Seasonal amino multi-element energy storage capacity configuration method based on time sequence component extraction

Through the improved STL decomposition algorithm and timing component extraction technology, combined with battery energy storage and thermal energy storage systems, the capacity configuration of ammonia energy storage systems is optimized, and the imbalance of power supply and demand caused by intermittent and seasonal fluctuations in the power system is solved, and economically stable energy storage configuration and efficient absorption of wind and light resources are achieved.

CN120497981APending Publication Date: 2025-08-15NORTHEAST DIANLI UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510587948.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-08
Publication Date
2025-08-15

AI Technical Summary

Technical Problem

The prior art is difficult to effectively solve the imbalance of power supply and demand caused by intermittent and seasonal fluctuations in renewable energy in the power system, especially in the multi-energy storage configuration, where existing frequency domain decomposition methods cannot meet seasonal demand.

Method used

The improved STL decomposition algorithm is used to extract the timing component of wind power output, photovoltaic output and thermal load data, and construct sub-scenario constraints, combine battery energy storage and thermal energy storage systems to build a flat-economic dual-dimensional optimization model, and optimize the capacity configuration of the multi-dimensional energy storage system.

Benefits of technology

The dual optimization in terms of economy and stability is achieved. Through precise timing component matching, the energy storage capacity is reasonably allocated, the system fluctuations are effectively suppressed, the cost is reduced, and the system's ability to absorb wind and light resources is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120497981A_ABST
    Figure CN120497981A_ABST
Patent Text Reader

Abstract

The invention discloses a seasonal amino multi-element energy storage capacity configuration method based on time sequence component extraction. The method comprises the following steps: constructing a multi-element energy storage system which takes an ammonia energy storage system as a core and comprises battery energy storage and heat energy storage; the method comprises the following steps: performing time sequence component extraction on wind power output, photovoltaic output and thermal load data in a power system by adopting an improved STL decomposition algorithm, and constructing sub-scene constraints according to a time sequence component extraction result; and based on the multi-element energy storage system and the sub-scene constraint, constructing a stabilization-economy two-dimensional optimization model, and optimizing the capacity configuration of the multi-element energy storage system to obtain an optimal configuration scheme. According to the method, stable and economical ammonia energy storage is introduced into comprehensive energy capacity planning, so that double optimization of economical efficiency and stability is realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of integrated energy system planning, and in particular relates to a seasonal amino multi-element energy storage capacity configuration method based on time series component extraction. Background Art

[0002] As the global energy mix shifts toward a low-carbon future, renewable energy sources, such as wind and photovoltaics, are increasingly accounting for a larger share of the power system. However, the intermittent and seasonal fluctuations of these energy sources are leading to a growing imbalance between power supply and demand, placing increasingly stringent demands on energy storage.

[0003] At present, the method of configuring multivariate energy storage capacity is mainly based on signal decomposition, usually using Fourier transform or wavelet transform to decompose the power system signal into different frequency domain components, and then matching them with the response characteristics of the energy storage equipment. However, this type of frequency domain-based decomposition method is difficult to directly associate with specific time scales, and focuses more on short-term energy storage configuration, which cannot fully meet the needs of seasonal multivariate energy storage. Research on the application of time series component extraction to energy storage configuration, especially the matching of multivariate seasonal energy storage characteristics based on ammonia, is still relatively scarce, and its exploration has important research value and potential. Summary of the Invention

[0004] The present invention proposes a seasonal amino multi-element energy storage capacity configuration method based on time series component extraction to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a seasonal amino multi-element energy storage capacity configuration method based on time series component extraction, comprising the following steps:

[0006] Build a multi-energy storage system with an ammonia energy storage system as the core, including battery energy storage and thermal energy storage;

[0007] An improved STL decomposition algorithm is used to extract time series components from wind power output, photovoltaic output, and thermal load data in the power system, and scenario-based constraints are constructed based on the time series component extraction results.

[0008] Based on multiple energy storage systems and scenario constraints, a two-dimensional optimization model of leveling and economy is constructed to optimize the capacity configuration of multiple energy storage systems and obtain the optimal configuration plan.

[0009] Preferably, the ammonia energy storage system includes an ammonia synthesis module, a storage module, and a utilization module; the system operating cost is quantitatively represented as:

[0010]

[0011] Where, They are electrolyzer operating cost, hydrogen-to-ammonia cost, ammonia storage cost, and ammonia fuel cell operating cost.

[0012] Preferably, the improved STL decomposition algorithm includes:

[0013] Perform K-means cluster analysis on the original data to extract representative typical daily data;

[0014] Generate time series data based on typical daily data and decompose it using the STL algorithm;

[0015] A variance threshold test is introduced in the decomposition process to eliminate components that do not meet the independence requirements.

[0016] Preferably, the time series component extraction result includes a trend component, a seasonal component and a random fluctuation component.

[0017] Preferably, constructing scenario-specific constraints based on the time series component extraction results includes:

[0018] The trend component and the random fluctuation component are added together to construct the joint component scenario constraint, which is used to configure the capacity of the battery energy storage;

[0019] Seasonal scenario balance constraints are constructed with seasonal components to configure the capacity of ammonia energy storage and thermal energy storage.

[0020] Preferably, the objective function of the two-dimensional optimization model of stabilization and economy is:

[0021]

[0022] Where, are the unit investment costs of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage device respectively; P EL 、P AFC 、M ABS 、M APS , Q EB , Q THS 、P BESS are the rated capacities of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage, r is the interest rate; τ is the investment recovery period, are the unit wind curtailment, solar curtailment and load curtailment costs, They are wind power curtailment, solar power curtailment and load curtailment respectively.

[0023] Preferably, the conversion model of the ammonia energy storage system includes:

[0024]

[0025] Where, P EL,AC is the AC power before input into the electrolytic cell; PEL,DC is the DC power input to the electrolytic cell; is the AC-DC conversion efficiency of the electrolyzer; Power for hydrogen production in electrolyzer; The efficiency of the recovery device in absorbing the waste heat from the electrolytic cell; Q HRU (t) is the heat power recovered by the electrolytic cell during period t; is the mass of hydrogen produced by the electrolyzer during period t; It is the high calorific value of hydrogen; is the mass of ammonia produced during time period t; is the energy consumption required for hydrogen to ammonia conversion per unit time period; are the energy consumption of the power-to-ammonia equipment during period t and the thermal power provided by the ammonia system for unit ammonia production; η heat It is the ratio of heat released by the ammonia production equipment used for heating.

[0026] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0027] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method when executed by a processor.

[0028] The present invention also provides a computer program product, comprising a computer program, which implements the steps of the method when executed by a processor.

[0029] Compared with the prior art, the present invention has the following advantages and technical effects:

[0030] The present invention proposes a capacity configuration method for seasonal amino multi-element energy storage characteristics based on time series component extraction. This method aims to achieve dual optimization of economy and stability by introducing stable and economical ammonia energy storage into comprehensive energy capacity planning. Existing energy storage capacity configuration methods do not fully consider the time series correlation between renewable energy output and load. This method improves the time series decomposition method and deeply explores the time series correlation between renewable energy output and load, thereby solving the energy intermittency and seasonal fluctuation problems caused by the increasing proportion of renewable energy such as wind power and photovoltaics in the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0032] Figure 1 This is a framework topology diagram of a seasonal amino multi-element energy storage system according to an embodiment of the present invention;

[0033] Figure 2 This is an improved STL decomposition flow chart of an embodiment of the present invention;

[0034] Figure 3 This is a decomposition diagram of wind power output according to an embodiment of the present invention;

[0035] Figure 4 This is a photovoltaic output decomposition diagram of an embodiment of the present invention;

[0036] Figure 5 This is a heat load decomposition diagram of an embodiment of the present invention;

[0037] Figure 6 The following are the full-time electric and thermal power balance analysis diagrams of the system according to the embodiment of the present invention, wherein (a) is the full-time electric power balance diagram of the system; (b) is the full-time thermal power balance diagram of the system;

[0038] Figure 7 Variance constraint sensitivity analysis diagram of the multivariate energy storage capacity configuration according to an embodiment of the present invention, wherein (a) is an analysis diagram of the difference in energy storage device capacity under different thresholds; (b) is an analysis diagram of the total cost-source-load balance under different thresholds. DETAILED DESCRIPTION

[0039] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Example 1

[0042] This embodiment provides a seasonal amino multi-element energy storage capacity configuration method based on time series component extraction, including the following steps:

[0043] Build a multi-energy storage system with an ammonia energy storage system as the core, including battery energy storage and thermal energy storage;

[0044] An improved STL decomposition algorithm is used to extract time series components from wind power output, photovoltaic output, and thermal load data in the power system, and scenario-based constraints are constructed based on the time series component extraction results.

[0045] Based on multiple energy storage systems and scenario constraints, a two-dimensional optimization model of leveling and economy is constructed to optimize the capacity configuration of multiple energy storage systems and obtain the optimal configuration plan.

[0046] The details are as follows:

[0047] Multi-element energy storage system framework Figure 1 As shown in the figure, the seasonal amino multi-energy storage system: mainly based on ammonia energy storage, including electrolyzers, hydrogen-to-ammonia equipment, ammonia storage tanks and ammonia fuel cells, plays a key role in seasonal source-load balance, ensuring the stable operation of the system on a long-term scale; battery energy storage alleviates short-term source-load fluctuations through rapid charging and discharging, providing rapid response capabilities; thermal energy storage captures the heat generated during the ammonia storage process and dynamically adjusts the heat according to the fluctuation of the heat load.

[0048] The multi-energy storage system specifically includes:

[0049] 1) A two-stage model of electric-to-ammonia conversion considering electric-thermal coupling;

[0050] The first stage: prepare hydrogen, the key reactant required for ammonia synthesis. The mechanism model is as follows:

[0051]

[0052] In the second stage, nitrogen and hydrogen are mixed and fed into the ammonia reactor. Under the influence of high temperature, high pressure, and a catalyst, the Haber-Bosch reaction occurs. This process can be described by the following equation:

[0053]

[0054] Where: P EL,AC is the AC power before input into the electrolytic cell; P EL,DC is the DC power input to the electrolytic cell; is the AC-DC conversion efficiency of the electrolyzer; Power for hydrogen production in electrolyzer; The efficiency of the recovery device in absorbing the waste heat from the electrolytic cell; Q HRU (t) is the heat power recovered by the electrolytic cell during period t; is the mass of hydrogen produced by the electrolyzer during period t; The high calorific value of hydrogen. is the mass of ammonia produced during time period t; The energy consumption required for hydrogen to ammonia conversion per unit time period (including the electrical power consumed by PSA to produce nitrogen); are the energy consumption of the power-to-ammonia equipment during period t and the thermal power provided by the ammonia system for unit ammonia production; η heat It is the ratio of heat released by the ammonia production equipment used for heating.

[0055] 2) Fuel cell cogeneration model;

[0056] As the output unit of the ammonia energy storage system, fuel cells and waste heat recovery can improve energy utilization and achieve cogeneration. The mechanism model is as follows:

[0057]

[0058]

[0059] Where: M AFC (t) is the mass of ammonia consumed by the ammonia fuel cell during period t; P AFC (t), Q AFC (t) are the power generation and heat generation of the fuel cell in period t; η FC ,η FC,H is the power generation efficiency and thermal efficiency of the fuel cell, η FC It is the lower heating value of ammonia.

[0060] 3) Electric boiler model;

[0061] The output power model of the electric heater can be expressed by formula (5):

[0062] Q EB (t) = η EB P EB (t) (5)

[0063] Where: Q EB (t), P EB (t) are the thermal power output and electrical power input of the electric heater during period t respectively; η EB is the thermal efficiency of the electric heater.

[0064] 4) Thermal power unit model;

[0065] The operating characteristics of thermal power units involve many aspects, including their efficiency, economy and environmental impact. The secondary function of thermal power units is as follows:

[0066]

[0067] Where: m coal (t) is the coal consumed by the thermal power unit, a, b, c are the fuel cost coefficients of the thermal power unit, and I is the operating status of the unit in period t, which is a 0-1 variable.

[0068] 5) Multivariate energy storage model;

[0069] ① Ammonia storage tank model:

[0070] Ammonia storage tanks are key infrastructure for addressing seasonal energy supply and demand mismatches, achieving cross-seasonal energy balance through large-scale ammonia storage. As the core of the integrated electricity-ammonia-heat energy storage framework, the mathematical model of this device is characterized as follows:

[0071]

[0072]

[0073] ② Thermal energy storage model:

[0074] This study uses molten salt energy storage as a thermal energy storage model, which can optimize thermal energy distribution and improve daily heat management capabilities. Thermal energy storage stores excess heat when there is excess heat and releases it when needed, reducing heat waste. The model can be expressed using the following mathematical formula:

[0075]

[0076] ③Battery energy storage model:

[0077]

[0078] Where: are the storage amounts of ammonia in the ammonia storage tank during period t and the previous period respectively; Q is the change in ammonia gas in the ammonia storage tank during period t. S (t), Q S (t-1) is the storage capacity of the heat storage device in period t and the previous period respectively; Q ch (t) is the heat energy input of the heat storage device during period t; Q dis (t) is the output of heat energy of the heat storage device during period t; η h,ch is the efficiency of the heat storage device input; η h,dis E is the efficiency of the heat storage device output. SOC (t) is the state value of the battery energy storage at time t; P ch (t) is the charging power of the battery energy storage at time t; P dis (t) is the discharge power of the battery energy storage device at time t; η e,ch is the charging efficiency of battery energy storage; η e,dis The discharge efficiency of battery energy storage; Δt is the time step of battery energy storage charge and discharge.

[0079] 2. Solution of multi-energy storage model based on time series components:

[0080] 1) The multi-energy storage modeling system adopts a dual-dimensional optimization architecture of "stabilization and economy" and builds a scenario-based constraint system based on the STL decomposition algorithm. In the stabilization dimension, it focuses on system volatility, and in the economic dimension, it implements the optimal energy storage economic configuration, including configuration cost, operating cost, and penalty cost. The objective function of this model can be expressed as:

[0081] f=C inv +C op +C r (11)

[0082]

[0083]

[0084]

[0085] Where: are the unit investment costs of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage device respectively; P EL 、P AFC 、M ABS 、M APS , Q EB , Q THS 、P BESS They are the rated capacities of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage. r is the interest rate; τ is the investment recovery period, are the unit wind curtailment, solar curtailment and load curtailment costs, They are wind power curtailment, solar power curtailment and load curtailment respectively.

[0086] The system operating costs are:

[0087]

[0088] Where: They are the operating costs of the ammonia energy storage system, battery energy storage, thermal energy storage system, and coal-fired unit.

[0089] The ammonia energy storage system consists of three core modules: ammonia synthesis, storage, and utilization. The system operating costs can be quantitatively characterized as:

[0090]

[0091] Where: They are electrolyzer operating cost, hydrogen-to-ammonia cost, ammonia storage cost, and ammonia fuel cell operating cost.

[0092]

[0093] Where: c EL 、c APS 、c ABS 、c AFC They are the unit power operation cost of the electrolyzer, the unit power operation cost of the ammonia production device, the unit mass storage cost of the ammonia energy storage device, the unit power generation cost of the ammonia fuel cell, and the unit power heating cost. coal is the unit price of coal.

[0094] A scenario-based constraint system is constructed based on the improved STL decomposition algorithm. The STL decomposition algorithm belongs to a decomposition statistical algorithm, which can decompose the original data into trend components, seasonal components, and random fluctuation components, as shown in the following formula:

[0095] Y(t)=S(t)+R(t)+P(t) (19)

[0096] Where: Y(t), S(t), R(t), and P(t) are the original data, seasonal component, random fluctuation component, and trend component, respectively.

[0097] When applying the STL decomposition algorithm to the power system for time series component energy storage configuration, the components have a direct impact on the capacity of the energy storage configuration. This paper improves the time series component extraction algorithm and introduces a statistical variance threshold test to make it more accurate in extracting power system components and accurately matching the corresponding energy storage. The threshold test is simplified as follows:

[0098]

[0099] Where: ∈ rel is the variance threshold, C i S(t), R(t), and P(t) are original time series data.

[0100] Based on this, the trend component and the fluctuation component are added together as a joint component scenario constraint to configure the battery energy storage capacity; the seasonal component is used to construct a seasonal scenario balance constraint to configure the ammonia energy storage and thermal energy storage capacity. The system operation constraints are as follows:

[0101] System power balance constraints by scenario:

[0102]

[0103] Where: P th,c (t), P wt,c (t), P pv,c (t), P load,c (t), P EB,c (t), Q EB,c (t), Q load,c (t) The output of thermal power units, wind power output, photovoltaic output, electric load, electric power consumption of electric boilers, thermal output of electric boilers, and thermal load in period t under the combined scenario. P th,s (t), P wt,s (t), P wt,s (t), P load,s (t), P EB,s (t), Q EB,s (t), Q load,s(t) are the output of thermal power units, wind power output, photovoltaic output, electric load, electric boiler power consumption, electric boiler heat output, and heat load in period t under seasonal scenarios.

[0104] (2) Ammonia energy storage system output constraints:

[0105]

[0106] (3) Thermal energy storage output constraints:

[0107]

[0108] Where: is the heat storage state variable, which indicates heat storage when it is 1; It is the exothermic state variable, and when it is 1, it means exothermic.

[0109] (4) Battery energy storage constraints:

[0110]

[0111] Where: It is the charging state variable, when it is 1, it means charging; It is the discharge state variable, and when it is 1, it means discharge.

[0112] Electric boiler output constraints:

[0113]

[0114]

[0115] Where: are the predicted powers of the two wind farms in period t.

[0116] (6) Thermal power unit output constraints:

[0117]

[0118]

[0119] Where: P M,max , ΔP climb are the maximum capacity of the thermal power unit and the ramp rate of the thermal power unit respectively.

[0120] The variance threshold test is introduced into the improved STL data decomposition process. The specific structure is shown in Figure 2 The decomposition results are shown in Figure 3 (Wind power output breakdown diagram), Figure 4 (Photovoltaic output breakdown diagram) and Figure 5(Heat load decomposition diagram). Based on this, the decomposed data was input into the capacity configuration model for verification to evaluate and demonstrate the superiority of the proposed method. The system parameters are detailed in Table 1.

[0121] Table 1

[0122]

[0123] Testing has shown that, when large-scale wind and solar resources are connected to the grid and the source-side power supply regulation capacity is insufficient, this strategy, using the data provided by the above method and decomposing the source-load data, can rationally allocate the configuration capacity of different energy storage devices on demand, achieving near-complete absorption of wind and solar power generation. While ensuring supply and demand balance and keeping economic costs low, this strategy can improve system stability and ensure sufficient regulation capabilities to cope with the uncertainty of wind and solar resource connection and sudden load changes.

[0124] This embodiment also performs the following verification:

[0125] To verify the effectiveness of the proposed seasonal amino multi-element energy storage configuration strategy based on time series component extraction, a comparative analysis was conducted from the perspective of total cost. Using MATLAB software, the gurobi solver was used to calculate the planning costs under three scenarios.

[0126] Scenario 1: Construct a seasonal amino multi-element energy storage framework, without extracting the time series component, and directly solve the energy storage capacity.

[0127] Scenario 2: Construct a seasonal amino multi-element energy storage framework, use the improved STL decomposition algorithm to extract time series components, and build scenario-based constraints to calculate the energy storage capacity.

[0128] Combining typical daily data of wind, solar and heat, the system planning costs under two different scenarios are shown in Table 2.

[0129] Table 2

[0130]

[0131] Through the solution, it can be seen from the comparison of energy storage configuration capacity and cost under different scenarios shown in Table 2 that the total cost of scenario 2 is reduced by $163,400 compared with scenario 1. After introducing the time component scenario constraint, the system can reasonably configure the multi-element energy storage capacity, greatly reduce the penalty cost, and realize the full-time fluctuation smoothing of the system. The time component driven configuration strategy (scenario 2) proposed in this embodiment shows significant advantages over the traditional energy storage capacity configuration method (scenario 1). The system's leveling capability is very high. Figure 6 , Figure 7 As shown, not only the lowest total cost is achieved, but also the wind and solar resources are almost completely absorbed.

[0132] This example addresses the limitations of the traditional STL (Seasonal-Trend Decomposition using Loess) algorithm in integrated energy system planning and proposes an improved STL method based on statistical test constraints. The core innovation lies in the introduction of a variance independence test mechanism to enhance the independence of decomposed components. However, the size of the constraints significantly influences the configuration results. To address this, additional examples are added to analyze the configuration results using different variance thresholds.

[0133] from Figure 7 As shown in the figure, as the STL decomposition variance threshold increases, the source-load dynamic mismatch index and total system cost both increase, and the device configuration error also increases. This indicates that at a lower error threshold, STL decomposition can provide more accurate eigenvalues, improving the reliability of energy storage system configuration. However, a higher variance threshold may lead to a decrease in the accuracy of eigenvalue decomposition and insufficient independence of the components, affecting the energy storage system configuration results and, in turn, the overall performance.

[0134] This embodiment further provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method.

[0135] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method are implemented.

[0136] This embodiment also provides a computer program product, including a computer program, which implements the steps of the method when executed by a processor.

[0137] The above are merely preferred embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A seasonal amino multi-element energy storage capacity configuration method based on time series component extraction, characterized in that: The following steps are involved: Build a multi-energy storage system with an ammonia energy storage system as the core, including battery energy storage and thermal energy storage; An improved STL decomposition algorithm is used to extract time series components from wind power output, photovoltaic output, and thermal load data in the power system, and scenario-based constraints are constructed based on the time series component extraction results. Based on multiple energy storage systems and scenario constraints, a two-dimensional optimization model of leveling and economy is constructed to optimize the capacity configuration of multiple energy storage systems and obtain the optimal configuration plan.

2. The method according to claim 1, characterized in that The ammonia energy storage system includes an ammonia synthesis module, a storage module, and a utilization module. The system operating cost is quantitatively represented as follows: Where, They are electrolyzer operating cost, hydrogen-to-ammonia cost, ammonia storage cost, and ammonia fuel cell operating cost.

3. The method according to claim 1, characterized in that The improved STL decomposition algorithm comprises: Perform K-means cluster analysis on the original data to extract representative typical daily data; Generate time series data based on typical daily data and decompose it using the STL algorithm; A variance threshold test is introduced in the decomposition process to eliminate components that do not meet the independence requirements.

4. The method according to claim 1, wherein The time series component extraction result includes a trend component, a seasonal component and a random fluctuation component.

5. The method according to claim 4, characterized in that Based on the time series component extraction results, scenario constraints are constructed, including: The trend component and the random fluctuation component are added together to construct the joint component scenario constraint, which is used to configure the capacity of the battery energy storage; Seasonal scenario balance constraints are constructed with seasonal components to configure the capacity of ammonia energy storage and thermal energy storage.

6. The method according to claim 1, characterized in that The objective function of the dual-dimensional optimization model of stabilization and economy is: Where, are the unit investment costs of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage device respectively; P EL 、P AFC 、M ABS 、M APS , Q EB , Q THS 、P BESS are the rated capacities of electrolyzer, ammonia fuel cell, ammonia storage tank, ammonia production equipment, electric heating device, heat storage device, and battery energy storage, r is the interest rate; τ is the investment recovery period, are the unit wind curtailment, solar curtailment and load curtailment costs, They are wind power curtailment, solar power curtailment and load curtailment respectively.

7. The method according to claim 1, characterized in that The conversion model of the ammonia energy storage system includes: Where, P EL,AC is the AC power before input into the electrolytic cell; P EL,DC is the DC power input to the electrolytic cell; is the AC-DC conversion efficiency of the electrolyzer; Power for hydrogen production in electrolyzer; The efficiency of the recovery device in absorbing the waste heat from the electrolytic cell; Q HRU (t) is the heat power recovered by the electrolytic cell during period t; is the mass of hydrogen produced by the electrolyzer during period t; It is the high calorific value of hydrogen; is the mass of ammonia produced during time period t; is the energy consumption required for hydrogen to ammonia conversion per unit time period; are the energy consumption of the power-to-ammonia equipment during period t and the thermal power provided by the ammonia system for unit ammonia production; η heat It is the ratio of heat released by the ammonia production equipment used for heating.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.