A marine park intelligent microgrid optimization scheduling method and system

Abstract

The present application relates to the technical field of intelligent microgrid optimization scheduling of offshore engineering park, in particular to an intelligent microgrid optimization scheduling method and system of offshore engineering park. First, the present application constructs a microgrid system model containing various energy conversion and energy storage devices; second, the minimum operation cost, the minimum energy consumption and the minimum carbon emission are taken as sub-goals, and the analytic hierarchy process is used to determine the weight of each sub-goal; at the same time, the constraint condition is constructed, and the dimensionless comprehensive fitness function is established based on the comprehensive objective function and the constraint condition, the Tent chaotic mapping is used to initialize the population when solving, the differential evolution strategy and the adaptive scaling factor are introduced in the foraging stage to update the position, and the fitness is calculated by combining the constraint penalty function, and the optimal output plan of each device is obtained through iterative optimization. The present application can effectively improve the convergence accuracy and global search ability of the algorithm, while ensuring the economic operation of the intelligent microgrid of offshore engineering park, reducing the system energy consumption and carbon emission level.

Description

Technical Field

[0001] This invention relates to the field of microgrid optimization scheduling technology, and more specifically, to a smart microgrid optimization scheduling method and system for marine engineering parks. Background Technology

[0002] Against the backdrop of global efforts to address climate change and promote energy transition, industrial parks, especially marine engineering equipment manufacturing and operation parks with high energy consumption and high reliability requirements, are of great significance for green and low-carbon transformation in order to reduce carbon emissions, improve energy efficiency, promote the consumption of renewable energy, and ensure high-reliability energy use.

[0003] Marine engineering industrial parks, also known as marine engineering industrial parks, are important platforms for developing the marine economy and promoting marine science and technology innovation. They facilitate the intensive development and high-end utilization of marine resources by aggregating related enterprises, improving the industrial chain, and strengthening infrastructure. Therefore, marine engineering parks are characterized by dense energy loads and complex energy consumption patterns, and typically possess natural advantages for developing clean energy sources such as distributed photovoltaic power and nearby offshore wind power, providing ideal application scenarios for building smart microgrids. However, the multiple uncertainties in source-load resources within the parks, as well as the inherent contradictions between operational objectives, pose significant challenges to the optimal scheduling of their energy systems.

[0004] Smart microgrids, as an effective carrier for integrating distributed energy, loads, and energy storage systems, are a core technological path for realizing the cascade utilization and refined management of energy in marine engineering parks. An excellent dispatch strategy is key to unlocking the comprehensive benefits of microgrids. Currently, the operation of microgrids in industrial parks generally faces multiple pressures: First, in a competitive market environment, economic efficiency is the lifeline of park operations, requiring efforts to reduce energy costs; second, to improve energy utilization efficiency, energy conservation (i.e., reducing total energy consumption, especially fossil fuel consumption) is an inherent requirement; finally, to fulfill social responsibility and cope with potential carbon tax policies, low-carbon emission reduction has become a rigid constraint. These goals are interconnected and mutually restrictive. For example, simply pursuing the lowest economic efficiency may lead to increased carbon emissions, while an extreme pursuit of low carbon emissions may significantly increase operating costs. Therefore, how to synergistically optimize these three goals is the core challenge of current research.

[0005] Existing research on microgrid scheduling either focuses on a single economic objective or only considers the dual objectives of economic and environmental optimization, falling short in terms of systematically coordinating the balance between economy, energy conservation, and low carbon emissions. Particularly in the specific scenario of offshore engineering parks, the unique characteristics of their load, resource endowment, and policy environment place higher demands on the adaptability and comprehensiveness of scheduling methods. Traditional methods often struggle to provide scheduling schemes that simultaneously satisfy optimal or satisfactory solutions across all three dimensions under complex and variable operating conditions.

[0006] For example, invention patent CN117892959A discloses a method for optimizing the configuration of distributed energy systems based on an improved Zebra optimization algorithm. This method aims to minimize annual construction and operation costs, pollutant emissions, and fuel consumption, optimizing the equipment capacity configuration of a distributed energy system coupling solar and geothermal energy. Essentially, this method falls under the capacity optimization problem of the planning / design phase. Its decision variables are the rated power / capacity of the equipment, and the optimization period is the entire life cycle or a typical year. It cannot respond to real-time fluctuations in load and renewable energy output during the operation of marine engineering parks. However, the operation and scheduling of smart microgrids in marine engineering parks requires dynamic allocation of unit output, adjustment of energy storage charging and discharging power, and response to time-of-use pricing on a minute / hour timescale. This involves entirely different sets of decision variables (such as distributed power output at different times, power purchased from the grid, and energy storage charging and discharging rates) and constraints (such as power balance, ramp-up constraints, and continuous changes in state of charge). Furthermore, the energy-saving objective of the existing technology is "minimizing fuel consumption," while this invention focuses on "minimizing total fossil energy consumption" and introduces "carbon emissions" separately as a low-carbon constraint, resulting in different objective connotations. Its application scenario is a general distributed energy system, and it does not model the special loads of marine engineering parks (such as ship commissioning loads and shore power impact loads) or the strong randomness of the marine environment. Therefore, this method is difficult to directly transfer to the real-time collaborative scheduling scenario of microgrids in marine engineering parks, and it cannot solve the dynamic balance problem of the three-dimensional objectives of economy, energy saving, and low carbon at the operational level.

[0007] In addition, the invention patent with publication number CN121581280A, entitled "Energy Consumption Optimization System for Low-Carbon Dwellings in Traditional Villages Based on Artificial Intelligence", elevates the optimization perspective from isolated individual buildings to village groups. It achieves village-level collaborative energy management by establishing a collaborative scheduling mechanism. However, it is geared towards traditional village dwelling scenarios, which differ significantly from the industrial load characteristics of marine engineering parks. Another example is the invention patent with publication number CN121440793A, entitled "A Low-Carbon Optimization Scheduling Method for Microgrids Based on Demand Response". It minimizes operating costs and pollutant emissions in an optimization model, but it is still a dual-objective optimization and does not treat energy conservation (fossil energy consumption) as an independent objective to balance economy and low carbon.

[0008] To this end, this invention proposes a smart microgrid optimization scheduling method for marine engineering parks that takes into account economic, energy-saving and low-carbon goals. This method aims to effectively balance the relationship between park operating costs, energy utilization efficiency and carbon emissions through multi-objective collaborative optimization modeling, thereby providing a scientific decision support tool for the green, economical and efficient operation of marine engineering parks and helping the industrial sector achieve high-quality development and low-carbon transformation. Summary of the Invention

[0009] The purpose of this invention is to overcome the shortcomings of existing technologies and propose an optimized scheduling method for smart microgrids in marine engineering parks that balances economic, energy-saving, and low-carbon objectives. This method constructs a multi-objective optimized scheduling model for smart microgrids in marine engineering parks based on the chaotic adaptive differential zebra optimization algorithm. This model effectively overcomes the limitations of existing scheduling methods in coordinating economic, energy-saving, and low-carbon objectives. By simulating the intelligent behavior of zebra swarms, it improves the algorithm's optimization ability and obtains scheduling results with superior overall performance.

[0010] The technical problem solved by this invention is achieved through the following technical solution: A method for optimizing the scheduling of a smart microgrid in an offshore engineering park, comprising the following steps: S1: Construct a smart microgrid system model for the marine engineering park, including wind turbine model, photovoltaic model, micro gas turbine model, waste heat recovery device model, gas boiler model, battery model, electric chiller model, absorption chiller model, and thermal storage tank model; S2: With the three sub-objectives of lowest system operating cost, lowest total fossil energy consumption, and lowest carbon emissions, a comprehensive objective function is established, and the weight coefficients of each sub-objective in the comprehensive objective function are determined to obtain a weighted objective function, and then a dimensionless comprehensive fitness function is constructed. S3: Construct power balance constraints including electric power balance, thermal power balance, and cold power balance, as well as constraint conditions for battery state of charge and thermal storage tank state of heat; and transform the constraint conditions into a total constraint penalty function; S4: The zebra population is initialized using the Tent chaotic mapping strategy to generate a diverse set of initial decision variables covering the entire solution space, i.e., the initial scheduling scheme set. The iterative optimization process of the chaotic adaptive differential zebra optimization algorithm is started. In each iteration, the population position update is performed sequentially during the foraging and defense phases. Based on the comprehensive fitness function determined in step S2 and the total constraint penalty function established in step S3, the comprehensive fitness value of each zebra individual is calculated, and the individual optimal position and the global optimal position are updated, thereby obtaining the specific values ​​of the current optimal set of decision variables. S5: Determine whether the current iteration count has reached the preset maximum iteration count. If not, return to step S5 to continue iterating. If it has reached the maximum, output the optimal scheduling scheme corresponding to the current global optimal position, i.e., the output plan of each device in each scheduling period. S6: Analyze the obtained optimal scheduling scheme and select preset evaluation indicators to evaluate the comprehensive performance of the scheduling scheme in order to verify its economy, energy saving and low carbon emissions.

[0011] Furthermore, including: The process of constructing the weighted objective function includes: The sub-objective function that minimizes operating cost is established as follows: ; In the formula, Operating costs; For equipment maintenance costs; Equipment depreciation costs; The interaction cost between the microgrid and the power grid; For natural gas costs; The sub-objective function that minimizes energy consumption is established as follows: ; In the formula, TEC Energy consumption refers to the total amount of natural gas consumed. They are respectively t Real-time natural gas consumption of power grids, gas boilers, and micro-turbines; Establish a sub-objective function that minimizes carbon emissions, expressed as: ; In the formula, CDE For carbon emissions; This represents the CO2 emission coefficient during grid power generation. This represents the CO2 emission coefficient of natural gas. A comprehensive objective function is established with the sub-objectives of lowest operating cost, lowest energy consumption, and lowest carbon emissions as its constituent objectives, expressed as: ; In the formula, As a comprehensive indicator; These are the weighting coefficients.

[0012] Furthermore, including: The construction of the dimensionless comprehensive fitness function includes: Weights are obtained using the analytic hierarchy process. The weights are then incorporated into the comprehensive objective function to construct a weighted objective function: ; To eliminate the weighted objective function F With total constraint penalty function Due to the inherent differences in physical dimensions and numerical magnitudes, the two are normalized to construct a dimensionless comprehensive fitness function. Assume the current zebra population size is N In each iteration, the weighted objective function value for all individuals in the population is first calculated. F and the total constraint penalty function value And record the maximum and minimum values ​​in the current population, respectively. Then construct the comprehensive fitness function: ; In the formula, The term is an infinitesimal positive number used to prevent the denominator from being 0. The first term reflects the normalized economic, energy consumption, and carbon emission levels; the second term reflects the degree of constraint violation after normalization. If an individual satisfies all constraints, then After normalization, the penalty function term is 0; if the constraint is violated, the penalty function value increases, and the individual's overall fitness value deteriorates accordingly, thus leading to its elimination in the process of population evolution.

[0013] Furthermore, including: The sequential execution of population position updates during the foraging and defense phases includes: During the foraging phase, a differential evolution strategy and an adaptive scaling factor are used for position updates. During the defense phase, position updates are performed according to preset zebra defense behavior rules. Specifically: During the foraging phase, individuals use differential evolution strategies to update their positions, enhancing their global exploration capabilities and thus obtaining a better scheduling scheme, mathematically expressed as: ; In the formula, for Random numbers within the interval; The position of the vanguard zebra; For population change control parameters; The locations of randomly selected distinct individuals; The scaling factor is expressed as: ; In the formula, These represent the maximum and minimum values ​​of the scaling factor, respectively. An exponential parameter used to control the rate of decrease; This represents the current population fitness variance.

[0014] Furthermore, including: In obtaining the current optimal set of decision variable values, the decision variables are represented as follows: ; in, These refer to the output of wind turbines, photovoltaic units, battery banks, power grids, micro gas turbines, electric refrigeration units, absorption chillers, gas boilers, and thermal storage tanks.

[0015] Secondly, the present invention also provides a smart microgrid optimization scheduling system for marine engineering parks, comprising: The model building module is used to build a smart microgrid system model for marine engineering parks. The system model includes a wind turbine model, a photovoltaic model, a micro gas turbine model, a waste heat recovery device model, a gas boiler model, a battery model, an electric chiller model, an absorption chiller model, and a thermal storage tank model. The fitness function construction module is used to establish a comprehensive objective function with three sub-objectives: lowest system operating cost, lowest total fossil energy consumption, and lowest carbon emissions. It also determines the weight coefficients of each sub-objective in the comprehensive objective function to obtain a weighted objective function, and then constructs a dimensionless comprehensive fitness function. The constraint construction module is used to construct constraint conditions including power balance, thermal power balance, and cold power balance, as well as battery state of charge constraints and thermal storage tank state of charge constraints; and to transform the constraint conditions into a total constraint penalty function. The optimization solution module is used to initialize the zebra population using the Tent chaotic mapping strategy, generate a diverse set of initial decision variables covering the entire solution space, initiate the iterative optimization process of the chaotic adaptive differential zebra optimization algorithm, sequentially perform population position updates during the foraging and defense phases in each iteration, calculate the comprehensive fitness value of each zebra individual based on the comprehensive fitness function and the total constraint penalty function, update the individual optimal position and the global optimal position, thereby obtaining the specific values ​​of the current optimal set of decision variables; The output module is used to determine whether the current iteration count has reached the preset maximum iteration count. If it has not reached the maximum iteration count, the iteration continues. If it has reached the maximum iteration count, the optimal scheduling scheme corresponding to the current global optimal position is output, that is, the output plan of each device in each scheduling period. The evaluation module is used to analyze the optimal scheduling scheme and select preset evaluation indicators to evaluate the overall performance of the scheduling scheme in order to verify its economy, energy saving and low carbon emissions.

[0016] Thirdly, the present invention also provides a computer device, comprising: one or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the steps of the optimized scheduling method for smart microgrids in marine engineering parks as described in the first aspect are implemented.

[0017] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, it implements the steps of the marine engineering park smart microgrid optimization scheduling method as described in the first aspect.

[0018] The advantages and positive effects of this invention are: 1. In the foraging stage of the zebra optimization algorithm, this invention incorporates the mutation strategy of the differential evolution algorithm into the position update process, so that while individuals move closer to the lead zebra, they can use the difference information between individuals in the population to perform directional perturbation, thereby enhancing the global exploration ability.

[0019] Building upon this foundation, this invention further designs an adaptive scaling factor based on population fitness variance. This allows the algorithm to exhibit a stronger mutation amplitude for broader searching when the fitness variance is large, and to automatically shrink the scaling factor for finer-grained development when the fitness variance is small. Compared to the traditional Zebra Optimization algorithm, this invention achieves improvements in all four evaluation metrics: energy efficiency increases from 79.12% to 79.42%, and fuel savings increase from 60.98% to 61.20%. The emission reduction rate increased from 69.63% to 71.25%, and the cost saving rate increased from 62.78% to 62.85%. These results demonstrate that the synergistic effect of the differential evolution strategy and the adaptive scaling factor effectively balances global search and local exploitation capabilities, avoiding the pitfalls of traditional algorithms that easily get trapped in local optima, and thus achieving a higher-quality scheduling scheme.

[0020] 2. This invention constructs power balance constraints for electricity, heat, and cooling, as well as operational constraints for energy storage devices. These constraints are transformed into a total constraint penalty function, which, together with a weighted objective function, constitutes a comprehensive fitness evaluation function. In each iteration, the economic efficiency, energy saving, low-carbon performance, and feasibility of the scheduling scheme are quantitatively evaluated and screened. The final scheduling result achieves an energy efficiency of 79.42%, a fuel saving rate of 61.20%, a 71.25% reduction in carbon emissions compared to a distributed supply system, and a 62.85% reduction in operating costs. This demonstrates that this invention effectively solves the problem of multi-objective dynamic balance at the operational level of microgrids in marine engineering parks, significantly reducing fossil fuel consumption and carbon emissions while ensuring economical system operation.

[0021] 3. This invention introduces a differential evolution mutation strategy during the foraging phase while retaining the counterattack mechanism of the Zebra Optimization Algorithm's defense phase, namely, the position update method that moves towards the current global optimum. The two form a synergistic effect in the later stages of iteration: the differential evolution strategy automatically shrinks the variable asynchronous length through an adaptive scaling factor, and performs fine perturbation near the optimal solution; the counterattack phase drives individuals in the population to gather towards the global optimum, strengthening the directionality of local development. As shown in Table 2 of the embodiments, this invention improves energy efficiency by 0.30 percentage points and cost savings by 0.07 percentage points compared to the scheduling results based on the Zebra Optimization Algorithm, verifying the effectiveness of this synergistic mechanism in actual optimization.

[0022] 4. This invention transforms the electrical, thermal, and cooling power balance constraints into precise penalty function forms and strictly incorporates the battery state of charge and thermal storage tank state of charge constraints into the comprehensive fitness evaluation. This allows the algorithm to perform complete constraint verification on each candidate scheduling scheme during the optimization process, ensuring that the optimal scheduling plan meets all physical constraints of the actual operation of the marine engineering park and guaranteeing the feasibility of the scheduling scheme in actual engineering. Attached Figure Description

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] Figure 1 This is a flowchart of the multi-objective optimization scheduling process of the intelligent microgrid in marine engineering parks based on the chaotic adaptive differential zebra optimization algorithm of the present invention; Figure 2 This is a diagram showing the output of each device in a multi-objective optimization scheduling model for a smart microgrid in an offshore engineering park, based on the chaotic adaptive differential zebra optimization algorithm. Figure 3 This is a structural diagram of the computer device described in this embodiment. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0026] like Figure 1 As shown, this embodiment provides a smart microgrid optimization scheduling method for offshore engineering parks that takes into account economic, energy-saving and low-carbon goals, including the following steps: Step 1: Construct a smart microgrid system model for the marine engineering park, mainly including wind turbines, photovoltaics, micro gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers, and thermal storage tanks, and set relevant parameters; Step 2: Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives; Step 3: Use the analytic hierarchy process (AHP) to determine the weights of each sub-objective, transform the multi-objective problem into a single-objective problem, construct a weighted objective function, and then comprehensively consider the function and system constraints to construct a dimensionless comprehensive fitness function. Step 4: Construct system constraints, including electrical, thermal, and cooling power balance constraints, energy storage equipment constraints such as batteries and thermal storage tanks, wind turbine and photovoltaic power output constraints, and other equipment operation constraints; Step 5: Set the parameters of the chaotic adaptive differential zebra optimization algorithm, including zebra population size, maximum number of iterations, maximum and minimum scaling factor, and crossover probability; Step 6: Initialize the zebra population based on the Tent chaotic mapping strategy to generate a diverse set of initial scheduling schemes covering the entire solution space; Step 7: The chaotic adaptive differential zebra optimization algorithm begins iterative optimization; Step 8: Calculate the overall fitness value for each zebra individual, update the individual optimal position and the global optimal position, and obtain the position of the zebra individual with the best fitness value in the current iteration of the chaotic adaptive differential zebra optimization algorithm; Step 9: Determine whether the Chaotic Adaptive Differential Zebra Optimization Algorithm has reached the maximum number of iterations. If it has, output the current global optimal position (i.e., the optimal scheduling scheme). If not, return to step 7. Step 10: Output and execute the optimal scheduling scheme obtained by iterative optimization using the chaotic adaptive differential zebra optimization algorithm to obtain the output plan of each device; Step 11: Analyze the scheduling results and select evaluation indicators to assess the scheduling results of the method of the present invention.

[0027] The specific implementation method of this embodiment is as follows: Step 1: Construct a smart microgrid system model for the marine engineering park, which mainly includes wind turbines, photovoltaics, micro gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers, and thermal storage tanks, and set relevant parameters.

[0028] (1.1) Model the wind turbine as shown in formula (1): (1) In the formula, P W Mechanical power; T W For mechanical torque; ρ air density; R Where is the blade radius; v Wind speed; This refers to the fan speed; This is the wind energy utilization coefficient.

[0029] (1.2) Model the photovoltaic system as shown in formula (2): (2) In the formula, η PV This is the ratio of the actual output of the photovoltaic unit to its rated power, used to account for losses caused by dirt and shading on the photovoltaic panels and their own aging. P PV This refers to the output power of the photovoltaic unit.P STC The rated power of the photovoltaic unit under standard test conditions; k The power temperature coefficient; G This represents the actual irradiance. G STC Irradiance under standard test conditions; T STC Temperature under standard test conditions; T E and T C These are ambient temperature and photovoltaic panel surface temperature, respectively.

[0030] (1.3) Model the micro-turbine and waste heat recovery device as shown in formula (3): (3) In the formula, P MT This refers to the electrical power output of the micro-engine; F MT This refers to the natural gas consumption of the micro gas turbine; η MT The power generation efficiency of the micro gas turbine; H HR The heat power recovered by the waste heat recovery device; η HR The heat recovery efficiency of the waste heat recovery device; H NG This refers to the calorific value of natural gas.

[0031] (1.4) Model the gas-fired boiler as shown in formula (4): (4) In the formula, H GB and η GB These are the heating power and heating efficiency of the gas-fired boiler, respectively. F GB This refers to the natural gas consumption of the gas-fired boiler.

[0032] (1.5) Model the battery as shown in formula (5): (5) In the formula, for t The electrical energy stored in the battery pack at all times; E STC This refers to the capacity of the battery pack under standard test conditions. This refers to the capacity temperature coefficient. for t The temperature of the battery pack surface at all times.

[0033] (1.6) Model the electric chiller as shown in formula (6): (6) In the formula, C EC and P EC These are the cooling capacity and electrical power consumed by the electric refrigeration unit, respectively. η EC The refrigeration efficiency of the electric refrigeration unit.

[0034] (1.7) Model the absorption chiller as shown in formula (7): (7) In the formula, C AC This refers to the cooling power output of the absorption chiller unit. H AC The heat power input to the absorption chiller unit; η AC This refers to the refrigeration efficiency of an absorption chiller.

[0035] (1.8) Model the thermal storage tank as shown in formula (8): (8) In the formula, They are respectively t Time and t The thermal energy stored in the thermal storage tank at time -1; This is the self-loss coefficient of thermal energy in the thermal storage tank; They are respectively t The heat absorption and release power of the thermal storage tank at all times; These are the heat absorption efficiency and heat release efficiency of the heat storage tank, respectively.

[0036] Step 2: Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives.

[0037] (2.1) Set the decision variables as the output of each device in each time period within the scheduling cycle, as shown in formula (9): (9) In the formula, These refer to the output of wind turbines, photovoltaic units, battery banks, power grids, micro gas turbines, electric refrigeration units, absorption chillers, gas boilers, and thermal storage tanks.

[0038] (2.2) Establish the sub-objective function with the lowest operating cost, as shown in formula (10): (10) In the formula, C Eco Operating costs; C M For equipment maintenance costs; C Loss Equipment depreciation costs; C Grid The interaction cost between the microgrid and the power grid; C Gas For natural gas costs; T To optimize time periods; for t Time of the first i The output of the equipment; K M,i , L i , r i and C Cost,i The first i Maintenance factor, depreciation period, annual depreciation rate, and installation cost per unit capacity of the equipment; N R,i For the first i Installation capacity of the equipment; They are respectively t The grid unit price and the on-grid unit price at any given time; They are respectively t The power that the microgrid purchases and sells to the grid; c Gas,out and H NG These are the unit price and calorific value of natural gas, respectively. n Number of equipment types; They are respectively t The output power of gas-fired boilers and micro-turbines at all times.

[0039] (2.3) Establish the sub-objective function with the lowest energy consumption, as shown in formula (11): (11) In the formula, TEC Energy consumption refers to the total amount of natural gas consumed. They are respectively t The amount of natural gas consumed by the power grid, gas boilers and micro-turbines at all times.

[0040] (2.4) Establish the sub-objective function that minimizes carbon emissions, as shown in formula (12): (12) In the formula, CDE For carbon emissions; This represents the CO2 emission coefficient during grid power generation. This represents the CO2 emission coefficient of natural gas.

[0041] (2.5) Establish a comprehensive objective function with the minimum operating cost, minimum energy consumption, and minimum carbon emissions as sub-objectives, as shown in formula (13): (13) In the formula, As a comprehensive indicator; These are the weighting coefficients.

[0042] Step 3: Use the analytic hierarchy process (AHP) to determine the weights of each sub-objective, thus transforming the multi-objective problem into a single-objective problem.

[0043] (3.1) Determine the correspondence between scores and relative importance; The relative importance of the standard layer indicators was scored using a pairwise comparison method and a comparison scale of 1 to 9. Specifically, "equally important" was scored as "1"; "median of equal and slightly important" was scored as "2"; "slightly important" was scored as "3"; "median of slightly important and significantly important" was scored as "4"; "significantly important" was scored as "5"; "median of significantly important and strongly important" was scored as "6"; "significantly important" was scored as "7"; "median of strongly important and extremely important" was scored as "8"; and "extremely important" was scored as "9".

[0044] (3.2) Determine the scores for operating costs, energy consumption, and carbon emissions based on the correspondence between importance and score; The relative importance of operating costs, energy consumption, and carbon emissions is set, and the score of each sub-objective is determined according to the correspondence between the importance and the score, resulting in the judgment matrix as shown in formula (14): (14) (3.3) The judgment matrix is ​​processed according to formula (15) to obtain the eigenvector matrix. Then the obtained eigenvector matrix is ​​normalized to obtain the weights of operating cost, energy consumption and carbon emissions. (15) In the formula, S i To determine the product of the elements in each row of a matrix; The eigenvector matrix; U i For the first i The weight of each indicator.

[0045] (3.4) The operating costs, energy consumption, and carbon emission weights obtained by the analytic hierarchy process are respectively denoted as... The weights are then incorporated into the comprehensive objective function to construct a weighted objective function, which is expressed as follows: (16) The weighted objective function serves as the fundamental function for evaluating individual fitness in the chaotic adaptive differential zebra optimization algorithm.

[0046] The calculation of the overall fitness value for each zebra individual includes: To eliminate the weighted objective function F With total constraint penalty function Due to the inherent differences in physical dimensions and numerical magnitudes, this invention normalizes both to construct a dimensionless comprehensive fitness function. Since both are dimensionless scalars, their direct addition has a clear mathematical meaning: minimizing the comprehensive performance index while prioritizing the satisfaction of system operational constraints.

[0047] Assume the current zebra population size is N In each iteration, the weighted objective function value for all individuals in the population is first calculated. F and the total constraint penalty function value P pen And record the maximum and minimum values ​​in the current population, respectively. Then the comprehensive fitness function can be constructed, as shown in formula (17): (17) In the formula, It is an infinitesimal positive number, used to prevent the denominator from being 0.

[0048] Step 4: Construct system constraints, including electrical, thermal, and cooling power balance constraints, energy storage equipment constraints such as batteries and thermal storage tanks, wind turbine and photovoltaic power output constraints, and other equipment operation constraints.

[0049] To address the microgrid optimization and scheduling problem, this invention constructs constraints on the balance of electrical, thermal, and cooling power, constraints on energy storage devices such as batteries and thermal storage tanks, constraints on wind turbine and photovoltaic power output, and constraints on the operation of other equipment, to ensure that the scheduling scheme obtained during the optimization process is feasible in practical applications.

[0050] (4.1) Establish the power balance constraints for electricity, heat, and cold, as shown in formula (18): (18) In the formula, They are respectively t The output power of wind turbines, photovoltaic units, and micro gas turbines at all times; and They are respectively t The power purchase and sales capacity of Time Microgrid; They are respectively t The charging and discharging power of the battery pack at all times; They are respectively t The power load demand of the microgrid and the power demand of the electric chiller units; and respectively t The thermal power of the waste heat recovery device and the gas boiler; They are respectively t The heat release capacity and heat storage capacity of the thermal storage tank at all times; They are respectively t The heat power consumed by the heat exchanger and absorption chiller unit at all times; They are respectively t The cooling capacity of electric refrigeration units and absorption refrigeration units at any given time; for t The cooling load requirement at any time.

[0051] (4.2) Establish the equipment constraints for the storage battery and the thermal storage tank, as shown in formula (19) and formula (20) respectively: (19) In the formula, for t The state of charge of the battery pack at all times; These represent the minimum and maximum states of charge of the battery pack, respectively. These are the minimum and maximum charging power of the battery pack, respectively. These are the minimum and maximum discharge power of the battery pack, respectively.

[0052] (20) In the formula, for t The thermal storage tank is constantly under heat load. These represent the minimum and maximum heat load states of the thermal storage tank, respectively. These are the minimum and maximum thermal storage capacities of the thermal storage tank, respectively. These represent the minimum and maximum heat release power of the thermal storage tank, respectively.

[0053] (4.3) Establish the output constraints for wind turbines and photovoltaics, as shown in formula (21): (twenty one) In the formula, These represent the maximum active power output of the wind turbine and the photovoltaic unit, respectively.

[0054] (4.4) In order to ensure that the optimization results meet the system operation constraints, the power balance constraints of electricity, heat and cold and the energy storage device constraints are transformed into penalty functions and introduced into the comprehensive fitness function.

[0055] The power balance penalty term is: (twenty two) The thermal power balance penalty term is: (twenty three) The cold power balance penalty term is: (twenty four) The penalty for the battery state of charge constraint is: (25) The penalty for the thermal storage tank under heat load condition constraint is as follows: (26) Therefore, the total constraint penalty function is expressed as: (27) In each iteration of the chaotic adaptive differential zebra optimization algorithm, the weighted objective function value is first calculated based on the weight coefficients obtained in step 3, then the constraint penalty function value is calculated based on the constraints established in step 4, and the individual comprehensive fitness value is calculated according to formula (17). When a scheduling scheme violates the power balance constraint or equipment operation constraint, its penalty function value increases, thereby reducing the fitness of the individual and causing it to be eliminated in the population evolution process.

[0056] In the above formula, These are the penalty coefficients for constraints on electric power balance, thermal power balance, cold power balance, battery state of charge, and thermal storage tank state of charge, respectively; the meanings of the other symbols are consistent with those in formula (18).

[0057] Therefore, this invention achieves a synergistic fusion between constraints and the chaotic adaptive differential zebra optimization algorithm, becoming a key part of solving the optimization scheduling problem of smart microgrids in marine engineering parks. In each iteration of the chaotic adaptive differential zebra optimization algorithm, the scheduling scheme is evaluated through fitness values, and all the aforementioned constraints are considered when calculating the fitness values.

[0058] Step 5: Set the parameters of the chaotic adaptive differential zebra optimization algorithm, including zebra population size, maximum number of iterations, maximum and minimum scaling factors, and crossover probability.

[0059] Step 6: Initialize the zebra population based on the Tent chaotic mapping strategy to generate a diverse set of initial scheduling schemes to ensure full coverage of the entire solution space.

[0060] The Tent chaotic mapping strategy is used to initialize the zebra population to generate an initial population with high randomness and uncertainty, thereby ensuring broad coverage of the solution space. By introducing high uncertainty and sensitivity, the Tent chaotic mapping generates numerical sequences with good distribution characteristics, effectively avoiding the population concentration problem that may occur with traditional initialization methods and providing stronger global search capabilities. Specifically, the numerical sequence based on the Tent chaotic mapping is generated iteratively through formula (28), as follows: (28) In the formula, The first generation generated based on the Tent chaotic mapping strategy initialization Individual.

[0061] Step 7: The chaotic adaptive differential zebra optimization algorithm begins iterative optimization.

[0062] (7.1) Calculate the initial fitness value of the population using the comprehensive fitness function; Calculate the overall fitness score for each zebra individual: (29) In the formula, It is a very small positive constant whose core function is to prevent the denominator from being zero, ensuring the stability and robustness of numerical calculations. The first term reflects the normalized economic, energy consumption, and carbon emission levels; the second term reflects the degree of constraint violation after normalization. If an individual satisfies all constraints, then... After normalization, the penalty function term is 0; if the constraint is violated, the penalty function value increases, and the individual's overall fitness value deteriorates accordingly, thus leading to its elimination in the process of population evolution.

[0063] (7.2) The population enters the foraging phase in the chaotic adaptive differential zebra optimization algorithm; In the foraging phase, the chaotic adaptive differential zebra optimization algorithm updates the position of individuals using a differential evolution strategy to enhance global exploration capabilities, thereby obtaining a better scheduling scheme. Mathematically, this is expressed as: (30) In the formula, for Random numbers within the interval; The position of the vanguard zebra; For population change control parameters; , The locations of randomly selected distinct individuals; The scaling factor is based on an adaptive parameter strategy, and its mathematical expression is shown in formula (31): (31) In the formula, These represent the maximum and minimum values ​​of the scaling factor, respectively. An exponential parameter used to control the rate of decrease; This represents the current population fitness variance.

[0064] In each iteration, this invention utilizes a position update mechanism based on a differential evolution strategy and a scaling factor based on an adaptive parameter strategy to mutate individual positions and facilitate information exchange between individuals, thereby enhancing global search capabilities. This mechanism leverages the global exploration capability of the differential evolution algorithm and the local optimization characteristics of the adaptive parameter strategy, enabling the chaotic adaptive differential zebra optimization algorithm to effectively focus on a refined search for the optimal solution while broadly searching the solution space during scheduling optimization, thus improving the optimization efficiency and solution quality of the scheduling scheme.

[0065] (7.3) The population enters the defense phase in the chaotic adaptive differential zebra optimization algorithm; In the chaotic adaptive differential zebra optimization algorithm, the defense phase of the zebra population is divided into an escape phase based on lion attacks and a counterattack phase based on attacks from other predators. The position update in the escape phase is shown in formula (32): (32) In the formula, ; for Random numbers within the interval; For the first t The chaotic mapping value of the next iteration. ; The locations of the randomly selected distinct individuals.

[0066] The position update during the counterattack phase is shown in formula (33): (33) In the formula, The location of the zebra being attacked ( ); This represents the current globally optimal individual position.

[0067] Step 8: Calculate the comprehensive fitness value for each zebra individual according to formula (17), and update the individual's optimal position and the global optimal position based on the fitness value. The comprehensive fitness value simultaneously reflects operating costs, energy consumption, carbon emissions, and constraint satisfaction, thereby achieving synergistic optimization of the economy, energy saving, and low carbon emissions of the marine engineering park's smart microgrid.

[0068] Step 9: Determine whether the Chaotic Adaptive Differential Zebra Optimization Algorithm has reached the maximum number of iterations. If it has, output the current global optimal position (i.e., the optimal scheduling scheme). If not, return to step 7.

[0069] Step 10: Output and execute the optimal scheduling scheme obtained by iterative optimization using the chaotic adaptive differential zebra optimization algorithm to obtain the output plan of each device.

[0070] Step 11: Analyze the scheduling results and select evaluation indicators to assess the scheduling results of the method of the present invention.

[0071] Adopting energy efficiency ( η Energy ), fuel saving rate ( η TEC ), CO2 emission reduction rate ( η CDE ) and cost savings rate ( η Eco The evaluation index is used to evaluate the results. The mathematical expression of the evaluation index is:

[0072] In the formula, TEC Natural gas consumed by the microgrid; TEC SES Natural gas consumed by distributed energy systems; CDE and CDE SES These are the CO2 emissions from microgrids and distributed energy systems, respectively. C Eco and C Eco , SES These are the operating costs for microgrids and distributed energy systems, respectively.

[0073] The output plan diagram of each device in step 10 is displayed on the computer screen using MATLAB software; and the evaluation effect of each evaluation index in step 11 on the invention is displayed on the computer screen using MATLAB software.

[0074] Through the above steps, the intelligent microgrid optimization scheduling function for marine engineering parks of this invention has been completed.

[0075] The above-mentioned method for optimizing the scheduling of a smart microgrid in marine engineering parks, which takes into account economic, energy-saving and low-carbon goals, uses existing technology for equipment modeling, which includes wind turbines, photovoltaics, micro gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers and thermal storage tanks. This technology is well known to those skilled in the art. The above-mentioned method for optimizing and scheduling a smart microgrid in an offshore engineering park that takes into account economic, energy-saving and low-carbon goals, wherein the method of inputting the parameters of the chaotic adaptive differential zebra optimization algorithm into the computer is a well-known method. The aforementioned method for optimizing the scheduling of a smart microgrid in marine engineering parks, which balances economic, energy-saving, and low-carbon goals, uses computers, monitors, and MATLAB computer software that were all purchased commercially.

[0076] In this embodiment, Figure 1 The process of a smart microgrid optimization scheduling method for offshore engineering parks that takes into account economic, energy-saving, and low-carbon goals is as follows: Start → Construct a smart microgrid system model for the offshore engineering park → Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives → Determine the weights of each sub-objective using the analytic hierarchy process (AHP) → Construct system constraints → Set parameters for the chaotic adaptive differential zebra optimization algorithm → Initialize the zebra population based on the Tent chaotic mapping strategy → Generate a diverse set of initial scheduling schemes covering the entire solution space → The chaotic adaptive differential zebra optimization algorithm begins iterative optimization → Calculate the fitness value corresponding to each zebra individual → Update the individual optimal position and the global optimal position → Determine whether the chaotic adaptive differential zebra optimization algorithm has reached the maximum number of iterations → Output the optimal solution at this time (i.e., the global optimal position, representing the optimal scheduling scheme) → Output and execute the optimal scheduling scheme obtained by the iterative optimization of the chaotic adaptive differential zebra optimization algorithm → Obtain the output plan of each device → Analyze the scheduling results → Select evaluation indicators to evaluate the scheduling results of the method of this invention → End.

[0077] Figure 2 This diagram shows the power output of each device in the multi-objective optimization scheduling model of the smart microgrid in the marine engineering park based on the chaotic adaptive differential zebra optimization algorithm. The horizontal axis represents time (24-hour system), and the vertical axis represents power value. The curves represent the power values ​​of electrical load, cold load, and hot load, respectively, and the stacked bars represent the power output of each device.

[0078] In a preferred embodiment, a smart microgrid optimization scheduling method for marine engineering parks that takes into account economic, energy-saving and low-carbon goals is proposed. A PC is used as the platform for model building, with an i7-14700KF 3.40GHz CPU, 32 G of installed memory, Windows 10 64-bit operating system, and MATLAB R2022a version.

[0079] The specific implementation method of this embodiment is as follows: Step 1: Construct a smart microgrid system model for the marine engineering park, mainly including wind turbines, photovoltaics, micro gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers, and thermal storage tanks, and set relevant parameters; Step 2: Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives; Step 3: Use the analytic hierarchy process (AHP) to determine the weights of each sub-objective, transform the multi-objective problem into a single-objective problem, construct a weighted objective function, and then comprehensively consider the function and system constraints to construct a dimensionless comprehensive fitness function. Step 4: Construct system constraints, including electrical, thermal, and cooling power balance constraints, energy storage equipment constraints such as batteries and thermal storage tanks, wind turbine and photovoltaic power output constraints, and other equipment operation constraints; Step 5: Set the parameters of the chaotic adaptive differential zebra optimization algorithm, including zebra population size, maximum number of iterations, maximum and minimum scaling factor, and crossover probability; Step 6: Initialize the zebra population based on the Tent chaotic mapping strategy to generate a diverse set of initial scheduling schemes covering the entire solution space; Step 7: The chaotic adaptive differential zebra optimization algorithm begins iterative optimization; Step 8: Calculate the overall fitness value for each zebra individual, update the individual optimal position and the global optimal position, and obtain the position of the zebra individual with the best fitness value in the current iteration of the chaotic adaptive differential zebra optimization algorithm; Step 9: Determine whether the Chaotic Adaptive Differential Zebra Optimization Algorithm has reached the maximum number of iterations. If it has, output the current global optimal position (i.e., the optimal scheduling scheme). If not, return to step 7. Step 10: Output and execute the optimal scheduling scheme obtained by iterative optimization using the chaotic adaptive differential zebra optimization algorithm to obtain the output plan of each device; Step 11: Analyze the scheduling results and select evaluation indicators to assess the scheduling results of the method of the present invention.

[0080] The specific implementation method of this invention is as follows: Step 1: Construct a smart microgrid system model for the marine engineering park, which mainly includes wind turbines, photovoltaics, micro gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers, and thermal storage tanks, and set relevant parameters.

[0081] (1.1) Model the wind turbine; Formula (1) is the mathematical model for the wind turbine. In formula (1), P W Mechanical power; T W For mechanical torque; ρ air density; R Where is the blade radius; v Wind speed; This refers to the fan speed; This represents the wind energy utilization coefficient.

[0082] (1.2) Modeling photovoltaics; Formula (2) is the mathematical model for photovoltaics. In formula (2), η PV This is the ratio of the actual output of the photovoltaic unit to its rated power, used to account for losses caused by dirt and shading of the photovoltaic panels and their own aging, and its value is 0.9. P PV This refers to the output power of the photovoltaic unit. P STC The rated power of the photovoltaic unit under standard test conditions; k The power temperature coefficient has a value of -0.0047. G This represents the actual irradiance. G STC The irradiance under standard test conditions is 1000 W / m². 2 ; T STC The temperature under standard test conditions has a value of 25 ℃; T E and T C These are ambient temperature and photovoltaic panel surface temperature, respectively.

[0083] (1.3) Model the micro-turbine and waste heat recovery device; Formula (3) provides the mathematical model for the micro-turbine and waste heat recovery device. In formula (3), P MT This refers to the electrical power output of the micro-engine; F MT This refers to the natural gas consumption of the micro gas turbine; η MT The power generation efficiency of the micro gas turbine; H HR The heat power recovered by the waste heat recovery device; η HR The heat recovery efficiency of the waste heat recovery device; H NG The calorific value of natural gas is 9.7 kWh / m³. 3 .

[0084] (1.4) Model the gas-fired boiler; Formula (4) is the mathematical model for the gas-fired boiler. In formula (4), H GB and η GB These are the heating power and heating efficiency of the gas-fired boiler, respectively. F GB This refers to the natural gas consumption of the gas-fired boiler.

[0085] (1.5) Model the storage battery; Formula (5) is the mathematical model for the storage battery. In formula (5), for t The electrical energy stored in the battery pack at all times; E STC This refers to the capacity of the battery pack under standard test conditions. This refers to the capacity temperature coefficient. for t The temperature of the battery pack surface at all times.

[0086] (1.6) Model the electric chiller; Formula (6) is the mathematical model for the electric chiller. In formula (6), C EC and P EC These are the cooling capacity and electrical power consumed by the electric refrigeration unit, respectively. η EC The refrigeration efficiency of the electric refrigeration unit.

[0087] (1.7) Model the absorption chiller; Formula (7) is the mathematical model for the absorption chiller. In formula (7), C AC This refers to the cooling power output of the absorption chiller unit. H AC The heat power input to the absorption chiller unit; η AC This refers to the refrigeration efficiency of an absorption chiller.

[0088] (1.8) Model the thermal storage tank; Formula (8) provides the mathematical model for the thermal storage tank. In formula (8), They are respectively t Time and t The thermal energy stored in the thermal storage tank at time -1; This is the self-loss coefficient of thermal energy in the thermal storage tank; They are respectively t The heat absorption and release power of the thermal storage tank at all times; These are the heat absorption efficiency and heat release efficiency of the heat storage tank, respectively.

[0089] Step 2: Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives.

[0090] (2.1) Set the decision variables as the output of each device in each time period within the scheduling cycle; Based on formula (9), the decision variables are set as the output of each device in each time period within the scheduling cycle. In formula (9), P Wind , PPV , P Bat , P Grid , P MT , C EC , C AC , H GB , H TST These refer to the output of wind turbines, photovoltaic units, battery banks, power grids, micro gas turbines, electric refrigeration units, absorption chillers, gas boilers, and thermal storage tanks.

[0091] (2.2) Establish the sub-objective function with the lowest operating cost; Based on formula (10), a sub-objective function with the lowest operating cost is established. In formula (10), C Eco Operating costs; C M For equipment maintenance costs; C Loss Equipment depreciation costs; C Grid The interaction cost between the microgrid and the power grid; C Gas For natural gas costs; T To optimize time slots, T =24; for t Time of the first i The output of the equipment; K M,i , L i , r i and C Cost,i The first i Maintenance factor, depreciation period, annual depreciation rate, and installation cost per unit capacity of the equipment; N R,i For the first i Installation capacity of the equipment; They are respectively t The grid unit price and the on-grid unit price at any given time; and They are respectively t The power that the microgrid purchases and sells to the grid; c Gas,out and H NG These are the unit price and calorific value of natural gas, respectively. n Number of equipment types; They are respectively t The output power of gas-fired boilers and micro-turbines at all times.

[0092] (2.3) Establish the sub-objective function with the lowest energy consumption; Based on formula (11), a sub-objective function for minimizing energy consumption is established. In formula (11), TEC Energy consumption refers to the total amount of natural gas consumed. They are respectively t The amount of natural gas consumed by the power grid, gas boilers and micro-turbines at all times.

[0093] (2.4) Establish a sub-objective function that minimizes carbon emissions; Based on formula (12), a sub-objective function for minimizing carbon emissions is established. In formula (12), CDE For carbon emissions; λ e This represents the CO2 emission coefficient during grid power generation. λ f This represents the CO2 emission coefficient of natural gas.

[0094] (2.5) Establish a comprehensive objective function with the lowest operating cost, lowest energy consumption, and lowest carbon emissions as sub-objectives; Based on formula (13), a comprehensive objective function is established with the minimum operating cost, minimum energy consumption, and minimum carbon emissions as sub-objectives. In formula (13), As a comprehensive indicator; Let be the weight coefficient, and satisfy... .

[0095] Step 3: Use the analytic hierarchy process (AHP) to determine the weights of each sub-objective, thus transforming the multi-objective problem into a single-objective problem.

[0096] (3.1) Determine the correspondence between scores and relative importance; The relative importance of the standard layer indicators was scored using a pairwise comparison method and a comparison scale of 1 to 9. Specifically, "equally important" was scored as "1"; "median of equal and slightly important" was scored as "2"; "slightly important" was scored as "3"; "median of slightly important and significantly important" was scored as "4"; "significantly important" was scored as "5"; "median of significantly important and strongly important" was scored as "6"; "significantly important" was scored as "7"; "median of strongly important and extremely important" was scored as "8"; and "extremely important" was scored as "9".

[0097] (3.2) Determine the scores for operating costs, energy consumption, and carbon emissions based on the correspondence between importance and score; The relative importance of operating costs, energy consumption, and carbon emissions is set, and the score of each sub-objective is determined according to the correspondence between importance and score. Compared with energy consumption, the importance of operating costs is considered slightly more important; compared with carbon emissions, the importance of operating costs is also considered slightly more important. The judgment matrix is ​​obtained based on formula (14). .

[0098] (3.3) The judgment matrix is ​​processed according to formula (15) to obtain the eigenvector matrix. Then, the obtained eigenvector matrix is ​​normalized to obtain the weights of operating cost, energy consumption and carbon emissions, which are 0.6, 0.2 and 0.2, respectively. In formula (15), S i To determine the product of the elements in each row of a matrix; The eigenvector matrix; U i For the first i The weight of each indicator.

[0099] (3.4) The operating cost, energy consumption, and carbon emission weights obtained by the analytic hierarchy process are introduced into the comprehensive objective function to obtain the weighted objective function used for solving the chaotic adaptive differential zebra optimization algorithm. The weighted objective function serves as the fundamental function for evaluating individual fitness in the chaotic adaptive differential zebra optimization algorithm. Subsequently, a dimensionless comprehensive fitness function is constructed. .

[0100] Step 4: Construct system constraints, including electrical, thermal, and cooling power balance constraints, energy storage equipment constraints such as batteries and thermal storage tanks, wind turbine and photovoltaic power output constraints, and other equipment operation constraints.

[0101] (4.1) Establish electrical, thermal, and cooling power balance constraints; Based on formula (18), the power balance constraints for electricity, heat, and cold are established. In formula (18), They are respectively t The output power of wind turbines, photovoltaic units, and micro gas turbines at all times; They are respectively t The power purchase and sales capacity of Time Microgrid; They are respectively t The charging and discharging power of the battery pack at all times; They are respectively t The power load demand of the microgrid and the power demand of the electric chiller units; respectively t The thermal power of the waste heat recovery device and the gas boiler; They are respectively t The heat release capacity and heat storage capacity of the thermal storage tank at all times; They are respectively t The heat power consumed by the heat exchanger and absorption chiller unit at all times; They are respectively t The cooling capacity of electric refrigeration units and absorption refrigeration units at any given time; for t The cooling load requirement at any time.

[0102] (4.2) Establish constraints for battery and thermal storage tank equipment; The constraints for the battery equipment are established based on formula (19). In formula (19), for t The state of charge of the battery pack at all times; These represent the minimum and maximum states of charge of the battery pack, respectively. These are the minimum and maximum charging power of the battery pack, respectively. These are the minimum and maximum discharge power of the battery pack, respectively.

[0103] The constraints for the thermal storage tank equipment are established based on formula (20). In formula (20), for t The thermal load status of the heat storage tank at all times; These represent the minimum and maximum heat load states of the thermal storage tank, respectively. These are the minimum and maximum thermal storage capacities of the thermal storage tank, respectively. These represent the minimum and maximum heat release power of the thermal storage tank, respectively.

[0104] (4.3) Establish constraints on wind turbine and photovoltaic power output; Based on formula (21), the output constraints of wind turbines and photovoltaics are established. In formula (21), These represent the maximum active power output of the wind turbine and the photovoltaic unit, respectively.

[0105] (4.4) In order to ensure that the optimization results meet the system operation constraints, the power balance constraints of electricity, heat and cold and the energy storage device constraints are transformed into penalty functions and introduced into the comprehensive fitness function.

[0106] Based on formulas (22)-(26), the following penalty terms are established: electric power balance penalty term, thermal power balance penalty term, cold power balance penalty term, battery state of charge constraint penalty term, and thermal storage tank state of charge constraint penalty term. Therefore, the total constraint penalty function can be established using formula (27). In each iteration of the chaotic adaptive differential zebra optimization algorithm, the weighted objective function value is first calculated based on the weight coefficients obtained in step 3, then the constraint penalty function value is calculated based on the constraint conditions established in step 4, and the individual comprehensive fitness value is calculated according to formula (17). When a scheduling scheme violates the power balance constraint or equipment operation constraint, its penalty function value increases, thereby reducing the fitness of the individual and causing it to be eliminated in the population evolution process.

[0107] Step 5: Set the parameters of the chaotic adaptive differential zebra optimization algorithm, setting the zebra population size to 30, the maximum number of iterations to 500, the maximum scaling factor to 1.6 and the minimum scaling factor to 0.7, and the crossover probability to 0.7.

[0108] Step 6: Initialize the zebra population based on the Tent chaotic mapping strategy to generate a diverse set of initial scheduling schemes covering the entire solution space.

[0109] The Tent chaotic mapping strategy based on formula (21) generates an initial population with high randomness and uncertainty. In formula (21), The first generation generated based on the Tent chaotic mapping strategy initialization i +1 individual.

[0110] Step 7: The chaotic adaptive differential zebra optimization algorithm begins iterative optimization.

[0111] (7.1) Calculate the initial fitness value of the population using the comprehensive fitness function; The overall fitness value of each zebra individual is calculated based on formula (29). The individual with the best overall fitness value is determined as the current optimal solution and used to update the population information.

[0112] (7.2) The population enters the foraging phase in the chaotic adaptive differential zebra optimization algorithm; Based on formula (30), the location of individuals in the population during the foraging phase is updated. In formula (30), for Random numbers within the interval; The position of the vanguard zebra; For population change control parameters; The locations of randomly selected distinct individuals; The scaling factor based on the adaptive parameter strategy is calculated based on formula (31). , in formula (31), These represent the maximum and minimum values ​​of the scaling factor, respectively. This represents the current population fitness variance. The exponential parameter used to control the rate of decrease has a range of values ​​of [value range missing]. Within this range, the scaling factor can be either non-linear or linearly decreasing, both of which ensure algorithm convergence. The linear decrease in time ensures the most even transition between early exploration and later development. Preferably, take... .

[0113] (7.3) The population enters the defense phase in the chaotic adaptive differential zebra optimization algorithm; In the chaotic adaptive differential zebra optimization algorithm, the defense phase of the zebra population is divided into an escape phase based on lion attacks and a counterattack phase based on attacks from other predators. The position of the escape phase is updated according to formula (32). In formula (32), ; Random numbers within the interval; For the first t The chaotic mapping value of the next iteration. ; The positions of the randomly selected distinct individuals are updated according to formula (33) during the counterattack phase. The location of the zebra being attacked ( ); This represents the current globally optimal individual position.

[0114] Step 8: Calculate the comprehensive fitness value of each zebra individual according to formula (17), update the individual optimal position and the global optimal position, and obtain the zebra individual position with the best fitness value in the current iteration of the chaotic adaptive differential zebra optimization algorithm.

[0115] Step 9: Determine whether the Chaotic Adaptive Differential Zebra Optimization Algorithm has reached the maximum number of iterations. If it has, output the current global optimal position (i.e., the optimal scheduling scheme). If not, return to step 7.

[0116] Step 10: Output and execute the optimal scheduling scheme obtained by iterative optimization using the chaotic adaptive differential zebra optimization algorithm to obtain the output plan of each device.

[0117] Table 1 shows the power output plan of each device in the multi-objective optimization scheduling scheme of the smart microgrid in the marine engineering park based on the chaotic adaptive differential zebra optimization algorithm.

[0118] Table 1 Output Plan of Each Equipment 1 120.61 0 0 46.69 0 -35.96 0.03 42.48 -10.79 2 74.87 0 0 46.69 0 6.85 2.24 26.53 -33.64 3 97.74 0 0 46.69 0 -34.88 0.36 30.31 -33.89 4 29.13 0 0 46.69 0 33.46 1.64 22.99 -43.52 5 120.61 0 0 46.69 0 -51.53 2.58 19.50 -11.15 6 120.61 3.12 0 46.69 0 -44.85 1.60 24.88 -9.84 7 74.87 30.72 0 46.69 0 37.37 1.45 34.79 -9.84 8 120.61 61.49 0 46.69 0 38.95 16.87 0 55.42 9 143.48 87.27 0 46.69 0 76.63 33.30 0 70.64 10 150.00 107.035 17.02 46.69 38.31 18.32 36.26 0.07 3.67 11 150.00 119.88 0 46.69 0 -54.865 30.32 0 -17.07 12 150.00 126.12 0 46.69 0 -101.47 21.28 0.13 -42.62 13 143.48 125.49 0 46.69 0.02 -111.04 0.05 94.27 43.00 14 97.74 118.089 0 46.69 0 -21.72 21.17 0.54 -60.58 15 120.61 104.15 -49.24 46.69 0 -6.75 17.79 0.10 -58.51 16 74.87 84.09 -10.93 46.69 0 -6.75 16.18 0.01 -52.35 17 74.87 58.43 0 46.69 0 10.54 1.64 56.41 1.52 18 97.74 28.31 0 46.69 0 44.55 0.17 62.30 21.33 19 0 2.29 121.51 46.69 0 128.31 15.58 5.79 -3.87 20 120.61 0 94.74 46.69 0 72.15 19.86 0.54 20.38 21 29.13 0 265.03 46.69 56.85 0 1.10 87.81 60.50 22 0 0 274.84 46.69 35.20 0 23.16 0.02 0 23 0 0 227.59 46.69 144.62 0 0.28 89.18 0 24 29.13 0 133.47 46.69 34.22 0 18.50 0.60 0

[0119] Step 11: Analyze the scheduling results and select evaluation indicators to assess the scheduling results of the method of the present invention.

[0120] The results are evaluated using formulas (34), (35), (36), and (37). In formula (34), TEC For the natural gas consumed by the microgrid; in formula (35), TEC SES For the natural gas consumed by the distributed energy system; in formula (36), CDE and CDE SES These represent the CO2 emissions from microgrids and distributed energy systems, respectively; in formula (37), C Eco andC Eco , SES These are the operating costs for microgrids and distributed energy systems, respectively.

[0121] The output plan diagram of each device in step 10 is displayed on the computer screen using MATLAB software; and the evaluation effect of each evaluation index in step 11 on the invention is displayed on the computer screen using MATLAB software.

[0122] Through the above steps, the intelligent microgrid optimization scheduling function for marine engineering parks of this invention has been completed.

[0123] In this embodiment, to better demonstrate the effectiveness of the multi-objective optimization scheduling model of the intelligent microgrid in the marine engineering park based on the chaotic adaptive differential zebra optimization algorithm, MATLAB software was used for simulation, and the output plan diagram of each device was output on the computer screen. The results are as follows: Figure 2 As shown, where Figure 2 (a) represents the power balance diagram. The judgment criterion for this diagram is: the total height of the upward-stacking columns + the total depth of the downward-stacking columns = the position of the broken line, i.e., the total power demand. That is, the total power supply minus the total power consumption equals the load demand. The top of the column completely coincides with the broken line, indicating that the power balance constraint is met. The engineering significance of this diagram is: it visually verifies whether "power generation output + power purchase + power discharge" at any given time exactly covers "power load + power consumption of electric chillers + power sales + charging", ensuring the real-time supply and demand balance of microgrid power. Figure 2 (b) in the diagram is a heat power balance diagram. The judgment criterion is: the total height of the upward-stacking columns minus the total depth of the downward-stacking columns equals the position of the broken line, that is: the total heat supply minus the heat storage equals the heat load demand. The top of the column completely coincides with the broken line, indicating that the heat power balance constraint is met. The engineering significance is: this diagram visually verifies whether the coordinated heating of waste heat recovery, gas boilers, and heat storage tanks meets the heat load of the park and the heat energy demand of absorption refrigeration, ensuring the real-time balance of the heat network. Figure 2 (c) in the diagram represents the cooling power balance. The judgment criterion is: the total height of the stacked columns equals the position of the broken line, meaning the sum of the cooling capacity supplied by electric cooling and absorption cooling exactly equals the cooling load demand. The top of the column completely coincides with the broken line, indicating that the cooling power balance constraint is met. The engineering significance is that this diagram visually verifies whether the combined output of the two cooling methods meets the real-time cooling load demand of the park, ensuring cooling reliability.

[0124] To further verify the comprehensive performance of the method of the present invention in multi-objective optimization scheduling of smart microgrids in marine engineering parks, energy efficiency was selected (… η Energy ), fuel saving rate ( η TEC ), CO2 emission reduction rate ( ηCDE ) and cost savings rate ( η Eco Using the same conditions and parameter settings as the evaluation index, the scheduling results based on the chaotic adaptive differential zebra optimization algorithm, the scheduling results based on the gray wolf optimization algorithm, the scheduling results based on the particle swarm optimization algorithm, and the scheduling results based on the zebra optimization algorithm were comprehensively evaluated and compared. The specific evaluation results are shown in Table 2.

[0125] Table 2 Statistical Analysis of Evaluation Results Scheduling results based on particle swarm optimization algorithm 77.02% 59.46% 69.33% 59.88% Scheduling results based on the Grey Wolf algorithm 76.88% 59.35% 68.78% 59.84% Scheduling results based on Zebra Optimization Algorithm 79.12% 60.98% 69.63% 62.78% Scheduling results based on the chaotic adaptive differential zebra optimization algorithm (method of this invention) 79.42% 61.20% 71.25% 62.85%

[0126] As shown in Table 2, in the intelligent microgrid optimization scheduling task, the scheduling result based on the chaotic adaptive differential zebra optimization algorithm of this invention exhibits the best energy efficiency, reaching 79.42%, significantly higher than other comparative methods. Specifically, the result based on the zebra optimization algorithm is 79.12%, the result based on the particle swarm optimization algorithm is 77.02%, and the result based on the gray wolf algorithm is the lowest, at only 76.88%. This indicates that the proposed method effectively improves the overall energy utilization efficiency by introducing a chaotic mechanism and adaptive strategy. In terms of fuel saving rate, this invention also leads, achieving a saving rate of 61.20%, which is better than the zebra optimization algorithm (60.98%), the particle swarm optimization algorithm (59.46%), and the gray wolf algorithm (59.35%), demonstrating its significant advantage in reducing operating energy consumption. Regarding CO2 emission reduction, this invention achieved a score of 71.25%, slightly higher than the Zebra Optimization Algorithm (69.63%) and Particle Swarm Optimization Algorithm (69.33%), while the Gray Wolf Algorithm achieved 68.78%, indicating that this invention has stronger environmental friendliness in promoting green and low-carbon operation. In terms of cost savings, this invention ranked first with 62.85%, followed by the Zebra Optimization Algorithm (62.78%) and Particle Swarm Optimization Algorithm (59.88%), while the Gray Wolf Algorithm had the lowest score (59.84%), reflecting its not only energy efficiency but also good economic practicality. In summary, the scheduling method based on the chaotic adaptive differential Zebra Optimization Algorithm proposed in this invention outperforms traditional intelligent algorithms in all evaluation indicators, demonstrating comprehensive and stable optimization performance, and is suitable for complex multi-objective smart energy system scheduling scenarios.

[0127] In the above embodiments, the equipment modeling of wind turbines, photovoltaics, micro-gas turbines, waste heat recovery devices, gas boilers, batteries, electric chillers, absorption chillers, and thermal storage tanks is existing technology and well known to those skilled in the art; the method of inputting the parameters of the chaotic adaptive differential zebra optimization algorithm into the computer is a known method; the computer, monitor, and MATLAB computer software in the above-mentioned intelligent microgrid optimization scheduling method for marine engineering parks that takes into account economic, energy-saving, and low-carbon goals are all commercially purchased.

[0128] This invention provides a computer device 100, which includes a processor and a non-volatile memory storing computer instructions. When the computer instructions are executed by the processor, the computer device 100 executes the aforementioned optimized scheduling method based on a smart microgrid in an offshore engineering park. Figure 3 As shown, Figure 3 This is a structural block diagram of a computer device 100 provided in an embodiment of the present invention. The computer device 100 includes a memory 111, a processor 112, and a communication unit 113. To enable data transmission or interaction, the memory 111, processor 112, and communication unit 113 are electrically connected to each other directly or indirectly. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0129] In addition, this embodiment also provides a smart microgrid optimization and scheduling system for marine engineering parks, including: The model building module is used to build a smart microgrid system model for marine engineering parks. The system model includes a wind turbine model, a photovoltaic model, a micro gas turbine model, a waste heat recovery device model, a gas boiler model, a battery model, an electric chiller model, an absorption chiller model, and a thermal storage tank model. The fitness function construction module is used to establish a comprehensive objective function with three sub-objectives: the lowest system operating cost, the lowest total fossil energy consumption, and the lowest carbon emissions. It also determines the weight coefficients of each sub-objective in the comprehensive objective function to obtain a weighted objective function. By comprehensively considering the weighted objective function and system constraints, a dimensionless comprehensive fitness function is constructed. The constraint construction module is used to construct constraint conditions including power balance, thermal power balance, and cold power balance, as well as battery state of charge constraints and thermal storage tank state of charge constraints; and to transform the constraint conditions into a total constraint penalty function. The optimization solution module is used to initialize the zebra population using the Tent chaotic mapping strategy, generate a diverse set of initial decision variables covering the entire solution space, initiate the iterative optimization process of the chaotic adaptive differential zebra optimization algorithm, sequentially perform population position updates during the foraging and defense phases in each iteration, calculate the comprehensive fitness value of each zebra individual based on the comprehensive fitness function and the total constraint penalty function, update the individual optimal position and the global optimal position, thereby obtaining the specific values ​​of the current optimal set of decision variables; The output module is used to determine whether the current iteration count has reached the preset maximum iteration count. If it has not reached the maximum iteration count, the iteration continues. If it has reached the maximum iteration count, the optimal scheduling scheme corresponding to the current global optimal position is output, that is, the output plan of each device in each scheduling period. The evaluation module is used to analyze the optimal scheduling scheme and select preset evaluation indicators to evaluate the overall performance of the scheduling scheme in order to verify its economy, energy saving and low carbon emissions.

[0130] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0131] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0132] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0133] For example, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in a smart microgrid optimization scheduling method for offshore engineering parks.

[0134] The computer device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device may include, but is not limited to, a processor and memory.

[0135] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0136] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0137] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0138] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0139] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing the scheduling of a smart microgrid in an offshore engineering park, characterized in that, The method includes the following steps: S1: Construct a smart microgrid system model for the marine engineering park, including wind turbine model, photovoltaic model, micro gas turbine model, waste heat recovery device model, gas boiler model, battery model, electric chiller model, absorption chiller model, and thermal storage tank model; S2: With the three sub-objectives of lowest system operating cost, lowest total fossil energy consumption, and lowest carbon emissions, a comprehensive objective function is established, and the weight coefficients of each sub-objective in the comprehensive objective function are determined to obtain a weighted objective function, and then a dimensionless comprehensive fitness function is constructed. S3: Construct power balance constraints including electric power balance, thermal power balance, and cold power balance, as well as constraint conditions for battery state of charge and thermal storage tank state of heat; and transform the constraint conditions into a total constraint penalty function; S4: The zebra population is initialized using the Tent chaotic mapping strategy to generate a diverse set of initial decision variables covering the entire solution space, i.e., the initial scheduling scheme set. The iterative optimization process of the chaotic adaptive differential zebra optimization algorithm is started. In each iteration, the population position is updated sequentially during the foraging and defense phases. Based on the comprehensive fitness function determined in step S2 and the total constraint penalty function established in step S3, the comprehensive fitness value of each zebra individual is calculated, and the individual optimal position and the global optimal position are updated, thereby obtaining the specific values ​​of the current optimal set of decision variables. S5: Determine whether the current iteration count has reached the preset maximum iteration count. If not, return to step S5 to continue iterating. If it has reached the maximum, output the optimal scheduling scheme corresponding to the current global optimal position, i.e., the output plan of each device in each scheduling period. S6: Analyze the obtained optimal scheduling scheme and select preset evaluation indicators to evaluate the comprehensive performance of the scheduling scheme in order to verify its economy, energy saving and low carbon emissions.

2. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 1, characterized in that, The process of constructing the weighted objective function includes: The sub-objective function that minimizes operating cost is established as follows: ； In the formula, Operating costs; C M For equipment maintenance costs; Equipment depreciation costs; The interaction cost between the microgrid and the power grid; For natural gas costs; The sub-objective function that minimizes energy consumption is established as follows: In the formula, TEC Energy consumption refers to the total amount of natural gas consumed. They are respectively t Real-time natural gas consumption of power grids, gas boilers, and micro-turbines; Establish a sub-objective function that minimizes carbon emissions, expressed as: In the formula, CDE For carbon emissions; This represents the CO2 emission coefficient during grid power generation. This represents the CO2 emission coefficient of natural gas. A comprehensive objective function is established with the sub-objectives of lowest operating cost, lowest energy consumption, and lowest carbon emissions as its constituent objectives, expressed as: In the formula, As a comprehensive indicator; These are the weighting coefficients.

3. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 2, characterized in that, The construction of the dimensionless comprehensive fitness function includes: Weights are obtained using the analytic hierarchy process. The weights are then incorporated into the comprehensive objective function to construct a weighted objective function: ； To eliminate the weighted objective function F With total constraint penalty function Due to the inherent differences in physical dimensions and numerical magnitudes, the two are normalized to construct a dimensionless comprehensive fitness function. Assume the current zebra population size is N In each iteration, the weighted objective function value for all individuals in the population is first calculated. F and the total constraint penalty function value And record the maximum and minimum values ​​in the current population, respectively. Then construct the comprehensive fitness function: ； In the formula, The term is an infinitesimal positive number used to prevent the denominator from being 0. The first term reflects the normalized economic, energy consumption, and carbon emission levels; the second term reflects the degree of constraint violation after normalization. If an individual satisfies all constraints, then After normalization, the penalty function term is 0; if the constraint is violated, the penalty function value increases, and the individual's overall fitness value deteriorates, thus leading to its elimination in the process of population evolution.

4. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 3, characterized in that, The equipment maintenance cost, equipment depreciation cost, interaction cost between the microgrid and the power grid, and natural gas cost are respectively expressed as follows: in, T To optimize time periods; for t Time of the first i The output of the equipment; The first i Maintenance factor, depreciation period, annual depreciation rate, and installation cost per unit capacity of the equipment; N R,i For the first i Installation capacity of the equipment; They are respectively t The grid unit price and the on-grid unit price at any given time; They are respectively t The power that the microgrid purchases and sells to the grid; These are the unit price and calorific value of natural gas, respectively. n Number of equipment types; They are respectively t The output power of gas-fired boilers and micro-turbines at all times.

5. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 4, characterized in that, The step of transforming the constraint into a penalty function includes: The power balance constraints for electrical power balance, thermal power balance, and cold power balance are transformed into penalty functions, including: The power balance penalty term is: The thermal power balance penalty term is: The cold power balance penalty term is: in, These are the penalty coefficients for the power balance constraints of electricity, heat, and cold, respectively. for t The power load demand of the microgrid at any time for t The cooling load requirement at any time, The total heat power consumed by the heat exchanger and absorption chiller; The battery state-of-charge constraints and thermal storage tank thermal state constraints are converted into penalty functions, including: The penalty for the battery state of charge constraint is: The penalty for the thermal storage tank under heat load condition constraint is as follows: in, This is the penalty coefficient for the battery's state of charge constraint. This is the penalty coefficient for the thermal state constraint of the thermal storage tank. for t The state of charge of the battery pack at all times. This represents the maximum state of charge of the battery pack. This represents the minimum state of charge of the battery pack. for t The thermal storage tank is constantly under heat load. These represent the minimum and maximum heat load states of the thermal storage tank, respectively. The total constraint penalty function is expressed as: 。 6. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 5, characterized in that, The sequential execution of population position updates during the foraging and defense phases includes: During the foraging phase, a differential evolution strategy and an adaptive scaling factor are used for position updates. During the defense phase, position updates are performed according to preset zebra defense behavior rules. Specifically: During the foraging phase, individuals use differential evolution strategies to update their positions, enhancing their global exploration capabilities and thus obtaining a better scheduling scheme, mathematically expressed as: In the formula, for Random numbers within the interval; The position of the vanguard zebra; For population change control parameters; The locations of randomly selected distinct individuals; The scaling factor is expressed as: ； In the formula, These represent the maximum and minimum values ​​of the scaling factor, respectively. An exponential parameter used to control the rate of decrease; This represents the current population fitness variance.

7. The method for optimizing and scheduling a smart microgrid in an offshore engineering park according to claim 6, characterized in that, In obtaining the current optimal set of decision variable values, the decision variables are represented as follows: ； in, These refer to the output of wind turbines, photovoltaic units, battery banks, power grids, micro gas turbines, electric refrigeration units, absorption chillers, gas boilers, and thermal storage tanks.

8. A smart microgrid optimization and scheduling system for marine engineering parks, characterized in that, include: The model building module is used to build a smart microgrid system model for marine engineering parks. The system model includes a wind turbine model, a photovoltaic model, a micro gas turbine model, a waste heat recovery device model, a gas boiler model, a battery model, an electric chiller model, an absorption chiller model, and a thermal storage tank model. The fitness function construction module is used to establish a comprehensive objective function with three sub-objectives: lowest system operating cost, lowest total fossil energy consumption, and lowest carbon emissions. It also determines the weight coefficients of each sub-objective in the comprehensive objective function to obtain a weighted objective function, and then constructs a dimensionless comprehensive fitness function. The constraint construction module is used to construct constraint conditions including power balance, thermal power balance, and cold power balance, as well as battery state of charge constraints and thermal storage tank state of charge constraints; and to transform the constraint conditions into a total constraint penalty function. The optimization solution module is used to initialize the zebra population using the Tent chaotic mapping strategy, generate a diverse set of initial decision variables covering the entire solution space, initiate the iterative optimization process of the chaotic adaptive differential zebra optimization algorithm, sequentially perform population position updates during the foraging and defense phases in each iteration, calculate the comprehensive fitness value of each zebra individual based on the comprehensive fitness function and the total constraint penalty function, update the individual optimal position and the global optimal position, thereby obtaining the specific values ​​of the current optimal set of decision variables; The output module is used to determine whether the current iteration count has reached the preset maximum iteration count. If it has not reached the maximum iteration count, the iteration continues. If it has reached the maximum iteration count, the optimal scheduling scheme corresponding to the current global optimal position is output, that is, the output plan of each device in each scheduling period. The evaluation module is used to analyze the optimal scheduling scheme and select preset evaluation indicators to evaluate the overall performance of the scheduling scheme in order to verify its economy, energy saving and low carbon emissions.

9. A computer device, characterized in that, include: One or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the steps of the intelligent microgrid optimization scheduling method for marine engineering parks as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the steps of the marine engineering park smart microgrid optimization scheduling method as described in any one of claims 1 to 7.

Images