Medium-voltage target net rack transition scheme generation method based on ant colony algorithm

Abstract

The invention discloses a medium-voltage target network frame transition scheme generation method based on an ant colony algorithm, and belongs to the technical field of power distribution network planning. According to the medium-voltage target net rack transition scheme generation method based on the ant colony algorithm, a current situation information database is established by collecting and sorting detailed information of a regional current situation power grid, and then related planning information is extracted in combination with regional planning to form a planning information database; then, defining and classifying available networking modules according to target net racks and current net rack structures of specific requirements of different regions; then, disassembling the current net rack, and identifying and classifying available modules; and finally, by using the learning and optimization capability of the ant colony algorithm, constructing a target net rack suitable for the region. The method can improve the planning efficiency and quality of the power distribution network, and is suitable for the differentiation requirements of different regions.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network planning, and in particular to a method for generating a medium voltage target grid transition plan based on an ant colony algorithm. Background Art

[0002] The transition of the target grid is a systematic project that requires comprehensive consideration of technical, economic and environmental factors to achieve sustainable development of the power grid. The traditional approach mainly relies on the requirements of the State Grid guidelines and manual experience. Although this method can solve the problem to a certain extent, it also has some obvious limitations: the planning results rely heavily on the personal experience and judgment of the planners, which may lead to the lack of objectivity and universality of the planning scheme. With the large-scale access of new energy, the target grid has become complex, and the transition of the target grid faces new demands and challenges. The traditional target grid transition scheme is difficult to adapt to the changes in the new situation, so it is necessary to develop new methods to ensure the safety and stability of the grid transition. Summary of the invention

[0003] In order to make up for the above shortcomings, the present invention provides a method for generating a medium voltage target grid transition scheme based on an ant colony algorithm, aiming to solve the problem that traditional target grid transition schemes are difficult to adapt to new changes in the situation.

[0004] The present invention is achieved in that:

[0005] The present invention provides a method for generating a medium voltage target grid transition solution based on an ant colony algorithm, comprising the following steps:

[0006] Step 1: Clarify the current status of regional power grid lines, including at least the length, model, wire diameter, distribution location, capacity, and switch station location information, and form a current status information database;

[0007] Step 2: Extract information such as integrated pipe corridors and planned sites in combination with the detailed planning or master plan of the region to form a planning information database;

[0008] Step 3: Based on the differentiated requirements of different regions and the current medium-voltage grid structure, and according to the requirements of different application scenarios and the current grid situation, define and categorize the available modules;

[0009] Step 4: Disassemble the existing medium-voltage grid. According to the results of the available module disassembly, divide the existing regional grid into several small-scale modules. According to the definition and classification results of the networking modules, identify and extract the available modules, and classify and sort the available modules.

[0010] Step 5: Based on the research results of networking module extraction, the ant colony algorithm is used to build standardized networking modules suitable for different target grid requirements through learning and optimization, and the networking module component results are given.

[0011] In one embodiment of the present invention, the information database in step 1 also includes the connection mode, connection rate, transfer rate, grid margin, and switch equipment survey information of the existing power grid in the planning area.

[0012] In an embodiment of the present invention, the planning area is divided into grids and units.

[0013] In one embodiment of the present invention, data cleaning is performed on the acquired regional data, including the following steps: 1. data collection and integration; 2. missing value processing; 3. outlier detection and processing; 4. data consistency check.

[0014] In an embodiment of the present invention, the regional differentiation in step 3 includes at least one of a low-carbon resource-rich area, an area with high disaster prevention requirements, and an area with high power supply reliability requirements.

[0015] In one embodiment of the present invention, the existing medium-voltage grid in step 4 is dismantled according to the wiring mode, connection rate, transfer rate, grid margin, and switchgear.

[0016] The beneficial effects of the present invention are: 1. Improving planning efficiency: The ant colony algorithm can quickly search for the optimal solution in the solution space by simulating the foraging behavior of ants, thereby effectively improving the efficiency of distribution network planning.

[0017] 2. Enhanced global search capabilities: The ant colony algorithm has positive feedback mechanisms and distributed computing characteristics, which can avoid local optimal solutions and enhance global search capabilities.

[0018] 3. Optimize resource allocation: Through the optimization of ant colony algorithm, the power grid resources can be better configured and the power supply reliability and economy of the power grid can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0020] Figure 1 It is a flow chart of a method for generating a medium voltage target grid transition solution based on an ant colony algorithm provided in an embodiment of the present invention.

[0021] Figure 2 It is a schematic diagram of a distribution network planning scheme generation method provided for an embodiment of the present invention.

[0022] Figure 3 It is a flowchart of an ant colony algorithm provided in an embodiment of the present invention;

[0023] Figure 4 This is a typical scene division schematic diagram provided for an embodiment of the present invention;

[0024] Figure 5 It is a schematic diagram of the current network structure provided for the embodiment of the present invention;

[0025] Figure 6 It is a schematic diagram of the available module extraction result provided by the embodiment of the present invention;

[0026] Figure 7 It is a schematic diagram of a target grid provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] Example

[0029] See also Figure 1-Figure 5 The present invention provides a method for generating a medium-voltage target grid transition plan based on an ant colony algorithm. The current information database is established by collecting and organizing detailed information on the current regional power grid, and then the relevant planning information is extracted in combination with the regional planning to form a planning information database. Next, the available networking modules are defined and classified according to the target grid and the current grid structure for specific needs of different regions. Subsequently, the current grid is disassembled, and the available modules are identified and classified. Finally, the learning and optimization capabilities of the ant colony algorithm are used to construct a target grid suitable for the region. This method can improve the efficiency and quality of distribution network planning and adapt to the differentiated requirements of different regions.

[0030] See also Figure 1 , a method for generating a medium voltage target grid transition scheme based on an ant colony algorithm includes the following steps:

[0031] First, the planning area is divided into grids and units, and a detailed investigation is conducted on the connection mode, interconnection rate, transfer rate, grid margin, switchgear, etc. of the existing power grid, while the problems existing in the current grid are recorded.

[0032] Secondly, conduct in-depth research on the topography, road network, corridor resources and municipal coordination in the planning area to form a current information database.

[0033] Again, data cleaning is performed on the acquired data in the region to ensure the accuracy and availability of the data.

[0034] ① Data collection and integration: Data needs to be collected from different sources. These data may include time series data, geographic location information, etc. These data are integrated into a unified data framework to ensure the consistency of data format and time series.

[0035] ② Missing value processing: Check the missing values ​​in the data set. For time series data, you can use the data from the previous day or the next day to fill in the missing values, or use a time series prediction model to estimate the missing values. For non-time series data, you may need to decide whether to delete or fill in the missing values ​​based on the specific situation.

[0036] ③Outlier detection and processing: Use statistical methods to identify outliers in the data. These outliers can be deleted or replaced, and the replacement value can be the average value or other statistics of the adjacent time points.

[0037] ④Data consistency check: Ensure that the data is logically consistent. For example, whether the load level is consistent with historical data and expected patterns.

[0038] Using the support vector machine classification model, we can distinguish different types of data points by finding an optimal hyperplane in the feature space. We use the support vector machine method to divide the available modules in the region into scenarios, mainly identifying three types of data sequences, namely, areas with rich low-carbon resources, areas with high requirements for specific disaster prevention, and areas with high power supply reliability requirements, and construct a multi-classification SVM. We preprocess the power grid-related data of the obtained area, select features that are helpful for classification, train the model using the SVM algorithm, and evaluate the performance of the model through cross-validation or retention method to ensure that the model has good generalization ability. Finally, we input the data of a random available module in the region into the algorithm model. According to the classification results output by the model, we can divide the available modules into scenarios and identify different data sequences such as areas with rich low-carbon resources, areas with high requirements for specific disaster prevention, and areas with high power supply reliability requirements.

[0039] Afterwards, the networking modules are defined and categorized according to the differentiated needs of different regions, such as low-carbon resource-rich areas, areas with high disaster prevention requirements, areas with high power supply reliability requirements, etc., combined with the power supply unit attributes. For example, low-carbon resource-rich areas may require more renewable energy access points, while areas with high specific disaster prevention requirements may require stronger disaster resistance.

[0040] Subsequently, disassemble the existing medium-voltage grid framework, which can be disassembled according to connection modes, connection rates, transfer supply rates, grid framework margins, switchgear, etc. According to the results of disassembling available modules, divide the existing regional grid framework into several small-scale modules. Based on the definition and classification results of network formation modules, identify and extract available modules, and classify and organize the available modules.

[0041] Finally, according to the extraction results of available modules and the classification of network formation module categories, use the ant colony algorithm to construct a target grid framework suitable for power supply units through learning and optimization.

[0042] Please refer to Figure 3 , the following are the steps of the ant colony algorithm provided in this application:

[0043] 1. Initialize parameters:

[0044] At the beginning of the calculation, relevant parameters need to be initialized, such as the size of the ant colony (number of ants) m, the importance factor α of pheromone, the importance factor β of the heuristic function, the pheromone evaporation factor P, the total pheromone release amount Q, the maximum number of iterations ier_max, and the initial value of the iteration number iter = 1.

[0045] 2. Construct the solution space:

[0046] Randomly place each ant in different standardized network formation module states. For each ant k (k = 1, 2..m), calculate its next standardized network formation module state until all ants complete the comparison of all network formation modules.

[0047] 3. Update pheromone:

[0048] Calculate the different target grid framework states constructed by each ant (k = 1, 2…, m), and record the optimal solution (optimal grid framework) in the current iteration. At the same time, update the pheromone concentration of different network formation modules.

[0049] 4. Judge whether to terminate:

[0050] If iter < iter_max, then set iter = ier + 1, clear the record table of the paths passed by the ants, and return to step (2); otherwise, terminate the calculation and output the optimal grid framework.

[0051] Specific implementation case:

[0052] Divide area M into 5 grids and 42 power supply units: 1 grid of type A / 18 units; 2 grids of type B / 22 units; 2 grids of type C / 2 units.

[0053]

[0054] Table 1 is a statistical table of the power grid division in Area M

[0055] Dismantle the existing medium voltage grid.

[0056] Wiring mode:

[0057] There are 34 10kV public overhead lines in the M area power grid. The connection modes mainly include single connection, double connection and multiple connection, among which single connection accounts for the highest proportion, reaching 58.82%.

[0058] In the municipal power supply area, the proportion of single-tie wiring mode is 58.82%, the proportion of two-tie wiring mode is 35.29%, and the proportion of multiple-tie wiring mode is 5.88%.

[0059]

[0060] Table 2 shows the 10kV power grid structure in Area M (overhead grid)

[0061] The M area power grid has a total of 83 10kV public cable lines, and the wiring modes mainly include single-loop network, double-loop network and others, among which the single-loop network accounts for the highest proportion, reaching 69.88%.

[0062] In the municipal power supply area, the proportion of single-loop network connection mode is 69.88%, and the proportion of double-loop network connection mode is 4.82%.

[0063]

[0064] Table 3 shows the 10kV power grid structure in Area M (cable network)

[0065] Contact rate:

[0066] The current medium-voltage line connection rate of the grid is 100%, and the effective connection rate is 96.58%. There are 4 invalid connection lines, namely 10kV Beiyan Village Line 1, Fengyu Line, Nanyu Line, and Zaoyuantou Line. The reason is that Fengyu Line and Nanyu Line are the first-end connections, and the line load cannot be flexibly transferred in sections when the mode is adjusted; Beiyan Village Line 1 and Zaoyuantou Line have busbar connection problems.

[0067] Switching facilities and equipment:

[0068] There are 61 10kV switch stations in M ​​District, 197 ring main units, 3 cable branch boxes, and 236 pole switches. The total number of 10kV switches is 2345, including 1905 circuit breakers and 440 load switches. The following table shows the switch facilities and equipment of 10kV power grid in M ​​District.

[0069]

[0070] Table 4: 10kV power grid switch facilities and equipment in Zone M

[0071] According to the differentiated requirements of different regions and the current medium voltage grid structure, according to the needs of different application scenarios, see the attached Figure 4 (such as areas with rich low-carbon resources, areas with high requirements for specific disaster prevention, areas with high requirements for power supply reliability, etc.) Combined with the current grid structure, see the attached Figure 5 The available modules are defined and categorized as follows. Figure 6 .

[0072] According to the available module extraction results and the classification of networking modules, the ant colony algorithm is used to build a target grid suitable for the power supply unit through learning and optimization. Figure 7 .

[0073] 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 generating a medium voltage target grid transition scheme based on an ant colony algorithm, characterized in that: The steps include: Step 1: Clarify the current status of regional power grid lines, including at least the length, model, wire diameter, distribution location, capacity, and switch station location information, and form a current status information database; Step 2: Extract information such as integrated pipe corridors and planned sites in combination with the detailed planning or master plan of the region to form a planning information database; Step 3: Based on the differentiated requirements of different regions and the current medium-voltage grid structure, and according to the requirements of different application scenarios and the current grid situation, define and categorize the available modules; Step 4: Disassemble the existing medium-voltage grid. According to the results of the available module disassembly, divide the existing regional grid into several small-scale modules. According to the definition and classification results of the networking modules, identify and extract the available modules, and classify and sort the available modules. Step 5: Based on the research results of networking module extraction, the ant colony algorithm is used to build standardized networking modules suitable for different target grid requirements through learning and optimization, and the networking module component results are given.

2. The method for generating a medium voltage target grid transition solution based on an ant colony algorithm according to claim 1 is characterized in that: The information database in step 1 also includes the connection mode, connection rate, transfer rate, grid margin, and switch equipment survey information of the existing power grid in the planning area.

3. The method for generating a medium voltage target grid transition solution based on an ant colony algorithm according to claim 2 is characterized in that: The planning area is divided into grids and units.

4. The method for generating a medium voltage target grid transition solution based on an ant colony algorithm according to claim 1 is characterized in that: The acquired regional data is cleaned, including the following steps:

1. Data collection and integration; 2. Missing value processing; 3. Outlier detection and processing; 4. Data consistency check.

5. The method for generating a medium voltage target grid transition solution based on an ant colony algorithm according to claim 1 is characterized in that: The regional differentiation in step 3 includes at least one of a low-carbon resource-rich region, a region with high disaster prevention requirements, and a region with high power supply reliability requirements.

6. The method for generating a medium voltage target grid transition solution based on an ant colony algorithm according to claim 1 is characterized in that: In the step 4, the existing medium voltage grid is dismantled according to the wiring mode, connection rate, transfer rate, grid margin and switchgear.

Images