A hierarchical scheduling optimization method for high-energy-consumption industrial microgrid based on load classification

Abstract

The application discloses a kind of high-energy-consuming industrial microgrid hierarchical scheduling optimization methods based on load classification, it is related to high-energy-consuming industrial microgrid optimization technical field, including clustering analysis to high-energy-consuming industrial microgrid load, identify load group with similar characteristics and extract key features;According to load clustering result, load is classified;Establish the mathematical model of high-energy-consuming industrial microgrid, ensure the coordinated optimization and operating efficiency of each subsystem by hierarchical scheduling optimization.The method described in the application is based on clustering analysis result, classifies high-energy-consuming industrial microgrid load, improves the accuracy and applicability of load classification, by establishing accurate high-energy-consuming industrial microgrid mathematical model, can more accurately and comprehensively describe high-energy-consuming industrial load characteristics, by hierarchical scheduling optimization, and establish the hierarchical coordinated optimization model of high-energy-consuming industrial microgrid, realize the coordinated optimization of each subsystem in microgrid, improve the overall performance of system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of high-energy-consumption industrial micro-grid optimization, in particular to a high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification. BACKGROUND

[0002] With the rapid development of high-energy-consumption industries, industrial micro-grids as a flexible energy system to support high-energy-consumption industries are attracting more and more attention. However, the existing technology still has obvious deficiencies in load analysis and classification, mathematical model construction, and optimization model design, which restricts the further development of high-energy-consumption industrial micro-grids.

[0003] In terms of load analysis and classification, the existing technology usually adopts traditional statistical analysis methods. Traditional statistical analysis methods can describe the basic characteristics of the load to some extent. However, for high-energy-consumption industrial loads, their characteristics are complex and have significant dynamic changes and diversity. Existing statistical analysis methods are usually difficult to accurately capture the characteristic correlation between loads, resulting in inaccurate identification and classification results.

[0004] In terms of mathematical model construction, traditional micro-grid load mathematical models are mostly based on overly simplified assumptions, such as assuming that loads are translatable or have fixed categories. Although such simplified assumptions help reduce computational complexity, they cannot accurately reflect the complex characteristics of high-energy-consumption industrial loads, especially the nonlinear and uncertain characteristics of loads in dynamic changing environments. In addition, traditional models fail to consider the mutual correlation between different loads and their impact on the overall operation efficiency of the micro-grid, limiting the applicability of existing models in load management and scheduling optimization.

[0005] In terms of optimization model design, the optimization models in the existing technology are mostly based on single-layer structures, and their objectives are often focused on the optimal solution of a single task. However, various subsystems within industrial micro-grids, such as power generation, energy storage, and load sides, have close collaborative relationships. The design of such single optimization models fails to effectively reflect the global coordination within the micro-grid. In addition, existing optimization models often lack support for hierarchical optimization when solving complex scenarios, making it difficult to balance global benefits and the dynamic adjustment capabilities of local subsystems. This deficiency not only limits the operation efficiency of the micro-grid but also may lead to energy waste and cost increases. SUMMARY

[0006] In view of the above problems, the present application is proposed.

[0007] Therefore, the technical problem solved by the present application is that the existing high-energy-consumption industrial micro-grid load management method has insufficient load classification accuracy, the mathematical model cannot comprehensively reflect the load characteristics, the optimization model lacks hierarchical scheduling capability, and how to realize the collaborative optimization and efficient operation of various subsystems within the micro-grid.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: a hierarchical scheduling optimization method for high-energy-consuming industrial microgrids based on load classification, comprising clustering analysis of high-energy-consuming industrial microgrid loads, identifying load groups with similar characteristics and extracting key features; classifying loads according to the load clustering results; establishing a mathematical model of the high-energy-consuming industrial microgrid, and ensuring the coordinated optimization and operating efficiency of each subsystem through hierarchical scheduling optimization.

[0009] As a preferred solution of the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids described in the present invention, the clustering analysis of the loads of high-energy-consuming industrial microgrids includes collecting historical load data, processing outliers and missing values ​​in the data, extracting load features, clustering the load data using the density-based DBSCAN algorithm, dividing the loads into several clusters, and excluding abnormal load points. The distance between all data points is calculated based on the Euclidean distance, which is expressed as:

[0010]

[0011] Among them, p i is the power value of the i-th load data point, p j is the power value of the jth load data point, For p i The value in the nth dimension, For p j The value in the nth dimension; calculate all points within the threshold ∈ distance of the load data point p to form the ∈ neighborhood of the load data point p, which is expressed as:

[0012] N ∈ (p)={q∈D}|dist(p,q)≤∈

[0013] Among them, N ∈ (p) is the set of all points whose distance from the load data point p does not exceed the threshold ∈, D is the load data point dataset, q is the load data point different from p, dist(p,q) is the Euclidean distance between the load data point p and the load data point q, ∈ is the distance threshold for judging the neighborhood; whether it is a core point is determined according to the number of neighborhood points, which is expressed as:

[0014]

[0015] Among them, minPts is the minimum number of neighborhood points for judging the core point. If the neighborhood N of the load data point p is ∈ The number of points in (p) |N ∈ (p)| is greater than or equal to the minimum number of neighborhood points minPts, then the load data point p is the core point. If the neighborhood N of the load data point p is greater than or equal to the minimum number of neighborhood points minPts, then the load data point p is the core point.∈ The number of points in (p) |N ∈ (p)| is less than the minimum number of neighborhood points minPts, then the load data point p is not a core point.

[0016] As a preferred solution of the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids of the present invention, the clustering analysis of the loads of high-energy-consuming industrial microgrids further includes evaluating the clustering effect by the Davidson-Boulding index and the silhouette coefficient, which is expressed as:

[0017]

[0018] Where DB is the Davidson-Botting index, k is the number of clusters, σ i is the average distance of cluster i, σ j is the average distance of cluster j, d ij is the distance between clusters i and j.

[0019] As a preferred solution of the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids described in the present invention, the loads are classified into controllable loads and uncontrollable loads according to the load clustering results.

[0020] As a preferred solution of the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids described in the present invention, the adjustable loads include time-limited transferable loads, continuous shiftable loads and all adjustable loads; if the load is a time-limited transferable load, the operating time period can be adjusted within a predetermined time range without affecting the production task; if the load is a continuously shiftable load, the start-up time can be flexibly adjusted according to the sequence requirements of the production line, and the normal operation of the production line can still be ensured after adjustment.

[0021] As a preferred solution of the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids of the present invention, the mathematical model of the high-energy-consuming industrial microgrid includes establishing power models of photovoltaic and wind turbine generator sets, which are expressed as:

[0022]

[0023] in, is the output power of photovoltaic and wind turbine at time t, is the maximum output power of photovoltaic and wind turbine at time t; establish the gas turbine power model, which is expressed as:

[0024]

[0025] in, are the electrical and thermal power output of the gas turbine at time t, is the natural gas power consumed by the gas turbine at time t, are the energy conversion efficiencies of the gas turbine output electric and heat power, respectively, are the upper and lower limits of the gas turbine output electric and heat power at time t, respectively; the gas boiler power model is established and expressed as:

[0026]

[0027] wherein, is the heat power output by the gas boiler at time t, is the natural gas power consumed by the gas boiler at time t, is the energy conversion efficiency of the heat power output by the gas boiler, are the upper and lower limits of the heat power output by the gas boiler at time t, respectively; the electric refrigeration / heat equipment power model is established and expressed as:

[0028]

[0029] wherein, is the output of the electric refrigeration / heat equipment at time t, η c / e is the energy conversion efficiency, is the power consumption of the electric refrigeration / heat equipment at time t, are the upper and lower limits of the output of the electric refrigeration / heat equipment at time t, respectively; the absorption refrigerator power model is established and expressed as:

[0030]

[0031] wherein, are the heat power input and the cold power output of the absorption refrigerator at time t, respectively, η AC is the conversion efficiency of the absorption refrigerator, are the upper and lower limits of the cold power output of the absorption refrigerator at time t, respectively; the energy storage equipment constraint condition includes the energy storage charging and discharging constraint condition, which is expressed as:

[0032]

[0033] wherein, is the capacity of the energy storage equipment at time t, is the capacity of the energy storage at time t+1, η ch is the charging efficiency of the energy storage, η dis is the discharging efficiency of the energy storage, is the charging power of the energy storage equipment at time t, is the discharging power of the energy storage equipment at time t, and Δt is the change time; if the charging and discharging powers of the energy storage equipment are equal within a time period, the energy storage charging and discharging constraint condition is expressed as:

[0034]

[0035] wherein T is the total length of the time period; the capacity constraint and power constraint of the energy storage device at each time are calculated and expressed as:

[0036]

[0037] wherein, are the upper and lower limits of the capacity of the energy storage device at t, are the upper and lower limits of the charging power of the energy storage device at t, are the upper and lower limits of the discharging power of the energy storage device at t, are 0-1 state variables of the charging and discharging of the energy storage device at t, when the value of is 0, the device stops working, when the value of is 1, the device is in working state.

[0038] As a preferred scheme of the high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification, the hierarchical scheduling optimization comprises establishing a hierarchical coordination optimization model of the high-energy-consumption industrial micro-grid, and establishing a total revenue function of the high-energy-consumption micro-grid, expressed as:

[0039]

[0040] wherein F IMG is the total revenue function of the high-energy-consumption micro-grid, is the energy purchasing function of the high-energy-consumption micro-grid to the upper-level grid, is the energy selling function of the high-energy-consumption micro-grid, is the low-carbon operation function of the high-energy-consumption micro-grid, is the maximum utilization function of photovoltaic and wind power of the high-energy-consumption micro-grid, is the equipment maintenance rate of the high-energy-consumption micro-grid; the inequality constraint of the high-energy-consumption industrial micro-grid is calculated and expressed as:

[0041]

[0042] wherein, β e,h,c are the upper and lower limit constraints of the energy selling price of the micro-grid, are the average constraints of the energy selling price sold and bought, are the constraints of the energy selling price sold and bought at t, P i is the output of the i-th device in the micro-grid, P i are the upper and lower limit constraints of the device output, E i ,H i ,C iThe electric, heat and cold energy constraints provided by the micro-grid to the user respectively; the high energy consumption industrial micro-grid power balance equation constraint is calculated, and is expressed as:

[0043]

[0044] Wherein, E e , E h , E c are the maximum power of electric, heat and cold energy provided by the high energy consumption industrial micro-grid respectively, P e,i , P h,i , P c,i are the electric, heat and cold output of the i-th device respectively; the total income function of the high energy consumption industrial user is established, the internal optimization of the high energy consumption industrial park in the jurisdiction of the user aggregator is carried out, the interface with the load user is responsible, the dispersed load resource is integrated, the total income function of the high energy consumption industrial user is expressed as:

[0045]

[0046] Wherein, F USER is the total income function of the high energy consumption industrial user, is the user efficiency function, is the participation in auxiliary peak shaving subsidy, is the energy consumption function, is the energy storage capacity leasing function, is the CO2 emission cost; the high energy consumption industrial load inequality constraint is calculated, and is expressed as:

[0047]

[0048] Wherein, are the upper and lower limits of the adjustable electric load of the high energy consumption industrial load respectively; the high energy consumption industrial user optimization layer is solved through the CPLEX solver, the optimal power consumption of the user is taken as the input, and the genetic algorithm is adopted in the high energy consumption industrial micro-grid scheduling layer to realize the optimal scheduling of the equipment in the jurisdiction.

[0049] Another object of the present application is to provide a high energy consumption industrial micro-grid hierarchical scheduling optimization system based on load classification, which can ensure the coordinated optimization and operation efficiency of each subsystem through the hierarchical scheduling optimization of the high energy consumption industrial micro-grid mathematical model, and solve the problem that the current optimization model design lacks hierarchical scheduling capability.

[0050] As a preferred scheme of the high-energy-consumption industrial micro-grid hierarchical scheduling optimization system based on load classification, wherein: comprising a load analysis module, a load classification module, and a hierarchical coordination optimization module; the load analysis module is used for cluster analysis of the high-energy-consumption industrial micro-grid load, identifying load groups with similar characteristics and extracting key features; the load classification module is used for classifying the load according to the load clustering result; and the hierarchical coordination optimization module is used for establishing a mathematical model of the high-energy-consumption industrial micro-grid, and ensuring the coordinated optimization and operation efficiency of each subsystem through hierarchical scheduling optimization.

[0051] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification.

[0052] A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of the high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification.

[0053] The high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification provided by the present application comprehensively analyzes the load in the high-energy-consumption industrial micro-grid, identifies different types of load characteristics, classifies the high-energy-consumption industrial micro-grid load based on the clustering analysis result, improves the accuracy and applicability of load classification, provides more accurate basic load data for high-energy-consumption industrial micro-grid scheduling optimization, improves the efficiency and effectiveness of energy management, establishes an accurate high-energy-consumption industrial micro-grid mathematical model, more accurately and comprehensively describes the high-energy-consumption industrial load characteristics, provides reliable model support for high-energy-consumption industrial micro-grid scheduling optimization, improves the overall scheduling optimization effect, realizes the coordinated optimization of each subsystem in the micro-grid through hierarchical scheduling optimization and the establishment of a hierarchical coordination optimization model of the high-energy-consumption industrial micro-grid, improves the overall performance of the system, including energy utilization efficiency, high-energy-consumption industrial load balancing capability, and system stability, and the present application achieves better results in terms of accuracy, adaptability, and stability. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Figure 1 A high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification provided by the first embodiment of the present application.

[0056] Figure 2 A module schematic diagram of a high-energy-consumption industrial micro-grid hierarchical scheduling optimization system based on load classification is provided for a third embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0058] Embodiment 1, with reference to Figure 1 For an embodiment of the present application, a high-energy-consumption industrial micro-grid hierarchical scheduling optimization method based on load classification is provided, comprising:

[0059] S1: Cluster analysis is performed on the high-energy-consumption industrial micro-grid load, similar load groups are identified and key features are extracted.

[0060] Further, the cluster analysis of the high-energy-consumption industrial micro-grid load includes collecting load historical data, processing abnormal values and missing values in the data, extracting load features, using DBSCAN algorithm based on density to cluster the load data, dividing the load into several clusters, and excluding abnormal load points. The distance between all data points is calculated based on Euclidean distance, represented as:

[0061]

[0062] Wherein, p i is the power value of the i-th load data point, p j is the power value of the j-th load data point, is the value of p i in the n-th dimension, is the value of p j in the n-th dimension; all points within the threshold distance of the load data point p are calculated, forming the neighborhood of the load data point p, represented as:

[0063] N ∈ (p)={q∈D}|dist(p,q)≤∈

[0064] Wherein, N ∈(p) is the set of all points within a distance threshold e from the load data point p, D is the dataset of load data points, q is a load data point different from p, dist(p, q) is the Euclidean distance between load data point p and load data point q, and e is the distance threshold for determining the neighborhood. Whether it is a core point is determined according to the number of neighborhood points, denoted as:

[0065]

[0066] where minPts is the minimum number of neighborhood points for determining a core point. If the number of points in the neighborhood N ∈ (p) of load data point p is greater than or equal to the minimum number of neighborhood points minPts, then load data point p is a core point. If the number of points in the neighborhood N ∈ (p) of load data point p is less than the minimum number of neighborhood points minPts, then load data point p is not a core point. ∈ ∈

[0067] It should be noted that the clustering analysis of high-energy-consuming industrial micro-grid loads also includes evaluating the clustering effect by the Davies-Bouldin index and the silhouette coefficient, denoted as:

[0068]

[0069] where DB is the Davies-Bouldin index, k is the number of clustering clusters, σ i is the average distance of cluster i, σ j is the average distance of cluster j, and d ij is the distance between clusters i and j.

[0070] It should also be noted that clustering analysis of various loads in high-energy-consuming industrial micro-grids can help identify load groups with similar characteristics, thereby providing a basis for subsequent load classification and optimal scheduling.

[0071] where data collection can collect historical data of various loads in high-energy-consuming industrial micro-grids, including but not limited to power consumption characteristics, load change patterns, operating time, and environmental temperature of various high-energy-consuming loads, and other related data.

[0072] Further, data preprocessing is performed to clean and standardize the collected data, handle outliers and missing values, to ensure data quality and consistency.

[0073] Further, feature extraction is performed to extract key features from the preprocessed data, such as average load, peak load, load volatility, load duration, and load time characteristics.

[0074] ​​Further, clustering analysis is performed, and DBSCAN algorithm is applied to the high energy consumption industrial load data for clustering analysis based on density with noise, so as to obtain a plurality of clusters, each cluster represents a type of high energy consumption load mode, and a plurality of noise points do not belong to any cluster, and the noise points can be regarded as abnormal load.

[0075] S2: classifying the load according to the load clustering result.

[0076] Further, the load classification according to the load clustering result includes controllable load and uncontrollable load.

[0077] It should be noted that the controllable load includes time-limited transferable load, continuous transferable load and all controllable load; if the load is time-limited transferable load, the operation time period can be adjusted within the predetermined time range, and the production task is not affected; if the load is continuous transferable load, the start time can be flexibly adjusted according to the requirements of the production line sequence, and the normal operation of the production line can still be ensured after adjustment.

[0078] It should also be noted that the load is classified based on the clustering result, the characteristics and control mode of each type of load are determined, and the uncontrollable load usually has high reliability requirements for power supply. Once the power consumption behavior is changed, the product being produced may be scrapped, the production equipment may be damaged, or the personal safety of the production personnel may be threatened, so the uncontrollable load cannot be easily adjusted.

[0079] The controllable load includes time-limited transferable load, continuous transferable load and all controllable load, and the specific characteristics are as follows:

[0080] 1. Time-limited transferable load: refers to industrial load that can adjust its use time within a certain time range. The main feature of this industrial load is that its use time has a certain flexibility, and can be shifted within a predetermined time window without affecting the completion of its function or task, which is represented as:

[0081]

[0082] P'(t) is the time-limited transferable industrial load at t, μ is the proportion of the time-limited transferable industrial load to the total load P(t) in a day, T is the maximum delay time of the transferable industrial load, and P'(t+i) is the load component of the time-limited transferable industrial load at t that is allocated to t+i. IMG IMG IMG

[0083] ​​​The time-limited translatable load can make the high-energy consumption industrial microgrid participate in the operation scheduling of the upper grid as a demand response load. Since it has a time-limited translatable characteristic, the maximum delay processing time of such an industrial load is 3 hours, and the specific modeling method is as follows:

[0084] Three 24x24 matrices are introduced, denoted as:

[0085]

[0086] where Y is an auxiliary matrix, Z is a time-limited translatable matrix, is a square matrix, is a power matrix.

[0087] 1) The auxiliary matrix Y limits the load translatable time, which is a 0-1 variable, denoted as:

[0088]

[0089] 2) Diagonalize the time-limited translatable matrix load into a square matrix denoted as:

[0090]

[0091] where Z t,t is the time-limited translatable load before adjustment at time t, and the Z matrix represents that the time-limited translatable load at time t can be translated to times t+1, t+2, and t+3, while the introduction of the auxiliary matrix Y limits the time period in which such load can be translated.

[0092] 3) Power matrix of time-limited translatable load after adjustment denoted as:

[0093]

[0094] where the column vector represents the time period in which the time-limited translatable load can be adjusted, and the row vector represents the load distribution of the time-limited translatable load after adjustment at the current time; in order to limit the translated load not to exceed the original total load, the following constraint is set, denoted as:

[0095] y t+n,t ≤z t,t , t = 1, 2,..., 24; n = 0, 1, 2, 3

[0096] The tthrow of the time-limited translatable matrix before adjustment is transferred to the t+1, t+2, and t+3 rows, and the sum of the tthcolumn vector at this time is the time-limited translatable load before adjustment at time t, denoted as:

[0097]

[0098] For the power distribution at time t after adjustment, the following can be done Summing the tth row of the row vector, denoted as:

[0099]

[0100] In order to avoid excessive regulation of load at a certain moment, a time-limited translatable load upper limit constraint can be set, denoted as:

[0101]

[0102] Continuous translatable load: This type of industrial load needs to control the sequence of production lines, and can produce complete products according to certain production steps, and there is no strict requirement for the start time of each production line operation. The start time of this type of load can be adjusted appropriately according to the demand. Continuous high-energy-consuming industrial load needs to control the sequence of production lines, and needs to ensure the continuous supply of electric energy within a certain time period, but there is no strict requirement for the start time of each production line operation. This application takes the continuous high-energy-consuming industrial load appearing at 03:00-06:00 as an example, and the specific modeling method is as follows:

[0103] 1) Introduce the continuous high-energy-consuming industrial load matrix P IMG_ys at 03:00-06:00, denoted as:

[0104] P IMG_ys = [c3, c4, c5, c6]

[0105] 2) Introduce the auxiliary matrix P IMG_sk , whose matrix elements are all 0-1 Boolean variables, denoted as:

[0106]

[0107] In order to realize the continuous supply of electric energy within a certain time period, the continuous high-energy-consuming industrial load can only be shifted to another time after adjustment, and cannot be shifted to multiple times. P IMG_sk Each column vector has only one element equal to 1, denoted as:

[0108]

[0109] 3) Introduce the matrix T b of the time after shifting to determine the specific time of the continuous high-energy-consuming industrial load after adjustment, denoted as:

[0110] T1 = [1, 2, 3, …, 24]

[0111] T b = T a P IMG_sk

[0112] First, considering the continuity of high energy-consuming industrial load starting time is 03:00, the transferred load should not be earlier than 03:00, T b The matrix elements are set as follows:

[0113]

[0114] t1 = 1,2

[0115] Second, the continuity of high energy-consuming industrial load has a timing feature, that is, it needs to follow a certain production step to produce a complete product, and this order cannot be changed after adjustment. T b The matrix elements are set as follows:

[0116]

[0117] The adjusted continuity of high energy-consuming industrial load matrix is represented as:

[0118]

[0119] Wherein, is the continuity of the transferable load matrix at T.

[0120] 3. All controllable loads: This type of load can be shifted in starting time and load size, and can also be appropriately reduced. It usually refers to auxiliary loads such as office lighting, office appliances, air conditioning refrigeration, heating, etc. in enterprises, represented as:

[0121]

[0122] Wherein, P''' IMG is the total controllable load, P tran is the transferable load, P cut is the reducible load, P''' max , P''' min The design of maximum and minimum values should be based on the principle of giving priority to meeting the production load control.

[0123] S3: Establish a mathematical model of high energy-consuming industrial microgrid, and ensure the coordinated optimization and operation efficiency of each subsystem through hierarchical scheduling optimization.

[0124] Further, the high energy consumption industrial microgrid operator is a supplier of user side energy, which connects the energy supply system and the user together; the IMG meets the user's energy demand through the combined cooling, heating and power generation (CCHP), and purchases electricity and natural gas by directly connecting with the power grid and the gas pipeline. The CCHP unit includes a gas turbine (GT), a gas boiler (GB), an absorption chiller (AC), an electric chiller (EC), and an electric boiler (EB). In this paper, a distributed photovoltaic generator (PV) is installed on the high energy consumption industrial user side, and the energy storage (ES) service is used to realize high charging and low discharging of electricity.

[0125] Further, the mathematical model of the high energy consumption industrial microgrid includes the power model of the photovoltaic and wind turbine generator, which is expressed as:

[0126]

[0127] wherein, Ppv(t) and Pw(t) are the output powers of the photovoltaic and wind turbine at time t, Ppvmax(t) and Pwmax(t) are the maximum output powers of the photovoltaic and wind turbine at time t; the power model of the gas turbine is established, which is expressed as:

[0128]

[0129] wherein, Pgt(t) and Pht(t) are the output electric and heat powers of the gas turbine at time t, Qgt(t) is the natural gas power consumed by the gas turbine at time t, ηgt(e) and ηgt(h) are the energy conversion efficiencies of the output electric and heat powers of the gas turbine, Pgtmax(e) and Pgtmax(h) are the upper and lower limits of the output electric and heat powers of the gas turbine at time t; the power model of the gas boiler is established, which is expressed as:

[0130]

[0131] wherein, Pgb(t) is the output heat power of the gas boiler at time t, Qgb(t) is the natural gas power consumed by the gas boiler at time t, ηgb is the energy conversion efficiency of the output heat power of the gas boiler, Pgbmax and Pgbmin are the upper and lower limits of the output heat power of the gas boiler at time t; the power model of the electric chiller / electric heating equipment is established, which is expressed as:

[0132]

[0133] wherein, is the power of the electric refrigeration / heating device at time t, η c / e is the energy conversion efficiency, is the power consumption of the electric refrigeration / heating device at time t, are the upper and lower limits of the power of the electric refrigeration / heating device at time t, respectively; the power model of the absorption chiller is established and expressed as:

[0134]

[0135] wherein, are the input heat power and the output cold power of the absorption chiller at time t, respectively, η AC is the conversion efficiency of the absorption chiller, are the upper and lower limits of the output cold power of the absorption chiller at time t, respectively; the constraint conditions of the energy storage device include the charging and discharging constraint conditions of the energy storage, which are expressed as:

[0136]

[0137] wherein, is the capacity of the energy storage device at time t, is the capacity of the energy storage at time t+1, η ch is the charging efficiency of the energy storage, η dis is the discharging efficiency of the energy storage, is the charging power of the energy storage device at time t, is the discharging power of the energy storage device at time t, and Δt is the change time; if the charging and discharging powers of the energy storage device are equal within a time period, the charging and discharging constraint conditions of the energy storage are expressed as:

[0138]

[0139] wherein, T is the total length of the time period; the capacity constraint and the power constraint of the energy storage device at each time are calculated and expressed as:

[0140]

[0141] wherein, are the upper and lower limits of the capacity of the energy storage device at time t, respectively, are the upper and lower limits of the charging power of the energy storage device at time t, respectively, are the upper and lower limits of the discharging power of the energy storage device at time t, respectively, are 0-1 state variables of the charging and discharging of the energy storage device at time t, respectively, when the value of is 0, it indicates that the device stops working, The value of 1 indicates that the device is in working condition.

[0142] It should be noted that the hierarchical scheduling optimization includes establishing a hierarchical coordination optimization model of the high-energy-consumption industrial microgrid, establishing a total revenue function of the high-energy-consumption microgrid, and representing as follows:

[0143]

[0144] Wherein, F IMG is the total revenue function of the high-energy-consumption microgrid, is the energy purchasing function of the high-energy-consumption microgrid to the upper-level power grid, is the energy selling function of the high-energy-consumption microgrid, is the low-carbon operation function of the high-energy-consumption microgrid, is the maximum utilization function of the high-energy-consumption microgrid photovoltaic and wind power, represents the wind and light curtailment rate, is the equipment maintenance rate of the high-energy-consumption microgrid; the inequality constraint of the high-energy-consumption industrial microgrid is calculated and represented as follows:

[0145]

[0146] Wherein, β e,h,c are the upper and lower limit constraints of the microgrid energy selling price, are the average constraints of the energy selling price sell and buy, are the constraints of the energy selling price sell and buy at time t, P i is the output of the i-th equipment in the microgrid, P i are the upper and lower limit constraints of the equipment output, E i ,H i ,C i are the energy constraints of the microgrid providing electricity, heat and cold to users; the power balance equality constraint of the high-energy-consumption industrial microgrid is calculated and represented as follows:

[0147]

[0148] Wherein, E e , E h , E c are the maximum power of the electricity, heat and cold energy provided by the high-energy-consumption industrial microgrid, P e,i , P h,i , P c,i are the electricity, heat and cold output of the i-th equipment; the total revenue function of the high-energy-consumption industrial user is established, the internal optimization of the high-energy-consumption industrial park in the jurisdiction of the user aggregator is carried out, the load user is connected, and the dispersed load resources are integrated, and the total revenue function of the high-energy-consumption industrial user is represented as follows:

[0149]

[0150] wherein F USER is the total revenue function of high energy-consuming industrial users, is the user efficiency function, is the participation in auxiliary peak shaving subsidy, is the energy consumption function, is the energy storage capacity leasing function, is the CO2 emission cost; the inequality constraint of high energy-consuming industrial load is calculated and expressed as:

[0151]

[0152] wherein, are the upper and lower limits of the controllable electrical load of high energy-consuming industrial load respectively; the optimization layer of high energy-consuming industrial users is solved by CPLEX solver, and the optimal power consumption of users is taken as the input quantity, and the genetic algorithm is adopted in the dispatching layer of high energy-consuming industrial micro-grid to realize the optimal dispatching of equipment in the jurisdiction.

[0153] It should also be noted that the establishment of the total revenue function of high energy-consuming micro-grid includes the calculation of the energy purchasing function of high energy-consuming micro-grid from the upper-level power grid, which is expressed as:

[0154]

[0155] wherein κ e , κ h are the electricity and heat purchasing prices of high energy-consuming micro-grid from the upper-level energy supplier respectively, is the power shortage of high energy-consuming micro-grid at time t; the energy selling function of high energy-consuming micro-grid is calculated and expressed as:

[0156]

[0157] wherein β e , β h , β c are the electricity, heat and cold selling prices of micro-grid to high energy-consuming industrial users respectively, are the electrical, heat and cold powers of micro-grid to high energy-consuming industrial users at time t respectively; the low-carbon operation function of high energy-consuming micro-grid is calculated and expressed as:

[0158]

[0159] wherein, is the carbon emission coefficient, and ε is the proportional coefficient, which represents that the carbon emissions generated by the electrical and heat powers purchased by micro-grid from the upper-level network need to be borne by the upper-level network in a certain proportion; the maximum utilization function of photovoltaic and wind power of high energy-consuming micro-grid is calculated and expressed as:

[0160]

[0161] The maintenance rate of high energy consumption micro-grid equipment is calculated and expressed as:

[0162]

[0163] Wherein, P fa is the rated power of the equipment in the micro-grid.

[0164] It should be noted that the establishment of the total income function of high energy consumption industrial users includes the calculation of the user efficiency function, which is expressed as:

[0165]

[0166] Wherein, P IMG is the regulated high energy consumption industrial load, a, b, and c are parameters of the energy utility function; the participation in auxiliary peak regulation subsidy is calculated and expressed as:

[0167]

[0168] Wherein, μ e is the auxiliary peak regulation compensation parameter, is the total power of the load participating in regulation; the energy consumption function is calculated and expressed as:

[0169]

[0170] The storage capacity leasing function is calculated and expressed as:

[0171]

[0172] Wherein, μ es is the price of leasing storage unit capacity; the CO2 emission cost is calculated and expressed as:

[0173]

[0174] The regulated high energy consumption industrial load equation constraint is calculated and expressed as:

[0175] P IMG = P' IMG + P" IMG + P''' IMG

[0176] Wherein, P' IMG is the time-limited transferable load, P" IMG is the adjusted continuous translatable load matrix, and P''' IMG is the total controllable load.

[0177] It should be noted that the hierarchical coordination optimization model of high energy consumption industrial micro-grid is solved, and the micro-grid dispatching layer needs to coordinate the internal equipment of high energy consumption industrial micro-grid according to the power demand uploaded by the load aggregator, so as to pursue the maximum profit of high energy consumption industrial micro-grid.

[0178] In the high energy consumption industrial user optimization layer, the load aggregator needs to sign a load regulation agreement with the high energy consumption industrial user, and needs to respond to the demand side according to the needs of the upper power grid.

[0179] The high energy consumption industrial user optimization layer is solved by CPLEX, and the optimal power consumption of the user is taken as the input, and the high energy consumption industrial micro-grid dispatching layer realizes the optimal scheduling of the equipment in the jurisdiction by using genetic algorithm.

[0180] The selling price of electricity and heat of the upper high energy consumption industrial micro-grid operator is initialized and updated by genetic algorithm, and the power consumption and heat consumption of the lower user aggregator are solved by calling CPLEX solver, at this time, the user side only needs to accept the price signal of the multi-energy micro-grid aggregator, and upload the current user energy signal, which can effectively avoid the leakage of information of each interest subject, and protect the privacy and safety, the specific solving process is as follows:

[0181] (1) input basic data, initialize parameters of each interest subject.

[0182] (2) the upper multi-energy micro-grid operator randomly generates n sets of selling price of electricity and heat by using genetic algorithm, and transmits the parameters to the lower layer.

[0183] (3) the user aggregator receives the n sets of selling price of electricity and heat randomly generated by the upper layer, optimizes the output of each device and the user side demand response by using CPLEX solver, obtains the current user operator income, and returns the current user power interaction to the upper layer.

[0184] (4) the multi-energy micro-grid operator calculates the current income according to the power interaction returned by the lower layer.

[0185] (5) new multi-energy micro-grid selling price of electricity and heat is generated by using selection, crossover, mutation and boundary conditions of genetic algorithm, steps (3)-(4) are repeatedly executed, and the income of high energy consumption industrial micro-grid and user aggregator is obtained.

[0186] (6) income iteration.

[0187] (7) judge convergence, if convergence, end the program; otherwise, return to step (3).

[0188] Embodiment 2, which is an embodiment of the present application, provides a high-energy-consuming industrial micro-grid hierarchical scheduling optimization method based on load classification. In order to verify the beneficial effects of the present application, economic benefit calculation and simulation experiments are carried out for scientific demonstration.

[0189] The test aims to verify the innovation and advantage of the high-energy-consuming industrial micro-grid load clustering analysis, classification and hierarchical optimization scheduling. The test object is a certain high-energy-consuming industrial park, which contains multiple high-energy-consuming equipment, including time-limited transferable load, continuous translatable load and uncontrollable load. The test is based on one week (7 days) of load data, covering key information such as power consumption characteristics, load fluctuation mode, running time and environmental temperature.

[0190] Test preparation:

[0191] 1. Data collection and preprocessing: Extract 7 days of historical data from the load monitoring system installed in the park, covering the running characteristics of all equipment, including average power, peak power and running time. Clean the data, eliminate outliers and fill in missing values, and standardize the processing to ensure consistency.

[0192] 2. Feature extraction: Extract key features, including average load, peak load, load volatility and continuous running time, to provide a basis for subsequent clustering analysis.

[0193] 3. Algorithm selection: Use DBSCAN algorithm for load clustering analysis, set Euclidean distance threshold and minimum core point neighborhood number, and classify data points into clusters.

[0194] 4. Cluster evaluation: Evaluate the clustering effect by Davies-Bouldin index and silhouette coefficient to ensure reasonable grouping.

[0195] Test implementation:

[0196] 1. Load clustering analysis: Import the load data into the DBSCAN algorithm, cluster according to the power characteristics, identify 3 main load clusters: time-limited transferable load, continuous translatable load and abnormal load points, eliminate abnormal load points, and retain key load clusters to lay the foundation for subsequent classification and scheduling optimization.

[0197] 2. Load classification: Based on the clustering results, further subdivide the load, including time-limited transferable load, continuous translatable load and uncontrollable load. According to the classification characteristics, design scheduling strategies, such as limiting the running of time-limited transferable load at peak time, and shifting continuous translatable load to smooth the load curve.

[0198] 3. Hierarchical optimization scheduling: a hierarchical optimization model is used to schedule the micro-grid, the scheduling layer optimizes the power of the combined cooling heating and power device and the distributed photovoltaic, and the user side optimization layer adjusts the operation parameters of various loads, the goal is to balance the total power and maximize the energy utilization rate, and the genetic algorithm is used to solve the multi-objective optimization function.

[0199] Referring to Table 1, the experimental data are compared and analyzed.

[0200] Table 1 Experimental data record table

[0201]

[0202]

[0203] As can be seen from the data in Table 1, by implementing the clustering analysis and scheduling optimization strategy of the application, the load management achieves obvious effect. First, the DBSCAN algorithm successfully divides the high-energy-consuming industrial micro-grid load into three main load clusters (time-limited transferable load, continuous transferable load and non-adjustable load), and effectively eliminates abnormal load points. The clustering effect evaluation result shows that the Davies-Bouldin index reaches 1.5-1.8, and the silhouette coefficient remains above 0.8, proving that the clustering result has good tightness and separation, which can more accurately identify the load characteristics and reduce the grouping error compared with the traditional statistical analysis method.

[0204] Through load classification, it can be seen that the time-limited transferable load has high flexibility, and after scheduling, the power is reduced from the original 800kW peak to 450kW, effectively reducing the pressure of load peak on the micro-grid. The continuous transferable load shifts the power peak from 1100kW to other time periods while maintaining the production order, making the overall load of the micro-grid more smooth. The non-adjustable load remains stable and does not cause production loss due to adjustment, fully embodying the accuracy and rationality of the classification strategy.

[0205] The results of scheduling optimization show that the total load is reduced from 2350kW peak before scheduling to 1800kW after scheduling, and the load distribution is smoothed, improving the stability and energy utilization efficiency of the micro-grid operation. The genetic algorithm has fast convergence speed in multi-objective optimization, and the optimization result is stable, realizing the coordinated operation of the combined cooling heating and power device and the load side. Compared with the traditional single-layer optimization model, the hierarchical optimization model proposed in the application fully considers the dynamic characteristics of the user side and the device side, ensures the independent optimization of each subsystem, and realizes global coordination.

[0206] In summary, the present application has innovation and advantages in load analysis, classification and optimal scheduling compared with the prior art, and effectively solves the problems of inaccurate load classification, insufficient mathematical model and single optimization structure of the traditional method by introducing the clustering analysis method and the hierarchical optimization model, thereby providing technical support for intelligent management of the high-energy-consumption industrial micro-grid and improving energy utilization efficiency and operation economy.

[0207] Embodiment 3, refer to Figure 2 For an embodiment of the present application, a high-energy-consumption industrial micro-grid hierarchical scheduling optimization system based on load classification is provided, which comprises a load analysis module, a load classification module and a hierarchical coordination optimization module.

[0208] The load analysis module is used for clustering analysis of the high-energy-consumption industrial micro-grid load, identifying load groups with similar characteristics and extracting key features; the load classification module is used for classifying the load according to the load clustering result; and the hierarchical coordination optimization module is used for establishing a mathematical model of the high-energy-consumption industrial micro-grid, and ensuring the coordinated optimization and operation efficiency of each subsystem through hierarchical scheduling optimization.

[0209] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0210] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logic functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, apparatus or device, such as a computer-based system, a system including a processor or other system that can fetch and execute instructions from the instruction execution system, apparatus or device, or in conjunction with these instructions. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, apparatus or device or in conjunction with these instructions. For the purpose of this specification, the "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, apparatus or device or in conjunction with these instructions.

[0211] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0212] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc. It should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention and are not intended to be limiting. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced with equivalents without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications should be encompassed by the claims of the present invention.

[0213] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A hierarchical scheduling optimization method for high-energy-consuming industrial microgrids based on load classification, characterized by: include: Perform cluster analysis on high-energy-consuming industrial microgrid loads to identify load groups with similar characteristics and extract key features; Classify the loads according to the load clustering results; Establish a mathematical model for high-energy-consuming industrial microgrids and ensure the coordinated optimization and operational efficiency of each subsystem through hierarchical scheduling optimization; The mathematical model for establishing a high-energy-consuming industrial microgrid includes establishing power models for photovoltaic and wind turbine generator sets, establishing power models for gas turbines, establishing power models for gas boilers, establishing power models for electric refrigeration / electric heating equipment, and establishing power models for absorption chillers; The hierarchical scheduling optimization includes establishing a hierarchical coordination optimization model for high-energy-consuming industrial microgrids and establishing a total benefit function for high-energy-consuming microgrids, which is expressed as: Among them, F IMG is the total revenue function of the high energy consumption microgrid, It is the energy purchasing function of high energy consumption microgrid from the upper power grid. is the energy selling function of the high energy consumption microgrid, For the low-carbon operation function of high-energy-consuming microgrids, It is the function for maximizing the utilization of photovoltaic and wind power in high-energy-consuming microgrids. Maintenance rate for high energy consumption microgrid equipment; Establish a total revenue function for high-energy-consuming industrial users, conduct internal optimization of high-energy-consuming industrial parks in the jurisdiction of user aggregators, be responsible for connecting with load users, and integrate dispersed load resources. The total revenue function for high-energy-consuming industrial users is expressed as: Among them, F USER is the total revenue function of high energy-consuming industrial users, is the user utility function, To participate in the auxiliary peak load subsidy, is the energy consumption function, is the energy storage capacity leasing function, Cost of CO2 emissions; The optimization layer of high-energy-consuming industrial users is solved by the CPLEX solver, and the optimal power consumption of users is taken as input. The high-energy-consuming industrial microgrid scheduling layer adopts genetic algorithm to achieve the optimal scheduling of equipment within the jurisdiction.

2. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 1 is characterized in that: The cluster analysis of high-energy-consuming industrial microgrid loads includes collecting historical load data, processing outliers and missing values ​​in the data, extracting load features, clustering the load data using the density-based DBSCAN algorithm, dividing the load into several clusters, and excluding abnormal load points. The distance between all data points is calculated based on the Euclidean distance, which is expressed as: Among them, p i is the power value of the i-th load data point, p j is the power value of the jth load data point, For p i The value in the nth dimension, For p j The value in the nth dimension; Calculate all points within the threshold ∈ distance of the load data point p to form the ∈ neighborhood of the load data point p, which is expressed as: N ∈ (p)={q∈D}|dist(p,q)≤∈ Among them, N ∈ (p) is the set of all points whose distance from the load data point p does not exceed the threshold ∈, D is the load data point dataset, q is the load data point different from p, dist(p,q) is the Euclidean distance between the load data point p and the load data point q, ∈ is the distance threshold for judging the neighborhood; Judging whether it is a core point is determined by the number of neighborhood points, expressed as: Among them, minPts is the minimum number of neighborhood points for judging the core point. If the neighborhood N of the load data point p is ∈ The number of points in (p) |N ∈ (p)| is greater than or equal to the minimum number of neighborhood points minPts, then the load data point p is the core point. If the neighborhood N of the load data point p is greater than or equal to the minimum number of neighborhood points minPts, then the load data point p is the core point. ∈ The number of points in (p) |N ∈ (p)| is less than the minimum number of neighborhood points minPts, then the load data point p is not a core point.

3. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 2 is characterized in that: The cluster analysis of high-energy-consuming industrial microgrid loads also includes evaluating the clustering effect through the Davidson-Boulding index and silhouette coefficient, which is expressed as: Where DB is the Davidson-Botting index, k is the number of clusters, σ i is the average distance of cluster i, σ j is the average distance of cluster j, d ij is the distance between clusters i and j.

4. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 3 is characterized in that: The loads are classified into adjustable loads and unadjustable loads according to the load clustering result.

5. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 4 is characterized in that: The adjustable loads include time-limited transferable loads, continuous translational loads and all adjustable loads; If the load is a time-limited transferable load, the operating period can be adjusted within the predetermined time range without affecting the production task; If the load is a continuous and movable load, the start-up time can be flexibly adjusted according to the sequence requirements of the production line, and the normal operation of the production line can still be ensured after adjustment.

6. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 5 is characterized in that: The mathematical model for establishing a high-energy-consuming industrial microgrid includes establishing photovoltaic and wind turbine power models, which are expressed as: in, is the output power of photovoltaic and wind turbine at time t, is the maximum output power of photovoltaic and wind turbine at time t; The gas turbine power model is established and expressed as: in, are the electrical and thermal power output of the gas turbine at time t, is the natural gas power consumed by the gas turbine at time t, are the energy conversion efficiency of the gas turbine output electricity and thermal power, are the upper and lower limits of the gas turbine output electrical and thermal power at time t respectively; The gas boiler power model is established and expressed as: in, is the thermal power output of the gas boiler at time t, is the natural gas power consumed by the gas boiler at time t, The energy conversion efficiency of the gas boiler output thermal power, are the upper and lower limits of the thermal power output of the gas boiler at time t; The power model of electric cooling / heating equipment is established and expressed as: in, The electric cooling / heating equipment at time t contribute, η c / e is the energy conversion efficiency, is the power consumption of the electric cooling / heating equipment at time t, are the upper and lower limits of the output of the electric cooling / heating equipment at time t respectively; The power model of the absorption chiller is established and expressed as: in, are the heat power input and cooling power output of the absorption refrigerator at time t, respectively, AC is the conversion efficiency of the absorption chiller, They are the upper and lower limits of the cooling power output of the absorption chiller at time t; The design constraints of energy storage equipment include energy storage charging and discharging constraints, which are expressed as: in, is the capacity of the energy storage device at time t, is the capacity of the energy storage at time t+1, is the energy storage charging efficiency, η dis is the energy storage discharge efficiency, is the charging power of the energy storage device at time t, is the discharge power of the energy storage device at time t, and Δt is the change time; If the charging and discharging power of the energy storage device is equal within a time period, the energy storage charging and discharging constraint condition is expressed as: Where T is the total duration of the time period; Calculate the capacity constraint and power constraint of the energy storage device at each moment, expressed as: in, are the upper and lower limits of the energy storage device capacity at time t, are the upper and lower limits of the energy storage device charging power at time t, are the upper and lower limits of the energy storage device discharge power at time t, are the 0-1 state variables of the energy storage device charging and discharging at time t, When the value is 0, it means the device stops working. When the value is 1, it means the device is in working state.

7. The method for hierarchical scheduling optimization of high-energy-consuming industrial microgrids based on load classification according to claim 6 is characterized in that: Calculate the inequality constraints of high-energy-consuming industrial microgrids, expressed as: in, They are the upper and lower limits of the microgrid energy sales price, are the average constraints of selling and buying energy prices, are the constraints on selling and buying energy prices at time t, P i Output power to the i-th device in the microgrid, are the upper and lower limit constraints of the equipment output, E i ,H i ,C i are the constraints on electricity, heat, and cooling energy provided by the microgrid to users, respectively; Calculate the power balance equation constraint of high-energy-consuming industrial microgrid, which is expressed as: Among them, E e 、E h 、E c are the maximum power of electricity, heat and cooling energy provided by high energy consumption industrial microgrid, P e,i 、P h,i 、P c,i are the electricity, heat and cooling output of the i-th device respectively; Calculate the inequality constraints for high energy-consuming industrial loads, expressed as: in, They are the upper and lower limits of the adjustable electric load for high energy-consuming industrial loads.

8. A system using the load classification-based hierarchical scheduling optimization method for high-energy-consuming industrial microgrids according to any one of claims 1 to 7, characterized in that: Including load analysis module, load classification module, and hierarchical coordination optimization module; The load analysis module is used to perform cluster analysis on high-energy-consuming industrial microgrid loads, identify load groups with similar characteristics and extract key features; The load classification module is used to classify the load according to the load clustering result; The hierarchical coordination optimization module is used to establish a mathematical model of a high-energy-consuming industrial microgrid, and ensure the coordination optimization and operation efficiency of each subsystem through hierarchical scheduling optimization; The mathematical model for establishing a high-energy-consuming industrial microgrid includes establishing power models for photovoltaic and wind turbine generator sets, establishing power models for gas turbines, establishing power models for gas boilers, establishing power models for electric refrigeration / electric heating equipment, and establishing power models for absorption chillers; The hierarchical scheduling optimization includes establishing a hierarchical coordination optimization model for high-energy-consuming industrial microgrids and establishing a total benefit function for high-energy-consuming microgrids, which is expressed as: Among them, F IMG is the total revenue function of the high energy consumption microgrid, It is the energy purchasing function of high energy consumption microgrid from the upper power grid. is the energy selling function of the high energy consumption microgrid, For the low-carbon operation function of high-energy-consuming microgrids, It is the function for maximizing the utilization of photovoltaic and wind power in high-energy-consuming microgrids. Maintenance rate for high energy consumption microgrid equipment; Establish a total revenue function for high-energy-consuming industrial users, conduct internal optimization of high-energy-consuming industrial parks in the jurisdiction of user aggregators, be responsible for connecting with load users, and integrate dispersed load resources. The total revenue function for high-energy-consuming industrial users is expressed as: Among them, P USER is the total revenue function of high energy-consuming industrial users, is the user utility function, To participate in the auxiliary peak load subsidy, is the energy consumption function, is the energy storage capacity leasing function, Cost of CO2 emissions; The optimization layer of high-energy-consuming industrial users is solved by the CPLEX solver, and the optimal power consumption of users is taken as input. The high-energy-consuming industrial microgrid scheduling layer adopts genetic algorithm to achieve the optimal scheduling of equipment within the jurisdiction.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the load classification-based high-energy-consuming industrial microgrid hierarchical scheduling optimization method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the load classification-based high-energy-consuming industrial microgrid hierarchical scheduling optimization method according to any one of claims 1 to 7 are implemented.

Images