An intelligent substation virtual terminal automatic connection method and system based on SCHO-GO algorithm

Abstract

The application discloses an intelligent substation virtual terminal automatic connection method and system based on an SCHO-GO algorithm, and the method comprises the following steps: obtaining a comprehensive distance according to an edit distance and a cosine distance of a virtual connection vector representation, and constructing a virtual terminal matching model according to the comprehensive distance; optimizing a distance weight vector in the virtual terminal matching model according to a preset SCHO-GO algorithm, obtaining an optimal target distance weight vector, updating the virtual terminal matching model according to the target distance weight vector, and obtaining a target virtual terminal matching model; inputting IED data to be matched into the target virtual terminal matching model, obtaining a comprehensive similarity of an input virtual terminal and an output virtual terminal by the target virtual terminal matching model, and matching and connecting the input virtual terminal and the output virtual terminal according to the comprehensive similarity and a preset matching rule. The efficiency and accuracy of the virtual terminal automatic connection are significantly improved, and the method is suitable for intelligent substation secondary design in a complex equipment naming scene.

Description

Technical Field

[0001] This invention belongs to the field of virtual terminal connection technology, and particularly relates to an automatic connection method and system for virtual terminals in intelligent substations based on the SCHO-GO algorithm. Background Technology

[0002] In the secondary design of smart substations, virtual terminal connection is a crucial step in enabling information exchange between devices. Traditional methods rely on manual matching of virtual terminals, which is labor-intensive, inefficient, and prone to errors. Existing technologies, such as template matching, are limited by manually defined template libraries and struggle to adapt to the diverse naming rules of equipment manufacturers. Furthermore, existing intelligent algorithms (such as particle swarm optimization and war strategy algorithms) lack a proper balance between global search and local optimization, easily getting trapped in local optima and leading to decreased matching accuracy. In addition, the calculation of virtual terminal naming similarity does not fully consider the differences in logical node (LN) weights, resulting in frequent mismatches. Therefore, there is an urgent need for an efficient and accurate automatic virtual terminal connection method that can adapt to equipment differences. Summary of the Invention

[0003] This invention provides an automatic connection method and system for virtual terminals in intelligent substations based on the SCHO-GO algorithm, which solves the technical problem of frequent mismatches caused by insufficient consideration of logical node (LN) weight differences in virtual terminal naming similarity calculation.

[0004] In a first aspect, the present invention provides an automatic connection method for virtual terminals in intelligent substations based on the SCHO-GO algorithm, comprising:

[0005] The comprehensive distance is obtained by combining the edit distance and the cosine distance represented by the virtual connection vector, and a virtual terminal matching model is constructed based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector;

[0006] The distance weight vector in the virtual terminal matching model is optimized according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and the virtual terminal matching model is updated according to the target distance weight vector to obtain the target virtual terminal matching model.

[0007] The IED data to be matched is input into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal. Based on the comprehensive similarity, the input virtual terminal and the output virtual terminal are matched and connected using a preset matching rule.

[0008] Secondly, the present invention provides an automatic connection system for virtual terminals in intelligent substations based on the SCHO-GO algorithm, comprising:

[0009] The construction module is configured to obtain a comprehensive distance based on the edit distance and the cosine distance represented by the virtual connection vector, and to construct a virtual terminal matching model based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector;

[0010] The optimization module is configured to optimize the distance weight vector in the virtual terminal matching model according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and update the virtual terminal matching model according to the target distance weight vector to obtain the target virtual terminal matching model.

[0011] The output module is configured to input the IED data to be matched into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal, and matches and connects the input virtual terminal and the output virtual terminal according to the comprehensive similarity using a preset matching rule.

[0012] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the automatic connection method for virtual terminals of a smart substation based on the SCHO-GO algorithm according to any embodiment of the present invention.

[0013] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the automatic connection method for virtual terminals of a smart substation based on the SCHO-GO algorithm according to any embodiment of the present invention.

[0014] This application presents an automatic connection method and system for virtual terminals in intelligent substations based on the SCHO-GO algorithm. It aims to address the problems of traditional template matching methods, which rely on manually predefined template libraries and suffer from poor adaptability, as well as existing intelligent algorithms, which are prone to getting trapped in local optima and have slow convergence speeds. By constructing a comprehensive similarity model and combining edit distance and cosine distance, the similarity of virtual terminal naming rules is quantified. The SCHO-GO algorithm is used to optimize the distance weight vector, leveraging its hyperbolic function switching mechanism to dynamically balance global exploration and local development capabilities. Simultaneously, genetic operators are integrated, using crossover and mutation to break the limitations of the current solution and explore new search regions. This method significantly improves the efficiency and accuracy of automatic virtual terminal connection and is suitable for secondary design of intelligent substations in complex equipment naming scenarios. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating an automatic connection method for virtual terminals in a smart substation based on the SCHO-GO algorithm, provided in an embodiment of the present invention;

[0017] Figure 2 A structural block diagram of an intelligent substation virtual terminal automatic connection system based on the SCHO-GO algorithm provided in an embodiment of the present invention;

[0018] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 The diagram shows a flowchart of an automatic connection method for virtual terminals in a smart substation based on the SCHO-GO algorithm, as described in this application.

[0021] like Figure 1 As shown, the automatic connection method for virtual terminals in smart substations based on the SCHO-GO algorithm specifically includes the following steps:

[0022] Step S101: Obtain the comprehensive distance based on the edit distance and the cosine distance represented by the virtual connection vector, and construct a virtual terminal matching model based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector.

[0023] In this step, the expression for the virtual terminal matching model is:

[0024]

[0025] In the formula, S(A, B) is the comprehensive similarity between the input virtual terminal and the output virtual terminal, A and B represent two strings to be compared, d(A, B) is the comprehensive distance, and W is the distance weight vector;

[0026] The expression for calculating the aggregate distance is as follows:

[0027] d(A, B) = β·d edit (A, B) + (1-β)·d cos (A, B),

[0028]

[0029] In the formula, β is the balance coefficient, and d edit (A, B) represents the edit distance, d cos (A, B) represents the cosine distance, |A| is the length of string A, |B| is the length of string B, and δ(A[-1], B[-1]) is the cost of replacing the two strings. If A[-1] = B[-1], then δ(A[-1], B[-1]) = 0; otherwise, δ(A[-1], B[-1]) = 1. edit (A[:-1], B) is the edit distance between B and the subsequence obtained by removing the last element from A, d edit (A, B[:-1]) is the edit distance between the subsequences of A and B after removing the last element, d edit (A[:-1], B[:-1]) is the edit distance between the subsequences of A and B after removing the last element, and ||v A || is the length of the dummy concatenation vector of string A, ||v B || represents the length of the virtual concatenation vector of string B, v A and v B These represent the virtual concatenation vectors of string A and string B, respectively.

[0030] Step S102: Optimize the distance weight vector in the virtual terminal matching model according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and update the virtual terminal matching model according to the target distance weight vector to obtain the target virtual terminal matching model.

[0031] In this step, the SCHO-GO parameters are initialized, and a set of candidate solutions for weight vectors is randomly initialized;

[0032] Based on the initial set of candidate weight vectors, the matching similarity between the two virtual terminals is calculated; the objective function of the optimization model is set to maximize f(L). k The sum of (W) is the sum of the distance weight vector W, which maximizes the similarity between the IED matching results and the virtual connection data under the constraint of the distance weight vector W.

[0033] Two-stage search strategy: perform global exploration in the early stages of iteration, and local development in the later stages;

[0034] Genetic operators: By crossing over and mutating, the limitations of the current solution are broken, and new search areas are explored. Genetic operators work together with the SCHO explore-explore mechanism to balance global exploration and local exploitation.

[0035] Bounded search strategy: When the number of iterations reaches a dynamic threshold, shrink the search space to the neighborhood of the current optimal solution;

[0036] Switching mechanism: Based on the hyperbolic function, sinh(t) / cosh(t) adjusts the probability weights of exploration and development, and finally obtains the optimal target distance weight vector.

[0037] The two-stage search strategy includes the first exploration stage and the second exploration stage in the early stage of iteration, and the first development stage and the second development stage in the later stage of iteration.

[0038] In the first exploration phase, the weights are updated according to the first exploration strategy, which is expressed as follows:

[0039]

[0040] W1=r3·a1·(v·sinhr4-1+coshr4),

[0041] a1=3·(ρ t -1.3+u),

[0042] In the formula, This represents the j-th position of the i-th solution in the (t+1)-th iteration. Let sgn() be the j-th position of the optimal solution vector in the current iteration, r4, r3, r2, and r1 be independent random numbers in the interval [0, 1], and W1 be the value of Y. t (i，j) The weighting coefficients, Y, in the first exploration phase t (i，j) Let a1 be the j-th position of the i-th solution in the t-th iteration, and ρ be the first monotonically decreasing function. t = t / Max_iteration, ρ t The parameters represent the progress ratio, Max_iteration is the maximum iteration value, v is the precision control coefficient for adjusting the initial exploration phase, and u is the sensitivity coefficient for controlling the exploration precision.

[0043] In the second exploration phase, the weights are updated according to the second exploration strategy, which is expressed as follows:

[0044]

[0045] W3 = r6·a2,

[0046] In the formula, r5 and r6 are independent random numbers in the interval [0,1], ε is a very small positive number, and W3 is the value of Y. t (i，j) In the second exploration phase, the weighting coefficients, a2, are the second monotonically decreasing function;

[0047] In the first development phase, the weights are updated according to the first development strategy, the expression of which is:

[0048]

[0049] W2=r9·a1·(v·sinhr 10 +coshr 10 ),

[0050] In the formula, r8, r7, r9, r 10 All are independent random numbers within the interval [0,1], and W2 is Y t (i，j) Weighting coefficients in the first development phase;

[0051] In the second development phase, the weights are updated according to the second development strategy, the expression of which is:

[0052]

[0053] In the formula, r 11 r 12 All are independent random numbers within the interval [0,1], and W3 is Y t (i，j) Weighting coefficients in the second development phase.

[0054] It should be noted that the operation steps of the genetic operator include:

[0055] The mutation operation involves taking a random integer within the range [0,1] for each dimension of each solution vector in the current population, and comparing the random number with a preset mutation rate ρ1. If the random number is less than ρ1, elements are selected from the predefined y-vector or z-vector to update the old vector. The mutation formula is as follows:

[0056]

[0057] In the formula, P o Let y be the current solution vector, z be predefined mutation candidate vectors, ρ1 be the mutation rate, and y be the mutation vector. Mu z Mu These are the offspring of the y vector after the mutation operation and the offspring of the z vector after the mutation operation, respectively.

[0058] The crossover operation, based on the mutated solution vector, generates new offspring through a linear combination of the first random weighting coefficient θ and the second random weighting coefficient θ′, as shown in the formula:

[0059] ω c =θ·y Mu +(1-θ′)·z Mu ,

[0060] In the formula, ω c The offspring after the crossover operation;

[0061] The selection operation employs a differential evolution strategy, comparing the fitness values ​​of the parent and offspring, and retaining the better solution through greedy selection. The formula is as follows:

[0062]

[0063] In the formula, Let Po represent the i-th solution vector in the (t+1)-th generation, f be the fitness function, and Po be the solution vector. i This is the solution for the i-th generation parent.

[0064] Furthermore, bounded search strategies specifically include:

[0065] A global search is performed in the early stages of the iteration to determine the initial trigger point for the bounded search, expressed as:

[0066] BS1=floor(Max_iteration / λ),

[0067] In the formula, BS1 is the initial trigger point of the bounded search, Max_iteration is the maximum iteration value, floor is the rounding function, and λ is the search strategy activation threshold.

[0068] Randomly initialize candidate solutions within the potential search space and dynamically adjust subsequent trigger points, as expressed by:

[0069]

[0070] In the formula, α is the sensitivity coefficient, and BS k For the k-th trigger point, BS k+1 This is the (k+1)th trigger point;

[0071] Calculate the search space boundary constraints for each iteration. The expression for the search space boundary constraints is:

[0072]

[0073] In the formula, ub k and lb k Let represent the upper and lower bounds of the search space at the k-th iteration, respectively. This represents the j-th position of the optimal solution vector in the current iteration. For the j-th position of the suboptimal solution of the vector, ρ t This is the progress ratio parameter.

[0074] The switching mechanism specifically includes:

[0075] The judgment index A′ is calculated using the following expression:

[0076]

[0077] In the formula, γ 15 The numbers are independent random numbers in the interval [0,1], and p and q are the balance coefficients for exploration and utilization during the iteration process, respectively.

[0078] When A′>1, the SCHO-GO algorithm switches to the exploration state; when A′≤1, the SCHO-GO algorithm switches to the exploit state.

[0079] Step S103: Input the IED data to be matched into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal. Based on the comprehensive similarity, the input virtual terminal and the output virtual terminal are matched and connected using a preset matching rule.

[0080] In this step, the expression for the matching rule is:

[0081]

[0082] In the formula, S AB Let A be the similarity score between string A and string B. i B j These are the strings in the i-th and j-th IED data to be matched that are associated with the n-th virtual terminal of the same type of device.

[0083] In summary, the method presented in this application aims to address the problems of traditional template matching methods, which rely on manually predefined template libraries and suffer from poor adaptability, as well as the tendency of existing intelligent algorithms to get trapped in local optima and have slow convergence speeds. By constructing a comprehensive similarity model that combines edit distance and cosine distance, the similarity of virtual terminal naming rules is quantified. The SCHO-GO algorithm is employed to optimize the distance weight vector, utilizing its hyperbolic function switching mechanism to dynamically balance global exploration and local development capabilities. Simultaneously, genetic operators are integrated to break the limitations of the current solution through crossover and mutation, exploring new search regions. This method significantly improves the efficiency and accuracy of automatic virtual terminal connection and is suitable for secondary design of intelligent substations in complex equipment naming scenarios.

[0084] In one specific embodiment, the automatic connection method for virtual terminals in a smart substation based on the SCHO-GO algorithm includes the following steps:

[0085] Step 1: Calculate the overall distance between virtual terminals.

[0086] In smart substations, virtual terminals serve as logical connection points for GOOSE and SV input / output signals, and can be categorized into four types: GOOSE input, GOOSE output, SV input, and SV output. Based on the domestic IEC 61850 standard, their naming format must adhere to the standard's general information model specifications. However, foreign manufacturers rarely address device reset signals when developing standards, leading to difficulties in finding suitable data points for modeling common functions of domestic relay protection devices within the standard model. my country has introduced a modeling standard tailored to the actual conditions of its local power grid; the latest version is Q / GDW1396-2012, "IEC 61850 Engineering Relay Protection Application Model." While modeling by specific manufacturers may differ slightly from the standard, these differences must be expressed using standard language.

[0087] A complete virtual terminal representation includes a data index, a Chinese description, and an IED name, each with its own function yet interconnected. The IED name indicates the IED it belongs to, the data reference identifies the communication port, and the Chinese description explains its meaning. For dedicated virtual terminals, the data reference and Chinese description complement each other, while for general virtual terminals, the Chinese description further clarifies its purpose.

[0088] In intelligent substations, virtual connections refer to the signal connections between signal transmitting IEDs and receiving IEDs, consisting of virtual terminals for the transmitting IED outputs and virtual terminals for the receiving IED inputs. The attributes and uses of these virtual terminals are described in Chinese. To accurately understand and connect these virtual terminals, the Chinese descriptions can be segmented using word segmentation and transformed into 128-dimensional word vector representations using Chinese word vector technology, thereby calculating the cosine distance. Besides the Chinese descriptions, other attributes are strings, and distance calculations are performed by editing them. Therefore, a comprehensive distance is established to calculate the distance between virtual terminals.

[0089] The integrated distance calculation can calculate the distance between Chinese descriptions and character differences, and can better adapt to device differences by leveraging their unique characteristics.

[0090] Step 2: Construct a matching model and complete the virtual terminal matching.

[0091] In this embodiment, L k The connection relationship between the k-th virtual terminal and the virtual terminal connected to a matched IED device is defined as follows:

[0092]

[0093] In the formula, and The input and output of the virtual contacts of the intelligent electronic device (IED) are identified respectively. The virtual interfaces for input and output are named respectively. and The five basic attributes are Chinese Device Description (DES), Logical Device (LD), Logical Node (LN), Data Object (DO), and Data Attribute (DA). If any attribute is missing, it is treated as a series of empty characters.

[0094] Based on the different signal types, virtual terminals for input and output can be further subdivided into GOOSE and SV type input and output virtual terminals. For two connected IEDs, their virtual terminals will also be matched. Therefore, utilizing this characteristic, the virtual terminals of the IED to be matched are sequentially connected to the virtual terminals of connected IEDs, forming a set of virtual connections A. set The definition is as follows:

[0095]

[0096] Among them, A set Let L represent the set of virtual connections; t represents the number of input virtual terminals, g represents the number of output virtual terminals, and L represents the number of output virtual terminals. tg This represents a connection established between the input of the t-th virtual contact of the intelligent electronic device and the output of the g-th virtual contact of the intelligent electronic device. For the output of the g-th smart electronic device's virtual contact, This is the input of the t-th virtual contact point of the intelligent electronic device;

[0097] Based on the generation of virtual connection sets, the virtual terminal matching data of the IED to be matched is divided into two parts: matching data A m and training data A t The number of similar pairs is M, A. m Defined as follows:

[0098]

[0099] in, This represents the matching data for the Kth virtual terminal of the same type of device M to be matched.

[0100] Virtual Link Set A set Matching data A m Perform sequential calculations to obtain the similarity between all possible virtual connections and the matching data. The formula for calculating the similarity and matching results is as follows:

[0101]

[0102] Where d and D represent the samples that best match the virtual connection. for and Similarity of matching data This refers to the matching data for the Kth virtual terminal of the same type of device j to be matched. The matching data is for the Kth virtual terminal of the same type of device i to be matched. for and The overall distance of the matched data.

[0103] The influence of the combined distance between different named elements of the two types of virtual connections on the similarity of virtual connections is defined by the following distance weight vector:

[0104]

[0105] In the formula, To output the weight vector corresponding to each element of the virtual terminal, The weight vector corresponding to each element of the input virtual terminal;

[0106] First, the distance weight vector can specify the influence of each different attribute. Second, the similarity calculation requires the distance weight vector. Finally, the similarity calculated from each virtual terminal is compared to find the virtual connection with the highest similarity and its corresponding matching sample.

[0107] Step 3: Calculation process of distance weight vector

[0108] In the process of calculating the overall distance of virtual connections, since the relative distance of each named element has a differentiating effect on the overall similarity assessment, the distance weight vector W is needed to quantify the degree of influence of different elements, so as to achieve more accurate similarity matching calculation.

[0109] Assume training dataset A tra The number of IEDs of the same type is R. According to the matching model, one IED is randomly selected as the device to be matched, and the virtual connection set of the remaining R-1 IEDs can be used as the pairing set. Each virtual connection is represented as L. k The set of virtual connections that match the correct IED is set as D. c Define function f(L) k (W)):

[0110]

[0111] In the formula, f(L) k (W) is used to determine whether the IED matching result satisfies the original virtual join data, L k (W) represents the k-th virtual connection, and D M (W) represents the virtual connection data of the selected IED;

[0112] Function W is used to determine whether the IED matching results match the virtual join data, and the objective function of the optimization model is established based on this. The optimization model is as follows:

[0113]

[0114] In the formula, w i These are the weighting coefficients. For any k-th virtual connection;

[0115] Taking a 220kV substation as an example, the substation is equipped with two three-phase double-winding load voltage regulating transformers with a voltage level of 220 / 10kV. There are 6 220kV outgoing lines, which adopt a single busbar segmented connection method; 16 10kV outgoing lines, which adopt a single busbar connection method; 3 reactive power compensator capacitors and 2 station service transformers are installed.

[0116] Detailed information on each piece of equipment in the intelligent substation is shown in Table 1.

[0117] Serial Number Equipment Name Equipment Model Installation location 1 Main transformer protection RCS-978TD1-DA-GCN prefabricated cabin 2 Main transformer measurement and control RCS-9705A-DA-1 prefabricated cabin 3 220 kV line protection device RCS-931DA-GCN prefabricated cabin 4 220 kV busbar sectional protection device RCS-923DA-DA-GCN-C prefabricated cabin 5 66 kV standby automatic transfer switch RCS-9651A-DA-GCN prefabricated cabin 6 220 kV busbar monitoring and control RCS-9705A-DA-4 prefabricated cabin 7 Main transformer non-electrical quantity protection RCS-978TD1-DA-GCN Smart cabinet 8 220 kV interval RCS-2212MA Smart cabinet 9 220 kV line bay RCS-2211MA-DA-GZK Smart cabinet 10 220 kV busbar segmented bay RCS-2241MA-DA-GZK Smart cabinet 11 220 kV bus tie bay RCS-2241MA-DA-GZK Smart cabinet 12 Main transformer low-voltage side bay RCS-2241MA-DA-GZK Smart cabinet Based on this information, the distance weight vector of the 220kV main transformer protection device was calculated. Using the calculated distance weight vector, the virtual terminal automatic connection of the 220kV main transformer protection device was completed in an actual smart substation. The automatic connection results were compared with the virtual connection of the 220kV main transformer protection device in the actual smart substation to verify the feasibility of the new method.

[0118] Table 2 shows the results of automatic matching of some virtual terminals.

[0119]

[0120] Experimental results show that this method can achieve high-precision matching. The optimized distance weight vector not only improves the accuracy of virtual terminal connections but also enhances the robustness and compatibility of the system, enabling it to better adapt to the diverse research requirements of IEDs from different manufacturers. The practical applicability of the method is demonstrated through the use of a 220kV main transformer protection device and its connected IEDs.

[0121] Please see Figure 2 The diagram shows a structural block diagram of an intelligent substation virtual terminal automatic connection system based on the SCHO-GO algorithm of this application.

[0122] like Figure 2 As shown, the intelligent substation virtual terminal automatic connection system 200 includes a construction module 210, an optimization module 220, and an output module 230.

[0123] The construction module 210 is configured to obtain a comprehensive distance based on the edit distance and the cosine distance represented by the virtual connection vector, and construct a virtual terminal matching model based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector; the optimization module 220 is configured to optimize the distance weight vector in the virtual terminal matching model according to a preset SCHO-GO algorithm to obtain an optimal target distance weight vector, and update the virtual terminal matching model according to the target distance weight vector to obtain a target virtual terminal matching model; the output module 230 is configured to input the IED data to be matched into the target virtual terminal matching model, the target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal, and match and connect the input virtual terminal and the output virtual terminal according to the comprehensive similarity using a preset matching rule.

[0124] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0125] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the automatic connection method for virtual terminals of intelligent substations based on the SCHO-GO algorithm in any of the above method embodiments.

[0126] In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows:

[0127] The comprehensive distance is obtained by combining the edit distance and the cosine distance represented by the virtual connection vector, and a virtual terminal matching model is constructed based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector;

[0128] The distance weight vector in the virtual terminal matching model is optimized according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and the virtual terminal matching model is updated according to the target distance weight vector to obtain the target virtual terminal matching model.

[0129] The IED data to be matched is input into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal. Based on the comprehensive similarity, the input virtual terminal and the output virtual terminal are matched and connected using a preset matching rule.

[0130] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the SCHO-GO algorithm-based intelligent substation virtual terminal automatic connection system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the SCHO-GO algorithm-based intelligent substation virtual terminal automatic connection system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0131] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the automatic connection method for virtual terminals in intelligent substations based on the SCHO-GO algorithm described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the automatic connection system for virtual terminals in intelligent substations based on the SCHO-GO algorithm. The output device 340 may include a display screen or other display device.

[0132] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0133] In one implementation, the above-described electronic device is applied to an automatic virtual terminal connection system for intelligent substations based on the SCHO-GO algorithm, serving as a client, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0134] The comprehensive distance is obtained by combining the edit distance and the cosine distance represented by the virtual connection vector, and a virtual terminal matching model is constructed based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector;

[0135] The distance weight vector in the virtual terminal matching model is optimized according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and the virtual terminal matching model is updated according to the target distance weight vector to obtain the target virtual terminal matching model.

[0136] The IED data to be matched is input into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal. Based on the comprehensive similarity, the input virtual terminal and the output virtual terminal are matched and connected using a preset matching rule.

[0137] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm, characterized in that, include: The comprehensive distance is obtained by combining the edit distance and the cosine distance represented by the virtual connection vector, and a virtual terminal matching model is constructed based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector; The distance weight vector in the virtual terminal matching model is optimized according to a preset SCHO-GO algorithm to obtain the optimal target distance weight vector. The virtual terminal matching model is then updated based on the target distance weight vector to obtain the target virtual terminal matching model. The optimization of the distance weight vector in the virtual terminal matching model according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector includes: Initialize the SCHO-GO parameters and randomly initialize a set of candidate solutions for the weight vector; Based on the initial set of candidate weight vectors, the matching similarity between the two virtual terminals is calculated; the objective function of the optimization model is set to maximize f(L). k The summation of (W) represents the process of maximizing the similarity between the IED matching results and the virtual connection data under the constraint of the distance weight vector W, where each virtual connection is represented as L. k The set of virtual connections that match the correct IED is set as D. c Define function f(L) k (W)) is: In the formula, f(L) k (W) is used to determine whether the IED matching result satisfies the original virtual join data, L k (W) represents the k-th virtual connection, and D M (W) represents the virtual connection data of the selected IED; Two-stage search strategy: perform global exploration in the early stages of iteration, and local development in the later stages; Genetic operators: By crossing over and mutating, the limitations of the current solution are broken, and new search areas are explored. Genetic operators work together with the SCHO explore-explore mechanism to balance global exploration and local exploitation. Bounded search strategy: When the number of iterations reaches a dynamic threshold, shrink the search space to the neighborhood of the current optimal solution; Switching mechanism: Based on the hyperbolic function, sinh(t) / cosh(t) adjusts the probability weights of exploration and development, and finally obtains the optimal target distance weight vector; The IED data to be matched is input into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal. Based on the comprehensive similarity, the input virtual terminal and the output virtual terminal are matched and connected using a preset matching rule.

2. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, in, The expression for the virtual terminal matching model is: In the formula, S(A, B) is the comprehensive similarity between the input virtual terminal and the output virtual terminal, A and B represent two strings to be compared, d(A, B) is the comprehensive distance, and W is the distance weight vector; The expression for calculating the aggregate distance is as follows: d(A,B)=β·d edit (A,B)+(1-β)·d cos (A,B), In the formula, β is the balance coefficient, and d edit (A, B) represents the edit distance, d cos (A, B) represents the cosine distance, |A| is the length of string A, |B| is the length of string B, and δ(A[-1]=B[-1]) is the cost of replacing the two strings. If A[-1]=B[-1], then δ(A[-1],B[-1])=0; otherwise, δ(A[-1],B[-1])=1. edit (A[:-1],B) is the edit distance between B and the subsequence obtained by removing the last element from A, d edit (A,B[:-1]) represents the edit distance between the subsequences of A and B after removing the last element, d edit (A[:-1], B[:-1]) is the edit distance between the subsequences of A and B after removing the last element, and ||v A || is the length of the dummy concatenation vector of string A, ||v B || represents the length of the virtual concatenation vector of string B, v A and v B These represent the virtual concatenation vectors of string A and string B, respectively.

3. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, The two-stage search strategy includes a first exploration stage and a second exploration stage in the early stage of iteration, and a first development stage and a second development stage in the later stage of iteration; In the first exploration phase, the weights are updated according to the first exploration strategy, which is expressed as follows: W1=r3·a1·(v·sinhr4-1+coshr4), a1=3·(ρ t -1.3+u), In the formula, This represents the j-th position of the i-th solution in the (t+1)-th iteration. Let sgn() be the j-th position of the optimal solution vector in the current iteration, r4, r3, r2, and r1 be independent random numbers in the interval [0, 1], and W1 be the value of Y. t (i，j) The weighting coefficients, Y, in the first exploration phase t (i，j) Let a1 be the j-th position of the i-th solution in the t-th iteration, and ρ be the first monotonically decreasing function. t = t / Max_iteration, ρ t The parameters represent the progress ratio, Max_iteration is the maximum iteration value, v is the precision control coefficient for adjusting the initial exploration phase, and u is the sensitivity coefficient for controlling the exploration precision. In the second exploration phase, the weights are updated according to the second exploration strategy, the expression of which is: W3 = r6·a2, In the formula, r5 and r6 are independent random numbers in the interval [0, 1], ε is a very small positive number, and W3 is the value of Y. t (i，j) In the second exploration phase, the weighting coefficients, a2, are the second monotonically decreasing function; In the first development phase, the weights are updated according to the first development strategy, the expression of which is: W2=r9 a1(v sinhr 10 +coshr 10 , In the formula, r8, r7, r9, r 10 All are independent random numbers within the interval [0, 1], and W2 is Y t (i，j) Weighting coefficients in the first development phase; In the second development phase, the weights are updated according to the second development strategy, the expression of which is: In the formula, r 11 r 12 All are independent random numbers within the interval [0, 1], and W3 is Y t (i，j) Weighting coefficients in the second development phase.

4. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, The operation steps of the genetic operator include: The mutation operation involves taking a random integer within the range [0, 1] for each dimension of each solution vector in the current population, and comparing the random number with a preset mutation rate ρ1. If the random number is less than ρ1, elements are selected from the predefined y-vector or z-vector to update the old vector. The mutation formula is as follows: In the formula, P o Let y be the current solution vector, z be predefined mutation candidate vectors, ρ1 be the mutation rate, and y be the mutation vector. Mu z Mu These are the offspring of the y vector after the mutation operation and the offspring of the z vector after the mutation operation, respectively. The crossover operation, based on the mutated solution vector, generates new offspring through a linear combination of the first random weighting coefficient θ and the second random weighting coefficient θ′, as shown in the formula: oh c =θ·y Mu +(1-θ′)·z Mu , In the formula, ω c The offspring after the crossover operation; The selection operation employs a differential evolution strategy, comparing the fitness values ​​of the parent and offspring, and retaining the better solution through greedy selection. The formula is as follows: In the formula, Let Po represent the i-th solution vector in the (t+1)-th generation, f be the fitness function, and Po be the solution vector. i This is the solution for the i-th generation parent.

5. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, The bounded search strategy specifically includes: A global search is performed in the early stages of the iteration to determine the initial trigger point for the bounded search, expressed as: BS1=floor(Max_iteration / λ), In the formula, BS1 is the initial trigger point of the bounded search, Max_iteration is the maximum iteration value, floor is the rounding function, and λ is the search strategy activation threshold. Randomly initialize candidate solutions within the potential search space and dynamically adjust subsequent trigger points, as expressed by: In the formula, α is the sensitivity coefficient, and BS k For the k-th trigger point, BS k+1 This is the (k+1)th trigger point; Calculate the search space boundary constraints for each iteration. The expression for the search space boundary constraints is: In the formula, ub k and lb k Let represent the upper and lower bounds of the search space at the k-th iteration, respectively. This represents the j-th position of the optimal solution vector in the current iteration. For the j-th position of the suboptimal solution of the vector, ρ t This is the progress ratio parameter.

6. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, The switching mechanism specifically includes: The judgment index A′ is calculated using the following expression: In the formula, r 15 Let p and q be independent random numbers in the interval [0, 1], and p and q be the balance coefficients for exploration and utilization during the iteration process, respectively. When A′>1, the SCHO-GO algorithm switches to the exploration state; when A′≤1, the SCHO-GO algorithm switches to the exploit state.

7. The method for automatic connection of virtual terminals in intelligent substations based on the SCHO-GO algorithm according to claim 1, characterized in that, The expression for the matching rule is: In the formula, S AB Let A be the similarity score between string A and string B. i B j These are the strings in the i-th and j-th IED data to be matched that are associated with the n-th virtual terminal of the same type of device.

8. An automatic connection system for virtual terminals in intelligent substations based on the SCHO-GO algorithm, characterized in that, include: The construction module is configured to obtain a comprehensive distance based on the edit distance and the cosine distance represented by the virtual connection vector, and to construct a virtual terminal matching model based on the comprehensive distance, wherein the virtual terminal matching model includes a distance weight vector; The optimization module is configured to optimize the distance weight vector in the virtual terminal matching model according to a preset SCHO-GO algorithm to obtain the optimal target distance weight vector, and update the virtual terminal matching model according to the target distance weight vector to obtain the target virtual terminal matching model. The optimization of the distance weight vector in the virtual terminal matching model according to the preset SCHO-GO algorithm to obtain the optimal target distance weight vector includes: Initialize the SCHO-GO parameters and randomly initialize a set of candidate solutions for the weight vector; Based on the initial set of candidate weight vectors, the matching similarity between the two virtual terminals is calculated; the objective function of the optimization model is set to maximize f(L). k The summation of (W) represents the process of maximizing the similarity between the IED matching results and the virtual connection data under the constraint of the distance weight vector W, where each virtual connection is represented as L. k The set of virtual connections that match the correct IED is set as D. c Define function f(L) k (W)) is: In the formula, f(L) k (W) is used to determine whether the IED matching result satisfies the original virtual join data, L k (W) represents the k-th virtual connection, and D M (W) represents the virtual connection data of the selected IED; Two-stage search strategy: perform global exploration in the early stages of iteration, and local development in the later stages; Genetic operators: By crossing over and mutating, the limitations of the current solution are broken, and new search areas are explored. Genetic operators work together with the SCHO explore-explore mechanism to balance global exploration and local exploitation. Bounded search strategy: When the number of iterations reaches a dynamic threshold, shrink the search space to the neighborhood of the current optimal solution; Switching mechanism: Based on the hyperbolic function, sinh(t) / cosh(t) adjusts the probability weights of exploration and development, and finally obtains the optimal target distance weight vector; The output module is configured to input the IED data to be matched into the target virtual terminal matching model. The target virtual terminal matching model outputs the comprehensive similarity between the input virtual terminal and the output virtual terminal, and matches and connects the input virtual terminal and the output virtual terminal according to the comprehensive similarity using a preset matching rule.

Images