] Among them, CAP i For the capacity of each component, Unic i and Unimc i For each component, the initial investment and maintenance unit cost, Unigb i and Unigs i is the unit electricity purchase price and electricity sales price, E G_in and E G_outis the amount of electricity purchased and sold at each moment, T is the life cycle of each component. k is a curve for adjusting the relationship between wind speed and power output based on a specific wind turbine, and in this embodiment, k = 1.4. G_in and E G_out The calculation is based on the difference between the electricity that clean energy can provide and the 8760-hour load data. The unmet load or surplus power generation at each moment needs to be purchased from the power grid or sold to the power grid.

[0103] Step S203, establish a carbon emission objective function. The electricity sold to the grid is regarded as a compensation for the carbon emissions generated by using grid power. Therefore, the total amount of emissions is calculated based on the difference between the electricity purchased from the grid and the electricity sold back. The carbon emission factor is set to 0.42 kg of carbon dioxide per kilowatt-hour of electricity. The specific function is Emitt G_in and Emitt G_out For the amount of electricity purchased and sold at each moment, is the carbon emission factor, and AO is the total operating time of the system.

[0104] In this embodiment, the carbon emission objective function is:

[0105]

[0106] Among them, Emit IES is the carbon emission objective function, Emit G_in and Emit G_out For the amount of electricity purchased and sold at each moment, is the carbon emission factor, and AO is the total operating time of the system. The calculation of electricity purchase and sales at each moment is based on the difference between the electricity that clean energy can provide and the load data of 8760 hours.

[0107] Step S204: Based on the above-mentioned integrated energy system model with fuel cells as the core, a Python model is established to implement the logic of step S1 and determine the capacity optimization boundary of each subsystem. The boundary restrictions are mainly site space restrictions (photovoltaic panels, wind turbines, lithium battery energy storage systems, fuel cell systems, hydrogen storage tanks) and building code requirements (hot water tanks).

[0108] Among them, the optimized boundary conditions may include one or more of photovoltaic panel area, wind turbine installed power, hydrogen storage tank volume, lithium battery storage capacity, hot water tank volume, and hydrogen fuel cell installed capacity. The following is an exemplary setting method.

[0109] (1) Photovoltaic panel area. The minimum value is 0, and the maximum value is determined by the area of ​​the building roof and the east / west / south facades. For example, since the roof has building components such as roof greening, electromechanical equipment, and elevator room, the remaining roof usable area may be only 50%. The building facade has external windows, sunshades, and other components, and the remaining inside usable area may also be only 50%. In this case, the photovoltaic boundary condition is the photovoltaic panel area of ​​0 to (50% of the roof area + 50% of the facade area).

[0110] (2) Wind turbine installed power: The minimum value is 0, and the maximum value is affected by the building shape, building layout area, and noise. The maximum installed power of the wind turbine can only be 10 kW. At this time, the boundary condition of the wind turbine is that the installed power of the wind turbine is 0 to 10 kW.

[0111] (3) Hydrogen storage tank capacity, the minimum value is 0, and the maximum value is subject to the area of ​​hydrogen storage tanks that the building can accommodate. For example, a building with a construction area of ​​20,000 square meters has a hydrogen storage tank area of ​​200m 2 At this time, the capacity of the hydrogen storage tank is 320m 3 , then the boundary condition of the hydrogen storage tank is that the volume of the hydrogen storage tank is 0~320m 3 .

[0112] (4) The minimum capacity of lithium battery is 0, and the maximum capacity is affected by the floor space of the building that can accommodate lithium batteries and the maximum power load of the building. According to project experience, the maximum capacity of lithium battery is about 20% of the total power load. For example, the boundary condition of lithium battery is 0~50MWh.

[0113] (5) Hot water tank capacity, the minimum value is 0, and the maximum value is affected by the building's domestic hot water consumption, which is determined by the number of people in the building. For example, the hot water tank boundary condition is that the hot water tank capacity is 0 to 900L;

[0114] (6) Hydrogen fuel cell installed capacity, the minimum value is 0, and the maximum value is determined by the building electricity demand and building area. For example, the boundary condition of hydrogen fuel cells is installed power of 0 to 25,000 kW.

[0115] Specifically, step S204 uses NSGA II to optimize the dual objective function, and the algorithm parameters are set as follows: the number of optimal solution sets is 500, and the number of iterations is 1400. In order to enhance the search efficiency of the algorithm and the diversity of Pareto solution sets, relevant processing is done from three aspects. First, considering the wide range of fuel cell settings, in order to avoid the uneven distribution of the initial population that may be caused by the traditional random sampling method, the sampling method adopts hypercube sampling, which can generate an initial population with uniform distribution in a high-dimensional space; in addition, the crossover method simulates binary crossover to search and expand the diversity of solutions and avoid the results of the algorithm falling into the local optimum. The probability is set to 0.8 and the discreteness is set to 15; finally, the role of mutation is similar to that of crossover, and a certain fluctuation is introduced near the individual solution, so that the solution may jump out of the current search space on the basis of local optimization, thereby improving the global exploration ability of NSGA II. The mutation method is polynomial mutation, the probability is set to 0.075, and the discreteness is set to 20. Finally, a set of Pareto frontier solution sets containing 500 solutions is obtained.

[0116] Step S3, making a Pareto solution set decision based on the entropy weight method approaching the ideal solution sorting technique.

[0117] See also Figure 4 , step S3 may include the following sub-steps:

[0118] Step S301, standardize the results of the economic target and carbon emission target in the 500 Pareto front solutions obtained in the above NSGAII. The standardization method adopts robust standardization, and calculates the median, the first quartile and the third quartile of the two sets of data respectively. By formula The standardized economic and carbon emission target results of each set of optimal solutions are obtained. Each solution includes the subsystem configuration capacity in the optimization solution, as well as the economic and carbon emission target function values ​​corresponding to the solution.

[0119] Step S302, calculate the entropy value and entropy weight of the standardized economic objective function and carbon emission objective function, and assign the entropy weight to the two function objectives in each optimal solution set to obtain the final objective function result, that is, the decision matrix.

[0120] Among them, the entropy value and entropy weight are calculated using the following formula:

[0121]

[0122] Among them, Ent is the entropy value, m is the number of samples, P ij The value of the objective function after each group of optimization solutions. Entropy weight, W j , the calculation formula is as follows, where n is the number of objective functions.

[0123] Decision Matrix V ij for:

[0124] V ij =W j ×P ij

[0125] Determine the positive ideal solution and the negative ideal solution. The positive ideal solution represents the optimization solution that contains the minimum value in each objective function, and the negative ideal solution represents the optimization solution that contains the maximum value in each objective function.

[0126] Calculate all optimization solutions and two objective function solutions to the positive ideal solution and negative ideal solution The Euclidean distance of each group of solutions is obtained, and the formula is used Get the approximation C i result.

[0127] Among them, the calculation formulas for positive ideal solutions and negative ideal solutions are as follows, where J1 is the economic objective function set and J2 is the carbon emission objective function set.

[0128]

[0129] The Euclidean distance is calculated using the following formula:

[0130]

[0131] Among them, m is the number of samples.

[0132] Step S303, sort and evaluate the obtained approximation results to obtain the final optimal solution set and the annual operation strategy of each system under the optimal solution set. Preferably, the solution with the approximation closest to 1 is selected as the final solution.

[0133] This method has the following characteristics:

[0134] (1) This method uses the coupling of multi-source clean energy generation subsystems and power grids in the integrated design of comprehensive energy systems based on fuel cells, and configures on-site water electrolysis hydrogen production and storage equipment and fuel cell power generation systems. Based on economic and environmental multi-objectives, the capacity configuration of each clean energy generation device, lithium battery and hydrogen storage tank energy storage device is optimized, and the recommended optimization operation strategy is provided as a reference for the later project operation;

[0135] (2) Compared with the traditional energy system design which uses the annual design load and performs calculations based on design experience and mathematical formulas, this method optimizes the configuration of the energy system by combining the hourly load data throughout the year with an optimization algorithm. While avoiding waste caused by excessive system configuration, it also provides the most environmentally and economically optimal configuration plan for the energy system.

[0136] (3) The multi-objective optimization algorithm based on the non-dominated sorting genetic algorithm II (NSGAII) is combined with the Pareto solution set decision model based on the entropy weight method to approximate the ideal solution sorting technology, and is applied to the optimal configuration of the hydrogen fuel cell integrated energy system. This method avoids the interference caused by human factors to a large extent and quickly provides decision makers with a clear integrated energy system configuration plan.

[0137] (4) This method provides a scientific, reasonable and efficient solution for the optimal configuration of the integrated design of hydrogen fuel cell comprehensive energy systems. This method can provide a design basis for designers and provide system operators with year-round operation strategy recommendations, including the annual operating time and start-stop conditions of the hydrogen fuel cell system, as well as the discharge conditions of the lithium battery charger. It also provides a reference for the optimal configuration of the same type of energy systems.

[0138] (5) The hydrogen fuel cell integrated energy system configured by this method provides an optimal solution for the capacity of each device in the system while ensuring optimal environmental and economic performance, thereby reducing initial investment and operating costs and improving the overall operating energy efficiency of the system and the utilization rate of clean energy.

[0139] Example 2

[0140] This embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the building fuel cell integrated energy system optimization configuration method based on multi-objective optimization as described in Example 1.

[0141] Example 3

[0142] This embodiment provides a computer-readable storage medium, including one or more programs for execution by one or more processors of an electronic device, wherein the one or more programs include instructions for executing the method for optimizing configuration of a building fuel cell integrated energy system based on multi-objective optimization as described in Example 1.

[0143] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization, characterized in that: The steps include: Step S1, modeling the process of realizing energy consumption, responding to electricity demand, and responding to hot water demand for the building fuel cell integrated energy system; Step S2, with the purpose of minimizing the carbon emission objective function and the economic objective function, the capacity configuration of the building fuel cell integrated energy system is iteratively optimized using NSGAII to obtain a Pareto frontier solution set; Step S3, based on the Pareto front solution set, by sorting the ideal solution based on the entropy weight method, the capacity configuration of the optimized building fuel cell integrated energy system is obtained.

2. According to the multi-objective optimization-based optimization method for building fuel cell integrated energy system according to claim 1, it is characterized in that: The modeling process in step S1 includes the following steps: Step S101, determine whether the photovoltaic and wind power generation can meet the power demand at the time. If the power generation is greater than the power demand at the time, use lithium batteries to store the power generation surplus and execute step S108. If the power generation is less than the power demand at the time, use lithium batteries to meet the remaining load and execute step S102. Step S102, determining whether the power reserve of the lithium battery is greater than the remaining power demand, if so, executing step S103, if not, using the fuel cell to meet the remaining load demand, executing step S106; Step S103, determining whether the hot water in the hot water tank meets the hot water demand, if so, ending the calculation, if not, using the lithium battery to meet the remaining hot water demand, and executing step S104; Step S104, determining whether the power reserve of the lithium battery is greater than the remaining hot water demand, if so, ending the calculation, if not, executing step S105; Step S105, purchasing electricity from the power grid to heat hot water to meet the remaining hot water demand, and then the calculation ends; Step S106, start the fuel cell system to meet the remaining power load demand, use the waste heat from power generation to produce hot water and store it in a hot water tank, and determine whether the fuel cell power generation can meet the remaining power load. If so, execute step S103, if not, execute step S107; Step S107, purchasing electricity from the power grid to meet the remaining load demand, and executing step S103; Step S108, determining whether the surplus power generation can be fully stored in the lithium battery, if so, executing step S103, if not, using the surplus power generation in the electrolytic water tank to produce hydrogen, executing step S109; Step S109, determining whether the hydrogen generated by electrolyzing water using the remaining clean energy surplus electricity can be fully stored in the hydrogen storage container, if so, executing step S103, if not, executing step S110; Step S110, selling the remaining energy surplus electricity to the power grid, and executing step S103.

3. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 1 is characterized in that: The step S2 comprises: Step S201, modeling photovoltaic and wind power generation processes under different weather conditions; Step S202, constructing an economic objective function that takes into account investment cost, electricity sales, electricity purchase, and operation and maintenance cost; Step S203, constructing a carbon emission objective function that takes into account electricity sales, electricity purchases and electricity storage; Step S204, under the consideration of capacity optimization boundary conditions, using NSGAII based on hypercube sampling, mutation and crossover, iteratively optimize the economic objective function and the carbon emission objective function to obtain a Pareto frontier solution set, wherein the boundary conditions include site space restrictions and building specifications.

4. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 3 is characterized in that: The photovoltaic and wind power generation processes under different weather conditions are modeled as follows: G PV =I A ×A PV ×N PV ×η PV Among them, G PV , G Wind are photovoltaic power generation and wind power generation, I A is the solar radiation intensity, A PV is the area of ​​each photovoltaic panel, N PV is the number of photovoltaic panels, η PV is the photoelectric conversion efficiency of each photovoltaic panel, G rated is the rated power of the wind power system, V Z is the wind speed at the height of the wind turbine, V rated is the rated power generation wind speed of the wind turbine, V cut is the wind turbine cut-in wind speed, V cut-out is the cut-out wind speed of the wind turbine, and k is a parameter used to adjust the relationship between wind speed and power output based on a specific wind turbine.

5. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 3 is characterized in that: The economic objective function is: Among them, SC IES is the economic objective function, CAP i For the capacity of each component, Unic i and Unimc i Unigb provides the initial investment cost and maintenance unit cost for each component. i and Unigs i is the unit electricity purchase price and electricity sales price, E G_in and E G_out is the amount of electricity purchased and sold at each moment, T is the life cycle of each component, I is the number of subsystems optimally configured in the integrated energy system, and AO is the total operating time of the system.

6. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 3 is characterized in that: The carbon emission objective function is: Among them, Emit IES is the carbon emission objective function, Emit G_in and Emit G_out For the amount of electricity purchased and sold at each moment, is the carbon emission factor, and AO is the total operating time of the system.

7. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 1 is characterized in that: The step S3 comprises: Step S301, standardizing the results obtained for the economic target and the carbon emission target in the Pareto front solution set, calculating the median, the first quartile and the third quartile for the results of the economic target and the results of the carbon emission target respectively, to achieve standardization of the economic and carbon emission target values ​​in the optimization scheme; Step S302, calculating the entropy value and entropy weight of the economic objective function and the carbon emission objective function, and assigning the entropy weight to the two function objectives in each optimization solution set to obtain a decision matrix; Step S303, for each optimization scheme, searching for a positive ideal solution including a minimum value in the objective function and a negative ideal solution including a maximum value in the objective function, and calculating the approximation between each optimization scheme and the positive ideal solution and the negative ideal solution; Step S304, sorting the optimization schemes according to the approximation to obtain the optimized capacity configuration of the building fuel cell integrated energy system.

8. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 7 is characterized in that: The standardization of the optimization scheme is achieved by the following formula:

9. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 7 is characterized in that: The approximation is calculated using the following formula: Among them, C i Proximity, are positive ideal solution and negative ideal solution respectively.

10. The method for optimizing the configuration of a building fuel cell integrated energy system based on multi-objective optimization according to claim 1, characterized in that: The building fuel cell integrated energy system comprises: Clean energy generation modules, including photovoltaic panels and wind turbines; The electrolyzer and the electrical load are connected to the clean energy power generation module, wherein the electrical load includes an air source heat pump and building electrical equipment; A hydrogen storage container connected to the electrolyzer; A hot water tank connected to the hot water load used; A fuel cell is connected to the hydrogen storage container, the electrical load and the hot water tank respectively; A battery energy storage subsystem, connected to the clean energy power generation module and the power load respectively; A power grid, connected to the clean energy power generation module, the fuel cell and the power load respectively; The air source heat pump is connected to the power grid and the hot water tank respectively.

Images