A distribution network layout optimization method and system

Abstract

The present application discloses a distribution network layout optimization method and system, wherein the method includes: obtaining power parameters and thermal parameters of a target area; extracting high-frequency components of the power parameters to obtain a power fluctuation data set, performing spectrum decomposition on the thermal parameters to obtain a thermal fluctuation data set; constructing an electric and thermal fluctuation data set based on the power fluctuation data set and the thermal fluctuation data set, performing cluster analysis on the electric and thermal fluctuation data set to obtain an abnormal fluctuation aggregate; calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set based on the abnormal fluctuation aggregate, and constructing a parameter matching result data set of the target area based on the bidirectional correlation; analyzing the parameter matching result data set, and controlling the interface conversion device to optimize the initial layout plan based on the analysis result, so as to achieve the optimization of the distribution network layout of the target area. The method provided by the present application can optimize the distribution network layout of the target area and improve the comprehensive utilization efficiency of energy.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a distribution network layout optimization method and system. Background Art

[0002] In the process of modern urbanization, the optimal layout of the energy system is crucial to improving energy efficiency, reducing energy waste, and enhancing the resilience of urban infrastructure. As the main components of the urban energy system, the demand forecast and layout planning of electricity and heat directly affect the sustainable development of the city and the quality of life of residents.

[0003] However, traditional distribution network layout optimization is often based on experience or the needs of a single system. For example, in the existing technology, power supply reliability is improved by adding backup lines and equipment, or by introducing distributed power sources and energy storage equipment. However, the above optimization methods that only consider a single system will affect the normal operation of the original line, thereby increasing the cost and complexity of the distribution network layout.

[0004] It can be seen that how to optimize the layout of the distribution network has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] The present application provides a distribution network layout optimization method and system to solve the technical problem of how to optimize the distribution network layout.

[0006] In order to solve the above technical problems, an embodiment of the present application provides a distribution network layout optimization method, which is applied to a target area distribution network provided with an interface conversion device, comprising:

[0007] Based on the acquired power demand of the target area, the distribution network of the target area is laid out to obtain an initial layout plan, and simulation is performed according to the initial layout plan to obtain power parameters of the target area; the acquired thermal demand of the target area is analyzed to obtain thermal parameters of the target area;

[0008] Extract high-frequency components of the power parameters based on the Haar wavelet transform method to obtain a power fluctuation data set, and perform spectrum decomposition of the thermal parameters based on the Fourier transform method to obtain a thermal fluctuation data set;

[0009] constructing an electric-thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set, and performing cluster analysis on the electric-thermal fluctuation data set to obtain an abnormal fluctuation aggregate;

[0010] calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and constructing the parameter matching result data set of the target area according to the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation data set and the thermal fluctuation data set;

[0011] The parameter matching result data set is analyzed, and according to the analysis result, the interface conversion device is controlled to optimize the initial layout scheme to achieve the distribution network layout optimization in the target area.

[0012] In a preferred embodiment of the present application, performing simulation calculation according to the initial layout scheme to obtain the power parameters of the target area includes:

[0013] According to the initial layout plan, a distribution network simulation model of the target area is established;

[0014] Setting simulation conditions based on the acquired environmental parameters of the target area;

[0015] The distribution network of the target area is simulated according to the distribution network simulation model and the simulation conditions, and the power parameters of the distribution network are calculated.

[0016] In a preferred embodiment of the present application, constructing the electric and thermal fluctuation dataset according to the electric power fluctuation dataset and the thermal fluctuation dataset comprises:

[0017] Performing time alignment processing on the electric power fluctuation data set and the thermal fluctuation data set to obtain an initial electric and thermal fluctuation data set;

[0018] Preprocessing the initial electrothermal fluctuation data set, wherein the preprocessing includes data cleaning, data denoising and data normalization;

[0019] Feature extraction is performed based on the preprocessed initial electrothermal fluctuation data set, and the electrothermal fluctuation data set is constructed according to the extracted features.

[0020] In a preferred embodiment of the present application, cluster analysis is performed on the electrothermal fluctuation data set to obtain abnormal fluctuation aggregates, including:

[0021] Performing standardization processing on the electrothermal fluctuation data set, and randomly selecting a plurality of sample data in the electrothermal fluctuation data set after the standardization processing as initial clustering centers;

[0022] In the distance calculation process, the distance from each sample data in the electrothermal fluctuation data set to each of the initial cluster centers is calculated;

[0023] In the process of determining the cluster center, the probability distribution of each of the sample data is calculated based on the distance, and a new cluster center is selected according to the probability distribution;

[0024] The distance calculation process and the cluster center determination process are repeated until the abnormal fluctuation aggregate reflecting the abnormal fluctuation of the power parameter and the thermal parameter is obtained.

[0025] In a preferred embodiment of the present application, the step of calculating the bidirectional correlation between the power fluctuation dataset and the thermal fluctuation dataset based on the abnormal fluctuation aggregate, and constructing the parameter matching result dataset of the target area based on the bidirectional correlation comprises:

[0026] Calculating a first correlation between the power fluctuation data set and the thermal fluctuation data set according to a preset correlation index;

[0027] Calculating a second correlation between the thermal fluctuation data set and the electric power fluctuation data set according to the correlation index;

[0028] Obtaining a bidirectional correlation between the power fluctuation dataset and the thermal fluctuation dataset according to the first correlation and the second correlation;

[0029] The parameters in the power fluctuation dataset and the thermal fluctuation dataset are matched according to the bidirectional correlation to obtain a parameter matching result dataset reflecting the degree of interaction between the power fluctuation dataset and the thermal fluctuation dataset.

[0030] In a preferred embodiment of the present application, analyzing the parameter matching result data set and controlling the interface conversion device to optimize the initial layout scheme according to the analysis result includes:

[0031] Preprocessing the parameter matching result data set, wherein the preprocessing includes missing value detection and format conversion;

[0032] Inputting the preprocessed parameter matching result data set into a pre-built thermoelectric correlation model for analysis to obtain analysis results;

[0033] An interface conversion device is designed according to the analysis result, and the matching of the power parameters and the thermal parameters in the target area is achieved through the interface conversion device.

[0034] In a preferred embodiment of the present application, the interface conversion device includes a frequency converter module and a heat exchanger module;

[0035] The matching of the power parameter and the thermal parameter in the target area by the interface conversion device includes:

[0036] The conversion of the power parameters is achieved through a frequency converter module, and the conversion of the thermal parameters is achieved through a heat exchanger module, so as to achieve matching of power and thermal parameters between the distribution networks in the target area.

[0037] In a preferred embodiment of the present application, after optimizing the distribution network layout of the target area, the method further includes:

[0038] The distribution network layout of the target area is simulated according to the optimized distribution network layout, and the design parameters of the inverter module and the heat exchanger module are optimized according to the simulation results.

[0039] In a preferred embodiment of the present application, optimizing the design parameters of the inverter module and the heat exchanger module according to the simulation results includes:

[0040] The power parameters and thermal parameters of the target area distribution network are obtained through simulation, and the design parameters are adjusted in real time according to the power parameters and the thermal parameters to achieve optimal configuration of the design parameters.

[0041] Another embodiment of the present application provides a distribution network layout optimization system, which is applied to a target area distribution network provided with an interface conversion device, including:

[0042] An acquisition module is used to layout the distribution network of the target area based on the acquired power demand of the target area to obtain an initial layout plan, perform simulation according to the initial layout plan to obtain power parameters of the target area; and analyze the acquired thermal demand of the target area to obtain thermal parameters of the target area;

[0043] An extraction module, used for extracting high-frequency components of the power parameters based on a Haar wavelet transform method to obtain a power fluctuation data set, and performing spectrum decomposition of the thermal parameters based on a Fourier transform method to obtain a thermal fluctuation data set;

[0044] A clustering module, used for constructing an electric and thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set, and performing cluster analysis on the electric and thermal fluctuation data set to obtain an abnormal fluctuation aggregate;

[0045] a calculation module, configured to calculate a bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and construct a parameter matching result data set of the target area according to the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation data set and the thermal fluctuation data set;

[0046] The analysis module is used to analyze the parameter matching result data set and control the interface conversion device to optimize the initial layout plan according to the analysis result to achieve the distribution network layout optimization in the target area.

[0047] Compared with the prior art, the beneficial effects of the embodiments of the present application are at least one of the following:

[0048] 1) The high-frequency components of power parameters are extracted by using Haar wavelet transform, which can accurately capture the detailed information of power fluctuations, such as instantaneous changes, periodic fluctuations, etc.; the frequency components of thermal fluctuations can be analyzed by performing spectral decomposition of thermal parameters through Fourier transform, which provides a powerful tool for subsequent clustering analysis and correlation calculation.

[0049] 2) Cluster analysis of the electric and thermal fluctuation data set can identify abnormal fluctuation clusters in power and thermal parameters. These abnormal fluctuations may represent potential problems or unstable factors in the power grid or thermal system. By identifying abnormal fluctuations, potential safety hazards can be discovered and dealt with in a timely manner, thereby improving the stability of the power grid and thermal system.

[0050] 3) Based on the abnormal fluctuation aggregate, the two-way correlation between the power fluctuation data set and the thermal fluctuation data set is calculated, reflecting the degree of interaction between the two. Through correlation analysis, we can gain an in-depth understanding of the mutual influence between the power and thermal systems, providing a scientific basis for the subsequent optimization of the distribution network layout. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of a distribution network layout optimization method in one embodiment of the present application;

[0052] Figure 2 It is a structural diagram of a distribution network layout optimization system in one embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0055] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used in this article are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application. The term "and / or" used in this article includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0056] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0057] It should be noted that in modern cities, electricity and heat are the two most basic energy needs. With the acceleration of urbanization and population growth, the demand for these two energy sources is also increasing and showing diversified characteristics. The traditional distribution network layout often only focuses on the transmission and distribution of electricity, while ignoring the correlation and mutual influence between heat demand and electricity demand.

[0058] The power system and the thermal system do not exist in isolation in modern cities, and there is a complex interactive relationship between them. For example, fluctuations in power supply may affect the stable operation of the thermal system, and vice versa. Therefore, when optimizing the distribution network layout, this interactivity and synergy must be considered to ensure the stability and efficiency of the entire energy system. The traditional distribution network layout often has problems such as unreasonable structure and low efficiency, which makes it difficult to meet the high requirements of modern cities for energy supply.

[0059] Therefore, an embodiment of the present application provides a method for optimizing the layout of a distribution network. For details, see Figure 1 , Figure 1 The flowchart of the method for optimizing the layout of a distribution network in one embodiment of the present application is shown, which is applied to a distribution network in a target area provided with an interface conversion device, and includes steps S1-S5:

[0060] S1: Based on the acquired power demand of the target area, the distribution network of the target area is laid out to obtain an initial layout plan, and simulation is performed according to the initial layout plan to obtain power parameters of the target area; the acquired thermal demand of the target area is analyzed to obtain thermal parameters of the target area;

[0061] In one embodiment of the present application, based on the power demand of the target area, the preliminary layout of the distribution network is first carried out. Specifically, the three-dimensional spatial coordinate points of the target area are obtained from the building information database, and these coordinate points represent the positions of residential buildings in three-dimensional space. The floor height and building area are calculated, and combined with the number of surrounding business districts, the scale of public facilities and other information, a basic database of regional power load is established.

[0062] The density clustering algorithm is used to cluster the number of household electrical equipment and the power consumption period to obtain the power load distribution coordinate data set. Through cluster analysis, the distribution characteristics of the power load in the target area can be obtained, such as high-load areas, low-load areas, and load change periods.

[0063] For the power load distribution coordinate data set, a genetic algorithm with constraints (such as NSGA-II) is used to calculate the power supply radius and power supply capacity of the distribution equipment. Through the iterative optimization process, the genetic algorithm can find the optimal solution or approximate optimal solution that meets the constraints (such as power supply reliability, economy, environmental protection, etc.). According to the calculation results of the genetic algorithm, the layout coordinate points of the distribution equipment in three-dimensional space are determined. These coordinate points should meet the requirements of power supply radius and power supply capacity, and minimize line loss and operation and maintenance costs.

[0064] According to the three-dimensional layout coordinate points of the power distribution equipment, Dijkstra's Algorithm is used to search for cable laying channels. Dijkstra's Algorithm is a classic algorithm for solving the single-source shortest path problem, which can find the shortest path from the starting point to all other points. In the cable laying path planning, the cable current carrying capacity and cross-sectional area can be used as weight values ​​to optimize the selection of cable paths.

[0065] The coordinate sequence of the cable routing path is obtained by the calculation of the Dijkstra algorithm. These coordinate sequences represent the cable routing path in three-dimensional space and should meet the requirements of safety, economy, and aesthetics.

[0066] Preferably, in one embodiment of the present application, simulation calculation is performed according to the initial layout scheme to obtain the power parameters of the target area, including:

[0067] According to the initial layout plan, a distribution network simulation model of the target area is established;

[0068] Setting simulation conditions based on the acquired environmental parameters of the target area;

[0069] The distribution network in the target area is simulated according to the distribution network simulation model and simulation conditions, and the power parameters of the distribution network are calculated.

[0070] Specifically, a distribution network simulation model is established, and environmental parameters (such as temperature, humidity, wind speed, etc.) are considered to set the simulation conditions. Through simulation, the power parameters of the distribution network, such as voltage, current, power factor, power level, frequency, etc., are calculated to evaluate the performance of the initial layout plan.

[0071] Furthermore, the thermal demand data of the target area is collected, including the demand for heating, cooling, hot water, etc. According to the thermal demand data, a thermal system layout plan that meets the thermal demand is planned. Through thermal system simulation or experiments, key parameters of the thermal system, such as heating capacity, temperature level, pressure level, heating time, etc., are obtained to evaluate the performance of the thermal system and optimize the layout of the thermal system.

[0072] S2: Extract high-frequency components of power parameters based on Haar wavelet transform method to obtain power fluctuation data set, and perform spectrum decomposition of thermal parameters based on Fourier transform method to obtain thermal fluctuation data set;

[0073] Among them, Haar wavelet transform is a commonly used discrete wavelet transform, which is used to decompose the signal into low-frequency approximate components and high-frequency detail components. For the power parameter data set, Haar wavelet transform is applied to perform multi-layer decomposition to extract the high-frequency components.

[0074] Specifically, the appropriate number of decomposition layers is selected, which depends on the range of fluctuation frequencies that you want to capture. Apply the Haar wavelet transform to the power parameter data set to obtain the low-frequency and high-frequency components of each layer. Extract the high-frequency components of the highest layer, which represent the high-frequency fluctuations in the power parameters. Organize the extracted high-frequency components into a power fluctuation data set.

[0075] Among them, Fourier transform is a mathematical tool that converts signals from time domain to frequency domain. For the thermal parameter data set, Fourier transform is applied to perform spectrum decomposition to obtain the amplitude and phase information of different frequency components.

[0076] Specifically, a fast Fourier transform (FFT) is applied to the thermal parameter data set to obtain a spectrum. The spectrum is analyzed to identify the main frequency components. The spectrum data within the frequency range of interest are extracted, which represent the different frequency fluctuations in the thermal parameters. The extracted spectrum data are organized into a thermal fluctuation data set.

[0077] S3: construct an electric and thermal fluctuation dataset based on the power fluctuation dataset and the thermal fluctuation dataset, perform cluster analysis on the electric and thermal fluctuation dataset, and obtain abnormal fluctuation aggregates;

[0078] Preferably, in one embodiment of the present application, constructing an electric and thermal fluctuation dataset according to the electric power fluctuation dataset and the thermal fluctuation dataset includes:

[0079] Perform time alignment processing on the electric power fluctuation data set and the thermal fluctuation data set to obtain an initial electric and thermal fluctuation data set;

[0080] Preprocessing the initial electrothermal fluctuation data set, including data cleaning, data denoising and data normalization;

[0081] Feature extraction is performed based on the initial electrothermal fluctuation data set after preprocessing, and the electrothermal fluctuation data set is constructed according to the extracted features.

[0082] It is understandable that before performing the time alignment process, it is necessary to ensure that the timestamps of the power fluctuation dataset and the thermal fluctuation dataset are continuous and have the same time interval. If the timestamps are discontinuous or the time intervals are different, interpolation or resampling is required.

[0083] Align the power fluctuation dataset and the thermal fluctuation dataset according to the timestamp. This means that for each time point, there must be corresponding power and thermal data. If a time point is missing from one of the datasets, you can choose to fill it in (such as using the data from the previous time point) or delete the time point (if there is not much missing data).

[0084] According to the analysis requirements, relevant features are selected from the preprocessed initial electric and thermal fluctuation data set. These features may include the fluctuation amplitude, fluctuation frequency, fluctuation trend, etc. of electric and thermal power. The selected features are extracted. The extracted features are combined to construct the electric and thermal fluctuation data set.

[0085] Preferably, in one embodiment of the present application, cluster analysis is performed on the electrothermal fluctuation data set to obtain abnormal fluctuation aggregates, including:

[0086] The electrothermal fluctuation data set is standardized, and a plurality of sample data in the standardized electrothermal fluctuation data set are randomly selected as initial clustering centers;

[0087] In the distance calculation process, the distance from each sample data in the electrothermal fluctuation data set to each initial cluster center is calculated;

[0088] In the process of determining the cluster center, the probability distribution of each sample data is calculated based on the distance, and a new cluster center is selected according to the probability distribution;

[0089] The distance calculation process and the cluster center determination process are repeated until an abnormal fluctuation aggregate reflecting abnormal fluctuations of power parameters and thermal parameters is obtained.

[0090] It is understandable that since different features in the electrothermal fluctuation dataset may have different dimensions and orders of magnitude, in order to eliminate such differences, the data needs to be standardized. Standardization can convert the data into a dimensionless form so that different features are comparable. Commonly used standardization methods include Z-score standardization and minimum-maximum standardization.

[0091] Randomly select multiple sample data from the standardized electrothermal fluctuation data set as initial cluster centers. These initial cluster centers will serve as the starting point of the clustering process. In each iteration, calculate the distance from each sample data in the electrothermal fluctuation data set to each initial cluster center (or current cluster center). Commonly used distance measurement methods include Euclidean distance, Manhattan distance, etc.

[0092] Based on the calculated distance, the probability distribution of each sample data belonging to each cluster center can be calculated. According to the probability distribution, a new cluster center is selected. The new cluster center is usually the maximum value point of the probability distribution in each cluster, or is calculated by weighted average or other methods. Repeat the above distance calculation process and cluster center determination process until a certain stopping condition is met. The stopping condition can be reaching the maximum number of iterations, the cluster center no longer changes (or changes very little), etc.

[0093] After multiple iterations, the final clustering results can be obtained. Some clusters may represent normal power and heat fluctuation patterns, while others may represent abnormal fluctuation patterns. These abnormal fluctuation patterns can be regarded as abnormal fluctuation aggregates.

[0094] S4: The bidirectional correlation between the power fluctuation dataset and the thermal fluctuation dataset is calculated based on the abnormal fluctuation aggregate, and the parameter matching result dataset of the target area is constructed based on the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation dataset and the thermal fluctuation dataset;

[0095] Preferably, in one embodiment of the present application, the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set is calculated according to the abnormal fluctuation aggregate, and the parameter matching result data set of the target area is constructed according to the bidirectional correlation, including:

[0096] Calculating a first correlation between the power fluctuation data set and the thermal fluctuation data set according to a preset correlation index;

[0097] Calculate a second correlation between the thermal fluctuation data set and the electric power fluctuation data set according to the correlation index;

[0098] Obtaining a bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the first correlation and the second correlation;

[0099] The parameters in the power fluctuation data set and the thermal fluctuation data set are matched according to the bidirectional correlation, and a parameter matching result data set reflecting the degree of interaction between the power fluctuation data set and the thermal fluctuation data set is obtained.

[0100] It is understandable that before calculating the correlation, one or more correlation indicators need to be preset. These indicators should be able to accurately reflect the degree of interaction between the power fluctuation data set and the thermal fluctuation data set. Commonly used correlation indicators include Pearson correlation coefficient, Kendall harmony coefficient, etc.

[0101] According to a preset correlation index, a first correlation between the power fluctuation data set and the thermal fluctuation data set is calculated. This usually involves statistical analysis of the two data sets to obtain a correlation coefficient or a rank correlation coefficient between them. Similarly, according to the preset correlation index, a second correlation between the thermal fluctuation data set and the power fluctuation data set is calculated.

[0102] The first correlation degree and the second correlation degree are averaged or weighted to obtain a bidirectional correlation degree between the power fluctuation data set and the thermal fluctuation data set. According to the calculated bidirectional correlation degree, the parameters in the power fluctuation data set and the thermal fluctuation data set are matched. In one embodiment of the present application, the matching principle may be that the higher the correlation degree, the higher the matching degree between the parameters. The matched parameters are organized according to a certain structure or format to construct a parameter matching result data set.

[0103] S5: Analyze the parameter matching result data set, and control the interface conversion device to optimize the initial layout plan according to the analysis result to achieve the distribution network layout optimization in the target area.

[0104] Preferably, in one embodiment of the present application, the parameter matching result data set is analyzed, and the interface conversion device is controlled to optimize the initial layout scheme according to the analysis result, including:

[0105] Preprocess the parameter matching result data set, including missing value detection and format conversion;

[0106] The preprocessed parameter matching result data set is input into the pre-built thermoelectric correlation model for analysis to obtain the analysis result;

[0107] An interface conversion device is designed based on the analysis results, and the matching of power parameters and thermal parameters in the target area is achieved through the interface conversion device.

[0108] Missing value detection includes: checking each data point in the parameter matching result data set, identifying and marking missing or abnormal data. For missing values, you can adopt a strategy of filling (such as using the mean, median, mode, etc.) or deletion. For abnormal values, you need to analyze their source and decide whether to keep or modify them.

[0109] Format conversion includes ensuring that the data type, unit, precision, etc. in the dataset meet the input requirements of the thermoelectric correlation model. For example, it may be necessary to convert certain values ​​from string format to numeric format, or to unify parameters in different units to the same standard.

[0110] In this step, the pre-built thermoelectric correlation model is used to analyze the parameter matching result data set to reveal the correlation and mutual influence between power parameters and thermal parameters. Specifically, the pre-processed parameter matching result data set is used as input and imported into the pre-built thermoelectric correlation model to generate analysis results. The analysis results are interpreted to identify the key correlation points between power and thermal parameters, such as correlation, sensitivity, synergy, etc.

[0111] Based on the analysis results, an interface conversion device is designed and implemented to optimize the initial layout plan and achieve matching of power and thermal parameters in the target area.

[0112] Preferably, in one embodiment of the present application, the interface conversion device includes a frequency converter module and a heat exchanger module;

[0113] The interface conversion device is used to match the power parameters and thermal parameters in the target area, including:

[0114] The conversion of power parameters is achieved through the inverter module, and the conversion of thermal parameters is achieved through the heat exchanger module, so as to achieve the matching of power and thermal parameters between the distribution networks in the target area.

[0115] Specifically, in order to solve the problem of mismatching parameters between the power system and the thermal system in the target area, this application designs an interface conversion device, which realizes the conversion of the frequency and voltage level of the power system and the temperature and pressure level of the thermal system by integrating the frequency converter module and the heat exchanger module, thereby achieving the matching of power and thermal parameters. Including:

[0116] Obtain the operating parameters of the inverter (such as input voltage, input frequency, output current, etc.) and the capacity parameters of the transformer (such as rated power, rated voltage, rated current, etc.). Based on the above parameters, calculate the rated capacity data of the inverter (such as maximum output power, maximum input current, etc.) and the speed regulation range data (such as minimum and maximum output frequencies).

[0117] According to the electric heat demand, the hot water load and heating heat load are calculated. Based on the hot water load and heating heat load, the flow parameters of the heat exchanger (such as circulating water volume, flow rate, etc.) and heat transfer coefficient parameters (such as heat transfer efficiency, thermal resistance, etc.) are calculated. These parameters will be used to determine the operating conditions of the heat exchanger.

[0118] For the operation condition of the heat exchanger, we need to consider the fluctuations between the inverter output parameters (such as output voltage, output frequency) and the heat exchanger output parameters (such as outlet water temperature, pressure, etc.). In one embodiment of the present application, in order to optimize these fluctuations, the constrained Lagrange multiplier method is used for calculation. Through calculation, the fluctuation optimization data of the inverter output parameters and the heat exchanger output parameters can be obtained.

[0119] In order to achieve a reasonable layout of the inverter module and the heat exchanger module in the interface conversion device, this application uses a hierarchical space layout algorithm for calculation. Based on the calculation results of the algorithm, the layout coordinate sequence of the inverter module and the heat exchanger module can be obtained. These coordinate sequences will meet the constraints of the insulation distance and heat dissipation spacing of the interface conversion device to ensure the safety and reliability of the system. According to the layout coordinate sequence, the inverter module and the heat exchanger module are reasonably installed inside the interface conversion device.

[0120] Preferably, in one embodiment of the present application, after optimizing the distribution network layout in the target area, the method further includes:

[0121] The distribution network layout of the target area is simulated according to the optimized distribution network layout, and the design parameters of the inverter module and the heat exchanger module are optimized according to the simulation results.

[0122] Preferably, in one embodiment of the present application, the design parameters of the inverter module and the heat exchanger module are optimized according to the simulation results, including:

[0123] The power parameters and thermal parameters of the distribution network in the target area are obtained through simulation, and the design parameters are adjusted in real time according to the power parameters and thermal parameters to achieve optimal configuration of the design parameters.

[0124] Specifically, after the distribution network layout is optimized, the distribution network in the target area is simulated using professional power system simulation software and thermal system simulation software. The simulation model needs to include information such as the optimized distribution network layout, power load distribution, thermal load distribution, connection methods of the inverter module and the heat exchanger module, and their initial design parameters.

[0125] In the simulation software, set reasonable simulation conditions, such as time step, simulation duration, load change mode, etc., and run the simulation model. During the simulation process, the software will calculate and output the power parameters (such as voltage, current, power factor, etc.) and thermal parameters (such as temperature, pressure, flow, etc.) of the distribution network in real time.

[0126] The simulation results are analyzed in detail to evaluate the performance of the optimized distribution network layout in actual operation, including the stability, efficiency, and safety of the power and thermal systems.

[0127] In one embodiment of the present application, the design parameters of the inverter module and the heat exchanger module are optimized according to the simulation results, including:

[0128] From the interface conversion device, obtain the operation record data of the inverter module and the heat exchanger module. These data should include key parameters such as current, voltage, temperature, pressure, etc. of the equipment under different working conditions. Clean and organize the obtained operation record data, remove abnormal values ​​and noise, and ensure the accuracy and reliability of the data.

[0129] Maxwell's equations are used to calculate the electromagnetic field distribution inside the inverter module, including the electric field strength, magnetic field strength, etc. Heat and mass transfer equations are used to calculate the temperature field and flow field distribution inside the heat exchanger module, including temperature gradient, flow velocity, etc.

[0130] The inverter space and heat exchanger space are divided into tetrahedral meshes to discretize the continuous space into a series of small tetrahedral units. This helps the accuracy and efficiency of subsequent numerical calculations. On the discretized tetrahedral meshes, the finite difference method and the finite volume method are used to calculate the current density distribution and the temperature gradient distribution. These methods can accurately simulate the distribution of electromagnetic fields and temperature fields.

[0131] The deep neural network is used to fit and calculate the inverter characteristics and heat exchanger characteristics. The neural network can learn and simulate the behavior characteristics of the equipment under different working conditions. The input current density distribution value and temperature gradient distribution value are used as the input of the neural network, and the output inverter output characteristics and heat exchanger heat transfer characteristics are used as the output of the neural network.

[0132] Calculate the error between the fitting value output by the neural network and the actual operation record data. According to the error results, train and adjust the neural network to improve the accuracy and precision of the fitting. At the same time, consider the coupling relationship between the inverter and the heat exchanger, and further correct and optimize the fitting results.

[0133] Based on the fitting results and error correction results of the deep neural network, the equipment operation correction values ​​are calculated. These correction values ​​reflect the performance deviation and optimization space of the equipment in actual operation. The electrical insulation strength and material temperature limit are input as constraints. These constraints ensure that the equipment operates within a safe and reliable range. Considering the impact of the constraints on the equipment operation correction values, the correction values ​​are adjusted and optimized.

[0134] Based on the adjusted equipment operation correction value and constraint conditions, the inverter output voltage limit and heat exchanger heat load limit are calculated. These limits are used as performance indicators after equipment optimization to guide the actual operation and maintenance of the equipment.

[0135] Furthermore, in one embodiment of the present application, based on the optimized design parameters of the inverter and heat exchanger modules in the interface device, the power and thermal parameters of the target area are monitored in real time, and the design parameters of the inverter and heat exchanger modules are adjusted to enable energy complementarity and optimal configuration of different energy forms between distribution networks of different residential buildings.

[0136] Specifically, power parameters such as voltage value, current value, power value, etc. are obtained from the power monitoring unit. Thermal parameters such as temperature value, pressure value, flow value, etc. are obtained from the thermal monitoring unit at preset time intervals.

[0137] Median filtering is used to eliminate noise in power parameters to improve the accuracy and reliability of data. Wavelet filtering is used to smooth thermal parameters to reduce the impact of data fluctuations on subsequent analysis. After filtering, an equidistant sampling data set is formed, providing a basis for subsequent data analysis and prediction.

[0138] Gradient boosted regression tree is used to predict the trend of power parameters. Gradient boosted regression tree can handle complex nonlinear relationships and improve the accuracy of prediction. Support vector regression is used to predict the trend of thermal parameters. Support vector regression has good performance in processing high-dimensional data and complex relationships. Combined with the inverter speed range and heat exchanger adjustment range, the operation adjustment parameters are generated according to the prediction results. These parameters will be used for subsequent equipment control and energy optimization configuration.

[0139] The power transmission limit is calculated through the line capacity to ensure that the power transmission is carried out within a safe range. The flow transmission limit is calculated through the pipeline resistance to ensure the stability and reliability of heat transmission. Combined with the operating constraints (such as equipment capacity, safety standards, etc.), the regional energy complementary configuration value is calculated.

[0140] According to the regional energy monitoring data structure, a linear programming solver with inequality constraints is used to optimize the calculation of power and thermal load data. The linear programming solver can efficiently handle optimization problems with constraints. The regional energy configuration optimization values ​​are obtained by taking the upper limit of the power distribution line and the upper limit of the pressure of the thermal network as constraints. These values ​​reflect the distribution of power and thermal loads in the target area distribution network while meeting safety and economic requirements.

[0141] Deep reinforcement learning is used to optimize the frequency adjustment of the inverter and the temperature adjustment of the heat exchanger. The inverter operating frequency limit and the heat exchanger operating temperature limit are used as constraints to obtain the equipment operation control quantity. These control quantities will be directly used for real-time control of the equipment.

[0142] According to the equipment operation control quantity, the Newton iteration method is used to balance the distribution power transmission and thermal flow transmission. Among them, the Newton iteration method can quickly converge to the optimal solution and is suitable for dealing with complex balance problems. The rated capacity of the interconnection line and the rated flow of the pipeline are used as boundary conditions to obtain the inter-regional energy complementary transmission instructions. These instructions will guide the power and heat transmission in the target area and realize the optimal configuration and complementary utilization of energy.

[0143] In one embodiment of the present application, by real-time monitoring and analysis of the operating data of the adjusted inverter and heat exchanger modules in the interface conversion device, a real-time assessment of the health status of the interface conversion device is performed based on the changing trend of the operating data within a preset time.

[0144] Specifically, the frequency converter monitoring device is used to collect voltage harmonic values, current harmonic values, power factor values, and speed vibration values ​​in real time. At the same time, the heat exchanger monitoring device is used to obtain fluid noise values, temperature fluctuation values, pressure fluctuation values, and pipeline vibration values ​​in real time.

[0145] The collected signals are processed by wavelet filtering to remove noise interference and improve the accuracy and reliability of the data. Wavelet filtering technology can adaptively process signals of different frequencies to achieve effective noise reduction.

[0146] Perform fast Fourier transform (FFT) on the monitoring signal after noise reduction to convert it from time domain to frequency domain. By calculating the ratio of fundamental component to harmonic component, the harmonic distortion rate is obtained to evaluate the degree of signal distortion. At the same time, the root mean square value (RMS) of the vibration signal is calculated to obtain the amplitude value to reflect the strength of the vibration signal.

[0147] Key features are extracted from the harmonic distortion rate and amplitude values, which can reflect the operating status of the inverter and heat exchanger. The harmonic distortion rate reflects the distortion of the signal, while the amplitude value reflects the strength of the vibration signal. Together, they constitute an important basis for evaluating the health status of the equipment.

[0148] The long short-term memory network (LSTM) is used to model the trend of the inverter insulation aging index, bearing wear index, heat exchanger scaling coefficient and pipeline corrosion rate. The LSTM network can capture the long-term dependencies in time series data and is suitable for long-term tracking and prediction of equipment health status. By inputting the pre-processed monitoring data, the LSTM network can output the equipment operation health value, which reflects the current health status of the equipment. The output results of the LSTM network are used to perform trend analysis on the equipment operation health value. By observing the changing trend of the health value, the future health status of the equipment can be predicted, providing decision support for equipment maintenance and management.

[0149] Recurrent neural network (RNN) is used to predict the insulation aging rate, bearing wear rate, scaling growth rate and corrosion expansion rate. RNN network can handle the time dependency in sequence data and is suitable for predicting the dynamic changes of equipment status. By inputting the output results of LSTM network, RNN network can output the predicted value of the future state of the equipment, which provides an important reference for the preventive maintenance of the equipment. According to the output results of RNN network, the operation status evaluation results are generated. The evaluation results include the current health status of the equipment, the predicted value of the future health status and the corresponding maintenance suggestions. These evaluation results can provide a scientific basis for the maintenance and management of the equipment and improve the reliability and service life of the equipment.

[0150] The obtained health status of the interface conversion device is compared with the preset health status threshold. If the health status of the interface conversion device is lower than the preset health status threshold, the corresponding recovery strategy is matched in the pre-built recovery strategy library, and during the execution of the recovery strategy, the health status of the interface conversion device is continuously evaluated. If the health status of the interface conversion device changes, the matched recovery strategy is dynamically adjusted.

[0151] Compared with the prior art, the embodiments of the present application have the following advantages:

[0152] 1) The high-frequency components of power parameters are extracted by using Haar wavelet transform, which can accurately capture the detailed information of power fluctuations, such as instantaneous changes, periodic fluctuations, etc.; the frequency components of thermal fluctuations can be analyzed by performing spectral decomposition of thermal parameters through Fourier transform, which provides a powerful tool for subsequent clustering analysis and correlation calculation.

[0153] 2) Cluster analysis of the electric and thermal fluctuation data set can identify abnormal fluctuation clusters in power and thermal parameters. These abnormal fluctuations may represent potential problems or unstable factors in the power grid or thermal system. By identifying abnormal fluctuations, potential safety hazards can be discovered and dealt with in a timely manner, thereby improving the stability of the power grid and thermal system.

[0154] 3) Based on the abnormal fluctuation aggregate, the two-way correlation between the power fluctuation data set and the thermal fluctuation data set is calculated, reflecting the degree of interaction between the two. Through correlation analysis, we can gain an in-depth understanding of the mutual influence between the power and thermal systems, providing a scientific basis for the subsequent optimization of the distribution network layout.

[0155] Another embodiment of the present application provides a distribution network layout optimization system. For details, see Figure 2 , Figure 2 The structure diagram of the distribution network layout optimization system in one embodiment of the present application is shown, which is applied to the target area distribution network provided with an interface conversion device, and includes an acquisition module 11, an extraction module 12, a clustering module 13, a calculation module 14, an analysis module 15,

[0156] The acquisition module 11 is used to layout the distribution network of the target area based on the acquired power demand of the target area, obtain an initial layout plan, perform simulation according to the initial layout plan, and obtain power parameters of the target area; analyze the acquired thermal demand of the target area to obtain thermal parameters of the target area;

[0157] An extraction module 12 is used to extract high-frequency components of power parameters based on a Haar wavelet transform method to obtain a power fluctuation data set, and to perform spectrum decomposition of thermal parameters based on a Fourier transform method to obtain a thermal fluctuation data set;

[0158] A clustering module 13 is used to construct an electric and thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set, and to perform cluster analysis on the electric and thermal fluctuation data set to obtain an abnormal fluctuation aggregate;

[0159] A calculation module 14 is used to calculate the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and to construct a parameter matching result data set of the target area according to the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation data set and the thermal fluctuation data set;

[0160] The analysis module 15 is used to analyze the parameter matching result data set and control the interface conversion device to optimize the initial layout plan according to the analysis result to achieve the distribution network layout optimization in the target area.

[0161] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A distribution network layout optimization method, characterized in that: Applicable to the target area distribution network provided with the interface conversion device, including: Based on the acquired power demand of the target area, the distribution network of the target area is laid out to obtain an initial layout plan, and simulation is performed according to the initial layout plan to obtain power parameters of the target area; the acquired thermal demand of the target area is analyzed to obtain thermal parameters of the target area; Extract high-frequency components of the power parameters based on the Haar wavelet transform method to obtain a power fluctuation data set, and perform spectrum decomposition of the thermal parameters based on the Fourier transform method to obtain a thermal fluctuation data set; constructing an electric-thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set, and performing cluster analysis on the electric-thermal fluctuation data set to obtain an abnormal fluctuation aggregate; calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and constructing the parameter matching result data set of the target area according to the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation data set and the thermal fluctuation data set; The step of calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and constructing the parameter matching result data set of the target area according to the bidirectional correlation comprises: Calculating a first correlation between the power fluctuation data set and the thermal fluctuation data set according to a preset correlation index; Calculating a second correlation between the thermal fluctuation data set and the electric power fluctuation data set according to the correlation index; Obtaining a bidirectional correlation between the power fluctuation dataset and the thermal fluctuation dataset according to the first correlation and the second correlation; Matching the parameters in the power fluctuation dataset and the thermal fluctuation dataset according to the bidirectional correlation to obtain a parameter matching result dataset reflecting the degree of interaction between the power fluctuation dataset and the thermal fluctuation dataset; The parameter matching result data set is analyzed, and according to the analysis result, the interface conversion device is controlled to optimize the initial layout scheme to achieve the distribution network layout optimization in the target area.

2. The method for optimizing the distribution network layout according to claim 1, characterized in that: The performing simulation calculation according to the initial layout scheme to obtain the power parameters of the target area includes: According to the initial layout plan, a distribution network simulation model of the target area is established; Setting simulation conditions based on the acquired environmental parameters of the target area; The distribution network of the target area is simulated according to the distribution network simulation model and the simulation conditions, and the power parameters of the distribution network are calculated.

3. The method for optimizing the distribution network layout according to claim 1, characterized in that: The step of constructing the electric and thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set comprises: Performing time alignment processing on the electric power fluctuation data set and the thermal fluctuation data set to obtain an initial electric and thermal fluctuation data set; Preprocessing the initial electrothermal fluctuation data set, wherein the preprocessing includes data cleaning, data denoising and data normalization; Feature extraction is performed based on the preprocessed initial electrothermal fluctuation data set, and the electrothermal fluctuation data set is constructed according to the extracted features.

4. The method for optimizing the distribution network layout according to claim 1, characterized in that: The cluster analysis of the electrothermal fluctuation data set to obtain abnormal fluctuation aggregates includes: Performing standardization processing on the electrothermal fluctuation data set, and randomly selecting a plurality of sample data in the electrothermal fluctuation data set after the standardization processing as initial clustering centers; In the distance calculation process, the distance from each sample data in the electrothermal fluctuation data set to each of the initial cluster centers is calculated; In the process of determining the cluster center, the probability distribution of each of the sample data is calculated based on the distance, and a new cluster center is selected according to the probability distribution; The distance calculation process and the cluster center determination process are repeated until the abnormal fluctuation aggregate reflecting the abnormal fluctuation of the power parameter and the thermal parameter is obtained.

5. The method for optimizing the distribution network layout according to claim 1, characterized in that: The step of analyzing the parameter matching result data set and controlling the interface conversion device to optimize the initial layout scheme according to the analysis result includes: Preprocessing the parameter matching result data set, wherein the preprocessing includes missing value detection and format conversion; Inputting the preprocessed parameter matching result data set into a pre-built thermoelectric correlation model for analysis to obtain analysis results; An interface conversion device is designed according to the analysis result, and the matching of the power parameters and the thermal parameters in the target area is achieved through the interface conversion device.

6. The method for optimizing the layout of a distribution network according to claim 5, characterized in that: The interface conversion device includes a frequency converter module and a heat exchanger module; The matching of the power parameter and the thermal parameter in the target area by the interface conversion device includes: The conversion of the power parameters is achieved through a frequency converter module, and the conversion of the thermal parameters is achieved through a heat exchanger module, so as to achieve matching of power and thermal parameters between the distribution networks in the target area.

7. The method for optimizing the layout of a distribution network according to claim 6, characterized in that: After achieving the distribution network layout optimization in the target area, the method further includes: The distribution network layout of the target area is simulated according to the optimized distribution network layout, and the design parameters of the inverter module and the heat exchanger module are optimized according to the simulation results.

8. The method according to claim 7, characterized in that The optimizing the design parameters of the inverter module and the heat exchanger module according to the simulation results includes: The power parameters and thermal parameters of the target area distribution network are obtained through simulation, and the design parameters are adjusted in real time according to the power parameters and the thermal parameters to achieve optimal configuration of the design parameters.

9. A distribution network layout optimization system, characterized in that: Applicable to the target area distribution network provided with the interface conversion device, including: An acquisition module is used to layout the distribution network of the target area based on the acquired power demand of the target area to obtain an initial layout plan, perform simulation according to the initial layout plan to obtain power parameters of the target area; and analyze the acquired thermal demand of the target area to obtain thermal parameters of the target area; An extraction module, used for extracting high-frequency components of the power parameters based on a Haar wavelet transform method to obtain a power fluctuation data set, and performing spectrum decomposition of the thermal parameters based on a Fourier transform method to obtain a thermal fluctuation data set; A clustering module, used for constructing an electric and thermal fluctuation data set according to the electric power fluctuation data set and the thermal fluctuation data set, and performing cluster analysis on the electric and thermal fluctuation data set to obtain an abnormal fluctuation aggregate; A calculation module, used for calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and constructing the parameter matching result data set of the target area according to the bidirectional correlation; the bidirectional correlation reflects the degree of interaction between the power fluctuation data set and the thermal fluctuation data set; wherein, the calculating the bidirectional correlation between the power fluctuation data set and the thermal fluctuation data set according to the abnormal fluctuation aggregate, and constructing the parameter matching result data set of the target area according to the bidirectional correlation, comprises: Calculating a first correlation between the power fluctuation data set and the thermal fluctuation data set according to a preset correlation index; Calculating a second correlation between the thermal fluctuation data set and the electric power fluctuation data set according to the correlation index; Obtaining a bidirectional correlation between the power fluctuation dataset and the thermal fluctuation dataset according to the first correlation and the second correlation; Matching the parameters in the power fluctuation dataset and the thermal fluctuation dataset according to the bidirectional correlation to obtain a parameter matching result dataset reflecting the degree of interaction between the power fluctuation dataset and the thermal fluctuation dataset; The analysis module is used to analyze the parameter matching result data set and control the interface conversion device to optimize the initial layout plan according to the analysis result to achieve the distribution network layout optimization in the target area.

Images