Substation reactive power optimization configuration method and device based on curve clustering and covering method
The method optimizes reactive power configuration in substations by using curve clustering and covering techniques to balance investment, switching frequency, and regulation capability, addressing inefficiencies in existing methods and extending equipment life.
Patent Information
- Application Number
- CN202210157596.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-02-21
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2042-02-21
AI Technical Summary
Existing reactive power planning methods for substations face challenges in balancing investment cost, reactive power regulation capability, and capacitor switching frequency, leading to equipment overcompensation, undercompensation, and reduced service life due to frequent switching.
A method and device that utilize curve clustering and covering techniques to optimize reactive power configuration by minimizing mismatch areas, switching times, and investment costs, using a genetic algorithm to determine optimal capacitor placement based on substation load curves and transformer parameters.
The solution provides a high-accuracy, fast optimization of reactive power configuration, extending equipment life by reducing frequent switching and optimizing reactive power regulation while considering load volatility and timing.
Smart Images

Figure CN114548266B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of reactive power planning of distribution networks, and in particular relates to a method and a device for optimizing reactive power configuration of a substation based on curve clustering and covering methods. Background Art
[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.
[0003] Reactive power optimization configuration of substations is an important research content of reactive power planning of distribution networks. Reasonable reactive power planning is related to the safe and stable operation of the power system and can effectively improve the economic efficiency of power grid operation.
[0004] Power capacitors are important reactive power compensation equipment in power systems. They are widely used in reactive power planning of substations because of their low cost and simple equipment maintenance and repair. In the reactive power planning process, the optimal installation location and capacity of reactive power compensation equipment must be determined first, and then reactive power compensation equipment such as capacitors must be optimized and grouped according to actual conditions.
[0005] There are two types of capacitor grouping: equal capacity grouping and unequal capacity grouping. The equal grouping method is simple and easy to implement, but because the characteristics of load changes are not carefully considered, when the number of groups is small, it is easy to cause overcompensation when one group is put into use and undercompensation when one group is cut off. The reactive power regulation ability is poor, resulting in reactive power mismatch when there are idle equipment in the system. The unequal capacity grouping method often has a strong reactive power regulation ability without significantly increasing the investment cost, and can adapt well to load changes. However, in terms of equipment operating costs, unequal capacity grouping will cause frequent switching of equipment, increase operation and maintenance costs, and greatly reduce the service life of the equipment. Summary of the invention
[0006] In order to solve at least one technical problem existing in the above-mentioned background technology, the present invention provides a method and device for optimizing reactive power configuration of a substation based on curve clustering and covering method, which considers the mismatch area and switching times of capacitor groups on the basis of considering the investment cost in traditional reactive power planning of substations, and coordinates the relationship among investment cost, reactive power regulation capability and switching frequency when configuring reactive power of substations, so as to take into account the reactive power regulation capability of capacitor groups while avoiding too frequent switching of capacitors and prolong the service life of equipment.
[0007] In order to achieve the above object, the present invention adopts the following technical solution:
[0008] A first aspect of the present invention provides a method for optimizing reactive power configuration of a substation based on curve clustering and covering method, comprising the following steps:
[0009] Obtain the substation annual load change curve and transformer parameters;
[0010] According to the substation annual load change curve and transformer parameters, the substation annual reactive power demand curve is obtained;
[0011] Cluster the obtained substation annual reactive power demand curve into a cluster curve;
[0012] The optimal coverage of the capacitor step curve is carried out on the cluster curve, and the substation reactive power optimization planning model is constructed with the minimum reactive power mismatch area, the minimum number of capacitor switching times and the minimum capacitor investment cost as multiple objectives;
[0013] Based on the reactive power optimization planning model of substation, genetic algorithm is used and the optimization variables are obtained as the reactive power configuration scheme of substation according to the constraints.
[0014] A second aspect of the present invention provides a substation reactive power optimization configuration device based on curve clustering and covering method, comprising:
[0015] The data acquisition module is configured to: obtain the annual load change curve and transformer parameters of the substation;
[0016] The curve clustering module is configured to: obtain the annual reactive power demand curve of the substation according to the annual load change curve of the substation and the transformer parameters;
[0017] Cluster the obtained substation annual reactive power demand curve into k cluster curves;
[0018] The reactive power optimization model building module is configured to: optimally cover the capacitor level step curves on k clustering curves, and build a substation reactive power optimization planning model with multiple objectives of minimizing reactive power mismatch area, minimizing capacitor switching times, and minimizing capacitor investment costs;
[0019] The reactive power configuration scheme output module is configured as follows: based on the reactive power optimization planning model of the substation, a genetic algorithm is used, and according to the constraint conditions, the obtained optimized variables are used as the reactive power configuration scheme of the substation.
[0020] A third aspect of the present invention provides a computer-readable storage medium.
[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned method for optimizing reactive power configuration of a substation based on curve clustering and covering method.
[0022] A fourth aspect of the present invention provides a computer device.
[0023] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for optimizing reactive power configuration of a substation based on curve clustering and covering method as described above are implemented.
[0024] Compared with the prior art, the present invention has the following beneficial effects:
[0025] The present invention performs optimal coverage of capacitor gear step curves on cluster curves, obtains reactive mismatch area, and establishes a multi-objective reactive optimization model with minimum mismatch area, minimum switching times and minimum investment cost. The present invention considers the mismatch area and switching times of capacitor groups on the basis of considering investment cost in traditional substation reactive power planning, and can take into account the reactive power regulation capability of capacitor groups while avoiding too frequent switching of capacitors, thereby extending the service life of equipment.
[0026] The present invention adopts a genetic algorithm to solve the optimal reactive power configuration scheme, with high solving accuracy and fast speed.
[0027] The "clustering" described in the present invention combines the advantages of curve segmentation and clustering method to take into account load volatility and timing, and the "covering" combines the advantages of the optimal covering method to take into account the reactive regulation effect of the capacitor on its curve. Optimization calculations are performed on multiple clustering curves to provide a corresponding solution that is often difficult for a typical daily curve to meet actual needs. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0029] Figure 1 It is a schematic diagram of a reactive power optimization configuration process of a substation based on curve clustering and covering method according to the first embodiment of the present invention;
[0030] Figure 2 The first embodiment of the present invention is the optimal coverage on the reactive power demand curve;
[0031] Figure 3 is a flow chart of a genetic algorithm according to a first embodiment of the present invention; DETAILED DESCRIPTION
[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0033] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.
[0034] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.
[0035] Embodiment 1
[0036] like Figure 1-Figure 2 As shown, this embodiment provides a method for optimizing reactive power configuration of a substation based on curve clustering and covering method, comprising the following steps:
[0037] S101: Obtaining the annual load change curve and transformer parameters of the substation;
[0038] S102: Calculate the annual reactive power demand curve of the substation according to the annual load change curve of the substation and the transformer parameters;
[0039] S103: clustering the obtained substation annual reactive power demand curve into k cluster curves using a k-means algorithm;
[0040] S104: Optimally cover the capacitor level step curve on the clustering curve, take the minimum mismatch area, the minimum switching times and the minimum investment cost as multiple objectives, take the total capacity constraint, the total number of groups constraint and the single group capacity constraint as constraint conditions, and build a substation reactive power optimization planning model;
[0041] S105: Based on the substation reactive power optimization planning model, a genetic algorithm is used to obtain the optimized variables as a reactive power configuration plan for the substation according to the constraint conditions.
[0042] Among them, in S102, the calculation process of the substation annual reactive power demand curve includes:
[0043] S201: According to the load side active power P L and load side power factor Get the substation reactive load Q L ;
[0044] Substation reactive load Q L Refers to the reactive power on the load side of the substation during the actual operation of the power system, which is proportional to the active power P on the load side. L and load side power factor The calculation formula is:
[0045]
[0046] Among them, P Lis the active power on the load side of the transformer, is the load side power factor.
[0047] S202: Obtaining the transformer reactive loss according to the transformer no-load reactive loss, the transformer load side active power, the transformer load side active power and the transformer short-circuit impedance.
[0048] Transformer reactive loss ΔQ LT It represents the corresponding reactive power absorbed by the transformer in the substation during the actual operation of the power system. In the calculation process of this paper, it is assumed that the reactive load is fully compensated on site and the approximate system voltage is the rated voltage of the transformer, then ΔQ LT The transformer no-load reactive power loss ΔQ0 and the transformer load side active power P L , Transformer rated voltage V N and transformer short-circuit impedance X T The calculation formula is:
[0049]
[0050] S203: Obtain the reactive power demand Q of the substation according to the reactive load of the substation and the reactive power loss of the transformer B ;
[0051] Substation reactive power demand Q B It indicates the corresponding reactive capacity that the substation should compensate during the actual operation of the power system. Its size is the same as the reactive load Q of the substation calculated above. L and transformer reactive loss ΔQ LT The calculation formula is as follows:
[0052] Q B =Q L +ΔQ LT
[0053] In S103, the obtained substation annual reactive power demand curve is clustered into k cluster curves, including:
[0054] S301: According to the daily reactive power demand curve of the substation within one year, k data objects are randomly selected as initial clustering centers;
[0055] S302: Calculate the Euclidean distance between the remaining data objects and the cluster center, and assign the data object to the cluster where the cluster center closest to the data object is located according to the Euclidean distance;
[0056] The calculation formula is as follows:
[0057]
[0058] In the formula, x is the data object; C iis the i-th cluster center; m is the dimension of the data object; x j , C ij are x, C i The j-th attribute value of .
[0059] S303: Calculate the mean of the data objects in each cluster as the new cluster center, and calculate the sum of squared errors (SSE) of all clusters;
[0060] The calculation formula for the sum of squared errors (SSE) of all clusters is as follows:
[0061]
[0062] S304: Determine whether the SSE value has changed. If so, jump back to S302. Otherwise, clustering ends and the final clustering result is output to obtain k clustered daily reactive power demand curves.
[0063] In S104, the multi-objective function includes: capacitor investment cost, annual reactive power loss cost and capacitor switching cost. The calculation formula is as follows:
[0064] W Σ =W C +W L +W M
[0065] Among them, the capacitor investment cost W C It includes two parts: investment in each set of supporting facilities and capacitor cost. The calculation formula is:
[0066]
[0067] Where: N Σ Indicates the number of capacitor groups; Q C It is expressed as the total reactive power compensation capacity of the power station, taking the maximum value of the clustering curve; w N 、w Q They represent the unit price of capacitor groups and the unit price of capacity respectively; r and γ represent the depreciation rate and depreciation period of the capacitor group respectively.
[0068] The annual reactive power loss cost W L In order to convert the reactive mismatch area into reactive loss cost, the calculation formula is as follows:
[0069] W L =SL Σ ×TK×w L
[0070] In the formula, SL ∑ Represents the total reactive power mismatch area on each cluster curve. The optimal coverage calculation is performed on the cluster curve using the optimal coverage idea to obtain the reactive power mismatch area on each cluster curve:
[0071]
[0072] In the formula, SL z represents the mismatch area on the z-th cluster curve, TK represents the time length of one year; w L Represents the reactive power loss price.
[0073] The capacitor switching cost W M for:
[0074]
[0075] In the formula, is the weight of the z-th clustering curve; NK z It indicates the number of daily curves contained in the class to which the z-th cluster curve belongs; TK=365 indicates the total number of daily curves of the substation in one year.
[0076] NTL z The capacitor is in the zth cluster day curve f i (t) the number of switching times; w M Indicates the cost of switching the capacitor each time.
[0077] Considering that frequent switching of capacitors will inevitably increase the workload of operation and maintenance personnel and increase the operating cost of equipment, in order to avoid the problem of too many unequal capacity grouping gears, the capacitor switching cost is included in the calculation.
[0078] Calculate the switching times of capacitors when the optimal coverage is achieved. After calculating the switching times of capacitors on each cluster curve when the optimal coverage is achieved one by one, the total switching times is:
[0079] The constraints include total capacity constraint, total group number constraint and single group capacity constraint:
[0080]
[0081] Where N Σ 、N Σ,max and N Σ,min Indicates the total number of capacitor groups and their upper and lower limits; Q 0u , Q 0u,max and Q 0u,min Represents the single group capacity of the uth group of capacitors and its upper and lower limits.
[0082] Set the optimization variable to single group capacity Q 0u , a total of N Σ,max , and use genetic algorithm to solve;
[0083] The calculated capacity of each single group Q 0uThe formed set is recorded as:
[0084] Q0={Q 0u |u∈(1,N Σ,max )}
[0085] It should be noted that there is Q in the calculation results 0u When it is zero, it means that there is no need to configure this group of capacitors.
[0086] The single capacity set corresponds to the genetic algorithm individual, and the single capacity corresponds to a chromosome of the individual. Calculating the individual fitness is the objective function value obtained by calculating the single capacity set. The individual with the best fitness is the best single capacity set.
[0087] The specific implementation process is as follows:
[0088] like Figure 3 As shown, in S105, using a genetic algorithm to obtain a single group capacity as a reactive power configuration scheme for a substation includes the following steps:
[0089] S501: Set the evolutionary generation counter g=0, set the maximum evolutionary generation G, and set the chromosome length to N Σ,max , randomly generate N P individuals as the initial population P(0), where each individual v corresponds to a possible value of the single group capacity Q0;
[0090] S502: Correspond each individual to Q0 and calculate the objective function value W Σ , and then calculate the fitness of each individual in the population P(g):
[0091] f v =1 / (W Σ +1)
[0092] In the formula, f v represents the fitness of individual v. In particular, when individual v does not meet the constraints, f v =0; F v Represents the objective function value of individual v.
[0093] S503: Apply the selection operator to the population, and select some excellent individuals according to the fitness of the individuals and the roulette wheel method to be inherited to the next generation population. The probability of individual v being selected is:
[0094]
[0095] S504: Apply the crossover operator to the population, and exchange some of the chromosomes between the selected pairs of individuals with a certain probability to generate new individuals. The adaptive crossover probability formula related to the evolutionary algebra is as follows:
[0096] m pc =P c,max ×2 (-g / G)
[0097]
[0098] In the formula, m pc is an intermediate calculation variable; P c (t) is the crossover probability of the t-th generation population; P cmax , P cmin are the preset maximum and minimum crossover probabilities respectively.
[0099] S505: Apply the mutation operator to the population, and for the selected individuals, change one or some gene values to other alleles with a certain probability. Adaptive mutation probability related to genetic evolution generation and individual fitness:
[0100]
[0101] In the formula, m pm is an intermediate counting variable; f v,max is the maximum fitness value in the current population; P m,max , P m,min are the preset maximum and minimum mutation probabilities; P m (g) is the mutation probability of individual v in the g-th generation population.
[0102] S506: If g≤G, then g=g+1, and go to step S502; if g>G, then the individual with the maximum fitness obtained in this evolution process is output as the optimal solution as the final Q0, and the calculation is terminated.
[0103] Embodiment 2
[0104] This embodiment provides a substation reactive power optimization configuration device based on curve clustering and covering method, including:
[0105] The data acquisition module is configured to: obtain the annual load change curve and transformer parameters of the substation;
[0106] The curve clustering module is configured to: obtain the annual reactive power demand curve of the substation according to the annual load change curve of the substation and the transformer parameters;
[0107] Cluster the obtained substation annual reactive power demand curve into k cluster curves;
[0108] The reactive power optimization model building module is configured to: optimally cover the capacitor level step curves on k clustering curves, and build a substation reactive power optimization planning model based on constraints with the minimum reactive power mismatch area, the minimum number of capacitor switching times, and the minimum capacitor investment cost as multiple objectives;
[0109] The reactive power configuration scheme output module is configured as follows: based on the reactive power optimization planning model of the substation, a genetic algorithm is used, and according to the constraint conditions, the obtained optimized variables are used as the reactive power configuration scheme of the substation.
[0110] Embodiment 3
[0111] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for optimizing reactive power configuration of a substation based on curve clustering and covering method as described above are implemented.
[0112] Embodiment 4
[0113] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for optimizing reactive power configuration of a substation based on curve clustering and covering method as described above are implemented.
[0114] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.
[0115] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0116] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0118] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for optimizing reactive power configuration of a substation based on curve clustering and covering method, characterized in that: The steps include: Obtain the substation annual load change curve and transformer parameters; According to the substation annual load change curve and transformer parameters, the substation annual reactive power demand curve is obtained; Cluster the obtained substation annual reactive power demand curve into a cluster curve; The optimal coverage of the capacitor step curve is carried out on the cluster curve, and the substation reactive power optimization planning model is constructed with the minimum reactive power mismatch area, the minimum number of capacitor switching times and the minimum capacitor investment cost as multiple objectives; Based on the substation reactive power optimization planning model, a genetic algorithm is used to obtain the optimized variables as the substation reactive power configuration plan according to the constraints. The step of clustering the obtained substation annual reactive power demand curve into a cluster curve includes: According to the daily reactive power demand curve of the substation within one year, k data objects are randomly selected as the initial clustering centers; Calculate the Euclidean distance between the remaining data objects and the cluster center, and assign the data object to the cluster with the closest cluster center according to the Euclidean distance; The calculation formula is as follows: In the formula, x is the data object; C i is the i-th cluster center; m is the dimension of the data object; x j , C ij are x, C i The j-th attribute value of ; Calculate the mean of the data objects in each cluster as the new cluster center, and calculate the sum of squared errors (SSE) of all clusters; The calculation formula for the sum of squared errors (SSE) of all clusters is as follows: Determine whether the SSE value has changed. If so, return to recalculate the Euclidean distance. Otherwise, clustering ends and the final clustering result is output to obtain k clustered daily reactive power demand curves. The multi-objective function includes: capacitor investment cost, annual reactive power loss cost and capacitor switching cost; the calculation formula is as follows: minW Σ =W C +W L +W M Among them, the capacitor investment cost W C It includes the investment in each set of supporting facilities and the capacitor cost. The calculation formula is: Where: N Σ Indicates the number of capacitor groups; Q C It is expressed as the total reactive power compensation capacity of the power station, taking the maximum value of the clustering curve; w N 、w Q They represent the unit price of the number of capacitor groups and the unit price of capacity respectively; r and γ represent the depreciation rate and depreciation period of the capacitor group respectively; Annual reactive power loss cost W L In order to convert the reactive mismatch area into reactive loss cost, the calculation formula is as follows: W L =SL Σ ×TK×w L In the formula, SL ∑ Represents the total reactive mismatch area on each cluster curve. The optimal coverage calculation is performed on the cluster curve using the optimal coverage idea to obtain the reactive mismatch area on each cluster curve, which is expressed as: In the formula, is the weight of the z-th clustering curve, SL z represents the mismatch area on the z-th cluster curve, TK represents the time length of one year; w L Indicates the price of reactive power loss; Capacitor switching cost W M for: In the formula, NK z Indicates the number of daily curves contained in the class of the z-th cluster curve; TK indicates the total number of daily curves of the substation in one year; NTL z represents the number of times the capacitor is switched on the zth cluster day curve; w M Indicates the cost of switching the capacitor each time.
2. The method for optimizing reactive power configuration of a substation based on curve clustering and covering method according to claim 1, characterized in that: The calculation process of the substation annual reactive power demand curve includes: The reactive load of the substation is obtained according to the active power on the load side and the power factor on the load side; The transformer reactive loss is obtained according to the transformer no-load reactive loss, the transformer load side active power, the transformer load side active power and the transformer short-circuit impedance; The reactive power demand of the substation is obtained according to the reactive load of the substation and the reactive power loss of the transformer.
3. The method for optimizing reactive power configuration of substations based on curve clustering and covering method according to claim 1, characterized in that: The switching times of the capacitor are obtained by: Calculate the switching times of capacitors when the optimal coverage is achieved. After calculating the switching times of capacitors on each cluster curve when the optimal coverage is achieved one by one, the total switching times is: In the formula, is the weight of the z-th clustering curve, NTL z Represents the number of times the capacitor is switched on the zth cluster curve.
4. The method for optimizing reactive power configuration of substations based on curve clustering and covering method according to claim 1, characterized in that: The constraints include total capacity constraint, total group number constraint and single group capacity constraint: Where N Σ 、N Σ,max and N Σ,min Indicates the total number of capacitor groups and their upper and lower limits; Q 0u , Q 0u,max and Q 0u,min Represents the single group capacity of the uth group of capacitors and its upper and lower limits.
5. The method for optimizing reactive power configuration of substations based on curve clustering and covering method according to claim 4, characterized in that: Using genetic algorithm, according to the constraints, the obtained optimization variables are used as the reactive power configuration plan of the substation. The single capacity set corresponds to the genetic algorithm individual. By calculating the individual fitness, that is, calculating the objective function value of the single capacity set, the individual with the best fitness is the optimal single capacity set.
6. A reactive power optimization configuration device for a substation based on curve clustering and covering method, characterized in that: include: The data acquisition module is configured to: obtain the annual load change curve and transformer parameters of the substation; The curve clustering module is configured to: obtain the annual reactive power demand curve of the substation according to the annual load change curve of the substation and the transformer parameters; Cluster the obtained substation annual reactive power demand curve into a cluster curve; The reactive power optimization model building module is configured to: optimally cover the capacitor gear step curve on the cluster curve, take the minimum reactive power mismatch area, the minimum capacitor switching times and the minimum capacitor investment cost as multiple objectives, and build the substation reactive power optimization planning model according to the constraints; The reactive power configuration scheme output module is configured as follows: based on the reactive power optimization planning model of the substation, a genetic algorithm is used to obtain the optimized variables according to the constraint conditions as the reactive power configuration scheme of the substation; The step of clustering the obtained substation annual reactive power demand curve into a cluster curve includes: According to the daily reactive power demand curve of the substation within one year, k data objects are randomly selected as the initial clustering centers; Calculate the Euclidean distance between the remaining data objects and the cluster center, and assign the data object to the cluster with the closest cluster center according to the Euclidean distance; The calculation formula is as follows: In the formula, x is the data object; C i is the i-th cluster center; m is the dimension of the data object; x j , C ij are x, C i The j-th attribute value of ; Calculate the mean of the data objects in each cluster as the new cluster center, and calculate the sum of squared errors (SSE) of all clusters; The calculation formula for the sum of squared errors (SSE) of all clusters is as follows: Determine whether the SSE value has changed. If so, return to recalculate the Euclidean distance. Otherwise, clustering ends and the final clustering result is output to obtain k clustered daily reactive power demand curves. The multi-objective function includes: capacitor investment cost, annual reactive power loss cost and capacitor switching cost; the calculation formula is as follows: minW Σ =W C +W L +W M Among them, the capacitor investment cost W C It includes the investment in each set of supporting facilities and the capacitor cost. The calculation formula is: Where: N Σ Indicates the number of capacitor groups; Q C It is expressed as the total reactive power compensation capacity of the power station, taking the maximum value of the clustering curve; w N 、w Q They represent the unit price of the number of capacitor groups and the unit price of capacity respectively; r and γ represent the depreciation rate and depreciation period of the capacitor group respectively; Annual reactive power loss cost W L In order to convert the reactive mismatch area into reactive loss cost, the calculation formula is as follows: W L =SL Σ ×TK×w L In the formula, SL ∑ Represents the total reactive mismatch area on each cluster curve. The optimal coverage calculation is performed on the cluster curve using the optimal coverage idea to obtain the reactive mismatch area on each cluster curve, which is expressed as: In the formula, is the weight of the z-th clustering curve, SL z represents the mismatch area on the z-th cluster curve, TK represents the time length of one year; w L Indicates the price of reactive power loss; Capacitor switching cost W M for: In the formula, NK z Indicates the number of daily curves contained in the class of the z-th cluster curve; TK indicates the total number of daily curves of the substation in one year; NTL z represents the number of times the capacitor is switched on the zth cluster day curve; w M Indicates the cost of switching the capacitor each time.
7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the method for optimizing reactive power configuration of a substation based on curve clustering and covering method as described in any one of claims 1 to 5 are implemented.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the method for optimizing reactive power configuration of a substation based on curve clustering and covering method as described in any one of claims 1 to 5 are implemented.
