Micro-grid energy collaborative management method, device, system, equipment and medium

Abstract

The invention discloses a micro-grid energy collaborative management method, device, system and equipment and a medium. The method comprises the following steps: acquiring target micro-grid data and a target micro-grid energy management optimization model of a target micro-grid system; wherein the target microgrid energy management optimization model is constructed based on a microgrid power generation stability parameter, a photovoltaic consumption parameter and a fuel cell life loss parameter; inputting the target micro-grid data into the target micro-grid energy management optimization model for model solution to obtain a target management instruction; performing multi-energy collaborative management on the target microgrid system according to the target management instruction; wherein the target microgrid system comprises a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit and a load unit. According to the technical scheme, the characteristics of slow starting and service life sensitivity of the fuel cell are fully considered, micro-grid energy optimization management is achieved through micro-grid multi-energy cooperative operation, and stable and efficient operation of a micro-grid system is guaranteed.

Description

A method, device, system, equipment, and medium for microgrid energy collaborative management. Technical Field

[0001] This invention relates to the field of energy management technology, and in particular to a microgrid energy collaborative management method, device, system, equipment and medium. Background Technology

[0002] With the acceleration of the global energy transition, distributed energy systems have been widely researched and applied due to their advantages such as high energy efficiency and environmental friendliness. Microgrids, as a core component of distributed energy systems, can integrate renewable energy generation equipment such as photovoltaics, energy storage systems, fuel cells, and various loads to achieve local energy production and consumption, improving the reliability and flexibility of energy supply.

[0003] Solid oxide fuel cells (SOFCs), as a highly efficient electrochemical power generation device, have advantages such as wide fuel adaptability, high power generation efficiency, and low emissions, making them very suitable as the main power source for microgrids. However, they have significant operational limitations: 1. Long start-up time: SOFCs typically require 8-12 hours for cold start and 2-4 hours for hot start, making them unable to quickly respond to load changes or fluctuations in renewable energy output; 2. SOFC lifespan is sensitive to operating conditions: Frequent start-ups and shutdowns, large fluctuations in output, and sudden changes in operating temperature can all lead to a significant reduction in their lifespan, seriously affecting the long-term stable operation of the microgrid as a whole.

[0004] Existing microgrid energy management methods mostly focus on the coordinated scheduling of photovoltaics, energy storage, and loads, or consider the operation and control of fuel cells alone. They fail to fully integrate the characteristics of fuel cells, such as slow start-up and lifespan sensitivity, and fail to deeply optimize their synergy with photovoltaic-storage-load systems as the main power source. If the long start-up time of fuel cells is not fully considered, blindly demanding rapid output increases or emergency starts of fuel cells when the microgrid experiences power shortages can easily lead to start-up failures or significant lifespan losses. Furthermore, most methods only focus on power balance and minimizing economic costs as optimization objectives, neglecting fuel cell lifespan degradation. This results in frequent fluctuations in fuel cell output and excessive start-stop cycles, significantly shortening their lifespan and increasing equipment replacement costs later on. Summary of the Invention

[0005] This invention provides a microgrid energy collaborative management method, device, system, equipment, and medium. It fully considers the slow start-up and lifespan sensitivity of fuel cells, uses fuel cells as the main power source, and achieves microgrid energy optimization management through multi-energy collaborative operation, which helps to ensure the stable and efficient operation of the microgrid system.

[0006] According to one aspect of the present invention, a microgrid energy collaborative management method is provided, the method comprising:

[0007] Acquire target microgrid data and target microgrid energy management optimization model for the target microgrid system; wherein, the target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifetime loss parameters;

[0008] The target microgrid data is input into the target microgrid energy management optimization model to solve the model and obtain the target management command.

[0009] The target microgrid system is managed collaboratively with multiple energy sources according to the target management instructions; wherein the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit.

[0010] According to another aspect of the present invention, a microgrid energy collaborative management device is provided, the device comprising:

[0011] The information acquisition module is used to acquire target microgrid data and target microgrid energy management optimization model of the target microgrid system; wherein, the target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters and fuel cell lifetime loss parameters;

[0012] The optimization model solving module is used to input the target microgrid data into the target microgrid energy management optimization model to solve the model and obtain the target management instructions.

[0013] The microgrid energy management module is used to perform multi-energy collaborative management of the target microgrid system according to the target management instructions; wherein, the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit.

[0014] According to another aspect of the present invention, a microgrid energy collaborative management system is provided, the microgrid energy collaborative management system comprising a target microgrid system and an energy management center, the target microgrid system comprising a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit, and the energy management center being equipped with a microgrid energy collaborative management device.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the microgrid energy collaborative management method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the microgrid energy collaborative management method according to any embodiment of the present invention.

[0018] The technical solution of this invention first acquires target microgrid data and a target microgrid energy management optimization model. The target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifespan loss parameters. Then, the target microgrid data is input into the target microgrid energy management optimization model for model solving to obtain target management instructions. Subsequently, multi-energy collaborative management of the target microgrid system is performed according to the target management instructions. The target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit. This technical solution fully considers the slow start-up and lifespan sensitivity of fuel cells, using fuel cells as the primary power source. Through multi-energy collaborative operation of the microgrid, it achieves optimized energy management of the microgrid, helping to ensure the stable and efficient operation of the microgrid system.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 is a schematic diagram of a target microgrid system according to an embodiment of the present invention;

[0022] Figure 2 is a schematic diagram of a microgrid energy collaborative management system according to an embodiment of the present invention;

[0023] Figure 3 is a flowchart of a microgrid energy collaborative management method according to an embodiment of the present invention;

[0024] Figure 4 is a flowchart of another microgrid energy collaborative management method provided according to an embodiment of the present invention;

[0025] Figure 5 is a structural schematic diagram of a microgrid energy collaborative management device according to an embodiment of the present invention;

[0026] Figure 6 is a schematic diagram of the structure of an electronic device that implements a microgrid energy collaborative management method according to an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] This invention is applicable to the multi-energy collaborative optimization management of a target microgrid system. Therefore, it is necessary to pre-construct the target microgrid system based on a multi-energy collaborative microgrid architecture. As shown in Figure 1, the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit, all connected via a microgrid bus. The photovoltaic power generation unit, as a renewable energy source for the target microgrid system, has advantages such as being clean, pollution-free, and inexhaustible. However, photovoltaic output is affected by natural factors such as sunlight intensity and weather, exhibiting strong intermittency and fluctuation. If not effectively absorbed, it will not only waste energy but also affect the voltage and frequency stability of the target microgrid system. The energy storage unit, as an important flexible adjustment resource in the target microgrid system, can achieve rapid charging and discharging, compensate for power shortages or absorb redundant power, and smooth power fluctuations. However, the energy storage unit suffers from SOC (State of Charge) limitations, charging and discharging efficiency constraints, and lifespan degradation. Disordered scheduling can lead to energy storage lifespan degradation and increased operating costs. SOFC in fuel cell power generation units, as a high-efficiency electrochemical power generation device for the target microgrid system, has the advantages of wide fuel adaptability, high power generation efficiency and low emissions, making it very suitable as the main power generation source for the target microgrid system.

[0030] Specifically, the functional positioning of each unit in the target microgrid system is as follows:

[0031] (1) Fuel cell power generation unit: As the main power generation resource, it is responsible for providing the basic load power of the target microgrid system; during steady-state operation, it maintains the high-efficiency and low-loss operating range (such as 60%-80% of the rated output); during the start-up phase, the start-up sequence is planned in advance according to the start-up time characteristics (such as 8-12 hours for cold start and 2-4 hours for hot start) to avoid emergency start-up; during operation, the output ramp-up rate and temperature fluctuation are strictly controlled to reduce life loss.

[0032] (2) Photovoltaic power generation unit: As a renewable energy power generation resource, it prioritizes meeting the electricity demand of local flexible loads, maximizing self-consumption; it obtains the predicted photovoltaic output value for future periods in advance through a photovoltaic output prediction model, providing a basis for energy dispatch. The input variables of the photovoltaic output prediction model include historical output data, predicted light intensity, predicted temperature, and weather type (such as sunny, cloudy, rainy, etc.), and its output variable is the predicted photovoltaic output value for future periods. For example, the photovoltaic output prediction model can use a BP neural network. The BP neural network (Backpropagation Neural Network) is a multi-layer feedforward neural network based on the backpropagation algorithm. Specifically, the BP neural network includes an input layer, hidden layers (which may contain multiple layers), and an output layer, with each layer connected via a fully connected method.

[0033] (3) Energy storage unit: As a flexible adjustment resource, it is responsible for making up for the power shortage during the start-up phase of the fuel cell or when the photovoltaic output is insufficient, absorbing the photovoltaic output redundancy or the excessive output of the fuel cell; during operation, it maintains the SOC within a preset range (e.g., 10%-90%) to avoid overcharging and over-discharging. For example, the energy storage unit can be a lithium battery energy storage device.

[0034] (4) Load Units: Based on flexible load construction, specifically including deferred loads (such as electric vehicle charging, washing machines, etc.), interruptible loads (such as industrial auxiliary equipment, air conditioners, etc.), and adjustable loads (such as lighting systems, constant temperature equipment, etc.); orderly scheduling is carried out according to energy supply conditions and load response priorities to help smooth power fluctuations and improve photovoltaic absorption rate. For example, load response priorities can be divided according to load importance, such as interruptible loads having the lowest priority, deferred loads having the second highest priority, and adjustable loads having the highest priority; in actual scheduling, loads with lower priority are scheduled first.

[0035] Furthermore, this invention also constructs a microgrid energy collaborative management system, as shown in Figure 2. This system includes a target microgrid system and an energy management center. The target microgrid system comprises fuel cell power generation units, photovoltaic power generation units, energy storage units, and load units. The energy management center is equipped with microgrid energy collaborative management devices. The energy management center can interact with each unit in the target microgrid system and issue commands via a communication network. As the core of the microgrid energy collaborative management, the energy management center is responsible for collecting operational status data from each unit, establishing and solving the target microgrid energy management optimization model, generating management commands for each unit, and simultaneously monitoring the operational status of the target microgrid system in real time and handling sudden disturbances.

[0036] Example 1

[0037] Figure 3 is a flowchart of a microgrid energy collaborative management method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where efficient and stable energy management of a microgrid is achieved through the collaborative operation of multiple energy sources. This method can be executed by a microgrid energy collaborative management device, which can be implemented in hardware and / or software. This microgrid energy collaborative management device can be configured in an electronic device with data processing capabilities. As shown in Figure 3, the method includes:

[0038] S110, acquire the target microgrid data and the target microgrid energy management optimization model of the target microgrid system; wherein, the target microgrid energy management optimization model is constructed based on the microgrid power generation stability parameters, photovoltaic absorption parameters and fuel cell lifetime loss parameters.

[0039] The target microgrid system can refer to a microgrid system requiring multi-energy collaborative management. Target microgrid data can refer to operational data from the target microgrid system, specifically including photovoltaic data, fuel cell data, energy storage data, load data, and microgrid operation data. The target microgrid energy management optimization model can refer to an optimization model used for energy management of the target microgrid system. This optimization model can be constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifetime loss parameters. For example, the microgrid power generation stability parameter can be set as the total power fluctuation of the microgrid, the photovoltaic absorption parameter can be set as the photovoltaic absorption rate, and the fuel cell lifetime loss parameter can be set as the fuel cell lifetime loss per unit time. The unit time can be flexibly set according to actual needs; for example, it can be set to one day.

[0040] In this embodiment, target microgrid data and energy management optimization models for the target microgrid system can be obtained based on a target scheduling cycle. The target scheduling cycle refers to the pre-set energy scheduling interval for the target microgrid system according to actual needs. For example, the target scheduling cycle can be set to 15 minutes, meaning data acquisition and energy scheduling are performed every 15 minutes. Specifically, the energy management center can utilize sensors, smart meters, communication modules, and other devices to acquire target microgrid data through real-time acquisition or prediction. For example, the target microgrid data may include:

[0041] (1) Photovoltaic data: This may include the photovoltaic output forecast for the future scheduling period (e.g., the next 24 hours), the current actual photovoltaic output, and the photovoltaic inverter operating status. The photovoltaic output forecast can be obtained through a photovoltaic output forecast model. For example, the photovoltaic inverter operating status may include normal, fault, and shutdown. (2) Fuel cell data: This may include the current fuel cell output power, operating temperature, fuel consumption rate, start-up status (e.g., not started, cold start, hot start, steady-state operation), cumulative lifetime loss, historical start-up data, and total fuel supply. (3) Energy storage data: This may include the current energy storage SOC value, charge and discharge power, charge and discharge efficiency, rated capacity, rated power, and SOC upper and lower limits. (4) Load data: This may include the load forecast power for the future scheduling period (e.g., the next 24 hours) (loads can be divided into rigid loads and flexible loads according to load type; rigid loads are non-adjustable loads, such as basic residential electricity consumption; flexible loads are dispatchable loads), the current actual power consumption of each load, the response priority of flexible loads, and the adjustable capacity. (5) Microgrid operation data: may include microgrid bus voltage, operating frequency, power factor and network loss power.

[0042] In this embodiment, optionally, the process of constructing the target microgrid energy management optimization model includes: determining the total power generation fluctuation of the microgrid, the photovoltaic absorption rate, and the fuel cell lifetime loss per unit time during the current scheduling period; constructing an objective function based on the weighted sum of the total power generation fluctuation of the microgrid, the photovoltaic absorption rate, and the fuel cell lifetime loss per unit time during the current scheduling period; wherein, the total power generation fluctuation of the microgrid has the highest weight; constructing the constraints of each unit in the target microgrid system during the current scheduling period; and determining the target microgrid energy management optimization model corresponding to the current scheduling period based on the objective function and the constraints.

[0043] It should be noted that the target microgrid energy management optimization model is a multi-objective and multi-constraint optimization model. The core objective is to optimize the stability of microgrid power generation, while also taking into account maximizing photovoltaic absorption and minimizing fuel cell lifetime loss. It can be described by objective functions and constraints.

[0044] Specifically, the total power fluctuation of microgrid generation, photovoltaic absorption rate, and fuel cell life loss per unit time are first determined during the current scheduling period, and used as the microgrid power generation stability parameter, photovoltaic absorption parameter, and fuel cell life loss parameter, respectively, during the current scheduling period. Optionally, determining the total power fluctuation of the microgrid, the photovoltaic absorption rate, and the fuel cell lifespan loss per unit time during the current scheduling period includes: determining the total power fluctuation of the microgrid during the current scheduling period based on the absolute value of the difference between the total power of the microgrid during the current scheduling period and the previous scheduling period; wherein the total power of the microgrid is determined based on the sum of the fuel cell output power, photovoltaic output power, and energy storage charging and discharging power; determining the photovoltaic absorption rate during the current scheduling period based on the ratio of the actual photovoltaic absorption power to the total predicted photovoltaic output power; wherein the actual photovoltaic absorption power includes the photovoltaic output power consumed by the load unit and the photovoltaic output power absorbed by the energy storage unit; and determining the fuel cell lifespan loss per unit time during the current scheduling period based on the weighted sum of at least two operating parameters of the fuel cell during the current scheduling period; wherein the operating parameters of the fuel cell include the number of daily start-stop cycles, output ramp-up rate, operating temperature fluctuation range, and fuel purity.

[0045] In this embodiment, the fluctuation of the total power generation of the microgrid can be defined as the sum of the absolute values ​​of the differences in the total power generation of the microgrid during adjacent scheduling periods. The smaller the fluctuation of the total power generation of the microgrid, the better the stability of the microgrid's power generation. For example, the fluctuation of the total power generation of the microgrid ΔP can be expressed as follows:

[0046] ΔP=Σ|(P_sofc(t)+P_pv(t)+P_ess(t))-(P_sofc(t-1)+P_pv(t-1)+P_ess(t-1))|;

[0047] Where t is the current scheduling period, t=1,2,...,T (e.g., T=96, corresponding to 24 hours, with each period lasting 15 minutes), and t-1 is the previous scheduling period; P_sofc(t) represents the SOFC output power during period t; P_pv(t) represents the photovoltaic output power during period t; and P_ess(t) represents the energy storage charging and discharging power during period t, where P_ess(t)>0 indicates charging and P_ess(t)<0 indicates discharging.

[0048] The higher the photovoltaic (PV) grid integration rate, the better the PV grid integration effect. For example, the PV grid integration rate η_pv can be expressed as follows: η_pv = P_pv_consumed / P_pv_total. Where P_pv_consumed is the actual PV power consumed (i.e., the sum of PV power consumed by the load unit and absorbed by the energy storage unit), and P_pv_total is the predicted total PV power output.

[0049] The lower the lifespan loss per unit time of a fuel cell, the less lifespan loss occurs. For example, taking SOFC as an example, the lifespan loss per unit time, L_sofc (% / day), can be determined using the SOFC lifespan loss model, specifically expressed as follows: L_sofc = a·N_start + b·R_ramp + c·ΔT + d·(1-γ_fuel). Where N_start represents the number of start-stop cycles of the SOFC per day, R_ramp represents the SOFC output ramp-up rate (% rated power / min), ΔT represents the SOFC operating temperature fluctuation range (°C / h), and γ_fuel represents fuel purity (%); a, b, c, and d represent different weighting coefficients, the specific values ​​of which can be determined by fitting the SOFC stack characteristic curve using the least squares method, for example, a = 0.005, b = 0.002, c = 0.001, d = 0.003. Specifically, the weighting coefficients can have units of measurement to balance the equation.

[0050] In this embodiment, after determining the total power fluctuation of the microgrid, the photovoltaic absorption rate, and the unit-time lifespan loss of the fuel cell during the current scheduling period, the three can be weighted and summed to construct the objective function. The weighted summation method transforms a multi-objective optimization problem into a single-objective optimization problem. For example, the objective function F can be expressed as: min F = ω1·ΔP + ω2·(1-η_pv) + ω3·L_sofc. Here, ω1, ω2, and ω3 represent different weights, satisfying ω1 + ω2 + ω3 = 1. For example, based on the microgrid's operational priority, ω1 can be set to a range of 0.5-0.7 (prioritizing power generation stability), ω2 to a range of 0.2-0.3 (considering the photovoltaic absorption rate), and ω3 to a range of 0.1-0.2 (ensuring SOFC lifespan). The weights can be dynamically adjusted based on the target microgrid system's operational status evaluation indicators.

[0051] In this embodiment, it is also necessary to construct the constraints of each unit in the target microgrid system during the current scheduling period, and then determine the energy management optimization model of the target microgrid based on the objective function and the constraints. Optionally, constructing the constraints of each unit in the target microgrid system during the current scheduling period includes: determining the constraints of each unit in the target microgrid system during the current scheduling period based on the target microgrid data of each unit in the target microgrid system during the current scheduling period; wherein, the constraints include power balance constraints, fuel cell operation constraints, photovoltaic absorption constraints, energy storage operation constraints, flexible load scheduling constraints, and microgrid safe operation constraints; fuel cell operation constraints include at least one of start-up time constraints, output upper and lower limit constraints, output ramp-up rate constraints, temperature constraints, fuel supply constraints, and lifetime loss constraints.

[0052] Specifically, the total power generation of the microgrid and the load power need to meet the power balance. After considering the network loss, the power balance constraint can be expressed as: P_sofc(t)+P_pv(t)+P_ess(t)=P_load_rigid(t)+P_load_flex(t)+P_loss(t). Wherein, P_load_rigid(t) represents the rigid load power (non-adjustable) during time period t; P_load_flex(t) represents the flexible load power (adjustable) during time period t, P_load_flex_min(t)≤P_load_flex(t)≤P_load_flex_max(t), where P_load_flex_min(t) is the minimum power consumption of the flexible load, and P_load_flex_max(t) is the maximum power consumption of the flexible load; P_loss(t) represents the microgrid loss power during time period t, which can be set as P_loss(t)=0.05×(P_sofc(t)+P_pv(t)+P_ess(t)) based on the microgrid topology and operating experience; P_pv(t)≤P_pv_pred(t), where P_pv_pred(t) is the predicted photovoltaic output during time period t.

[0053] For example, taking SOFC as an example, the start-up time constraint may include: in cold start state, the time required for SOFC to reach 60% of rated output from start-up is t_cold≥8h; in hot start state, the time required for SOFC to reach 60% of rated output from start-up is t_hot≥2h; during the start-up process, SOFC output increases linearly: P_sofc_start(t)=P_sofc_min+(P_sofc_rated×60%-P_sofc_min)×(t-t_start) / t_start_duration, where t_start is the start-up time, t_start_duration is the start-up time, P_sofc_min is the minimum output power of SOFC, and P_sofc_rated is the rated output power of SOFC.

[0054] For example, taking SOFC as an example, the upper and lower limits of output can be set as P_sofc_min≤P_sofc(t)≤P_sofc_max, where P_sofc_min is the minimum stable output of SOFC (usually 20% of rated power), and P_sofc_max is the rated output power of SOFC. The output ramp-up rate constraint can be set as -R_ramp_down≤(P_sofc(t)-P_sofc(t-1)) / Δt≤R_ramp_up, where R_ramp_up is the maximum output ramp-up rate of SOFC (≤2% rated power / min), and R_ramp_down is the maximum output ramp-down rate of SOFC (≤3% rated power / min). The temperature constraint can be set as T_sofc_min≤T_sofc(t)≤T_sofc_max, where T_sofc_min is the minimum operating temperature of the SOFC (e.g., 600℃) and T_sofc_max is the maximum operating temperature of the SOFC (e.g., 850℃); the temperature fluctuation range constraint can be set as |T_sofc(t)-T_sofc(t-1)|≤ΔT_max, where ΔT_max=5℃ / h.

[0055] For example, the fuel supply constraint can be set as P_sofc(t)≤F_fuel(t)×η_fuel_electric, where F_fuel(t) is the SOFC fuel supply rate (mol / s) during time period t, which can be dynamically configured by fuel resource supply conditions, gas properties, etc., and η_fuel_electric is the SOFC fuel electro-conversion efficiency (e.g., 45%-60%). The lifetime loss constraint can be set as N_start≤1 time / day, R_ramp≤2% rated power / min, ΔT≤5℃ / h, and L_sofc≤0.01% / day.

[0056] For photovoltaic (PV) power consumption constraints, under the premise of ensuring the safe operation of the microgrid, PV output is prioritized for full consumption, which can be expressed as: P_pv(t)≤P_load_rigid(t)+P_load_flex(t)+P_ess_charge_max(t), where P_ess_charge_max(t) is the maximum charging power of energy storage during time period t. When PV output exceeds the PV power consumption constraint, deferred loads can be scheduled to operate during this time period to improve the consumption capacity through flexible load transfer, thereby increasing P_load_flex(t). Only when the flexible load adjustment capacity is insufficient, PV output is restricted, i.e., P_pv(t)=P_load_rigid(t)+P_load_flex_max(t)+P_ess_charge_max(t), at which point the PV curtailment rate is ≤5%.

[0057] Specifically, energy storage operation constraints can include SOC constraints, SOC variation constraints, charging / discharging power constraints, and power smoothing constraints. For example, the SOC constraint can be set as SOC_min ≤ SOC(t) ≤ SOC_max, where SOC_min = 10% and SOC_max = 90%. For the charging state, i.e., P_ess(t) > 0, the SOC variation constraint can be set as SOC(t) = SOC(t-1) + P_ess(t) × Δt × η_ess_charge / E_ess_rated; for the discharging state, i.e., P_ess(t) < 0, the SOC variation constraint can be set as SOC(t) = SOC(t-1) + P_ess(t) × Δt / (η_ess_discharge × E_ess_rated); where η_ess_charge is the energy storage charging efficiency (≥85%), η_ess_discharge is the energy storage discharging efficiency (≥85%), and E_ess_rated is the rated energy storage capacity. The charging and discharging power constraint can be set as -P_ess_discharge_max ≤ P_ess(t) ≤ P_ess_charge_max, where P_ess_charge_max is the maximum charging power of the energy storage (≤50% of the rated power), and P_ess_discharge_max is the maximum discharging power of the energy storage (≤50% of the rated power). The power smoothing constraint can be set as |P_ess(t) - P_ess(t-1)| ≤ P_ess_ramp_max, where P_ess_ramp_max is the maximum rate of change of the energy storage charging and discharging power (≤10% of the rated power / min).

[0058] For flexible load scheduling constraints, these can specifically include response priority constraints, regulating capacity constraints, and time constraints. For example, the response priority constraint can be set to have the lowest priority for interruptible loads, followed by deferred loads, and then the highest priority for deferred loads. The regulating capacity constraint can be set to P_load_flex_min(t) ≤ P_load_flex(t) ≤ P_load_flex_max(t), where P_load_flex_min(t) is the minimum power consumption of the flexible load during time period t (ensuring basic functional operation), and P_load_flex_max(t) is the maximum power consumption of the flexible load during time period t (the sum of the rated power of the equipment). For time constraints, deferred loads have earliest start time and latest end time constraints. For example, the earliest start time for electric vehicle charging loads is 18:00, and the latest end time is 7:00 the next day; power consumption must be scheduled within this time window during scheduling.

[0059] Constraints for the safe operation of microgrids can specifically include voltage constraints and frequency constraints. For example, the voltage constraint can be set as U_min ≤ U(t) ≤ U_max, where U_min and U_max are the minimum and maximum voltages, respectively, U_min = 0.95U_rated, U_max = 1.05U_rated, and U_rated is the microgrid's rated voltage (e.g., 380V). The frequency constraint can be set as f_min ≤ f(t) ≤ f_max, where f_min and f_max are the minimum and maximum frequencies, respectively, f_min = 49.5Hz, f_max = 50.5Hz.

[0060] This invention fully considers the operating characteristics of fuel cells. Addressing the slow start-up and lifespan sensitivity of fuel cells, it establishes a fuel cell operating constraint system that includes at least one of the following: start-up time constraint, output ramp-up rate constraint, temperature and its fluctuation amplitude constraint, and lifespan loss constraint. This system aims to avoid frequent start-ups and shutdowns and large output fluctuations through optimized scheduling. Simultaneously, by incorporating fuel cell lifespan loss parameters into the optimization objective, it effectively reduces fuel cell lifespan loss and extends its service life. Furthermore, this invention focuses on minimizing the total power fluctuation of microgrid generation as its core optimization objective. Through rapid charging and discharging of energy storage and flexible load scheduling, it smooths out fluctuations in photovoltaic output and changes in fuel cell output, contributing to improved microgrid power generation stability. Additionally, this invention establishes a principle of prioritizing self-consumption of photovoltaic power generation. It enhances photovoltaic absorption capacity through flexible load scheduling and energy storage charging, limiting only a small amount of photovoltaic output in extreme cases, thereby increasing photovoltaic absorption rate, reducing energy waste, and improving energy utilization efficiency.

[0061] S120: Input the target microgrid data into the target microgrid energy management optimization model to solve the model and obtain the target management command.

[0062] In this embodiment, after acquiring the target microgrid data and the target microgrid energy management optimization model, the target microgrid data can be input into the target microgrid energy management optimization model for solution, thereby obtaining the target management instructions. For example, linear programming, genetic algorithms, and Model Predictive Control (MPC) algorithms can be used to solve the optimization model. Among these, the MPC algorithm is an advanced control algorithm based on model, optimization, and feedback, featuring rolling optimization and feedback correction. It can effectively handle constrained dynamic optimization problems and is applicable to microgrid energy management scenarios.

[0063] For example, when using the MPC algorithm to solve the optimization model, the prediction time domain N_p = 24 (corresponding to 6 hours, with each period lasting 15 minutes) and the control time domain N_c = 8 (corresponding to 2 hours) can be set. That is, during each optimization, based on the target microgrid data for the current scheduling period, the microgrid status for the next 24 periods is predicted, and optimization control instructions for the next 8 periods are output. The optimization control instruction for the first of these 8 periods is designated as the target management instruction for the current scheduling period, while the remaining 7 periods' optimization control instructions can be used by maintenance personnel to view the trend changes of the microgrid in future periods. After executing the target management instruction for the current scheduling period, the process rolls to the next scheduling period for re-optimization, thus achieving dynamic scheduling. For example, the target management instructions can include fuel cell output instructions, energy storage charging and discharging power instructions, and flexible load power instructions.

[0064] S130 performs multi-energy collaborative management of the target microgrid system according to the target management instructions.

[0065] Upon receiving the target management instructions, the energy management center can distribute these instructions to each unit within the target microgrid system via a communication network for execution, thereby achieving dynamic optimization management of microgrid energy. Specifically, for fuel cell power generation units, the fuel supply rate can be adjusted according to fuel cell output instructions to maintain stable operating temperature and output, avoiding frequent output fluctuations and start-stop cycles. For energy storage units, the charging and discharging states can be adjusted according to energy storage charging and discharging power instructions to maintain the SOC value within a reasonable range; during charging, priority is given to absorbing redundant photovoltaic output, and during discharging, priority is given to compensating for insufficient fuel cell output. For load units, the operating time of delayable loads, the connection or disconnection status of interruptible loads, and the power consumption of adjustable loads can be adjusted according to flexible load power instructions to help smooth power fluctuations and improve photovoltaic absorption rate. Furthermore, the energy management center can monitor the microgrid status in real time, update the target microgrid data every 15 minutes, and perform a rolling model optimization to dynamically adjust the target management instructions.

[0066] The technical solution of this invention first acquires target microgrid data and a target microgrid energy management optimization model. The target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifespan loss parameters. Then, the target microgrid data is input into the target microgrid energy management optimization model for model solving to obtain target management instructions. Subsequently, multi-energy collaborative management of the target microgrid system is performed according to the target management instructions. The target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit. This technical solution fully considers the slow start-up and lifespan sensitivity of fuel cells, using fuel cells as the primary power source. Through multi-energy collaborative operation of the microgrid, it achieves optimized energy management of the microgrid, helping to ensure the stable and efficient operation of the microgrid system.

[0067] In this embodiment, optionally, the method further includes: determining the operation status evaluation index of the target microgrid system based on the target evaluation period; wherein the target evaluation period is longer than the target scheduling period, and the operation status evaluation index includes the microgrid total power generation fluctuation index, photovoltaic absorption rate index, fuel cell cumulative life loss index, and load power supply reliability index; and dynamically adjusting the weights in the objective function according to the operation status evaluation index.

[0068] In this embodiment, the energy management center can periodically assess the operational status of the target microgrid system based on the target assessment cycle, calculating multiple operational status assessment indicators. These may include the microgrid's total power generation fluctuation indicator ΔP_total, the photovoltaic absorption rate indicator η_pv_total, the SOFC cumulative lifetime loss indicator L_sofc_total, the energy storage SOC maintenance level indicator, and the load power supply reliability indicator (power outage time / total operating time), etc. The weights (i.e., ω1, ω2, ω3) in the objective function are dynamically adjusted according to the above operational status assessment indicators. For example, if the target scheduling cycle is 15 minutes, the target assessment cycle can be set to 1 day.

[0069] For example, if the cumulative SOFC lifespan loss index L_sofc_total > 0.01% / day, then increase ω3 to 0.25 and decrease ω1 to 0.5 to reduce SOFC output fluctuations and lifespan loss. If the photovoltaic absorption rate index η_pv_total < 90%, then increase ω2 to 0.35 and decrease ω1 to 0.55 to prioritize photovoltaic absorption and dispatch flexible loads to improve absorption capacity. If the microgrid power generation fluctuation index ΔP_total > 10% of rated power, then increase ω1 to 0.7 and decrease ω2 to 0.2 to prioritize power generation stability and strengthen power smoothing through energy storage and flexible loads. If the load power supply reliability index < 99.9%, then increase ω1 to 0.65 and decrease ω3 to 0.1 to prioritize power balance and load power supply, and appropriately relax SOFC lifespan loss constraints.

[0070] This solution, through its dynamic adjustment and optimization of target weights, can adapt to the needs of different operating scenarios, thereby improving the practicality and flexibility of microgrid energy management.

[0071] In this embodiment, optionally, the method further includes: when a sudden disturbance is detected in the target microgrid system, determining the current sudden disturbance type; determining a target emergency dispatch instruction based on a preset mapping table and the current sudden disturbance type; wherein the preset mapping table is used to describe the correspondence between the sudden disturbance type and the emergency dispatch instruction.

[0072] In this embodiment, an emergency dispatch mechanism is specifically designed to effectively address sudden disturbances in the microgrid. During the microgrid energy collaborative management process, it is possible to detect in real time whether a sudden disturbance occurs in the target microgrid system. If no sudden disturbance is detected in the target microgrid system, conventional dispatching methods are used for control, i.e., target management instructions are issued and executed, with rolling optimization adjustments every 15 minutes. If a sudden disturbance is detected in the target microgrid system, the emergency dispatch mechanism is immediately triggered to prioritize ensuring the stable operation of the microgrid and the reliability of load power supply.

[0073] Specifically, when a sudden disturbance is detected in the target microgrid system, the type of the disturbance is first determined. For example, the disturbance type may include a sudden drop in photovoltaic output, a sudden load change, a fuel cell fault, and an abnormal state of charge (SBC) disturbance in energy storage. Specifically, if the sudden drop in photovoltaic output exceeds a first preset value (e.g., 30%), the disturbance can be classified as a sudden drop in photovoltaic output. A sudden load change may include a sudden increase in load and a sudden decrease in load. Specifically, if the increase in load exceeds a second preset value (e.g., 20%), the disturbance can be classified as a sudden increase in load; if the decrease in load exceeds a third preset value (e.g., 20%), the disturbance can be classified as a sudden decrease in load. Fuel cell fault disturbances can include fuel cell shutdown disturbances and fuel cell output drop disturbances. If the fuel cell output is 0, the sudden disturbance can be identified as a fuel cell shutdown disturbance. If the sudden drop in fuel cell output is greater than a fourth set value (e.g., the fourth set value is 20%), the sudden disturbance can be identified as a fuel cell output drop disturbance. Energy storage state of charge (SBC) abnormal disturbances can include first energy storage SBC abnormal disturbances and second energy storage SBC abnormal disturbances. If the energy storage SBC is not higher than a first threshold (e.g., the first threshold is 15%), the sudden disturbance can be identified as a first energy storage SBC abnormal disturbance. If the energy storage SBC is not lower than a second threshold (e.g., the second threshold is 85%), the sudden disturbance can be identified as a second energy storage SBC abnormal disturbance.

[0074] After determining the current type of sudden disturbance, the corresponding emergency dispatch command in the preset mapping table can be used to find the current type of sudden disturbance and set it as the target emergency dispatch command. Optionally, the correspondence between sudden disturbance types and emergency dispatch commands in the preset mapping table includes: when the sudden disturbance type is a sudden drop in photovoltaic output, the emergency dispatch command includes scheduling the energy storage unit to output at maximum discharge power, limiting the fuel cell output ramp-up rate, and scheduling interruptible load shedding; when the sudden disturbance type is a sudden increase in load, the emergency dispatch command includes setting the energy storage unit to discharge mode, increasing fuel cell output, and scheduling delayed operation of deferred loads; when the sudden disturbance type is a sudden decrease in load, the emergency dispatch command includes setting the energy storage unit to charging mode and limiting photovoltaic output; when the sudden disturbance type is a fuel cell failure... During a disturbance, the emergency dispatch instructions include dispatching the energy storage unit to output power according to load demand and dispatching interruptible loads. When the sudden disturbance type is a first energy storage state of charge abnormality disturbance, the emergency dispatch instructions include dispatching the energy storage unit to stop discharging and increasing the fuel cell output. The energy storage state of charge under the first energy storage state of charge abnormality disturbance is not higher than the first threshold. When the sudden disturbance type is a second energy storage state of charge abnormality disturbance, the emergency dispatch instructions include dispatching the energy storage unit to stop charging and dispatching delayed loads to operate. The energy storage state of charge under the second energy storage state of charge abnormality disturbance is not lower than the second threshold, and the second threshold is greater than the first threshold.

[0075] For example, regarding the emergency dispatch mechanism, when a sudden drop in photovoltaic output is detected, the energy storage unit immediately switches to discharge mode and outputs at maximum discharge power to compensate for the power deficit; the SOFC output ramp-up rate is limited to ≤1% of rated power / min to avoid increased lifespan loss of the SOFC due to a sudden increase in output; the dispatch can interrupt load shedding to further balance power. When a sudden increase in load is detected, the energy storage unit is prioritized for discharge. If the energy storage discharge capacity is insufficient, the SOFC output is appropriately increased while meeting the SOFC ramp-up rate constraint, and the dispatch can delay the operation of loads. When a sudden drop in load is detected, the energy storage unit is prioritized for charging to absorb redundant power. If the energy storage charging capacity is insufficient, the photovoltaic output is limited to avoid microgrid voltage and frequency fluctuations.

[0076] For example, regarding the emergency dispatch mechanism, when a SOFC fault disturbance is detected, the energy storage unit immediately assumes the main power supply responsibility, outputting power according to load demand; if a backup SOFC is available, it is activated, and the activation sequence is planned according to the startup characteristic prediction model; interruptible loads with lower dispatch priority are disconnected to ensure power supply to core loads. When an abnormal disturbance in energy storage SOC is detected (e.g., SOC≤20% or SOC≥80%), if SOC≤20%, the energy storage unit stops discharging, prioritizes absorbing photovoltaic power for charging, and simultaneously increases SOFC output to reduce the pressure on energy storage power supply; if SOC≥80%, the energy storage unit stops charging, and dispatch can delay the load commissioning to improve photovoltaic absorption rate, and limit photovoltaic output if necessary.

[0077] This solution, through its design and emergency dispatch mechanism, effectively handles sudden disturbances such as sharp drops in photovoltaic output, load fluctuations, and SOFC failures, enhancing its adaptability to such disturbances and contributing to the stable operation of the microgrid. By constructing a dual-active redundant energy supply system (with the fuel cell power generation unit as the primary power source and the energy storage unit as the backup power source), combined with flexible load dispatch and emergency dispatch mechanisms, this invention can quickly balance power when equipment failures or output fluctuations are detected, ensuring the continuity of power supply to core loads and thus guaranteeing the reliability of load power supply (up to over 99.9%).

[0078] Example 2

[0079] Figure 4 is a flowchart of a microgrid energy collaborative management method provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and optimized. Specifically, the optimization is as follows: the target microgrid data is input into the target microgrid energy management optimization model for model solving to obtain the target management command, including: determining the fuel cell start-up prediction parameters based on the fuel cell data of the current scheduling period; wherein, the fuel cell start-up prediction parameters include the predicted value of the start-up time and the predicted values ​​of output and temperature for multiple scheduling periods during the start-up process; updating the start-up time constraint, output upper and lower limit constraint, and temperature constraint in the fuel cell operation constraints based on the fuel cell start-up prediction parameters; solving the target microgrid energy management optimization model corresponding to the current scheduling period to obtain the target management command corresponding to the current scheduling period; wherein, the target management command includes the fuel cell output command, the energy storage charging and discharging power command, and the flexible load power command.

[0080] As shown in Figure 4, the method in this embodiment specifically includes the following steps:

[0081] S210, acquire the target microgrid data and the target microgrid energy management optimization model of the target microgrid system; wherein, the target microgrid energy management optimization model is constructed based on the microgrid power generation stability parameters, photovoltaic absorption parameters and fuel cell lifetime loss parameters.

[0082] The target microgrid energy management optimization model includes an objective function and constraints. The constraints include fuel cell operation constraints, which include at least one of the following: start-up time constraint, output upper and lower limit constraint, output ramp rate constraint, temperature constraint, fuel supply constraint, and lifespan loss constraint.

[0083] S220, determine the fuel cell start-up prediction parameters based on the fuel cell data of the current scheduling period; wherein, the fuel cell start-up prediction parameters include the predicted value of the start-up time and the predicted values ​​of output and temperature for multiple scheduling periods during the start-up process.

[0084] In this embodiment, a fuel cell start-up characteristic prediction model can be pre-constructed based on historical fuel cell start-up data (such as historical start-up time, historical ambient temperature, historical fuel supply rate, and the relationship between historical output changes). This model can be a numerical model or a neural network model. During actual use, fuel cell data for the current scheduling period is input into the fuel cell start-up characteristic prediction model, specifically including ambient temperature, fuel supply rate, and start-up type (cold start / hot start). The model then predicts and outputs fuel cell start-up parameters (including predicted start-up time and predicted output and temperature values ​​for each scheduling period during the start-up process). The data acquisition duration corresponding to the historical fuel cell start-up data is consistent with the duration of the current scheduling period.

[0085] S230, based on the fuel cell start-up prediction parameters, updates the start-up time constraint, output upper and lower limit constraint, and temperature constraint in the fuel cell operation constraints of the target microgrid energy management optimization model under the current scheduling period.

[0086] After obtaining the predicted parameters for fuel cell startup, these parameters can be integrated into the constraints of the target microgrid energy management optimization model. This allows for the updating of the fuel cell operation constraints in the original constraints based on the predicted startup parameters, thereby avoiding unreasonable scheduling of the fuel cell during the startup phase. Specifically, the predicted startup parameters can be compared with the corresponding original fuel cell operation constraints, and the more stringent boundary values ​​can be selected as the boundary values ​​for the updated fuel cell operation constraints. For example, if the predicted minimum fuel cell output for a certain scheduling period is greater than the minimum stable output in the original upper and lower output limits constraints, then the predicted minimum fuel cell output can replace the minimum stable output in the original upper and lower output limits constraints, thus updating the upper and lower output limits constraints.

[0087] S240, Solve the target microgrid energy management optimization model corresponding to the current scheduling period to obtain the target management instruction corresponding to the current scheduling period.

[0088] The target management commands include fuel cell output commands, energy storage charging and discharging power commands, and flexible load power commands. In this embodiment, for example, an improved MPC algorithm can be used to solve the optimization model. This improved MPC algorithm, based on the traditional MPC algorithm, introduces fuel cell start-up characteristic prediction and adaptive particle swarm optimization, thereby improving the algorithm's solution accuracy and robustness. The adaptive particle swarm optimization algorithm is used to perform rolling solutions on the optimization model. This algorithm improves convergence speed and solution accuracy by adjusting inertia weights to balance global and local search capabilities.

[0089] In this embodiment, optionally, the target management instruction corresponding to the current scheduling period is obtained by solving the target microgrid energy management optimization model corresponding to the current scheduling period, including: using the objective function of the current scheduling period as the particle fitness function, calculating the fitness value of each particle under the constraints of the current scheduling period; updating the inertia weight using a combination of linear decrease and dynamic correction; wherein, the dynamic correction is adapted to the change of particle fitness value; iteratively updating the velocity and position of the particles based on the updated inertia weight according to the individual optimal fitness value and the group optimal fitness value; when the iteration stopping condition is met, the optimization instruction corresponding to the group optimal position is determined as the target management instruction corresponding to the current scheduling period; wherein, the iteration stopping condition is that the current iteration number reaches the maximum iteration number or the change in the group optimal fitness value is less than a preset value for multiple consecutive iterations.

[0090] Specifically, the process of using the adaptive particle swarm optimization algorithm to solve the optimization model in a rolling manner is as follows: (1) Initialize the particle swarm: The number of particles can be set to 50, the maximum number of iterations to 100, and the particle dimension to 3×N_c (corresponding to the fuel cell output, energy storage charging and discharging power, and flexible load power in the future N_c time periods); among which, the range of particle values ​​is determined according to the constraint conditions. (2) Calculate the fitness function: The objective function F of the target microgrid energy management optimization model under the current scheduling period is used as the particle fitness function, and the fitness value of each particle is calculated. (3) Adaptive inertia weight adjustment: The inertia weight ω is adaptively adjusted by combining linear decrease and dynamic correction. The formula is as follows: ω=ω_max-(ω_max-ω_min)×iter / iter_max+Δω. Wherein, ω_max=0.9, ω_min=0.4, iter is the current iteration number, iter_max is the maximum iteration number, Δω is the dynamic correction term (adjusted according to the change of particle fitness value, Δω is positive when the fitness value decreases, improving the global search ability; Δω is negative when the fitness value is stable, improving the local search ability); by adjusting the inertia weight ω, the weights (i.e. ω1, ω2, ω3) in the objective function can be indirectly affected. (4) Update particle position and velocity: Update particle velocity and position according to the optimal fitness value of individual particles and the optimal fitness value of the group. The update formula is as follows: v_i(T+1)=ω·v_i(T)+c1·r1·(pbest_i-x_i(T))+c2·r2·(gbest-x_i(T)), x_i(T+1)=x_i(T)+v_i(T+1). Where v_i(T) is the velocity of the i-th particle at time T, x_i(T) is the position of the i-th particle at time T, c1 and c2 are learning factors (c1=c2=2), r1 and r2 are random numbers in the interval [0,1], pbest_i is the individual optimal position of the i-th particle, and gbest is the population optimal position. (5) Constraint handling: The penalty function method is used to handle the constraint conditions. For particles that do not meet the constraints, a penalty term is added to the fitness value. The penalty term formula is: penalty=k·Σ(max(0, g_j(x))), where k is the penalty coefficient (k=100), and g_j(x) is the constraint function (g_j(x)≤0 when the constraint is met, and g_j(x)>0 when the constraint is not met). (6) Iteration termination: If the current iteration number reaches the maximum iteration number or the population optimal fitness value does not change significantly for 10 consecutive iterations (e.g., the change amount ≤10 -6 Stop iteration and output the optimization instructions (including fuel cell output instructions, energy storage charging and discharging power instructions, and flexible load power instructions) corresponding to the optimal position of the group as target management instructions.

[0091] S250 performs multi-energy collaborative management of the target microgrid system according to the target management instructions.

[0092] The technical solution of this invention, when inputting target microgrid data into the target microgrid energy management optimization model for model solving to obtain target management instructions, firstly determines fuel cell start-up prediction parameters based on fuel cell data of the current scheduling period; wherein, the fuel cell start-up prediction parameters include the predicted value of the start-up time and the predicted values ​​of output and temperature for multiple scheduling periods during the start-up process; then, the start-up time constraint, output upper and lower limit constraint, and temperature constraint in the fuel cell operation constraints are updated based on the fuel cell start-up prediction parameters; then, the target microgrid energy management optimization model corresponding to the current scheduling period is solved to obtain the target management instructions corresponding to the current scheduling period; wherein, the target management instructions include fuel cell output instructions, energy storage charging and discharging power instructions, and flexible load power instructions. This technical solution improves the traditional MPC algorithm by introducing fuel cell start-up characteristic prediction and adaptive particle swarm optimization, realizing constraint condition correction and dynamic rolling optimization of the target microgrid energy management optimization model, which helps to improve the accuracy and speed of solving target management instructions and enhance the stability and robustness of microgrid energy management.

[0093] In this embodiment, optionally, after solving the target microgrid energy management optimization model corresponding to the current scheduling period to obtain the target management instruction corresponding to the current scheduling period, the method further includes: obtaining the actual microgrid operation data after the target microgrid system executes the target management instruction; comparing the actual microgrid operation data with the target management instruction corresponding to the current scheduling period to determine the target deviation; using a proportional-integral controller to correct the target deviation to obtain the deviation correction amount; and adjusting the target microgrid energy management optimization model and / or target management instruction for the next scheduling period based on the deviation correction amount.

[0094] In this embodiment, after the target management command obtained from the solution is issued to each unit of the target microgrid system for execution, the actual operating data of the target microgrid system (including the actual output of fuel cells, the actual charging and discharging power of energy storage, the actual power consumption of flexible loads, the actual output of photovoltaics, and the voltage and frequency of the microgrid bus) can be collected in real time through the energy management center. The deviation Δx between the actual operating data x_actual and the optimized prediction data x_pred in the target management command is calculated using the formula Δx=x_actual-x_pred as the target deviation. Then, a proportional-integral controller is used to correct the target deviation, generating a deviation correction amount Δu. This Δu is then incorporated into the target microgrid energy management optimization model and / or target management command for the next scheduling period to adjust the optimization parameters and enhance the robustness of the algorithm.

[0095] Specifically, the deviation correction amount Δu can be used to adjust target management commands, such as the power of SOFC, energy storage, and flexible loads, to ensure that the optimization of the next scheduling period is closer to the actual operating requirements; the deviation correction amount Δu can be used to adjust the predicted values ​​of power generation units, such as the predicted output values ​​of photovoltaic and SOFC; the deviation correction amount Δu can also be used to adjust the constraints in the target microgrid energy management optimization model, such as microgrid voltage and frequency, to ensure the operational stability of the target microgrid system.

[0096] Example 3

[0097] Figure 5 is a schematic diagram of a microgrid energy collaborative management device provided in Embodiment 3 of the present invention. This device can execute the microgrid energy collaborative management method provided in any embodiment of the present invention, and possesses the corresponding functional modules and beneficial effects of the method. As shown in Figure 5, the device includes:

[0098] The information acquisition module 310 is used to acquire target microgrid data and target microgrid energy management optimization model of the target microgrid system; wherein, the target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters and fuel cell lifetime loss parameters;

[0099] The optimization model solving module 320 is used to input the target microgrid data into the target microgrid energy management optimization model to solve the model and obtain the target management instructions.

[0100] The microgrid energy management module 330 is used to perform multi-energy collaborative management of the target microgrid system according to the target management instructions; wherein, the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit.

[0101] Optionally, the apparatus further includes: an optimization model building module, used for:

[0102] Determine the fluctuation of total microgrid power generation, photovoltaic absorption rate, and fuel cell lifespan loss per unit time during the current scheduling period;

[0103] The objective function is constructed by weighted summation of the total power fluctuation of microgrid generation, photovoltaic absorption rate, and fuel cell lifespan loss per unit time during the current scheduling period; among them, the total power fluctuation of microgrid generation has the highest weight.

[0104] Construct the constraints for each unit in the target microgrid system during the current scheduling period;

[0105] The target microgrid energy management optimization model corresponding to the current scheduling period is determined based on the objective function and the constraints.

[0106] Optionally, the optimization model construction module is further used for:

[0107] The fluctuation of the total power generation of the microgrid in the current scheduling period is determined by the absolute value of the difference between the total power generation of the microgrid in the current scheduling period and the previous scheduling period; wherein, the total power generation of the microgrid is determined based on the sum of the fuel cell output power, photovoltaic output power and energy storage charging and discharging power;

[0108] The photovoltaic absorption rate for the current scheduling period is determined by the ratio of the actual photovoltaic power absorbed to the total predicted photovoltaic output during the current scheduling period; wherein, the actual photovoltaic power absorbed includes the photovoltaic output power consumed by the load unit and the photovoltaic output power absorbed by the energy storage unit.

[0109] The fuel cell lifespan loss per unit time during the current scheduling period is determined by weighted summation of at least two operating parameters of the fuel cell during the current scheduling period; wherein, the operating parameters of the fuel cell include the number of start-stop cycles per day, the output ramp-up rate, the operating temperature fluctuation range, and the fuel purity.

[0110] Optionally, the optimization model construction module is further used for:

[0111] Based on the target microgrid data of each unit in the target microgrid system during the current scheduling period, determine the constraints of each unit in the target microgrid system during the current scheduling period;

[0112] The constraints include power balance constraints, fuel cell operation constraints, photovoltaic absorption constraints, energy storage operation constraints, flexible load dispatch constraints, and microgrid safe operation constraints; the fuel cell operation constraints include at least one of start-up time constraints, output upper and lower limit constraints, output ramp-up rate constraints, temperature constraints, fuel supply constraints, and lifespan loss constraints.

[0113] Optionally, the optimization model solving module 320 is used for:

[0114] The fuel cell start-up prediction parameters are determined based on the fuel cell data during the current scheduling period; wherein, the fuel cell start-up prediction parameters include the predicted value of the start-up time and the predicted values ​​of output and temperature during multiple scheduling periods during the start-up process;

[0115] The start-up time constraint, output upper and lower limit constraint, and temperature constraint in the fuel cell operation constraints are updated based on the fuel cell start-up prediction parameters.

[0116] The target management instructions corresponding to the current scheduling period are obtained by solving the target microgrid energy management optimization model; wherein, the target management instructions include fuel cell output instructions, energy storage charging and discharging power instructions, and flexible load power instructions.

[0117] Optionally, the optimization model solving module 320 is further used for:

[0118] The objective function of the current scheduling period is used as the particle fitness function, and the fitness value of each particle is calculated under the constraints of the current scheduling period.

[0119] The inertia weights are updated using a combination of linear decrease and dynamic correction; wherein the dynamic correction adapts to changes in the particle fitness value.

[0120] Based on the updated inertia weights, the velocity and position of the particles are iteratively updated according to the individual optimal fitness value and the population optimal fitness value;

[0121] When the iteration stopping condition is met, the optimization instruction corresponding to the optimal position of the group is determined as the target management instruction corresponding to the current scheduling period; wherein, the iteration stopping condition is that the current iteration number reaches the maximum iteration number or the change in the optimal fitness value of the group is less than a preset value for multiple consecutive iterations.

[0122] Optionally, the device further includes: a deviation correction module, used for:

[0123] After solving the target microgrid energy management optimization model corresponding to the current scheduling period to obtain the target management instruction corresponding to the current scheduling period, the actual microgrid operation data of the target microgrid system after executing the target management instruction is obtained;

[0124] The target deviation is determined by comparing the actual operation data of the microgrid with the target management instructions corresponding to the current scheduling period.

[0125] The deviation correction amount is obtained by correcting the target deviation using a proportional-integral controller;

[0126] The target microgrid energy management optimization model and / or target management instructions for the next scheduling period are adjusted based on the deviation correction amount.

[0127] Optionally, the device further includes: an emergency dispatch module, used for:

[0128] When a sudden disturbance is detected in the target microgrid system, the type of the sudden disturbance is determined;

[0129] The target emergency dispatch instruction is determined based on a preset mapping table and the current sudden disturbance type; wherein, the preset mapping table is used to describe the correspondence between sudden disturbance types and emergency dispatch instructions.

[0130] Optionally, the correspondence between sudden disturbance types and emergency dispatch instructions in the preset mapping table includes:

[0131] When the sudden disturbance type is a sudden drop in photovoltaic output, the emergency dispatch instructions include dispatching the energy storage unit to output at maximum discharge power, limiting the fuel cell output ramp-up rate, and dispatching interruptible load cut-off.

[0132] When the sudden disturbance type is a sudden increase in load disturbance, the emergency dispatch command includes setting the energy storage unit to discharge mode, increasing the output of the fuel cell, and dispatching the delayed operation of the load that can be delayed.

[0133] When the sudden disturbance type is a sudden load reduction disturbance, the emergency dispatch command includes setting the energy storage unit to charging mode and limiting photovoltaic output;

[0134] When the sudden disturbance type is a fuel cell fault disturbance, the emergency dispatch command includes dispatching the energy storage unit to output power according to load demand and dispatching interruptible loads to cut off.

[0135] When the sudden disturbance type is a first energy storage state of charge abnormal disturbance, the emergency dispatch command includes dispatching the energy storage unit to stop discharging and increasing the output of the fuel cell; wherein, the energy storage state of charge under the first energy storage state of charge abnormal disturbance is not higher than a first threshold.

[0136] When the sudden disturbance type is a second energy storage state of charge abnormal disturbance, the emergency dispatch instruction includes dispatching the energy storage unit to stop charging and dispatching the operation of the delayable load; wherein, the energy storage state of charge under the second energy storage state of charge abnormal disturbance is not lower than the second threshold, and the second threshold is greater than the first threshold.

[0137] Optionally, the device further includes: a weighting adjustment module, used for:

[0138] The operational status evaluation indicators of the target microgrid system are determined based on the target evaluation period; wherein, the target evaluation period is longer than the target scheduling period, and the operational status evaluation indicators include the microgrid total power generation fluctuation indicator, photovoltaic absorption rate indicator, fuel cell cumulative lifespan loss indicator, and load power supply reliability indicator.

[0139] The weights in the objective function are adjusted based on the operational status evaluation indicators.

[0140] The microgrid energy collaborative management device provided in this embodiment of the invention can execute a microgrid energy collaborative management method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0141] Example 4

[0142] Figure 6 illustrates a schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0143] As shown in Figure 6, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0144] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0145] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as microgrid energy collaborative management methods.

[0146] In some embodiments, the microgrid energy collaborative management method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the microgrid energy collaborative management method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the microgrid energy collaborative management method by any other suitable means (e.g., by means of firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0152] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0153] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0154] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A microgrid energy collaborative management method, characterized in that, The method includes: acquiring target microgrid data and a target microgrid energy management optimization model; wherein the target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifetime loss parameters; inputting the target microgrid data into the target microgrid energy management optimization model to solve the model and obtain target management instructions; and performing multi-energy collaborative management of the target microgrid system according to the target management instructions; wherein the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit.

2. The method according to claim 1, characterized in that, The process of constructing the target microgrid energy management optimization model includes: determining the total power generation fluctuation of the microgrid, the photovoltaic absorption rate, and the fuel cell lifespan loss per unit time during the current scheduling period; constructing an objective function based on the weighted sum of the total power generation fluctuation, photovoltaic absorption rate, and fuel cell lifespan loss per unit time during the current scheduling period; wherein, the total power generation fluctuation of the microgrid has the highest weight; constructing the constraints of each unit in the target microgrid system during the current scheduling period; and determining the target microgrid energy management optimization model corresponding to the current scheduling period based on the objective function and the constraints.

3. The method according to claim 2, characterized in that, Determining the total power fluctuation of microgrid generation, photovoltaic absorption rate, and fuel cell lifespan loss per unit time during the current scheduling period includes: determining the total power fluctuation of microgrid generation during the current scheduling period based on the absolute value of the difference between the total power of microgrid generation during the current scheduling period and the previous scheduling period; wherein the total power of microgrid generation is determined based on the sum of fuel cell output power, photovoltaic output power, and energy storage charging and discharging power; determining the photovoltaic absorption rate during the current scheduling period based on the ratio of the actual photovoltaic absorption power to the total predicted photovoltaic output power during the current scheduling period; wherein the actual photovoltaic absorption power includes the photovoltaic output power consumed by the load unit and the photovoltaic output power absorbed by the energy storage unit; and determining the fuel cell lifespan loss per unit time during the current scheduling period based on the weighted sum of at least two operating parameters of the fuel cell during the current scheduling period; wherein the operating parameters of the fuel cell include the number of daily start-stop cycles, output ramp-up rate, operating temperature fluctuation range, and fuel purity.

4. The method according to claim 2 or 3, characterized in that, Constructing constraints for each unit in the target microgrid system during the current scheduling period includes: determining constraints for each unit in the target microgrid system during the current scheduling period based on target microgrid data for each unit in the target microgrid system during the current scheduling period; wherein the constraints include power balance constraints, fuel cell operation constraints, photovoltaic absorption constraints, energy storage operation constraints, flexible load scheduling constraints, and microgrid safe operation constraints; the fuel cell operation constraints include at least one of start-up time constraints, upper and lower output limits constraints, output ramp-up rate constraints, temperature constraints, fuel supply constraints, and lifespan loss constraints.

5. The method according to claim 4, characterized in that, The target microgrid data is input into the target microgrid energy management optimization model for model solving to obtain target management instructions. This includes: determining fuel cell start-up prediction parameters based on fuel cell data during the current scheduling period; wherein the fuel cell start-up prediction parameters include predicted start-up time and predicted output and temperature values ​​for multiple scheduling periods during the start-up process; updating the start-up time constraint, output upper and lower limit constraint, and temperature constraint in the fuel cell operation constraints based on the fuel cell start-up prediction parameters; and solving the target microgrid energy management optimization model corresponding to the current scheduling period to obtain target management instructions corresponding to the current scheduling period; wherein the target management instructions include fuel cell output instructions, energy storage charging and discharging power instructions, and flexible load power instructions.

6. The method according to claim 5, characterized in that, Solving the target microgrid energy management optimization model corresponding to the current scheduling period yields the target management instruction for the current scheduling period. This includes: using the objective function of the current scheduling period as the particle fitness function, calculating the fitness value of each particle under the constraints of the current scheduling period; updating the inertia weight using a combination of linear decrease and dynamic correction; wherein the dynamic correction adapts to changes in particle fitness values; iteratively updating the particle's velocity and position based on the updated inertia weight and the particle's individual optimal fitness value and the population optimal fitness value; and determining the optimization instruction corresponding to the population optimal position as the target management instruction for the current scheduling period when the iteration stopping condition is met; wherein the iteration stopping condition is that the current iteration count reaches the maximum iteration count or the change in the population optimal fitness value is less than a preset value for multiple consecutive iterations.

7. The method according to claim 5, characterized in that, After solving the target microgrid energy management optimization model corresponding to the current scheduling period to obtain the target management instruction corresponding to the current scheduling period, the method further includes: obtaining the actual microgrid operation data after the target microgrid system executes the target management instruction; comparing the actual microgrid operation data with the target management instruction corresponding to the current scheduling period to determine the target deviation; using a proportional-integral controller to correct the target deviation to obtain the deviation correction amount; and adjusting the target microgrid energy management optimization model and / or target management instruction for the next scheduling period based on the deviation correction amount.

8. The method according to claim 1, characterized in that, The method further includes: when a sudden disturbance is detected in the target microgrid system, determining the current sudden disturbance type; determining a target emergency dispatch instruction based on a preset mapping table and the current sudden disturbance type; wherein the preset mapping table is used to describe the correspondence between sudden disturbance types and emergency dispatch instructions.

9. The method according to claim 8, characterized in that, The correspondence between sudden disturbance types and emergency dispatch instructions in the preset mapping table includes: when the sudden disturbance type is a photovoltaic output drop disturbance, the emergency dispatch instruction includes dispatching the energy storage unit to output at maximum discharge power, limiting the fuel cell output ramp-up rate, and dispatching interruptible load shedding; when the sudden disturbance type is a load surge disturbance, the emergency dispatch instruction includes setting the energy storage unit to discharge mode, increasing fuel cell output, and dispatching delayed load operation; when the sudden disturbance type is a load decrease disturbance, the emergency dispatch instruction includes setting the energy storage unit to charging mode and limiting photovoltaic output; when the sudden disturbance type is a fuel cell fault disturbance... When the sudden disturbance type is a first energy storage state of charge abnormality, the emergency dispatch command includes scheduling the energy storage unit to output power according to load demand and scheduling interruptible loads to be cut off; when the sudden disturbance type is a first energy storage state of charge abnormality disturbance, the emergency dispatch command includes scheduling the energy storage unit to stop discharging and increasing the fuel cell output; wherein, the energy storage state of charge under the first energy storage state of charge abnormality disturbance is not higher than a first threshold; when the sudden disturbance type is a second energy storage state of charge abnormality disturbance, the emergency dispatch command includes scheduling the energy storage unit to stop charging and scheduling delayed loads to operate; wherein, the energy storage state of charge under the second energy storage state of charge abnormality disturbance is not lower than a second threshold, and the second threshold is greater than the first threshold.

10. The method according to claim 2, characterized in that, The method further includes: determining the operational status evaluation index of the target microgrid system based on the target evaluation period; wherein the target evaluation period is longer than the target scheduling period, and the operational status evaluation index includes the microgrid total power generation fluctuation index, photovoltaic absorption rate index, fuel cell cumulative life loss index, and load power supply reliability index; and adjusting the weights in the objective function according to the operational status evaluation index.

11. A microgrid energy collaborative management device, characterized in that, The device includes: an information acquisition module for acquiring target microgrid data and a target microgrid energy management optimization model for the target microgrid system; wherein the target microgrid energy management optimization model is constructed based on microgrid power generation stability parameters, photovoltaic absorption parameters, and fuel cell lifetime loss parameters; an optimization model solving module for inputting the target microgrid data into the target microgrid energy management optimization model to solve the model and obtain target management instructions; and a microgrid energy management module for performing multi-energy collaborative management of the target microgrid system according to the target management instructions; wherein the target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit.

12. A microgrid energy collaborative management system, characterized in that, The microgrid energy collaborative management system includes a target microgrid system and an energy management center. The target microgrid system includes a fuel cell power generation unit, a photovoltaic power generation unit, an energy storage unit, and a load unit. The energy management center is equipped with the microgrid energy collaborative management device as described in claim 11.

13. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the microgrid energy collaborative management method according to any one of claims 1-10.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the microgrid energy collaborative management method according to any one of claims 1-10.

Images