Random multi-objective optimization method and system for industrial park integrated energy system
By adopting a random multi-objective optimization method in the integrated energy system of industrial parks, building a double-layer optimization objective function and performing mixed integer linear planning solutions, the problem that traditional methods cannot take into account both economic, environmental protection and safety is solved, and efficient Economic and safe energy management.
Patent Information
- Application Number
- CN202411425827.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-14
- Publication Date
- 2024-11-08
AI Technical Summary
The existing technology is difficult to coordinately optimize economic, environmental protection and safety in the integrated energy system of industrial parks. Especially in the face of renewable energy uncertainty, traditional deterministic optimization methods cannot take into account the multiple uncertainties of the system. .
Random multi-objective optimization method is adopted to model the light intensity and wind speed to generate random scenes, reduce the scene by using clustering method, build a double-layer optimization objective function of carbon emissions, operating costs and safety, and use mixed integer linear planning. The method is optimized and solved to achieve multi-objective optimization.
It has improved energy utilization efficiency and system management costs, significantly improved the comprehensive energy management level of industrial parks, balanced economy, environmental protection and safety, and achieved sustainable development.
Smart Images

Figure CN118917500A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of energy optimization, and in particular to a random multi-objective optimization method and system for an integrated energy system of an industrial park. Background Art
[0002] An integrated energy system is an energy system that integrates energy production, consumption, conversion and storage systems to meet various energy needs and achieve a balance between energy production and consumption. An integrated energy system contains multiple energy carriers and can be defined as a multi-carrier energy system. Through energy interaction and cascade utilization, the system can improve energy consumption efficiency and reduce operational challenges of different energy sources, such as renewable energy, electricity, heat, and gas. The typical structure of an integrated energy system can be composed of power generation, distributed energy, energy storage system, cogeneration, boilers, chillers and other equipment.
[0003] At present, most of the research on the integrated energy system of industrial parks uses deterministic optimization methods to guide the operation of the integrated energy system. For strongly random renewable energy, the scheduling optimization results of the deterministic optimization method are difficult to take into account the deviation between the uncertainty of renewable energy and the actual situation, and the optimization results have limitations. In addition, most of the existing optimization guidance for integrated energy systems is based on economic efficiency, and there is a lack of research on other needs. In summary, it is difficult for traditional methods to coordinate and optimize the scheduling of the integrated energy system of industrial parks with multiple uncertainties, and it is impossible to take into account the goals of system economy, environmental protection and safety. Therefore, it is necessary to propose a new optimization framework for the above problems. Summary of the invention
[0004] In order to solve the above problems, the present invention proposes a stochastic multi-objective optimization method and system for an integrated energy system of an industrial park. Through a two-layer multi-objective function design based on carbon emissions, operating costs and safety, various factors affecting the operation process of the integrated energy system are fully considered, and the consideration is more comprehensive and reasonable, thereby achieving a scheduling optimization result for the integrated energy system of an industrial park. At the same time, the uncertainty of renewable energy data is considered in the optimization process.
[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a random multi-objective optimization method for an integrated energy system of an industrial park, comprising: Model the light intensity and wind speed in the industrial park and generate random scenarios; Using a clustering method to reduce the random scene; The typical scenarios of light intensity and wind speed obtained by clustering are input into wind turbines and photovoltaic generators to obtain the equipment output information under typical scenarios; Considering the carbon emissions, operating costs and safety of the system, the objectives are divided into primary and secondary objective functions according to their importance, and a two-layer optimization objective function is constructed; Based on the equipment output information, the double-layer optimization objective function is optimized and solved using a mixed integer linear programming method to achieve multi-objective optimization.
[0006] Preferably, the light intensity and wind speed of the industrial park are modeled to generate random scenarios, including: constructing a wind speed scenario based on Weibull distribution:
[0007]
[0008] Where PDF(·) represents the Weibull probability density function; is the actual wind speed; is the scale parameter; is the shape parameter; It is an important parameter in Weibull distribution, which is used to determine the shape of the distribution density curve. represents the variance, represents the mean; Used to zoom in or out on the curve. represents the gamma function.
[0009] Preferably, the method further comprises: constructing a lighting scene based on Beta distribution:
[0010]
[0011] in, Indicates the intensity of solar radiation; and is the shape parameter.
[0012] Preferably, the random scenes are reduced by using a clustering method, specifically: the random scenes are reduced by using an improved K-means clustering method; the improved K-means clustering method selects centroids based on parameter density and measures similarity based on mutual information.
[0013] Preferably, the main objective function is the minimization optimization of the system operation cost, and the secondary objective function is the minimization optimization of the pollutant emission index, the average reserve index and the energy shortage index.
[0014] Preferably, the two-layer optimization objective function is optimized and solved to achieve multi-objective optimization as follows: Based on the initial constraints, calculate the optimal total operating cost of the main objective function; The optimal total operating cost is taken as a constraint of the secondary objective function, and a compromise programming method is used to find the optimal solution.
[0015] Preferably, the mixed integer linear programming method is specifically:
[0016] in, is a linear objective function, is a column vector of constants, is a column vector of differential indices; the inequality constraints and equality constraints are used to represent The boundaries, linear constraints, and Restrictions on some components of . A, b, Aeq, beq, lb, and ub are custom parameters.
[0017] In a second aspect, the present invention provides a stochastic multi-objective optimization system for an integrated energy system of an industrial park, comprising: The scenario generation module is used to model the light intensity and wind speed of the industrial park and generate random scenarios; A reduction module, used for reducing the random scene by using a clustering method; An information generation module is used to input the typical scenarios of light intensity and wind speed obtained by clustering into wind turbines and photovoltaic generators to obtain equipment output information under typical scenarios; The objective function construction module is used to consider the carbon emissions, operating costs and safety of the system, and divide it into primary objective functions and secondary objective functions according to their importance to construct a two-layer optimization objective function; The optimization module is used to optimize and solve the double-layer optimization objective function based on the equipment output information by using a mixed integer linear programming method to achieve multi-objective optimization.
[0018] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the random multi-objective optimization method for an industrial park integrated energy system described in the first aspect.
[0019] In a fourth aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the random multi-objective optimization method for an industrial park integrated energy system described in the first aspect are implemented.
[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. From the perspective of energy utilization efficiency and system management cost, the present invention effectively reduces random scenarios through precise modeling and cluster analysis of light intensity and wind speed, thereby guiding the output prediction of wind and photovoltaic generators. This method not only constructs a two-layer optimization objective function covering carbon emissions, operating costs and safety, but also uses mixed integer linear programming for solution, achieving efficient, economical and safe energy utilization, and significantly improving the comprehensive energy management level of industrial parks.
[0021] 2. The present invention targets the impact of uncertainty in light intensity and wind speed in renewable energy power generation equipment on the stable operation of the integrated energy system of the industrial park. Based on Weibull distribution and Beta distribution, the random characteristics of wind speed and light intensity are modeled respectively to generate random scenarios of wind speed and light intensity, thereby improving the accuracy of simulating the random characteristics of wind speed and light intensity.
[0022] 3. An improved K-means clustering method proposed in the present invention is applied to the reduction of random scenes of renewable energy. The improved K-means clustering algorithm adopts a density-based initial cluster center selection method in cluster center selection, and updates a method of using mutual information to calculate data distance in clustering scheme; by reducing random energy scenes, a small number of representative scene sets can be extracted from a large number of possible energy scenes. This reduction helps to reduce the complexity of the problem and the scale of calculation, thereby improving the speed and efficiency of calculation. The reduction method of the present application can select a representative scene set that can cover the main characteristics and distribution patterns of the original data. The K-means algorithm improved based on density selection and mutual information can well improve the stability and accuracy of the detection effect.
[0023] 4. The present invention proposes a two-layer multi-objective function optimization method, which divides the issues of economy, environmental protection, safety, etc. concerned in the operation of the comprehensive energy system of the industrial park according to their importance, regards the operating cost that is the focus of attention in the system operation as the main objective function, and the carbon emissions, power shortage rate and average energy storage index in the system operation as secondary objective functions, and guides the operation of the comprehensive energy system of the industrial park through a mixed integer linear programming method. Among them, clearly taking the operating cost as the main objective function is conducive to giving priority to economic factors in the resource allocation and decision-making process, which helps to minimize costs and improve the economic benefits of the industrial park; although economy is the main concern, by taking carbon emissions, power shortage rate and average energy storage index as secondary objective functions, environmental protection and safety can be taken into account while ensuring economic benefits. The multi-objective optimization method of the present invention can balance different interests to a certain extent and achieve sustainable development.
[0024] 5. The present invention proposes a load dispatching method that applies a price-based demand response program to an industrial park, shifting the flexible load in the industrial park from peak hours to off-peak hours, reducing the system's energy purchase cost, and improving the economy of the system's energy use.
[0025] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their description are used to explain the present invention but do not constitute a limitation of the present invention.
[0027] Figure 1 A main flow chart of a random multi-objective optimization method for an industrial park integrated energy system provided by an embodiment of the present invention; Figure 2 A detailed flow chart of a random multi-objective optimization method for an integrated energy system of an industrial park provided by an embodiment of the present invention; Figure 3 The composition structure of the industrial park comprehensive energy system provided by the embodiment of the present invention. DETAILED DESCRIPTION
[0028] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0029] Embodiment 1 like Figure 1 As shown, this embodiment discloses a random multi-objective optimization method for an integrated energy system of an industrial park, comprising the following steps: S1: Model the light intensity and wind speed of the industrial park and generate random scenarios; S2: reducing the random scene by using a clustering method; S3: Input the typical scenarios of light intensity and wind speed obtained by clustering into the wind turbine generator set and the photovoltaic generator set to obtain the equipment output information under the typical scenario; S4: Considering the carbon emissions, operating costs and safety of the system, the two objective functions are divided into primary objective functions and secondary objective functions according to their importance, and a two-layer optimization objective function is constructed; S5: Based on the equipment output information, the double-layer optimization objective function is optimized and solved using a mixed integer linear programming method to achieve multi-objective optimization.
[0030] Next, combine Figure 2 , a random multi-objective optimization method for an industrial park integrated energy system disclosed in this embodiment is described in detail.
[0031] During the operation of the integrated energy system, there are uncertain parameters, such as solar radiation intensity and wind speed. The above uncertain parameters have inherent probabilities. Therefore, the present invention uses classical probability distribution functions to generate random weather scenarios to describe the uncertainty of renewable energy power generation.
[0032] In this embodiment, the probability distribution function based on historical data is regarded as the input of each uncertain parameter, and the specific steps of S1 are as follows: S101: According to the output of renewable energy power generation, the wind speed is determined to be a Weibull probability density function distribution, as shown in formulas (1) and (2).
[0033] (1) (2) Where PDF(·) represents the Weibull probability density function; is the actual wind speed; is the scale parameter. It is an important parameter in Weibull distribution and is a shape parameter that determines the shape of the distribution density curve. represents the variance, Represents the mean. It has the effect of enlarging or shrinking the curve, but does not affect the shape of the distribution. represents the gamma function. The cumulative distribution function of the Weibull distribution is: (3) S102: The output power of photovoltaics is mainly affected by the intensity of solar radiation, which is related to the position of the sun, the geographical location of the photovoltaic power generation equipment, and weather conditions. Studies have shown that the intensity of solar radiation over a period of time conforms to the beta probability density function distribution, as shown in formulas (4) and (5).
[0034] (4) (5) in, Indicates the intensity of solar radiation; and is the shape parameter.
[0035] Since a large number of probability density function data sets will affect the optimization efficiency of the integrated energy system of the industrial park, typical scenarios should be obtained based on clustering algorithms when a large number of scenarios are generated by typical probability density functions. This is used to achieve the scheduling optimization of the integrated energy system of the industrial park and provide typical random scenarios while meeting the uncertainty requirements of the energy supply system.
[0036] This embodiment further improves the K-means clustering algorithm and proposes an improved K-means clustering method based on density selection and mutual information. The specific steps of S2 are as follows: In the traditional K-means algorithm clustering process, the initial cluster center is selected randomly, which will lead to inappropriate point selection in the initial cluster centroid selection, such as the selection of the initial cluster center includes edge points and isolated points; the above centroid will inevitably increase the clustering effect of the algorithm and the time complexity of implementation, and may eventually cause the experimental results to be far apart. In order to solve this problem, this embodiment proposes an improved density-based selection K-means algorithm to determine the initial cluster centroid.
[0037] S201: First determine the initialization parameters, two sets of data objects and , initialize the centroid set , density parameter set , the average distance parameter Two groups of data objects, as shown in equations (6) and (7): (6) (7) in, , , Represents location data.
[0038] S202: Calculate the Euclidean distance according to formula (8), and calculate the set of density parameters of all data objects , As shown in formula (9): (8) (9) in, , Represents the Euclidean distance between data.
[0039] S203: is the average of all Euclidean distances. If Less than , then the corresponding Add 1, and the final Update to middle; S204: Calculate according to the formula , Represents the data object with the smallest density parameter value, corresponding to the first cluster center .
[0040] (10) S205: Based on this, the distance between other data objects and the cluster center is calculated according to the formula, and they are sorted in ascending order of distance to obtain the corresponding new centroid. : (11) Among them, S represents the ascending order of the distance between other data objects and the cluster center C1.
[0041] S206: Calculate the remaining centroids according to formula (12) to obtain all centroids.
[0042] (12) The general K-means method uses Euclidean distance as a measure of similarity between data. Euclidean distance focuses on the absolute value of the dimension value difference, which is beneficial for numerical data, but is mostly hard division for some non-numerical data. In order to better reflect the relationship between data and improve the accuracy of the K-means algorithm, this embodiment introduces mutual information as a similarity measure.
[0043] Mutual information comes from information theory. It can effectively describe the degree of mutual inclusion between two data. In the renewable energy scenarios generated by the probability density function, the scenarios generated by the same probability density function are similar to a large extent. According to this method, data clustering can be achieved by the degree of mutual inclusion between data. The clustering steps based on mutual information are as follows: S211: The centroid set obtained from step 1 , the mutual information between each data object in the data set and each initial cluster centroid is calculated, as shown in formula (13).
[0044] (13) in, Indicates that mutual information is calculated between each data object and each initial cluster center.
[0045] S212: Divide the objects with the largest mutual information into related clusters The clustering process ends when all data are divided into corresponding clusters.
[0046] S213: The corresponding cluster centroid is the typical scene, and the calculation formula of the scene occurrence probability is shown in formula (14): (14) in, Representation and The amount of associated data; Represents the total number of samples.
[0047] In S3, the typical scenarios of wind speed and light intensity obtained by clustering are input into the wind turbine generator set and the photovoltaic generator set to obtain the equipment output under the typical scenario. The mathematical models of the wind turbine generator set and the photovoltaic generator set are shown in the following equations (15) and (16): (15) (16) in, Indicates the hourly output power of the photovoltaic generator set; Represents the area of the photovoltaic panel; Indicates the power generation efficiency of photovoltaic panels; Indicates the sequence number of the scene; Indicates the total number of scenes; Indicates the probability of occurrence of the scenario; Indicates light intensity; Indicates i Energy hubs; Indicated in i Energy Hub, s Hourly output power of wind turbines in each scenario; Indicates hourly wind speed; Indicates the cut-in wind speed of the wind turbine; Indicates the cut-out wind speed of the wind turbine; Indicates the maximum output power of the wind turbine generator set; Indicates the rated power of the wind turbine generator set; In S4, the carbon emissions, operating costs and safety of the system are considered, and the main objective function and the secondary objective function are divided according to their importance to construct a two-layer optimization objective function. The specific steps are as follows: S401: Aiming at the economic problem of the operation of the integrated energy system of multiple industrial parks, the present invention takes the minimization of the system operation cost as the main objective function, so the total operation cost of the integrated energy system ( ) is shown in the following formula: (17) in, represents the total cost of electricity exchanged between the industrial park integrated energy system and the upstream power grid, represents the cost of natural gas purchased by the industrial park's integrated energy system, represents the cost of hot water purchased by the integrated energy system of the industrial park, represents the heat storage cost within the integrated energy system of the industrial park, represents the cooling cost within the integrated energy system of the industrial park, represents the charging and discharging cost of electric vehicles within the integrated energy system of the industrial park, represents the operating cost of photovoltaic power generation and solar cells in industrial parks, represents the operating cost of wind turbines in industrial parks, represents the load reduction cost in the industrial park, represents the costs associated with demand response in the industrial park, Represents the CO2 emission cost of the industrial park.
[0048] The total cost of electricity exchange between the integrated energy system and the upstream power grid is shown in formula (18): (18) in, represents the electricity price set by the upstream power grid, Represents the interactive electricity volume between the integrated energy system and the upstream power grid. Indicates the time interval. In this embodiment, the time interval is hourly.
[0049] The cost of natural gas and hot water purchased by the industrial park integrated energy system is shown in equations (19) and (20): (19) (20) in, represents the natural gas price set by the gas company, Indicates the amount of gas consumed by the integrated energy system. Indicates the hot water price set by the heating company. Indicates the amount of hot water consumed by the integrated energy system.
[0050] The cost of heat storage, cold storage and charging and discharging of electric vehicles within the industrial park's integrated energy system is shown in equations (21)-(23): (twenty one) (twenty two) (twenty three) in, represents the operating cost of the thermal storage system, Indicates the amount of heat stored in the hot water storage tank. Indicates the heat released from the hot water storage tank. represents the operating cost of the cold storage system, Indicates the amount of cold stored in the ice storage device. Indicates the amount of cold released from the ice storage device. represents the operating cost of a plug-in electric vehicle, Indicates the amount of electricity charged to the electric vehicle. Indicates the electrical energy released from an electric vehicle.
[0051] The operating costs of photovoltaic power generation, solar cells and wind turbines in industrial parks are shown in equations (24) and (25): (twenty four) (25) in, is the operation and maintenance cost of the photovoltaic generator set; Indicates the hourly output power of the photovoltaic generator set; represents the operation and maintenance cost of photovoltaic panels; Indicates the thermal power output of the photovoltaic panel hourly; represents the operation and maintenance cost of the wind turbine; Indicates the hourly output power of the wind turbine generator set. Represents the operation and maintenance cost coefficient.
[0052] The load reduction cost in the industrial park is shown in formula (26): (26) in, represents the penalty function for load shedding; Indicates the amount of electrical load reduction.
[0053] The CO2 emission cost of the industrial park is shown in formula (27): (27) in, is the price of carbon dioxide emissions; , and are the CO2 emission coefficients of the cogeneration unit, gas boiler and diesel generator set respectively; and They are the power generation and heating capacity of the cogeneration unit respectively; The heating capacity of the gas boiler; The power generation of the diesel generator set.
[0054] The cost associated with the demand response of the industrial park is shown in formula (28), where the price of demand response is shown in formula (29): (28) (29) in, , , , and They are the demand response prices for hot water, natural gas, cooling load, heating load and electrical load respectively; and They represent load upshift and load downshift in response to hot water demand respectively; and They represent load upshift and load downshift of natural gas demand response respectively; and They represent load upshift and load downshift of cooling load demand response respectively; and They represent load upshift and load downshift of heat load demand response respectively; and They represent load upshift and load downshift of electric load demand response respectively; Represents the price factor of demand response; E, W, G, C, and H represent electricity load, hot water load, natural gas load, cooling load, and heating load, respectively.
[0055] In addition to fixed loads, there are also a certain amount of transferable loads in the industrial park load. Adjusting the transferable load within a day will not affect the normal production of the industrial park. In order to relieve the pressure on the upper energy supply system, the upper energy company will give a time-of-use energy price to guide the park to adjust its own equipment to achieve the effect of smoothing load fluctuations. Based on the above two conditions, this embodiment takes the economic efficiency of the operation of the industrial park as the objective function, and guides the park to adjust the operating time of the equipment related to the transferable load under the guidance of the time-of-use price, so that the equipment works during the period with lower energy prices, thereby improving the overall economic efficiency of the system on a typical day. Therefore, formula (26) calculates the relevant costs of the equipment after the industrial park load is adjusted by demand response.
[0056] S402: In view of the environmental protection, reliability and flexibility of the integrated energy system of the industrial park in the energy supply process, the present invention constructs pollutant emission indicators, average reserve indicators and energy shortage indicators as secondary objective functions, and the calculation results of the above three objective functions are shown in the following equations (30)-(32). Equations (33)-(35) represent the emissions generated by the cogeneration unit, boiler and diesel generator set in the integrated energy system.
[0057] (30) (31) (32) (33) (34) (35) in, Indicates the amount of electricity load reduction at each moment; , , They represent the heat storage, cold storage, and electric vehicle charging and discharging capacity within the comprehensive energy system of the industrial park respectively; , , They are emissions from combined heat and power units, gas boilers and diesel generators, respectively; , , They represent the gas emissions from cogeneration units, gas boilers and diesel generators respectively; and They are the power generation and heating capacity of the cogeneration unit respectively; The heating capacity of the gas boiler; The power generation of the diesel generator set.
[0058] In S5, based on the equipment output information, the mixed integer linear programming method is used to optimize and solve the double-layer optimization objective function to achieve multi-objective optimization. The specific steps are: This embodiment proposes a multi-objective optimization framework, which simultaneously considers the system operation cost, pollutant emission index, average energy storage index and energy shortage index of the comprehensive energy system of the industrial park.
[0059] S501: Under the guidance of the best economic solution, the system operation cost index is determined as the main objective function, so the optimization framework is first formulated as a stochastic single-objective optimization with constraints, as shown in formula (36): (36) (37) S502: Calculate the optimal total operating cost from S501, and use the optimal total operating cost as the input of the second step, as a constraint of the secondary optimization target, to ensure that the total cost of the system remains unchanged during the secondary optimization process. The secondary optimization can be formulated as: (38) S503: For the multi-objective optimization problem in S502, a compromise planning method is used to solve the optimal solution. The compromise planning can be expressed as shown in formula (39): (39) in, represents the weight of the i-th working condition; represents the objective function corresponding to the i-th working condition; , They represent the maximum and minimum values of the objective function corresponding to the i-th working condition respectively; P represents the compromise penalty factor.
[0060] S504: The above two-level multi-objective optimization for the integrated energy system of the industrial park is implemented based on the mixed integer linear programming method. The elements of the mixed integer linear programming problem include: linear objective function ,in is a column vector of constants, is a column vector of differential indices; the inequality constraints and equality constraints are used to represent The boundaries, linear constraints, and The values of parameters A, b, Aeq, beq, lb, and ub can be customized. Therefore, the solution vector The expression of is shown in formula (40): (40) Figure 3 The stochastic multi-objective optimization method proposed in this embodiment is based on the comprehensive energy system structure for industrial loads. Figure 3 The integrated energy system is realized through Figure 3 The multi-energy coupling equipment in the industrial park can meet the cooling, heating and electrical load requirements.
[0061] Embodiment 2 This embodiment provides a stochastic multi-objective optimization system for an industrial park integrated energy system, including: The scenario generation module is used to model the light intensity and wind speed of the industrial park and generate random scenarios; A reduction module, used for reducing the random scene by using a clustering method; An information generation module is used to input the typical scenarios of light intensity and wind speed obtained by clustering into wind turbines and photovoltaic generators to obtain equipment output information under typical scenarios; The objective function construction module is used to consider the carbon emissions, operating costs and safety of the system, and divide it into primary objective functions and secondary objective functions according to their importance to construct a two-layer optimization objective function; The optimization module is used to optimize and solve the double-layer optimization objective function based on the equipment output information by using a mixed integer linear programming method to achieve multi-objective optimization.
[0062] Embodiment 3 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the random multi-objective optimization method for an industrial park integrated energy system as described in the above-mentioned embodiment 1 are implemented.
[0063] Embodiment 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the random multi-objective optimization method for an industrial park integrated energy system as described in the above-mentioned embodiment 1 are implemented.
[0064] The steps or modules involved in the above embodiments 2 to 4 correspond to those in embodiment 1. For the specific implementation, please refer to the relevant description of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.
[0065] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A stochastic multi-objective optimization method for an integrated energy system in an industrial park, characterized in that: include: Model the light intensity and wind speed in the industrial park and generate random scenarios; Using a clustering method to reduce the random scene; The typical scenarios of light intensity and wind speed obtained by clustering are input into wind turbines and photovoltaic generators to obtain the equipment output information under typical scenarios; Considering the carbon emissions, operating costs and safety of the system, the objectives are divided into primary and secondary objective functions according to their importance, and a two-layer optimization objective function is constructed; Based on the equipment output information, the double-layer optimization objective function is optimized and solved using a mixed integer linear programming method to achieve multi-objective optimization.
2. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 1, characterized in that: The light intensity and wind speed of the industrial park are modeled to generate random scenarios, including: constructing wind speed scenarios based on Weibull distribution: Where PDF(·) represents the Weibull probability density function; is the actual wind speed; is the scale parameter; is the shape parameter; It is an important parameter in Weibull distribution, which is used to determine the shape of the distribution density curve. represents the variance, represents the mean; Used to zoom in or out on the curve. represents the gamma function.
3. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 2, characterized in that: Also includes: Construct a lighting scene based on the Beta distribution: in, Indicates the intensity of solar radiation; and is the shape parameter.
4. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 1, characterized in that: The method of reducing the random scenes by using a clustering method is specifically: reducing the random scenes by using an improved K-means clustering method; the improved K-means clustering method selects centroids based on parameter density and measures similarity based on mutual information.
5. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 1, characterized in that: The main objective function is to minimize and optimize the system operation cost, and the secondary objective function is to minimize and optimize the pollutant emission index, the average reserve index and the energy shortage index.
6. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 1, characterized in that: The two-layer optimization objective function is optimized and solved to achieve multi-objective optimization as follows: Based on the initial constraints, calculate the optimal total operating cost of the main objective function; The optimal total operating cost is taken as a constraint of the secondary objective function, and a compromise programming method is used to find the optimal solution.
7. The random multi-objective optimization method for the integrated energy system of an industrial park according to claim 1, characterized in that: The mixed integer linear programming method is specifically: in, is a linear objective function, is a column vector of constants, is a column vector of differential indices; the inequality constraints and equality constraints are used to represent The boundaries, linear constraints, and Restrictions on some components of . A, b, Aeq, beq, lb, and ub are custom parameters.
8. A stochastic multi-objective optimization system for an integrated energy system in an industrial park, characterized in that: include: The scenario generation module is used to model the light intensity and wind speed of the industrial park and generate random scenarios; A reduction module, used for reducing the random scene by using a clustering method; An information generation module is used to input the typical scenarios of light intensity and wind speed obtained by clustering into wind turbines and photovoltaic generators to obtain equipment output information under typical scenarios; The objective function construction module is used to consider the carbon emissions, operating costs and safety of the system, and divide it into primary objective functions and secondary objective functions according to their importance to construct a two-layer optimization objective function; The optimization module is used to optimize and solve the double-layer optimization objective function based on the equipment output information by using a mixed integer linear programming method to achieve multi-objective optimization.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the stochastic multi-objective optimization method for an industrial park integrated energy system as described in any one of claims 1 to 7 are implemented.
10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the steps in the stochastic multi-objective optimization method of the industrial park integrated energy system as described in any one of claims 1-7.
Citation Information
Patent Citations
Method for establishing comprehensive energy system random optimization model considering scene simulation
CN111144668A
Park integrated energy system economic configuration method for promoting renewable energy consumption
CN111342451A
Multi-park integrated energy system multi-objective optimization method and system
CN116227167A
Micro-energy network group hierarchical optimization control method and system based on scene construction
CN116436085A
Wind, light, diesel, hydrogen and storage micro-grid multi-target double-layer optimization method and system
CN117650580A
