A comprehensive energy operation simulation method and system based on multi-objective optimization

Abstract

This invention discloses a comprehensive energy operation simulation method and system based on multi-objective optimization, belonging to the field of energy technology, aiming to solve the problems of equipment overload and discontinuous power supply caused by supply and demand imbalance under extreme climate conditions. The method establishes a multi-objective collaborative optimization model based on the renewable energy types and seawater desalination load characteristics of the island microgrid. An improved NSGA-III algorithm is used to simulate the model and generate a scheduling scheme, including the start-up and shutdown sequence of the hydrogen production equipment. When a typhoon warning signal is received, the seawater electrolysis hydrogen production equipment is forcibly locked, and the output power of the diesel generator is fixed within a preset range. During the operation of the hydrogen production equipment, the output fluctuation data of the wave energy generator is collected in real time, and the operating power of the reverse osmosis seawater desalination unit is adjusted through a dynamic correction algorithm. When the hydrogen storage capacity of the hydrogen production equipment reaches a threshold, the power lock of the diesel generator is released, switching to a multi-energy coupling control mode, and the charging and discharging strategy of the energy storage equipment is updated synchronously.

Description

Technical Field

[0001] This invention relates to the field of energy technology, specifically to a comprehensive energy operation simulation method and system based on multi-objective optimization. Background Technology

[0002] As the global energy structure transitions towards low-carbon development, island microgrids, as a crucial energy supply solution for remote areas, face severe challenges to operational reliability under extreme weather conditions. Particularly in isolated island scenarios, the dual impact of drastic fluctuations in renewable energy output caused by typhoons and sudden load changes in freshwater supply systems has become a core technological challenge. Existing research indicates that wind speeds during typhoons can reach over 40 m / s, causing wind turbines to enter a protective shutdown state, and photovoltaic equipment output to decrease by more than 65% due to cloud cover and sudden increases in humidity. Simultaneously, seawater desalination systems must cope with emergency replenishment demands for freshwater reserves, and their electrical load can surge to 200%-300% of normal operating conditions under extreme circumstances. This drastic fluctuation on both the supply and demand sides leads to two typical failure modes in traditional dispatch systems: first, the power regulation rate of diesel generator sets cannot match the slope of load changes, triggering a chain reaction of equipment overloads; second, there is a timing conflict between the charging and discharging strategies of energy storage devices and the start-up and shutdown logic of emergency hydrogen production units, resulting in continuous power interruptions to critical loads.

[0003] Existing technologies primarily focus on steady-state optimization of single energy sources, such as using the NSGA-II algorithm for coordinated wind, solar, and energy storage scheduling, or using demand response mechanisms to mitigate conventional load fluctuations. However, these methods have significant shortcomings when dealing with the dual extreme conditions of "power generation collapse - load surge" caused by typhoons: Firstly, traditional multi-objective optimization models do not incorporate dynamic constraints from novel coupled equipment such as seawater electrolysis for hydrogen production, making it difficult to achieve millisecond-level power locking between hydrogen production units and diesel generators; secondly, existing shock-resistant scheduling strategies lack the ability to adaptively correct for real-time fluctuations in ocean energy such as wave energy, failing to reconstruct energy balance within a 10-second timescale. More critically, when renewable energy output drops precipitously, the energy storage priority dispatch strategy relied upon by existing technologies will completely fail due to the rapid depletion of state of charge (SOC), ultimately forcing the system into an irreversible collapse state.

[0004] The above background information is provided only to aid in understanding the concept and technical solution of this invention. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above information was disclosed on the filing date of this patent application, the above background information should not be used to evaluate the novelty and inventiveness of this application. Summary of the Invention

[0005] This application provides a multi-objective optimization integrated energy operation simulation method and system to solve the problems of equipment overload and discontinuous power supply caused by supply and demand imbalance under extreme climatic conditions.

[0006] To achieve the above objectives, the embodiments of this application disclose the following technical solutions:

[0007] In a first aspect, embodiments of this application provide a comprehensive energy operation simulation method based on multi-objective optimization, comprising the following steps:

[0008] Based on the renewable energy types and seawater desalination load characteristics of the island microgrid, a multi-objective collaborative optimization model is established, which includes diesel generator output and constraints on the coupling of seawater electrolysis for hydrogen production.

[0009] The NSGA-III algorithm is used to simulate the multi-objective collaborative optimization model and generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment.

[0010] When a typhoon warning signal is detected, the forced lock mode of the seawater electrolysis hydrogen production equipment is activated, and the output power of the diesel generator is fixed to 80%-100% of the rated power in the current dispatch plan.

[0011] During the operation of the hydrogen production equipment, the output fluctuation data of the wave energy generator is collected in real time, and the operating power curve of the reverse osmosis seawater desalination unit is adjusted through a dynamic correction algorithm.

[0012] When the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, the power lock-up state of the diesel generator is turned off and the multi-energy coupling control mode is switched to synchronously update the charging and discharging strategy of the energy storage equipment.

[0013] In this embodiment, a multi-objective collaborative optimization model is constructed, incorporating descriptions of renewable energy output and seawater desalination load characteristics, as well as constraints on diesel generator output power and the coupling constraints of start-stop operation of seawater electrolysis hydrogen production. This model enables real-time control of energy supply and demand balance under extreme weather conditions such as typhoons. Specifically, the multi-objective collaborative optimization model in the island microgrid system aims to minimize fuel consumption and maximize renewable energy utilization, comprehensively modeling and solving the complex dynamic relationships between various subsystems within the energy system. The improved NSGA-III algorithm solves the multi-objective optimization model, utilizing non-dominated sorting, dynamic updating of reference points, and local search strategies to quickly obtain the optimal scheduling solution that satisfies energy constraints. When weather signals indicate an impending typhoon, the seawater electrolysis hydrogen production equipment enters a forced lockout mode, while simultaneously limiting the diesel generator output power to operate within a specified safe range, ensuring stable energy system supply even when facing the dual impacts of a sharp drop in power generation and a surge in load demand. The island microgrid system employs real-time data acquisition from wave energy generators and dynamic adjustment of the operating power of reverse osmosis desalination units to achieve rapid reconfiguration between power supply and demand. Even under extreme weather conditions, it effectively mitigates the cascading response problems caused by sudden changes in energy output. The entire operational simulation method fully considers the operating characteristics and dynamic constraints of each energy unit, constructing an integrated scheduling scheme. This ensures that the island microgrid system maintains high reliability and continuous power supply capability under extreme conditions such as typhoons, effectively solving the problems of equipment overload and discontinuous power supply caused by supply-demand imbalances under extreme weather conditions.

[0014] Secondly, embodiments of this application provide a comprehensive energy operation simulation system based on multi-objective optimization, comprising:

[0015] The model building module is used to establish a multi-objective collaborative optimization model that includes diesel generator output constraints and seawater electrolysis hydrogen production coupling constraints, based on the renewable energy types and seawater desalination load characteristics of the island microgrid.

[0016] The simulation processing module is used to simulate the multi-objective collaborative optimization model using the NSGA-III algorithm to generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment.

[0017] The typhoon warning response module is used to activate the forced lock mode of the seawater electrolysis hydrogen production equipment when a typhoon warning signal is detected, and fix the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan.

[0018] The real-time control module is used to collect the output fluctuation data of the wave energy generator in real time during the operation of the hydrogen production equipment, and adjust the operating power curve of the reverse osmosis seawater desalination unit through a dynamic correction algorithm.

[0019] The mode switching module is used to shut down the power lock-up state of the diesel generator and switch to the multi-energy coupling control mode when the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, and to synchronously update the charging and discharging strategy of the energy storage equipment.

[0020] Thirdly, embodiments of this application provide an electronic device, including one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any of the technical solutions of the first aspect.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method described in any of the technical solutions of the first aspect.

[0022] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the technical solutions of the first aspect.

[0023] The technical effects of any of the design methods in aspects two through five can be found in the technical effects of different design methods in aspect one, and will not be repeated here. Attached Figure Description

[0024] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0025] Figure 1 A flowchart illustrating a comprehensive energy operation simulation method based on multi-objective optimization, provided for some embodiments of this application;

[0026] Figure 2 This is a schematic diagram of the structure of a comprehensive energy operation simulation system based on multi-objective optimization, provided for some embodiments of this application.

[0027] Figure 3 A schematic diagram of the structure of an electronic device suitable for implementing some embodiments of this application;

[0028] Figure 4 This is a logical framework diagram of an integrated energy system. Detailed Implementation

[0029] Specific embodiments of the invention will now be described in detail. Although the invention is described in conjunction with these specific embodiments, it should be understood that it is not intended to limit the invention to these specific embodiments. Rather, these embodiments are intended to cover alternative, modified, or equivalent embodiments that may be included within the spirit and scope of the invention as defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. The invention may be practiced without some or all of these specific details.

[0030] When used in conjunction with the terms "comprising," "method comprising," or similar language in this specification and appended claims, the singular forms "a," "some," and "the" include plural references unless the context clearly indicates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0031] Application Overview: As the global energy structure transitions towards low-carbonization, island microgrids, as a crucial energy supply solution for remote areas, face severe challenges to operational reliability under extreme weather conditions. Particularly in isolated island scenarios, the dual coupled impact of drastic fluctuations in renewable energy output caused by typhoons and sudden load changes in freshwater supply systems has become a core technological challenge. Existing research indicates that wind speeds during typhoons can reach over 40 m / s, causing wind turbines to enter a protective shutdown state, and photovoltaic equipment output to decrease by more than 65% due to cloud cover and sudden increases in humidity. Simultaneously, seawater desalination systems must cope with emergency freshwater replenishment needs, and their electrical load can surge to 200%-300% of normal operating conditions under extreme circumstances. This drastic fluctuation on both the supply and demand sides leads to two typical failure modes in traditional dispatch systems: first, the power regulation rate of diesel generator sets cannot match the slope of load changes, triggering a chain reaction of equipment overloads; second, there is a timing conflict between the charging and discharging strategies of energy storage devices and the start-up and shutdown logic of emergency hydrogen production units, resulting in continuous power interruptions to critical loads.

[0032] Existing technologies primarily focus on steady-state optimization of single energy sources, such as using the NSGA-II algorithm for coordinated wind, solar, and energy storage scheduling, or using demand response mechanisms to mitigate conventional load fluctuations. However, these methods have significant shortcomings when dealing with the dual extreme conditions of "power generation collapse - load surge" caused by typhoons: Firstly, traditional multi-objective optimization models do not incorporate dynamic constraints from novel coupled equipment such as seawater electrolysis for hydrogen production, making it difficult to achieve millisecond-level power locking between hydrogen production units and diesel generators; secondly, existing shock-resistant scheduling strategies lack the ability to adaptively correct for real-time fluctuations in ocean energy such as wave energy, failing to reconstruct energy balance within a 10-second timescale. More critically, when renewable energy output drops precipitously, the energy storage priority dispatch strategy relied upon by existing technologies will completely fail due to the rapid depletion of state of charge (SOC), ultimately forcing the system into an irreversible collapse state.

[0033] To address the aforementioned technical issues, the overall approach of the technical solution provided in this application is as follows: A comprehensive energy operation simulation method based on multi-objective optimization is provided, comprising the following steps: Establishing a multi-objective collaborative optimization model that includes diesel generator output constraints and seawater electrolysis hydrogen production coupling constraints, based on the renewable energy types and seawater desalination load characteristics of the island microgrid; Simulating the multi-objective collaborative optimization model using the NSGA-III algorithm to generate a scheduling scheme that includes the start-up and shutdown sequence of the hydrogen production equipment; Activating the forced locking mode of the seawater electrolysis hydrogen production equipment when a typhoon warning signal is detected, fixing the output power of the diesel generator to 80%-100% of the rated power in the current scheduling scheme; Real-time acquisition of wave energy generator output fluctuation data during hydrogen production equipment operation, adjusting the operating power curve of the reverse osmosis seawater desalination unit through a dynamic correction algorithm; When the hydrogen storage capacity of the hydrogen production equipment reaches a threshold, shutting down the power locking state of the diesel generator and switching to the multi-energy coupling control mode, synchronously updating the charging and discharging strategy of the energy storage equipment.

[0034] This method employs a multi-objective collaborative optimization model that incorporates descriptions of renewable energy output and seawater desalination load characteristics, as well as constraints on diesel generator output power and the coupling of start-stop operations for seawater electrolysis hydrogen production. This model enables real-time control of energy supply and demand balance under extreme weather conditions such as typhoons. Specifically, the multi-objective collaborative optimization model in the island microgrid system aims to minimize fuel consumption and maximize renewable energy utilization, comprehensively modeling and solving the complex dynamic relationships between various subsystems within the energy system. The improved NSGA-III algorithm solves the multi-objective optimization model, utilizing non-dominated sorting, dynamic updating of reference points, and local search strategies to quickly obtain the optimal scheduling solution that satisfies energy constraints. When weather signals indicate an impending typhoon, the seawater electrolysis hydrogen production equipment enters a forced lockout mode, while simultaneously limiting the diesel generator output power to within a specified safe range, ensuring stable energy system supply even when facing the dual impacts of a sharp drop in power generation and a surge in load demand. The island microgrid system employs real-time data acquisition from wave energy generators and dynamic adjustment of the operating power of reverse osmosis desalination units to achieve rapid reconfiguration between power supply and demand. Even under extreme weather conditions, it effectively mitigates the cascading response problems caused by sudden changes in energy output. The entire operational simulation method fully considers the operating characteristics and dynamic constraints of each energy unit, constructing an integrated scheduling scheme. This ensures that the island microgrid system maintains high reliability and continuous power supply capability under extreme conditions such as typhoons, effectively solving the problems of equipment overload and discontinuous power supply caused by supply-demand imbalances under extreme weather conditions.

[0035] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. Please refer to... Figure 1 This application provides a comprehensive energy operation simulation method based on multi-objective optimization, including the following steps:

[0036] S101: Based on the renewable energy types and seawater desalination load characteristics of the island microgrid, establish a multi-objective collaborative optimization model that includes diesel generator output constraints and seawater electrolysis hydrogen production coupling constraints.

[0037] Specifically, the entity implementing the integrated energy operation simulation method based on multi-objective optimization can establish the above-mentioned multi-objective collaborative optimization model through the following steps:

[0038] The first step is to collect photovoltaic power generation output time-series data, wind turbine speed signals, and seawater desalination load conductivity monitoring data of the island microgrid through a preset multi-source data interface, and generate a renewable energy-load joint feature dataset through multi-dimensional correlation and integration.

[0039] The second step involves performing data standardization preprocessing and redundant data cleaning on the renewable energy-load joint characteristic dataset. Based on the fuel consumption rate curve of the diesel generator and the voltage-current characteristic equation of the electrolyzer, the maximum ramp rate constraint parameters of the diesel generator and the start-stop frequency constraint parameters of the hydrogen production equipment are calculated to generate a dynamic constraint parameter set. The formula for calculating the maximum ramp rate constraint parameter of the diesel generator is as follows:

[0040]

[0041] In the formula, This is the fuel consumption rate function of the diesel generator, reflecting the output power of the diesel generator. Fuel consumption rate at that time; For the selected time interval;

[0042] Hydrogen production equipment start-up and shutdown frequency constraint parameters The calculation formula is:

[0043]

[0044] In the formula, The cumulative number of start-ups and shutdowns for the hydrogen production equipment; The set start / stop frequency threshold; A very small positive number set to avoid division by zero;

[0045] Specifically, in some embodiments, the steps of performing data standardization preprocessing and redundant data cleaning operations on the renewable energy-load joint feature dataset, calculating the maximum ramp rate constraint parameters of the diesel generator and the start-stop frequency constraint parameters of the hydrogen production equipment based on the fuel consumption rate curve of the diesel generator and the voltage-current characteristic equation of the electrolyzer, and generating a dynamic constraint parameter set include:

[0046] The first sub-step involves using a wavelet transform algorithm to separate the high-frequency noise components in the original conductivity monitoring data in terms of time and frequency, generating a denoised conductivity feature vector.

[0047] The second sub-step involves performing baseline calibration on the photovoltaic power generation output time series data based on the sliding window mean algorithm to eliminate instantaneous pulse interference caused by sudden changes in illumination and generate a standardized output time series sequence.

[0048] The third sub-step involves using the Kalman filter algorithm to perform dynamic state estimation on the wind turbine generator speed signal and generate a smooth speed feature vector.

[0049] The fourth sub-step involves standardizing the power output time sequence and smoothing the rotational speed feature vector after denoising the conductivity feature vector, and then performing multi-dimensional matrix concatenation to generate a standardized renewable energy-load joint feature dataset.

[0050] The fifth sub-step involves calculating the maximum gradeability constraint parameters using a constraint parameter iterative algorithm based on the diesel generator speed-fuel consumption rate mapping table and the electrolyzer voltage-current differential equation.

[0051] The sixth sub-step generates fatigue damage coefficients characterizing the start-stop frequency constraints of the hydrogen production equipment, based on the start-stop frequency accumulation counter and the equipment thermal stress model. This scheme utilizes wavelet transform to separate high-frequency noise in the conductivity monitoring data; employs a sliding window mean algorithm to perform baseline calibration on the photovoltaic power generation time-series data to eliminate instantaneous interference caused by sudden changes in illumination; and uses a Kalman filter algorithm to dynamically estimate the wind speed signal to obtain smooth results. The standardized renewable energy and load joint feature dataset obtained by multi-dimensional matrix splicing is used to calculate the constraint parameters iteratively through the diesel generator fuel consumption rate curve and the electrolyzer voltage-current differential equation, generating constraint parameters describing the maximum ramp rate. Coefficients describing fatigue damage are extracted using the start-stop frequency accumulation counter and the equipment thermal stress model. The overall preprocessing and parameter calculation process ensures the accuracy of data representation, providing sufficient and accurate support for the equipment operation constraint characteristics in multi-objective optimization scheduling problems, thereby improving the safety of the scheduling scheme and the equipment's service life, and reducing the risk of equipment failure caused by operational imbalances.

[0052] The third step involves embedding the diesel generator output constraint and the seawater electrolysis hydrogen production coupling constraint into a multi-objective optimization framework based on a dynamic constraint parameter set and a nonlinear constraint mapping mechanism. This constructs a collaborative optimization model with the objective functions of minimizing operating costs and maximizing renewable energy absorption rate. In this way, a multi-dimensional correlated feature dataset can be constructed by collecting photovoltaic power generation, wind power generation, and load monitoring data, ensuring that the operating status of renewable energy and loads is accurately reflected in the data records.

[0053] Meanwhile, data standardization preprocessing and redundant data cleaning processes ensure the accuracy of input information. The maximum ramp rate and start-up / shutdown frequency constraint parameters of hydrogen production equipment are calculated using the diesel generator fuel consumption rate curve and the electrolyzer voltage-current characteristic equation. This allows the dynamic constraint parameter set to objectively represent the equipment's operating capabilities, thereby optimizing the solution process of the multi-objective collaborative scheduling model and improving the accuracy of system safety operation and response control.

[0054] S102: The NSGA-III algorithm is used to simulate the multi-objective collaborative optimization model and generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment.

[0055] Specifically, in some embodiments, a scheduling scheme containing the start-up and shutdown sequence of hydrogen production equipment can be generated through the following steps:

[0056] The first step is to generate an initial population that satisfies the power output constraints of the diesel generator based on a multi-objective collaborative optimization model and according to the preset population size and crossover mutation probability parameters.

[0057] The second step is to perform non-dominated sorting and simulated binary crossover operations in the NSGA-III algorithm on the initial population, and then generate an intermediate population by combining the adaptive reference point update strategy.

[0058] The third step is to perform a Gaussian mutation-based local search operation on the intermediate population and select the Pareto front solution set through the elite preservation strategy to generate a candidate scheduling strategy set.

[0059] The fourth step involves executing a dynamic priority decoding strategy on the candidate scheduling strategy set. This maps the optimal solution to the start-up and shutdown timing of the hydrogen production equipment and the power commands of the diesel generator, generating a scheduling scheme that includes the start-up and shutdown timing of the hydrogen production equipment. This scheme employs the NSGA-III algorithm, enabling the multi-objective collaborative optimization model to effectively search the solution space during the scheduling process and quickly identify the optimal solution set that satisfies the diesel generator output constraints and the start-up and shutdown timing requirements of the hydrogen production equipment. The algorithm performs global and local optimization of the dynamic scheduling variables in steps such as initial population construction, non-dominated sorting, binary crossover, and Gaussian mutation, ensuring that the generated candidate scheduling strategy set achieves a balance between global and local optima. The dynamic priority decoding strategy precisely maps the obtained optimal solution to specific equipment control commands, thereby ensuring that the optimization results can achieve coordinated effects of equipment start-up and shutdown and power regulation in the operation of the island microgrid, ultimately promoting the improvement of system power supply efficiency and operational safety.

[0060] S103: When a typhoon warning signal is detected, activate the forced lock mode of the seawater electrolysis hydrogen production equipment and fix the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan.

[0061] Specifically, in some embodiments, the forced locking mode of the seawater electrolysis hydrogen production equipment can be activated when a typhoon warning signal is detected, fixing the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan through the following steps:

[0062] The first step is to receive typhoon wind speed forecast data released by the meteorological department through the early warning monitoring module, and generate a typhoon early warning trigger identifier based on the preset threshold comparison.

[0063] The second step is to send a forced lock command to the PLC controller of the seawater electrolysis hydrogen production equipment according to the typhoon warning trigger mark, interrupt the priority scheduling queue of the hydrogen production equipment and generate an equipment lock status signal.

[0064] The third step involves combining the equipment lockout status signal with the rated power parameters of the diesel generator in the current dispatch plan, performing power lockout logic calculations to limit the output power of the diesel generator to 80%-100% of its rated power. This scheme receives wind speed forecast information from the meteorological department collected by the typhoon warning monitoring module, generates a trigger flag based on a preset threshold comparison, and then sends a forced lockout command to the PLC controller of the seawater electrolysis hydrogen production equipment. This locks the equipment into a locked state, strictly limiting the diesel generator output power to the rated power range specified in the current dispatch plan. This process ensures stable output power control of the energy system under extreme weather conditions, avoiding the risk of equipment overload and unstable power supply due to uncontrolled power regulation rates, thus guaranteeing the safe, stable, and continuous operation of the energy system even when subjected to extreme environmental disturbances caused by typhoons.

[0065] S104: During the operation of the hydrogen production equipment, the output fluctuation data of the wave energy generator is collected in real time, and the operating power curve of the reverse osmosis seawater desalination unit is adjusted through a dynamic correction algorithm.

[0066] Specifically, in some embodiments, the operating power curve can be generated through the following steps:

[0067] The first step is to acquire the instantaneous power output signal of the wave energy generator through a high-frequency sampling module, and then perform wavelet denoising processing on the instantaneous power output signal to generate a standardized wave feature sequence.

[0068] The second step involves using an adaptive sliding window algorithm, based on standardized fluctuation characteristic sequences, to predict the power demand deviation of the reverse osmosis seawater desalination unit and generate real-time power compensation. The specific formula is as follows:

[0069]

[0070] In the formula: This represents the power demand of the reverse osmosis seawater desalination unit predicted using the adaptive sliding window algorithm. This indicates the baseline operating power of the reverse osmosis seawater desalination unit;

[0071] The third step involves combining the real-time power compensation and the baseline power curve of the reverse osmosis seawater desalination unit, and then dynamically adjusting the speed setpoint of the high-pressure pump using a proportional-integral controller to generate a corrected operating power curve. The specific formula is as follows:

[0072] ;

[0073] In the formula, Indicates time The corrected operating power; This is the proportional gain coefficient; This is the integral gain coefficient; The variable is the integral variable. This scheme obtains instantaneous output through high-frequency acquisition, then performs wavelet denoising on the acquired signal to form a standardized fluctuation characteristic sequence. An adaptive sliding window prediction method is used to analyze the actual power demand of the reverse osmosis seawater desalination unit, obtaining deviation information between actual operation and baseline conditions. A proportional-integral controller then dynamically compensates for the actual deviation, achieving real-time correction of the operating power curve. This operational correction enables the seawater desalination unit to closely track changes in energy load, adjust output power promptly, promote power supply and demand balance, and ensure a continuous and stable power supply for the island energy system under extreme operating conditions.

[0074] Specifically, in some embodiments, the corrected operating power curve can be generated by dynamically adjusting the high-pressure pump speed setpoint using a proportional-integral controller by combining the real-time power compensation amount and the reference power curve of the reverse osmosis seawater desalination unit through the following steps:

[0075] The first sub-step involves constructing a transfer function model that incorporates the amplitude-frequency characteristics of wave energy fluctuations and the response delay characteristics of high-pressure pump speed.

[0076] The second sub-step involves discretizing the reference power curve into multiple power setpoints and configuring a fuzzy membership function for each setpoint.

[0077] The third sub-step involves generating an initial speed correction amount based on the gradient change direction of the real-time power compensation amount using a sliding mode control strategy.

[0078] The fourth sub-step involves performing membership interval matching on the initial rotational speed correction using a fuzzy inference engine to generate fuzzy correction weight coefficients.

[0079] The fifth sub-step involves using a recursive least squares method with a forgetting factor to identify the hydraulic characteristic parameters of the high-pressure pump online and generate a dynamic inertia compensation factor.

[0080] The sixth sub-step involves nonlinearly coupling the fuzzy correction weighting coefficients with the dynamic inertia compensation factor to generate the comprehensive speed adjustment; the specific formula is as follows:

[0081]

[0082] In the formula, Indicates the total speed adjustment amount; This represents the fuzzy correction weight coefficients obtained through the fuzzy inference engine; This represents the dynamic inertia compensation factor identified by the recursive least squares method.

[0083] The seventh sub-step involves using a fuzzy proportional-integral-derivative (FID) controller to superimpose the comprehensive speed adjustment onto the reference speed setpoint to obtain the corrected speed, thereby generating an anti-disturbance correction speed command. The formula for superimposing the comprehensive speed adjustment onto the reference speed to obtain the corrected speed is as follows:

[0084]

[0085] In the formula, This indicates the corrected high-pressure pump speed setting value; This indicates the reference speed setting value for the high-pressure pump;

[0086] Furthermore, to achieve closed-loop tracking control, a modified formula based on a fuzzy proportional-integral-derivative controller is adopted:

[0087]

[0088] In the formula, To correct the control signal; Indicates the speed setting value Compared with the measured speed Deviation between; , , These are the proportional, integral, and differential gain coefficients, respectively. The sampling time interval;

[0089] The eighth sub-step involves executing closed-loop tracking control and generating a corrected operating power curve based on the deviation between the corrected speed command and the measured speed of the high-pressure pump. This scheme uses a fuzzy inference engine and a recursive least squares method with a forgetting factor to determine the hydraulic characteristic parameters of the high-pressure pump identified online. By constructing a transfer function model incorporating wave energy fluctuation amplitude-frequency characteristics and the high-pressure pump speed response delay characteristics, the reference power curve is discretized into multiple power setpoints, and fuzzy membership functions are configured. A sliding mode control strategy is used to generate an initial speed correction. The fuzzy inference engine matches the initial correction to calculate the fuzzy correction weight coefficients. Simultaneously, a dynamic inertia compensation factor is obtained through online identification, and a comprehensive speed adjustment is formed through nonlinear coupling. This adjustment is then superimposed on the reference speed to generate the corrected speed setpoint. Finally, a fuzzy proportional-integral-derivative controller outputs a closed-loop control signal to achieve closed-loop speed tracking. The entire process achieves fine-tuning of the high-pressure pump speed and power output, ensuring immediate response to external disturbances and fluctuations, improving system stability and control accuracy, and ultimately enhancing the overall operating efficiency and reliability of the seawater desalination system.

[0090] S105: When the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, shut down the power lock-up state of the diesel generator and switch to the multi-energy coupling control mode, and synchronously update the charging and discharging strategy of the energy storage equipment.

[0091] Specifically, in some embodiments, the following steps can be used to achieve the following: when the hydrogen storage capacity of the hydrogen production equipment reaches a threshold, the power lock-up state of the diesel generator is turned off and the multi-energy coupling control mode is switched, and the charging and discharging strategy of the energy storage equipment is updated synchronously:

[0092] The first step is to calculate the real-time hydrogen storage mass using the pressure sensor signal and temperature compensation algorithm of the hydrogen storage tank, and generate a hydrogen storage state vector.

[0093] The second step is to perform fuzzy logic comparison based on the hydrogen storage state vector and the preset hydrogen storage safety threshold range to generate a hydrogen storage exceeding limit indicator.

[0094] The third step is to send a mode switching request to the multi-energy coupling controller based on the hydrogen storage limit flag and the current diesel generator power lock command, thereby releasing the diesel generator power lock flag and generating a multi-energy coupling enable signal.

[0095] The fourth step involves recalculating the charging and discharging power boundary conditions of the energy storage device using a distributed model predictive control strategy based on the multi-energy coupling enabling signal, thereby generating updated energy storage scheduling instructions. This scheme calculates real-time hydrogen storage quality using pressure sensing signals from the hydrogen storage tank and a temperature compensation algorithm. It directly compares the hydrogen storage state vector with a preset hydrogen storage safety threshold, generates an over-limit indicator using fuzzy logic, and logically associates this indicator with the diesel generator power lock-in state to generate a mode switching request. This achieves a smooth transition from the diesel generator power lock-in state to the multi-energy coupling control mode, while simultaneously updating the energy storage device's charging and discharging strategy. This optimizes the overall energy regulation and load balancing scheduling of the microgrid, ensuring energy supply security and system operational coordination.

[0096] Please see Figure 2 Based on the same inventive concept as the multi-objective optimization-based integrated energy operation simulation method in the foregoing embodiments, this application provides a multi-objective optimization-based integrated energy operation simulation system, including:

[0097] Model building module 201 is used to establish a multi-objective collaborative optimization model that includes diesel generator output constraints and seawater electrolysis hydrogen production coupling constraints based on the renewable energy type and seawater desalination load characteristics of the island microgrid.

[0098] The simulation processing module 202 is used to perform simulation processing on the multi-objective collaborative optimization model using the NSGA-III algorithm to generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment.

[0099] The typhoon warning response module 203 is used to activate the forced lock mode of the seawater electrolysis hydrogen production equipment when a typhoon warning signal is detected, and fix the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan.

[0100] The real-time control module 204 is used to collect the output fluctuation data of the wave energy generator in real time during the operation of the hydrogen production equipment, and adjust the operating power curve of the reverse osmosis seawater desalination unit through a dynamic correction algorithm.

[0101] The mode switching module 205 is used to shut down the power lock-up state of the diesel generator and switch to the multi-energy coupling control mode when the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, and to synchronously update the charging and discharging strategy of the energy storage equipment.

[0102] In some embodiments, the model building module 201 is specifically used for:

[0103] The system collects photovoltaic power generation time-series data, wind turbine speed signals, and seawater desalination load conductivity monitoring data of the island microgrid through a preset multi-source data interface, and generates a renewable energy-load joint feature dataset through multi-dimensional correlation and integration.

[0104] Data standardization preprocessing and redundant data cleaning were performed on the renewable energy-load joint characteristic dataset. Based on the fuel consumption rate curve of the diesel generator and the voltage-current characteristic equation of the electrolyzer, the maximum ramp rate constraint parameters of the diesel generator and the start-stop frequency constraint parameters of the hydrogen production equipment were calculated to generate a dynamic constraint parameter set. Among them, the maximum ramp rate constraint parameters of the diesel generator... The calculation formula is:

[0105]

[0106] In the formula, This is the fuel consumption rate function of the diesel generator, reflecting the output power of the diesel generator. Fuel consumption rate at that time; For the selected time interval;

[0107] Hydrogen production equipment start-up and shutdown frequency constraint parameters The calculation formula is:

[0108]

[0109] In the formula, The cumulative number of start-ups and shutdowns for the hydrogen production equipment; The set start / stop frequency threshold; A very small positive number set to avoid division by zero;

[0110] Based on a dynamic constraint parameter set, a multi-objective optimization framework is constructed by embedding the diesel generator output constraint and the seawater electrolysis hydrogen production coupling constraint into a nonlinear constraint mapping mechanism, thereby building a collaborative optimization model with the objective functions of minimizing operating costs and maximizing renewable energy absorption rate.

[0111] In some embodiments, the simulation processing module 202 is specifically used for:

[0112] Based on a multi-objective collaborative optimization model, an initial population that satisfies the diesel generator output constraint is generated according to the preset population size and crossover mutation probability parameters.

[0113] The initial population is subjected to non-dominated sorting and simulated binary crossover operations in the NSGA-III algorithm, and an intermediate population is generated by combining an adaptive reference point update strategy.

[0114] A Gaussian mutation-based local search operation is performed on the intermediate population, and a Pareto front solution set is selected through an elite preservation strategy to generate a candidate scheduling strategy set.

[0115] A dynamic priority decoding strategy is executed on the candidate scheduling strategy set to map the optimal solution to the start-up and shutdown sequence of the hydrogen production equipment and the power command of the diesel generator, thereby generating a scheduling scheme that includes the start-up and shutdown sequence of the hydrogen production equipment.

[0116] In some embodiments, the typhoon warning response module 203 is specifically used for:

[0117] The system receives typhoon wind speed forecast data from the meteorological department through the early warning monitoring module, and generates typhoon early warning trigger identifiers based on preset threshold comparisons.

[0118] Based on the typhoon warning trigger identifier, a forced lock command is sent to the PLC controller of the seawater electrolysis hydrogen production equipment to interrupt the priority scheduling queue of the hydrogen production equipment and generate an equipment lock status signal.

[0119] By combining the equipment lockout status signal and the rated power parameters of the diesel generator in the current dispatching scheme, a power lockout logic operation is performed to limit the output power of the diesel generator to 80%-100% of the rated power.

[0120] In some embodiments, the real-time control module 204 is specifically used for:

[0121] The instantaneous power output signal of the wave energy generator is obtained by a high-frequency sampling module, and wavelet denoising processing is performed on the instantaneous power output signal to generate a standardized wave feature sequence.

[0122] Based on standardized fluctuation characteristic sequences, an adaptive sliding window algorithm is used to predict the power demand deviation of reverse osmosis seawater desalination units and generate real-time power compensation quantities. The specific formula is as follows:

[0123]

[0124] In the formula: This represents the power demand of the reverse osmosis seawater desalination unit predicted using the adaptive sliding window algorithm. This indicates the baseline operating power of the reverse osmosis seawater desalination unit;

[0125] By combining the real-time power compensation and the baseline power curve of the reverse osmosis seawater desalination unit, the speed setpoint of the high-pressure pump is dynamically adjusted through a proportional-integral controller to generate a corrected operating power curve. The specific formula is as follows:

[0126] ;

[0127] In the formula, Indicates time The corrected operating power; This is the proportional gain coefficient; This is the integral gain coefficient; It is the integral variable.

[0128] In some embodiments, the mode switching module 205 is specifically used for:

[0129] The real-time hydrogen storage mass is calculated using the pressure sensor signal and temperature compensation algorithm of the hydrogen storage tank, and a hydrogen storage state vector is generated.

[0130] Based on the hydrogen storage state vector, fuzzy logic comparison is performed in combination with the preset hydrogen storage safety threshold range to generate a hydrogen storage exceeding limit identifier.

[0131] Based on the hydrogen storage limit exceeding the limit indicator and the current diesel generator power lock command, a mode switching request is sent to the multi-energy coupling controller to release the power lock flag of the diesel generator and generate a multi-energy coupling enable signal;

[0132] Based on the multi-energy coupling enable signal, a distributed model predictive control strategy is adopted to recalculate the charge and discharge power boundary conditions of the energy storage device and generate updated energy storage scheduling instructions.

[0133] In some embodiments, the model building module 201 is further configured to:

[0134] The high-frequency noise component in the original conductivity monitoring data is separated into time and frequency using the wavelet transform algorithm to generate a denoised conductivity feature vector.

[0135] Baseline calibration is performed on photovoltaic power generation output time series data based on the sliding window mean algorithm to eliminate instantaneous pulse interference caused by sudden changes in illumination and generate a standardized output time series sequence.

[0136] The Kalman filter algorithm is used to perform dynamic state estimation on the wind turbine generator speed signal to generate a smooth speed feature vector.

[0137] The denoised conductivity feature vector is standardized to output time series and smoothed speed feature vector, and then multi-dimensional matrix is ​​spliced ​​to generate a standardized renewable energy-load joint feature dataset.

[0138] Based on the diesel generator speed-fuel consumption rate mapping table and the electrolytic cell voltage-current differential equation, the constraint parameter iterative algorithm is used to calculate the maximum gradeability constraint parameters.

[0139] Based on the start-stop frequency cumulative counter and the equipment thermal stress model, a fatigue damage coefficient characterizing the start-stop frequency constraint of hydrogen production equipment is generated.

[0140] In some embodiments, the real-time control module 204 is further configured to:

[0141] A transfer function model incorporating the amplitude-frequency characteristics of wave energy fluctuations and the speed response delay characteristics of high-pressure pumps is constructed.

[0142] The reference power curve is discretized into multiple power setpoints, and a fuzzy membership function is configured for each setpoint.

[0143] Based on the gradient change direction of the real-time power compensation, a sliding mode control strategy is adopted to generate an initial speed correction.

[0144] The initial speed correction amount is matched with a membership interval by a fuzzy inference engine to generate fuzzy correction weight coefficients.

[0145] The recursive least squares method with a forgetting factor is used to identify the hydraulic characteristic parameters of the high-pressure pump online and generate a dynamic inertia compensation factor.

[0146] The fuzzy correction weighting coefficient is nonlinearly coupled with the dynamic inertia compensation factor to generate the comprehensive speed regulation; the specific formula is as follows:

[0147]

[0148] In the formula, Indicates the total speed adjustment amount; This represents the fuzzy correction weight coefficients obtained through the fuzzy inference engine; This represents the dynamic inertia compensation factor identified by the recursive least squares method.

[0149] The fuzzy proportional-integral-derivative (FID) controller superimposes the comprehensive speed adjustment onto the reference speed setpoint to obtain the corrected speed, generating an anti-disturbance correction speed command. The formula for superimposing the comprehensive speed adjustment onto the reference speed to obtain the corrected speed is as follows:

[0150]

[0151] In the formula, This indicates the corrected high-pressure pump speed setting value; This indicates the reference speed setting value for the high-pressure pump;

[0152] Furthermore, to achieve closed-loop tracking control, a modified formula based on a fuzzy proportional-integral-derivative controller is adopted:

[0153]

[0154] In the formula, To correct the control signal; Indicates the speed setting value Compared with the measured speed Deviation between; , , These are the proportional, integral, and differential gain coefficients, respectively. The sampling time interval;

[0155] Based on the deviation between the corrected speed command and the measured speed of the high-pressure pump, closed-loop tracking control is executed and a corrected operating power curve is generated.

[0156] It is understandable that the modules recorded in this multi-objective optimization-based integrated energy operation simulation system are similar to those in the reference system. Figure 1 The steps described correspond to those in the multi-objective optimization-based integrated energy operation simulation method. Therefore, the operations, characteristics, and beneficial effects described above are also applicable to the multi-objective optimization-based integrated energy operation simulation system and its constituent modules, and will not be repeated here.

[0157] Please see Figure 3 Based on the inventive concept of a comprehensive energy operation simulation method based on multi-objective optimization in the foregoing embodiments, this application provides an electronic device. This electronic device may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device includes a processing unit 301 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to programs stored in ROM 302 (read-only memory) or programs loaded from storage device 308 into RAM 303 (random access memory). RAM 303 also stores various programs and data required for the operation of the electronic device. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. Input / output interfaces (i.e., I / O interfaces 305) are also connected to the bus 304.

[0158] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touch screens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data.

[0159] In particular, according to some embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this application.

[0160] It should be noted that, in some embodiments of this application, the computer-readable medium described may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0161] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0162] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to implement the method steps of any of the aforementioned technical solutions.

[0163] Computer program code for performing operations of some embodiments of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0164] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0165] The modules described in some embodiments of this application can be implemented in software or hardware. The described modules can also be located in a processor. It is understood that the names of these modules do not, in some cases, constitute a limitation on the module itself.

[0166] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0167] Some embodiments of this application also provide a computer program product, including a computer program that, when executed by a processor, implements any of the above-described integrated energy operation simulation methods based on multi-objective optimization.

[0168] Although the present invention has been described in detail above with general descriptions and specific embodiments, modifications or improvements can be made to it, which will be obvious to those skilled in the art. Therefore, all such modifications or improvements made without departing from the spirit of the present invention fall within the scope of protection claimed by the present invention.

Claims

1. A comprehensive energy operation simulation method based on multi-objective optimization, characterized in that, Includes the following steps: We collect time-series data of photovoltaic power generation output, wind turbine speed signals, and conductivity monitoring data of seawater desalination load from island microgrids, and generate a joint feature dataset of renewable energy and load through multi-dimensional correlation and integration. Perform data standardization preprocessing and redundant data cleaning operations on the renewable energy-load joint feature dataset, calculate the maximum gradeability constraint parameters of the diesel generator and the start-stop frequency constraint parameters of the hydrogen production equipment, and generate a dynamic constraint parameter set. Hydrogen production equipment start-up and shutdown frequency constraints The calculation formula is: ， In the formula, The cumulative number of start-ups and shutdowns for the hydrogen production equipment; The set start / stop frequency threshold; A very small positive number set to avoid division by zero; Based on the aforementioned set of dynamic constraint parameters, the diesel generator output constraint and the seawater electrolysis hydrogen production coupling constraint are embedded into a multi-objective optimization framework through a nonlinear constraint mapping mechanism, thereby constructing a collaborative optimization model with the objective functions of minimizing operating costs and maximizing renewable energy absorption rate. The NSGA-III algorithm is used to simulate the collaborative optimization model and generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment. When a typhoon warning signal is detected, the forced lock mode of the seawater electrolysis hydrogen production equipment is activated, and the output power of the diesel generator is fixed to 80%-100% of the rated power in the current dispatch plan. During the operation of the hydrogen production equipment, the instantaneous power output signal of the wave energy generator is acquired through a high-frequency sampling module, and wavelet denoising processing is performed on the instantaneous power output signal to generate a standardized wave feature sequence. Based on the standardized fluctuation characteristic sequence, an adaptive sliding window algorithm is used to predict the power demand deviation of the reverse osmosis seawater desalination unit and generate real-time power compensation. By combining the real-time power compensation amount and the reference power curve of the reverse osmosis seawater desalination unit, the speed setting value of the high-pressure pump is dynamically adjusted through the proportional-integral controller to generate the corrected operating power curve. When the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, the power lock-up state of the diesel generator is turned off and the multi-energy coupling control mode is switched to synchronously update the charging and discharging strategy of the energy storage equipment.

2. The integrated energy operation simulation method based on multi-objective optimization according to claim 1, characterized in that, The steps described above for simulating the collaborative optimization model using the NSGA-III algorithm to generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment include: Based on the aforementioned collaborative optimization model, an initial population that satisfies the maximum gradeability constraint of the diesel generator is generated according to the preset population size and crossover mutation probability parameters. The initial population is subjected to non-dominated sorting and simulated binary crossover operations in the NSGA-III algorithm, and an intermediate population is generated by combining the adaptive reference point update strategy. A Gaussian mutation-based local search operation is performed on the intermediate population, and a Pareto front solution set is selected through an elite retention strategy to generate a candidate scheduling strategy set. A dynamic priority decoding strategy is executed on the candidate scheduling strategy set to map the optimal solution to the start-up and shutdown sequence of the hydrogen production equipment and the power command of the diesel generator, thereby generating a scheduling scheme that includes the start-up and shutdown sequence of the hydrogen production equipment.

3. The integrated energy operation simulation method based on multi-objective optimization according to claim 1, characterized in that, The step of activating the forced lockout mode of the seawater electrolysis hydrogen production equipment when a typhoon warning signal is detected, and fixing the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan, includes: The system receives typhoon wind speed forecast data from the meteorological department through the early warning monitoring module, and generates typhoon early warning trigger identifiers based on preset threshold comparisons. According to the typhoon warning triggering identifier, a forced lock command is sent to the PLC controller of the seawater electrolysis hydrogen production equipment to interrupt the priority scheduling queue of the hydrogen production equipment and generate an equipment lock status signal. Based on the device lock status signal and the rated power parameters of the diesel generator in the current scheduling scheme, a power lock logic operation is performed to limit the output power of the diesel generator to 80%-100% of the rated power.

4. The integrated energy operation simulation method based on multi-objective optimization according to any one of claims 1-3, characterized in that, The steps of shutting down the power lock-up state of the diesel generator and switching to multi-energy coupling control mode when the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, and synchronously updating the charging and discharging strategy of the energy storage equipment, include: The real-time hydrogen storage mass is calculated using the pressure sensor signal and temperature compensation algorithm of the hydrogen storage tank, and a hydrogen storage state vector is generated. Based on the hydrogen storage state vector, a fuzzy logic comparison is performed in combination with the preset hydrogen storage safety threshold range to generate a hydrogen storage exceeding limit identifier. Based on the hydrogen storage capacity over-limit indicator and the current diesel generator power lock command, a mode switching request is sent to the multi-energy coupling controller to release the diesel generator power lock flag and generate a multi-energy coupling enable signal. Based on the multi-energy coupling enable signal, a distributed model predictive control strategy is used to recalculate the charge and discharge power boundary conditions of the energy storage device and generate updated energy storage scheduling instructions.

5. A comprehensive energy operation simulation system based on multi-objective optimization, characterized in that, include: The model building module is used to collect time-series data of photovoltaic power generation output, wind turbine speed signals and conductivity monitoring data of seawater desalination load in island microgrids, and generate a joint feature dataset of renewable energy and load through multi-dimensional correlation integration; Perform data standardization preprocessing and redundant data cleaning operations on the renewable energy-load joint feature dataset, calculate the maximum gradeability constraint parameters of the diesel generator and the start-stop frequency constraint parameters of the hydrogen production equipment, and generate a dynamic constraint parameter set. Hydrogen production equipment start-up and shutdown frequency constraints The calculation formula is: ， In the formula, The cumulative number of start-ups and shutdowns for the hydrogen production equipment; The set start / stop frequency threshold; A very small positive number set to avoid division by zero; Based on the aforementioned set of dynamic constraint parameters, the diesel generator output constraint and the seawater electrolysis hydrogen production coupling constraint are embedded into a multi-objective optimization framework through a nonlinear constraint mapping mechanism, thereby constructing a collaborative optimization model with the objective functions of minimizing operating costs and maximizing renewable energy absorption rate. The simulation processing module is used to simulate the collaborative optimization model using the NSGA-III algorithm to generate a scheduling scheme that includes the start-up and shutdown sequence of hydrogen production equipment. The typhoon warning response module is used to activate the forced lock mode of the seawater electrolysis hydrogen production equipment when a typhoon warning signal is detected, and fix the output power of the diesel generator to 80%-100% of the rated power in the current dispatch plan. The real-time control module is used to acquire the instantaneous power output signal of the wave energy generator through the high-frequency sampling module during the operation of the hydrogen production equipment, and to perform wavelet denoising processing on the instantaneous power output signal to generate a standardized wave feature sequence. Based on the standardized fluctuation characteristic sequence, an adaptive sliding window algorithm is used to predict the power demand deviation of the reverse osmosis seawater desalination unit and generate real-time power compensation. By combining the real-time power compensation amount and the reference power curve of the reverse osmosis seawater desalination unit, the speed setting value of the high-pressure pump is dynamically adjusted through the proportional-integral controller to generate the corrected operating power curve. The mode switching module is used to shut down the power lock-up state of the diesel generator and switch to the multi-energy coupling control mode when the hydrogen storage capacity of the hydrogen production equipment reaches the threshold, and to synchronously update the charging and discharging strategy of the energy storage equipment.

6. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processing device, implements the method as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processing device, it implements the method of any one of claims 1 to 4.

Images