Electric power engineering design method and system

Abstract

The invention discloses an electric power engineering design method and system, and the method comprises the steps: obtaining the rated load and historical peak load data of an electric power engineering node, carrying out the numerical analysis, obtaining a load toughness value Rx, constructing a node toughness sequence, constructing a feature parameter vector of the node, determining a weak node through a genetic algorithm, and obtaining the expected distribution load of the weak node, whether the expected distribution load needs to be analyzed or not is judged, if the expected distribution load needs to be analyzed, the expected distribution load is predicted, overload time is obtained, the overload time and expected life time are combined to calculate a load adjustment factor and a rated adjustment load, weak nodes are redesigned, and it is judged that the redesigned weak nodes are not weak any more; the invention further provides a corresponding electric power engineering design system, computer equipment and a computer readable storage medium, and the stability of the electric power engineering can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power engineering design, and in particular to an electric power engineering design method and system. Background Art

[0002] In the field of power engineering, with the continuous development of social economy and the increasing demand for electricity, the stability and reliability of the power system are facing severe challenges. Traditional power engineering design has gradually exposed many shortcomings when dealing with the complex and changing power environment.

[0003] The existing technology does not comprehensively consider the historical operating data, rated load and expected service life of the nodes, which results in the inability of the existing technology to identify weak nodes in power projects and it is difficult to provide targeted guidance for system optimization and maintenance. If the rated load of the weak nodes cannot meet the actual needs during long-term operation, it will affect the overall reliability and power supply quality of the power system.

[0004] The existing technology does not conduct detailed predictive analysis of the expected distributed load of weak nodes, does not fully consider the load changes caused by the difference in the time when the buildings around the nodes are put into use, and then determine the overload time of the weak nodes. It does not regulate and optimize the weak nodes, nor does it re-analyze the redesigned weak nodes, making it difficult to ensure the stable operation of the power project.

[0005] To this end, the present invention provides a power engineering design method and system. Summary of the invention

[0006] The object of the present invention is to provide a power engineering design method and system to solve at least one of the above-mentioned prior art problems.

[0007] In a first aspect, the present invention provides a power engineering design method, comprising:

[0008] Step 1: Obtain the rated load and historical peak load data of the power engineering node, and store the rated load and historical peak load data in the node database;

[0009] Step 2: numerically analyze the historical peak load data in the node database to obtain the load toughness value Rx, and construct a node toughness sequence based on the load toughness value Rx;

[0010] Step 3: Based on the node resilience sequence, obtain the rated load and expected life of each node of the power project, and construct the characteristic parameter vector T of each power project node ij , based on the characteristic parameter vector T ijUse genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes;

[0011] Step 4: If it is necessary to analyze the expected distributed load of the weak node, perform a forecast analysis on the expected distributed load of the weak node to determine the overload time of the weak node;

[0012] Step 5. Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz. Based on the load adjustment factor, a numerical calculation is performed to obtain the rated adjustment load. Based on the rated adjustment load, the weak node is redesigned, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node no longer becomes a weak node.

[0013] In a second aspect, the present invention provides a power engineering design system, comprising:

[0014] Load acquisition module: obtains the rated load and historical peak load data of the power engineering node, and stores the rated load and historical peak load data in the node database;

[0015] Sequence construction module: Perform numerical analysis on the historical peak load data in the node database to obtain the load toughness value Rx, and construct the node toughness sequence based on the load toughness value Rx;

[0016] Node identification module: Based on the node toughness sequence, the rated load and expected life of each node of the power project are obtained, and the characteristic parameter vector T of each power project node is constructed. ij , based on the characteristic parameter vector T ij Use genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes;

[0017] Prediction and analysis module: if it is necessary to analyze the expected distribution load of the weak node, the expected distribution load of the weak node is predicted and analyzed to determine the overload time of the weak node;

[0018] Node adjustment module: Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz, and the rated adjustment load is obtained by numerical calculation based on the load adjustment factor. The weak node is redesigned based on the rated adjustment load, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node no longer becomes a weak node.

[0019] Beneficial effects of the present invention:

[0020] 1. By obtaining the node load data in the power project and constructing a node resilience sequence, combined with the rated load and expected life, the genetic algorithm model is used to determine the weak nodes. For these weak nodes, their overload time is further predicted, and the rated load is adjusted based on scientific calculations to achieve targeted optimization design of weak nodes. This processing method enhances the stability of the overall structure of the power project and effectively reduces the risk of insufficient power load supply caused by weak nodes.

[0021] 2. Accurately judge the load change trend by constructing time series and calculating the Pearson correlation coefficient, and make accurate prediction and analysis on the expected distribution load of weak nodes based on this, so that the power engineering design can better adapt to the complex and changeable power consumption environment, meet the growing power demand, and reduce the waste of resources or insufficient power supply capacity caused by over-design or under-design. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is a flowchart of node acquisition and resilience analysis provided by the first embodiment of the present invention;

[0024] Figure 2 is a flowchart of node adjustment and optimization provided by Embodiment 2 of the present invention;

[0025] Figure 3 This is a module diagram of a power engineering design system provided by Embodiment 3 of the present invention;

[0026] Figure 4 It is a structural diagram of a computer device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] Embodiment 1

[0029] Figure 1 This is a flowchart of a node acquisition and resilience analysis method provided in Embodiment 1 of the present invention. The embodiment of the present invention can be applied to the case of power engineering node analysis. The node acquisition and resilience method can be executed by a power engineering design system. The power engineering design system can be implemented by software or hardware. The power engineering design system can be configured in a computer device. Optionally, the computer device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and the embodiment of the present invention does not limit this.

[0030] like Figure 1 As shown, the node acquisition and resilience analysis method provided by the embodiment of the present invention specifically includes the following steps:

[0031] Step 1: Obtain the rated load and historical peak load data of the power engineering node, and store the rated load and historical peak load data in the node database;

[0032] In some embodiments, based on the power engineering design drawings, power engineering nodes are obtained, and the power engineering nodes include substations, transformers, converter stations, distribution boxes, etc.;

[0033] In some embodiments, historical load data of nodes of the same type are obtained in a power monitoring and acquisition system based on historical power engineering, and exported as a csv file, and the csv file is analyzed using Python's pandas and numpy libraries to obtain the historical peak load, peak load maintenance time, and peak demand time of the historical power engineering;

[0034] Obtain the rated load of each node of the power project and the historical peak load data of each node of the power project, wherein the historical peak load data includes: historical peak load, peak demand time, and peak load maintenance time;

[0035] Store the rated load and historical peak load of each node of the power project in the node database;

[0036] Step 2: Based on the node database, numerical analysis is performed on the historical peak load data of the power engineering node to obtain the load resilience value Rx, and a node resilience sequence is constructed based on the load resilience value Rx;

[0037] Extract the rated load and historical peak load data of each node from the node database;

[0038] The historical peak load of each node is subtracted from the rated load and the absolute value is taken to obtain the node load difference;

[0039] The node load difference is processed as a ratio with the peak load of the corresponding node to obtain the node load ratio, and the node load ratio is marked as Jh;

[0040] The maintenance time of the historical peak load of each node is processed by ratio with the peak demand time to obtain the node peak time ratio, which is marked as Jf;

[0041] Based on the node load ratio Jh and the node peak time ratio Jf, the load toughness value Rx is calculated;

[0042] By formula: Obtain the load toughness value Rx, where a = 0.785, b = 0.215;

[0043] Obtain the load resilience value Rx of each power engineering node, and construct a node resilience sequence according to the order of the load resilience value Rx of each node from large to small;

[0044] Node resilience sequence Rx i =[Rx 1 , Rx 2 , .., Rx n ], where i is the node number, i = 1, 2, ..., n, n is the total number of nodes;

[0045] The technical solution of this embodiment is: obtain the rated load and historical peak load data of the power engineering node, store the rated load and historical peak load data in the node database, perform numerical analysis on the historical peak load data of the power engineering node based on the node database, obtain the load toughness value Rx, construct a node toughness sequence based on the load toughness value Rx, and provide a data basis for analyzing the weakest node by determining the node toughness sequence.

[0046] Embodiment 2

[0047] like Figure 2 As shown, the node adjustment and optimization described in this embodiment includes the following steps:

[0048] Step 3: Based on the node resilience sequence, obtain the rated load and expected life of each node of the power project, and construct the characteristic parameter vector T of each power project node ij , based on the characteristic parameter vector T ij Use genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes;

[0049] In some embodiments, the maintenance files of historical power engineering projects are consulted to obtain the connectivity of power engineering nodes and the expected life span of each engineering node;

[0050] Based on the node resilience sequence, the rated load of each node and the expected life of each node in the power engineering design are obtained;

[0051] Construct a characteristic parameter vector T for each power engineering node ij =[t i1 , t i2 , t i3 ], where i is the number of the power engineering node, i = 1, 2, ..., n, j = 1, 2, 3, t i1 , t i2 , t i3 , are the load toughness value of each node, the rated load of each node, and the expected life time of each node;

[0052] Based on the characteristic parameter vector T of each node ij A node resilience analysis model is constructed using a genetic algorithm, and weak nodes of the power project are determined based on the node resilience analysis model;

[0053] Specifically, the node resilience analysis model is constructed as follows:

[0054] S1. For each node feature parameter vector T ij The load toughness value, rated load and expected life are binary coded. The length of the binary coding of the load toughness value, rated load and expected life of each node is 7 bits, 7 bits and 4 bits respectively. After the binary coding operation of the characteristic parameter vector of each node is performed, an 18-bit binary coding chromosome is established;

[0055] S2, genetic algorithm initialization: set the population size N = 50, randomly generate 50 chromosomes as the initial population, and number the chromosomes, j = 1, 2, ..., 50;

[0056] S3. Determine the fitness function F: F = c*t i1 +d*t i2 +e*t i3 , where c = 0.53, d = 0.361, e = 0.215;

[0057] It should be noted that the node load resilience value t i1 The lower the rated load t i2 The lower the life expectancy, i3 The lower the node fitness, the lower the fitness of the power engineering node, which means that the node is weak in the power engineering;

[0058] S4. Genetic operation: Use the roulette wheel selection method to calculate the sum of the fitness of all chromosomes Calculate the probability P of the chromosome being selected j , Select the chromosomes with probability in the range of [0.5,1] as the parent individuals, repeat N times, and select N parent individuals;

[0059] For example, if there are three chromosomes with fitness of 2, 3, and 5, the total fitness is 10. The fitness is ratioed to the total fitness. The probability of chromosomes with fitness of 2, 3, and 5 being selected is 0.2, 0.3, and 0.5, respectively. Then the chromosome with fitness of 5 is selected as the parent individual.

[0060] Determine the crossover probability Pc = 0.7, use the single-point crossover method to select the parent individuals, exchange the binary codes of the chromosomes of the two parent individuals at a random position on the chromosome, generate two offspring individuals, determine the mutation probability Pm = 0.01, and perform mutation operations on the binary codes of each chromosome of the offspring individuals generated by the crossover according to the mutation probability Pm, changing the binary codes of the chromosomes from 1 to 0, and 1 to 0;

[0061] For example, the crossover probability Pc=0.7, for each pair of selected parent individuals, a random number r in the interval [0,1] is generated, if r is less than Pc, a crossover operation is performed on the parent individuals, otherwise, the two parent individuals are copied to the offspring population;

[0062] If a crossover operation is required, a random number k is generated as the crossover point within the chromosome length range L, and the range of k is within [1, L). If the two parent individuals A = a 1 、a 2 ,...a L , B=b 1 、b 2 , ..., b L , k = 2, then the parent individual after the crossover operation is A′ = a 1 、b 2 ,...b L , B′=b 1 、a 2 ,...a L ;

[0063] S4, iterative termination: add the offspring after crossover and mutation to the new population, calculate the fitness of each individual in the new population, repeat the selection, crossover, and mutation operations, and terminate the algorithm when the number of crossover and mutation reaches 200, and select the node with the lowest fitness as the weak node;

[0064] Determine the weak nodes of power engineering based on the node resilience analysis model;

[0065] It should be noted that determining the weak nodes of the power project based on the toughness, rated load, and expected life of the nodes and analyzing the weak nodes of the power project will help improve the stability of the power project;

[0066] In some embodiments, obtaining an expected distributed load for an area served by the power project;

[0067] Obtain the expected distributed load of the weak node and compare it with the rated load of the weak node;

[0068] If the expected distributed load is lower than the rated load of the weak node, the expected distributed load of the weak node needs to be analyzed;

[0069] If the expected distributed load is higher than the rated load of the weak node, adjust the design load of the power engineering of the weak node so that the rated load of the weak node meets the needs of the expected distributed load;

[0070] Step 4: If it is necessary to analyze the expected distributed load of the weak node, perform a forecast analysis on the expected distributed load of the weak node to determine the overload time of the weak node;

[0071] If the expected distribution load of the weak node needs to be analyzed, the expected distribution load is segmented according to time, the expected distribution load of each time period is obtained, and the time series X is constructed. i =[x 1 x 2 ...x m ], where i represents the time corresponding to the time period, and the value range of i is [1, m], x 1 represents the expected distribution load of the first time period, and m represents the total number of time periods;

[0072] Construct the expected distribution load series Y i , Y i =[y 1 y 2 ...y m ];

[0073] It should be noted that due to the differences in the time when the buildings around the power engineering node are put into use, the expected distribution load changes gradually over time;

[0074] Based on the time series of weak nodes of the power project and the expected distribution load series, the Pearson correlation coefficient r of the time series and the expected distribution load series is calculated;

[0075] Specifically, the Pearson correlation coefficient r is obtained as follows:

[0076] By formula: Get the Pearson correlation coefficient r, where the value range of r is [-1,1], Cov(X i ,Y i ) is the covariance,

[0077] Among them, σ Xi , σ Yi The time series X i , expected distribution load sequence Y i Standard Deviation

[0078] Based on the Pearson correlation coefficient r, the difference between r and the maximum endpoint of the value range of r is processed to obtain the coefficient approximate difference;

[0079] The coefficient approximation difference is processed by ratio with the length of the r value range to obtain the coefficient approximation ratio;

[0080] Obtain the coefficient proximity ratio of m data in the sequence, sum and average the coefficient proximity ratios of the m data, and obtain the mean of the proximity ratio;

[0081] Compare the absolute value of the proximity ratio mean with the proximity ratio threshold to determine the time series X i , expected load distribution sequence Y i relevance;

[0082] It should be noted that the proximity ratio threshold is set by professionals in this field based on experience;

[0083] If the absolute value of the mean of the proximity ratio is higher than the threshold value, and the mean of the proximity ratio is greater than 0, then the time series X i , expected load distribution sequence Y i It shows a linear growth trend;

[0084] If the absolute value of the mean of the proximity ratio is lower than the proximity ratio threshold, then the time series X i , expected load distribution sequence Y i It is nonlinearly related;

[0085] If the absolute value of the mean of the proximity ratio is lower than the threshold value of the proximity ratio, and the mean of the proximity ratio is less than 0, then the time series X i , expected load distribution sequence Y i It shows a linear downward trend and no treatment is done;

[0086] If the time series X i , expected load distribution sequence Y i It shows a linear growth trend. i , expected load distribution sequence Y iThe least square method is used for fitting, with the X-axis being time and the Y-axis being the expected distributed load, and a prediction curve of time-expected distributed load is drawn in a two-dimensional coordinate system;

[0087] Taking the rated load of the weak node as the reference value, draw the rated load reference line in the two-dimensional coordinate system;

[0088] Extend the prediction curve of time-expected load distribution and intersect it with the rated load reference line, obtain the horizontal coordinate of the intersection of the rated load reference line and the prediction curve of time-expected load distribution, and obtain the overload time of the weak node;

[0089] If the absolute value of the mean of the proximity ratio is lower than the proximity ratio threshold, then the time series X i , expected load distribution sequence Y i It is nonlinearly related;

[0090] With the X-axis being time and the Y-axis being the expected distributed load, a time-expected distributed load variation curve is drawn in a two-dimensional coordinate system;

[0091] Acquisition time - the maximum value of the slope in the change curve of the expected distribution load. Based on the maximum value of the slope, calculate the time when the expected distribution load reaches the rated load and obtain the overload time of the weak node;

[0092] Step 5: Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz, and based on the load adjustment factor, a numerical calculation is performed to obtain the rated adjustment load. Based on the rated adjustment load, the weak node is redesigned, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node is no longer a weak node;

[0093] Based on the overload time of the weak node, the time corresponding to the expected life of the weak node is obtained to obtain the expected life time;

[0094] Based on the overload time of the weak node, the overload time of the weak node is compared with the expected life time of the weak node;

[0095] If the overload time of a weak node is longer than the expected life time of the weak node, the weak node in the power project will not be redesigned;

[0096] If the overload time of the weak node is lower than the expected life time of the weak node, the expected life time of the weak node is subtracted from the overload time to obtain the load life difference;

[0097] The load life difference is processed by ratio with the overload time to obtain the load life ratio of the weak node, and the load life ratio is marked as Fhs;

[0098] Based on the load life ratio Fhs and load toughness Rx of the weak node, calculate the load adjustment factor Tyz;

[0099] By formula: Obtain the load adjustment factor Tyz, g = 0.514, f = 0.65;

[0100] Multiply the rated load of the weak node by the load adjustment factor Tyz to obtain the rated additional load;

[0101] The rated additional load is summed with the rated load of the weak node to obtain the rated adjustment load;

[0102] Redesign the weak nodes of the power project according to the rated adjustment load, and substitute the redesigned weak nodes into the node resilience analysis model;

[0103] Identify the weak nodes again to determine whether the redesigned weak nodes become weak nodes again;

[0104] If the weak node after redesign does not become a weak node again, no treatment will be done;

[0105] If the redesigned weak node becomes a weak node again, the rated adjusted load and the load adjustment factor are continuously calculated to obtain a new rated adjusted load until the redesigned weak node no longer becomes a weak node;

[0106] The technical solution of this embodiment is: based on the node toughness sequence, the rated load and expected life of each node of the power project are obtained, and the characteristic parameter vector T of each power project node is constructed. ij , based on the characteristic parameter vector T ij A node resilience analysis model is constructed using a genetic algorithm to determine the weak nodes in the power project, obtain the expected distributed load of the weak nodes, and determine whether it is necessary to analyze the expected distributed load of the weak nodes. If it is necessary to analyze the expected distributed load of the weak nodes, a predictive analysis is performed on the expected distributed load of the weak nodes to determine the overload time of the weak nodes. Based on the overload time of the weak nodes, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz. The rated adjusted load is obtained by numerical calculation based on the load adjustment factor. The weak nodes are redesigned based on the rated adjusted load, and it is determined whether the redesigned weak nodes become weak nodes again. If they become weak nodes again, the rated adjusted load is continuously optimized until the redesigned weak nodes no longer become weak nodes, which is beneficial to reduce the waste of resources or insufficient power supply capacity caused by over-design or insufficient design.

[0107] Embodiment 3

[0108] like Figure 3 As shown, a power engineering design system includes:

[0109] Load acquisition module: obtains the rated load and historical peak load data of the power engineering node, and stores the rated load and historical peak load data in the node database;

[0110] Sequence construction module: Based on the node database, the historical peak load data of the power engineering node is numerically analyzed to obtain the load resilience value Rx, and the node resilience sequence is constructed based on the load resilience value Rx;

[0111] Node identification module: Based on the node toughness sequence, the rated load and expected life of each node of the power project are obtained, and the characteristic parameter vector T of each power project node is constructed. ij , based on the characteristic parameter vector T ij Use genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes;

[0112] Prediction and analysis module: if it is necessary to analyze the expected distribution load of the weak node, the expected distribution load of the weak node is predicted and analyzed to determine the overload time of the weak node;

[0113] Node adjustment module: Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz, and the rated adjustment load is obtained by numerical calculation based on the load adjustment factor. The weak node is redesigned based on the rated adjustment load, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node is no longer a weak node;

[0114] Embodiment 4

[0115] Reference Figure 4 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, an electric power engineering design method as described in any one of the above methods is implemented.

[0116] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that

[0117] Figure 4It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0118] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0119] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0120] Embodiment 5

[0121] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, an electric power engineering design method as described in any one of the above methods is implemented.

[0122] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0123] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0125] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0128] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A power engineering design method, characterized in that: The following steps are involved: Step 1: Obtain the rated load and historical peak load data of the power engineering node, and store the rated load and historical peak load data in the node database; Step 2: numerically analyze the historical peak load data in the node database to obtain the load toughness value Rx, and construct a node toughness sequence based on the load toughness value Rx; Step 3: Based on the node toughness sequence, obtain the rated load and expected life of each node of the power project, and build the characteristic parameter vector T of each power project node. ij , based on the characteristic parameter vector T ij Use genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes; Step 4: If it is necessary to analyze the expected distributed load of the weak node, perform a forecast analysis on the expected distributed load of the weak node to determine the overload time of the weak node; Step 5. Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz. Based on the load adjustment factor, a numerical calculation is performed to obtain the rated adjustment load. Based on the rated adjustment load, the weak node is redesigned, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node no longer becomes a weak node.

2. A power engineering design method according to claim 1, characterized in that: The load toughness value Rx is obtained as follows: The rated load and historical peak load data of each node are extracted from the node database and numerically calculated to obtain the node load ratio Jh and node peak time ratio Jf; Based on the node load ratio Jh and the node peak time ratio Jf, the load toughness value Rx is calculated; By formula: Obtain the load toughness value Rx, where a and b are preset proportional coefficients; Obtain the load resilience value Rx of each power engineering node, and construct a node resilience sequence according to the order of the load resilience value Rx of each node from large to small; Node resilience sequence Rx i =[Rx1, Rx2, .., Rx n ], where i is the number of nodes, i=1,2,..., n, n is the total number of nodes.

3. A power engineering design method according to claim 2, characterized in that: The node load ratio Jh is obtained as follows: Extracting the rated load and historical peak load data of each node from the node database, wherein the historical peak load data includes the historical peak load, the maintenance time of the historical peak load, and the peak demand time; The historical peak load of each node is subtracted from the rated load and the absolute value is taken to obtain the node load difference; The node load difference is processed as a ratio with the peak load of the corresponding node to obtain the node load ratio, and the node load ratio is marked as Jh; The node peak time ratio Jf is obtained as follows: The maintenance time of the historical peak load of each node is ratioed to the peak demand time to obtain the node peak time ratio, which is marked as Jf.

4. A power engineering design method according to claim 1, characterized in that: The node resilience sequence is constructed as follows: Obtain the load resilience value Rx of each power engineering node, and construct a node resilience sequence according to the order of the load resilience value Rx of each node from large to small; Node resilience sequence Rx i =[Rx1, Rx2, .., Rx n ], where i is the node number, i = 1, 2, ..., n, and n is the total number of nodes.

5. A power engineering design method according to claim 1, characterized in that: The weak nodes in the power engineering are determined as follows: Based on the node resilience sequence, the rated load of each node and the expected life of each node in the power engineering design are obtained; Construct a characteristic parameter vector T for each power engineering node ij =[t i1 , t i2 , t i3 ], where i is the node number, i = 1, 2, ..., n, j = 1, 2, 3, t i1 , t i2 , t i3 , are the load toughness value of each node, the rated load of each node, and the expected life time of each node; Based on the characteristic parameter vector T of each node ij A node resilience analysis model is constructed using a genetic algorithm, and weak nodes of the power project are determined based on the node resilience analysis model; Specifically, the node resilience analysis model is constructed as follows: S1. For each node feature parameter vector T ij The load toughness value, rated load and expected life are binary coded. The length of the binary coding of the load toughness value, rated load and expected life of each node is 7 bits, 7 bits and 4 bits respectively. After the binary coding operation of the characteristic parameter vector of each node is performed, an 18-bit binary coding chromosome is established; S2, genetic algorithm initialization: set the population size N = 50, randomly generate 50 chromosomes as the initial population, and number the chromosomes, j = 1, 2, ..., 50; S3. Determine the fitness function F: F = c*t i1 +d*t i2 +e*t i3 , where c, d, and e are preset proportional coefficients; S4. Genetic operation: Use the roulette wheel selection method to calculate the sum of the fitness of all chromosomes Calculate the probability P of the chromosome being selected j , Select the chromosomes with probability in the range of [0.5,1] as the parent individuals, repeat N times, and select N parent individuals; Determine the crossover probability Pc = 0.7, use the single-point crossover method to select the parent individuals, exchange the binary codes of the chromosomes of the two parent individuals at a random position on the chromosome, generate two offspring individuals, determine the mutation probability Pm = 0.01, and perform mutation operations on the binary codes of each chromosome of the offspring individuals generated by the crossover according to the mutation probability Pm, changing the binary codes of the chromosomes from 1 to 0, and 1 to 0; S4, iterative termination: add the offspring after crossover and mutation to the new population, calculate the fitness of each individual in the new population, repeat the selection, crossover, and mutation operations, and terminate the algorithm when the number of crossover and mutation reaches 200, and select the node with the lowest fitness as the weak node; Determine the weak nodes of power engineering based on the node resilience analysis model; Obtain the expected distributed load of the weak node and compare it with the rated load of the weak node; If the expected distributed load is lower than the rated load of the weak node, the expected distributed load of the weak node needs to be analyzed; If the expected distributed load is higher than the rated load of the weak node, adjust the design load of the power engineering project at the weak node so that the rated load of the weak node meets the needs of the expected distributed load.

6. A power engineering design method according to claim 1, characterized in that: The overload time of the weak node is obtained as follows: If the expected distribution load of the weak node needs to be analyzed, the expected distribution load is segmented according to time, the expected distribution load of each time period is obtained, and the time series X is constructed. i =[x1 x2...x m ], where i represents the time corresponding to the time period, the value range of i is [1, m], x1 represents the expected distribution load of the first time period, and m represents the total number of time periods; Construct the expected distribution load series Y i , Y i =[y1 y2...y m ]; Based on the time series of weak nodes of the power project and the expected distribution load series, the Pearson correlation coefficient r of the time series and the expected distribution load series is calculated; The difference between the Pearson correlation coefficient r and the maximum endpoint value of the value range of r is processed to obtain the coefficient approximate difference; The coefficient approximation difference is processed by ratio with the length of the r value range to obtain the coefficient approximation ratio; Obtain the coefficient proximity ratio of m data in the sequence, sum and average the coefficient proximity ratios of the m data, and obtain the mean of the proximity ratio; If the absolute value of the mean of the proximity ratio is higher than the threshold value, and the mean of the proximity ratio is greater than 0, then the time series X i , expected load distribution sequence Y i It shows a linear growth trend; If the absolute value of the mean of the proximity ratio is lower than the proximity ratio threshold, then the time series X i , expected load distribution sequence Y i It is nonlinearly related; If the absolute value of the mean of the proximity ratio is lower than the threshold value of the proximity ratio, and the mean of the proximity ratio is less than 0, then the time series X i , expected load distribution sequence Y i It shows a linear downward trend and no treatment is done; If the time series X i , expected load distribution sequence Y i It shows a linear growth trend, with the X-axis being time and the Y-axis being the expected distributed load, and a prediction curve of time-expected distributed load is drawn in a two-dimensional coordinate system; Taking the rated load of the weak node as the reference value, draw the rated load reference line in the two-dimensional coordinate system; Extend the prediction curve of time-expected load distribution and intersect it with the rated load reference line, obtain the horizontal coordinate of the intersection of the rated load reference line and the prediction curve of time-expected load distribution, and obtain the overload time of the weak node; If the absolute value of the mean of the proximity ratio is lower than the proximity ratio threshold, then the time series X i , expected load distribution sequence Y i It is nonlinearly related; With the X-axis being time and the Y-axis being the expected distributed load, a time-expected distributed load variation curve is drawn in a two-dimensional coordinate system; Obtain the maximum value of the slope in the change curve of the expected distributed load - time. Based on the maximum value of the slope, calculate the time when the expected distributed load reaches the rated load and obtain the overload time of the weak node.

7. A power engineering design method according to claim 6, characterized in that: The Pearson correlation coefficient r is obtained as follows: Specifically, the Pearson correlation coefficient r is obtained as follows: By formula: Get the Pearson correlation coefficient r, where the value range of r is [-1,1], Cov(X i ,Y i ) is the covariance, Among them, σ Xi , σ Yi The time series X i , expected distribution load sequence Y i Standard Deviation 8. A power engineering design method according to claim 1, characterized in that: The load adjustment factor Tyz is obtained as follows: Based on the overload time of the weak node, the time corresponding to the expected life of the weak node is obtained to obtain the expected life time; Compare the overload time of the weak node with the expected life time of the weak node; If the overload time of a weak node is longer than the expected life time of the weak node, the weak node in the power project will not be redesigned; If the overload time of the weak node is lower than the expected life time of the weak node, the expected life time of the weak node is subtracted from the overload time to obtain the load life difference; The load life difference is processed by ratio with the overload time to obtain the load life ratio of the weak node, and the load life ratio is marked as Fhs; Based on the load life ratio Fhs and load toughness Rx of the weak node, calculate the load adjustment factor Tyz; By formula: Get the load adjustment factor Tyz, where g and f are preset proportional coefficients.

9. A power engineering design method according to claim 1, characterized in that: The method for determining whether a redesigned weak node becomes a weak node again is: Multiply the rated load of the weak node by the load adjustment factor Tyz to obtain the rated additional load; The rated additional load is summed with the rated load of the weak node to obtain the rated adjustment load; Redesign the weak nodes of the power project according to the rated adjustment load, and substitute the redesigned weak nodes into the node resilience analysis model; Identify the weak nodes again to determine whether the redesigned weak nodes become weak nodes again; If the weak node after redesign does not become a weak node again, no treatment will be done; If the redesigned weak node becomes a weak node again, the rated adjusted load and the load adjustment factor are continuously calculated to obtain a new rated adjusted load until the redesigned weak node no longer becomes a weak node.

10. A power engineering design system, characterized in that: include: Load acquisition module: obtains the rated load and historical peak load data of the power engineering node, and stores the rated load and historical peak load data in the node database; Sequence construction module: Perform numerical analysis on the historical peak load data in the node database to obtain the load toughness value Rx, and construct the node toughness sequence based on the load toughness value Rx; Node identification module: Based on the node toughness sequence, the rated load and expected life of each node of the power project are obtained, and the characteristic parameter vector T of each power project node is constructed. ij , based on the characteristic parameter vector T ij Use genetic algorithms to build a node resilience analysis model, identify weak nodes in power engineering, obtain the expected distributed load of weak nodes, and determine whether it is necessary to analyze the expected distributed load of weak nodes; Prediction and analysis module: if it is necessary to analyze the expected distribution load of the weak node, the expected distribution load of the weak node is predicted and analyzed to determine the overload time of the weak node; Node adjustment module: Based on the overload time of the weak node, a numerical analysis is performed in combination with the expected life time to obtain the load adjustment factor Tyz, and the rated adjustment load is obtained by numerical calculation based on the load adjustment factor. The weak node is redesigned based on the rated adjustment load, and it is determined whether the redesigned weak node becomes a weak node again. If it becomes a weak node again, the entire rated adjustment load is continuously optimized until the redesigned weak node no longer becomes a weak node.

Images