Mobile hybrid distribution transformer and deployment method thereof in power distribution network

Abstract

The invention relates to the technical field of mobile transformers, and discloses a mobile hybrid distribution transformer and a deployment method thereof in a power distribution network, and the method comprises the steps: determining a potential deployment region, deployment capacity and deployment priority of the mobile transformer; constructing a load rate matrix and obtaining a distance cost matrix; determining the deployment position of the initial mobile transformer according to the generated earnings in combination with the potential deployment area and the deployment priority; and updating the load rate of the load rate matrix after the initial mobile transformer is added, constructing a constraint condition, carrying out income calculation on the other mobile transformers, and sequentially determining the deployment position of each mobile transformer until all the mobile transformers are deployed completely or meet the power supply demand. According to the method, the decision-making speed and quality can be improved, the deployment position of the hybrid distribution transformer can be quickly and accurately determined, the energy utilization efficiency is improved, energy waste is reduced, and the operation and maintenance cost of a power grid is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of mobile transformers, and in particular to a mobile hybrid distribution transformer and a method for deploying the same in a distribution network. Background Art

[0002] Voltage quality is one of the most basic indicators reflecting the quality of power. In recent years, with the diversification of power loads, the requirements for voltage quality have been continuously improved; however, the development of distributed power sources in distribution networks has increased their penetration rate in distribution networks, which has affected the power quality of distribution networks. On the other hand, with the diversification of loads, the emerging multi-loads have higher and higher requirements for power quality. Under this contradictory background, how to improve voltage quality has become a problem that must be solved in the process of intelligent development of distribution networks. As a flexible power resource solution, mobile hybrid distribution transformers (HDT) can be quickly deployed to different locations according to actual needs to meet temporary or seasonal increases in power demand. This solution mainly relies on the high flexibility and mobility of transformer units, enabling them to quickly respond to temporary changes in grid loads and optimize power distribution, thereby reducing energy waste and improving the overall reliability and service quality of the power system.

[0003] Therefore, a new solution is urgently needed to improve the adaptability and performance of the power distribution system. However, the current technology has not effectively combined the advantages of mobile transformers and hybrid transformers, resulting in a lack of high dynamics in voltage, active and reactive power control. At the same time, it is particularly important to develop a mobile hybrid distribution transformer and its corresponding deployment method to utilize the high efficiency and flexibility of mobile transformers to alleviate the pressure on the power quality of the distribution network.

[0004] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0005] In response to the problems in the related art, the present invention proposes a mobile hybrid distribution transformer and a deployment method thereof in a distribution network. The transformer effectively combines a mobile transformer with a hybrid transformer, and integrates a power electronic converter (PEC) in the mobile transformer, thereby achieving highly dynamic control of voltage, active power and reactive power. At the same time, the present invention provides a deployment method for the mobile hybrid distribution transformer to further improve its application flexibility and efficiency.

[0006] To this end, the specific technical solution adopted by the present invention is as follows:

[0007] According to one aspect of the present invention, there is provided a method for deploying a mobile hybrid distribution transformer in a distribution network, including the following steps:

[0008] S1. Use a machine learning algorithm to predict the load demands of each substation area at different time nodes in the future, and determine the potential deployment areas, deployment capacities, and deployment priorities of the mobile transformers according to the predicted load demands;

[0009] S2. Construct a load rate matrix of all substation areas and time nodes in combination with the predicted load demands, and obtain a distance cost matrix from each substation area to the other substation areas;

[0010] S3. Calculate the benefits generated by adding a mobile transformer to each substation area at each time node respectively, and determine the deployment locations of the initial mobile transformers according to the generated benefits in combination with the potential deployment areas and deployment priorities;

[0011] S4. Update the load rates in the load rate matrix after adding the initial mobile transformers, construct constraint conditions and calculate the benefits for the remaining mobile transformers, and determine the deployment locations of each mobile transformer in turn until all mobile transformers are deployed or the power supply demand is met.

[0012] Further, the step of using a machine learning algorithm to predict the load demands of each substation area at different time nodes in the future, and determining the potential deployment areas, deployment capacities, and deployment priorities of the mobile transformers according to the predicted load demands includes the following steps:

[0013] S11. Number all substation areas, obtain the real-time load data, historical load data, and weather data of each substation area, and use a machine learning algorithm to predict the load demands of each substation area at different time nodes in the future;

[0014] S12. Determine the potential deployment areas and corresponding deployment capacities of the mobile transformers according to the predicted load demands, and perform priority ranking on the potential deployment areas according to multi-objective optimization.

[0015] Further, the step of determining the potential deployment areas and corresponding deployment capacities of the mobile transformers according to the predicted load demands, and performing priority ranking on the potential deployment areas according to multi-objective optimization includes the following steps:

[0016] S121. Determine the high-load areas according to the comparison results between the predicted load demands and a preset load rate threshold, and use the high-load areas and the substation areas with load growth rates exceeding the preset growth threshold as the potential deployment areas of the mobile transformers;

[0017] S122. Calculate the capacities of the mobile transformers in the potential deployment areas using the predicted load demands, and adjust the capacity requirements in combination with the existing capacities and load transfer capabilities to obtain the deployment capacities of each potential deployment area;

[0018] S123. Taking load balancing, economy, flexibility and economy as optimization goals, construct a comprehensive objective function, determine constraints, and use an optimization algorithm to calculate a comprehensive score for each potential deployment area;

[0019] S124. Determine the deployment priority of each potential deployment area according to the ranking result of the comprehensive scores;

[0020] Among them, the expression of the comprehensive objective function is:

[0021] f(x)=ω 1 ·L+ω 2 ·C-ω 3 ·F-ω 4 ·E

[0022] The formula for calculating the comprehensive score is:

[0023] U i =ω 1 ·L i +ω 2 ·C i +ω 3 ·F i +ω 4 ·E i

[0024] Where f(x) is the comprehensive objective function value, L, C, F, and E are load balancing objectives, economic objectives, flexibility objectives, and emergency objectives, respectively. 1 ,ω 2 ,ω 3 ,ω 4 are the load balancing target weight, economic target weight, flexibility target weight and urgency target weight, respectively. i is the comprehensive score, L i , C i 、F i 、E i They are load balancing score, economy score, flexibility score and urgency score.

[0025] Furthermore, the construction of a load rate matrix of all substations and time nodes in combination with the predicted load demand, and obtaining a distance cost matrix from each substation to other substations includes the following steps:

[0026] S21, numbering each time period according to the preset time node, and obtaining the transformer parameters of each substation;

[0027] S22, obtaining the load data of each substation at each time node according to the predicted load demand, and generating a load rate matrix of each substation at each time node;

[0028] The rows in the load rate matrix are the area numbers, the columns are the time period numbers, and the content of each position in the matrix is ​​the load rate of the area at the time node, and the expression of the load rate is:

[0029]

[0030] In the formula, represents the load rate of the first mobile transformer in the s station at time t, It represents the calculated load of the transformer in the transformer area No. s at time t, S N，s Indicates the rated capacity of the transformer in the transformer area No. s;

[0031] S23, obtaining the distance cost from each substation to other substations, and constructing a distance cost matrix from each substation to other substations;

[0032] The rows in the route cost matrix are the starting points of the route, and the columns are the end points of the route. The content of each position in the matrix is ​​the route cost required from the starting site to the end site.

[0033] Furthermore, the calculation of the benefits generated by adding a mobile transformer to each area at each time node, and determining the deployment location of the initial mobile transformer according to the generated benefits combined with the potential deployment area and the deployment priority includes the following steps:

[0034] S31. Based on the transformer loss formula, calculate the difference between the transformer loss of each substation at any time point and the transformer loss generated after adding a mobile transformer;

[0035] The transformer loss formula is:

[0036]

[0037] Where P loss，s，t It represents the transformer loss caused by adding a mobile transformer to the transformer area No. s at time t, ΔP k，s Indicates the short-circuit active power loss of the transformer in the s transformer area, RL s，t represents the load rate of transformer section s at time t, S N，s Indicates the rated capacity of the transformer in the transformer area No. s, ΔP 0，t Indicates the no-load active power loss of the mobile transformer in the s transformer area, ΔP k，t It represents the short-circuit active power loss of the mobile transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the transformer area No. s;

[0038] S32, selecting an initial station area according to the potential deployment area and the deployment priority, and obtaining the travel cost of moving from the initial station area to all other stations;

[0039] S33, constructing a revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the revenue model;

[0040] S34, based on the benefits generated by moving the mobile transformer to each substation, combined with the potential deployment area, determine the substation location where the mobile transformer should be deployed at the time node;

[0041] S35. Repeat steps S31-S34 to determine the deployment position of the mobile transformer in each time period.

[0042] Furthermore, the method of constructing a revenue model based on the transformer loss difference and the distance cost when the initial transformer area is moved to other transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the revenue model includes the following steps:

[0043] S331. Obtain the transformer loss cost parameters and weights during the use of the mobile transformer; obtain the cost parameters and weights during the production and movement of the mobile transformer;

[0044] S332. Construct a revenue model based on the transformer loss cost parameters and weights during the use of the mobile transformer and the cost parameters and weights during the production and movement of the mobile transformer;

[0045] Among them, the expression of the revenue model is:

[0046] f ms =c 1 f 11 +c 2 f 12

[0047] In the formula, f ms represents the revenue value, c 1 Represents the weight coefficient of transformer loss, c 2 represents the cost weight coefficient of movement, f 11 represents the transformer loss cost parameter, f 12 A parameter representing the cost of movement.

[0048] Furthermore, in the process of determining the initial mobile transformer deployment location, if the minimum deployment time is set, the benefits generated by adding a mobile transformer to each substation at each time node are calculated respectively, and the initial mobile transformer deployment location is determined based on the generated benefits combined with the potential deployment area and deployment priority, including the following steps:

[0049] S31', determining the first deployment position of the mobile transformer to be deployed;

[0050] S32', repeating steps S31-S34 to obtain the substation location where the mobile transformer should be deployed at the time node, and determining whether the substation to be deployed at the time node is the same as the substation to be deployed in the previous time period. If so, repeating step S32' until the deployment position of the mobile transformer in each time period is determined. If not, executing step S33';

[0051] S33', determine the position where the mobile transformer should be deployed in the next period of time, and judge whether the position where the mobile transformer should be deployed at this time node is the same as the position where the mobile transformer should be deployed at the previous time node. If so, repeat step S32'; if not, update the deployment position.

[0052] Furthermore, the determining of the first time period deployment position of the mobile transformer to be deployed comprises the following steps:

[0053] S311', calculating the difference between the transformer loss of each area in the first time period and the transformer loss generated after adding a mobile transformer according to the transformer loss formula;

[0054] S312', selecting an initial station area according to the potential deployment area and deployment priority, and obtaining the distance cost of moving from the initial station area to all other stations;

[0055] S313', constructing a new revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the new revenue model;

[0056] Among them, the expression of the new profit model is:

[0057] f mm =c 1 f 21 +c 2 f 22

[0058] In the formula, f mm represents the new revenue value, c 1 Represents the weight coefficient of transformer loss, c 2 represents the cost weight coefficient of movement, f 21 represents the sum of transformer loss gains after the move, f 22 represents the sum of movement costs.

[0059] Further, updating the load factor matrix after adding the initial mobile transformer includes the following steps:

[0060] Obtain the initial deployment position of the mobile transformer, and calculate the proportion of the load of the original transformer in each substation after the initial mobile transformer is deployed at the position; update the load rate matrix based on the proportion of the load of the original transformer in each substation;

[0061] The calculation formula for the load ratio is:

[0062]

[0063] The update formula of the load factor matrix is:

[0064]

[0065] In the formula, p represents the proportion of the original transformer load in each area, S N，s Indicates the rated capacity of the transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the s transformer area. It represents the load rate of the nth mobile transformer in the s station area at time t.

[0066] According to another aspect of the present invention, there is provided a mobile hybrid distribution transformer, which includes a movable transformer carrier trolley, wheels are arranged at the bottom corners of the movable transformer carrier trolley, a transformer body is arranged inside the movable transformer carrier trolley, a plurality of insulators are arranged on the top of the transformer body, a high-voltage outlet line is arranged on the top of the insulator, a low-voltage outlet line is arranged at one end of the transformer body, and a power electronic converter connected to the transformer body is arranged on one side of the transformer body.

[0067] Compared with the prior art, the present invention provides a mobile hybrid distribution transformer and a method for deploying the same in a distribution network, which has the following beneficial effects:

[0068] (1) The present invention provides a method for deploying a mobile transformer, which can improve the speed and quality of decision-making, so that the optimal deployment location of the mobile transformer can be determined quickly and accurately, so that when facing complex and changeable power grid loads, the power demand can still be accurately predicted to ensure efficient use of energy and significantly reduce energy waste caused by uneven power distribution, thereby saving the operation and maintenance costs of the power grid and improving the power supply reliability of the power grid; in addition, this flexible deployment capability can help the local power grid manage the load more effectively and reduce management costs.

[0069] (2) The present invention combines the existing mobile distribution transformer with a power electronic converter. Compared with the traditional mobile distribution transformer, it can achieve highly dynamic control of voltage, active power and reactive power. It can better solve the problems of voltage drop and sudden rise caused by the dynamic process of the distribution network (such as switch switching, dynamic load adjustment, fault and distributed power output fluctuation) than ordinary mobile transformers, and effectively alleviate the problem of power quality in the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0071] Figure 1 is a flow chart of a method for deploying a mobile hybrid distribution transformer in a distribution network according to an embodiment of the present invention;

[0072] Figure 2 is a schematic diagram of transformer deployment positions according to a method for deploying a mobile hybrid distribution transformer in a distribution network according to an embodiment of the present invention;

[0073] Figure 3 is a load rate variation curve diagram of a method for deploying a mobile hybrid distribution transformer in a distribution network according to an embodiment of the present invention;

[0074] Figure 4 is a structural schematic diagram of a mobile hybrid distribution transformer according to an embodiment of the present invention;

[0075] Figure 5 yes Figure 4 Side view of.

[0076] In the figure:

[0077] 1. Movable transformer carrier trolley; 2. Wheels; 3. Transformer body; 4. Insulator; 5. High-voltage output line; 6. Low-voltage output line; 7. Power electronic converter. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] According to an embodiment of the present invention, a mobile hybrid distribution transformer and a method for deploying the same in a distribution network are provided.

[0080] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a method for deploying a mobile hybrid distribution transformer in a distribution network is provided, comprising the following steps:

[0081] S1. Use machine learning algorithms to predict the future load demand of each substation at different time points, and determine the potential deployment area, deployment capacity and deployment priority of mobile transformers based on the predicted load demand;

[0082] The method of using a machine learning algorithm to predict the load demand of each substation at different time nodes in the future and determining the potential deployment area, deployment capacity and deployment priority of the mobile transformer according to the predicted load demand includes the following steps:

[0083] S11. Number all substations, obtain real-time load data, historical load data and weather data of each substation, and use machine learning algorithms to predict the load demand of each substation at different time nodes in the future;

[0084] Specifically, the machine learning algorithm is used to predict the load demand of each substation at different time nodes in the future, including:

[0085] 1) Data preparation

[0086] 1.1) Data collection: real-time load data (including the actual load value of each substation at different times, such as power value, voltage, current, etc.), historical load data (including the load value of each substation in the past period of time, collected by hours, days, weeks, months, etc., and the data dimensions should include peak load, average load and valley load) and weather data (including temperature, humidity, wind speed, etc.);

[0087] 1.2) Data processing:

[0088] Data cleaning: Check and fix outliers (such as sudden load spikes) and fill in missing values ​​(such as using interpolation, historical averaging, etc.);

[0089] Feature engineering: creating time features (such as 24-hour system, day of the week, holiday markers, etc.), adding external features (such as temperature, humidity, social activity markers, etc.), and extracting historical load patterns (such as the average load in the past hour, day, or week as a feature);

[0090] Data segmentation: divided into training set, validation set and test set (such as 70% / 15% / 15%);

[0091] 2) Model development and training

[0092] 2.1) Feature Selection:

[0093] Input features: time features (hours, weeks, holiday markers, etc.), historical load (load data for the past hour, day, week), external features (weather data, economic activity data, etc.);

[0094] Output target: load values ​​at different time nodes in the future (such as the load of the next hour or the next day);

[0095] 2.2) Model construction: According to the data characteristics and objectives, select the appropriate algorithm for modeling: transform the load forecasting task into a regression problem, and input features such as time, weather, and historical load into the machine learning model (such as XGBoost, LightGBM);

[0096] 2.3) Model training:

[0097] Loss function selection: mean square error (MSE) and mean absolute error (MAE);

[0098] Hyperparameter optimization: Use Grid Search or Bayesian Optimization to find the best hyperparameters.

[0099] Early stopping mechanism: Use validation sets to monitor model training and prevent overfitting;

[0100] 3) Model evaluation and testing: Use cross-validation (such as rolling validation of time series) to evaluate model performance and ensure that the model performs consistently over different time periods;

[0101] 4) Deployment and application:

[0102] 4.1) Load prediction model deployment:

[0103] Real-time prediction: deploy the model to the cloud or locally, input the latest load data in real time, and predict the load demand at each time node in the future;

[0104] Batch forecasting: Batch forecasting of daily or weekly load demand for advance planning and scheduling;

[0105] 4.2) Result visualization: Visualize the prediction results (such as line graphs, heat maps), with the horizontal axis representing the time node and the vertical axis representing the load demand;

[0106] 4.3) Dynamic Update: Regularly update and retrain the model with the latest load data to ensure prediction accuracy.

[0107] S12. Determine potential deployment areas and corresponding deployment capacities of mobile transformers according to the predicted load demand, and prioritize the potential deployment areas according to multi-objective optimization.

[0108] Specifically, determining the potential deployment area and the corresponding deployment capacity of the mobile transformer according to the predicted load demand, and prioritizing the potential deployment area according to the multi-objective optimization includes the following steps:

[0109] S121, determining a high-load area according to a comparison result between the predicted load demand and a preset load rate threshold, and taking the high-load area and the area where the load growth rate exceeds the preset growth threshold as a potential deployment area for the mobile transformer, specifically including:

[0110] Screening potential high-load areas based on predicted load rates: Using predicted load demand, screen out areas where future load rates exceed a certain threshold (e.g., 85%) and prioritize these high-load areas;

[0111] Consider the load growth trend: For areas with faster predicted load growth, they are listed as potential deployment candidates even if the current load rate has not reached the threshold;

[0112] Inter-station coordination analysis: Analyze the load distribution and power transfer capacity between stations (such as whether there are adjacent low-load stations that can share the load). If a station is overloaded, whether the load of its neighboring stations is also close to full load will affect its priority as a potential deployment area;

[0113] S122. Calculate the capacity of the mobile transformer in the potential deployment area using the predicted load demand, and adjust the capacity demand in combination with the existing capacity and load transfer capability to obtain the deployment capacity of each potential deployment area, specifically including:

[0114] Calculate the required transformer capacity based on the predicted load: In the potential high-load area, the required transformer capacity C is determined based on the predicted peak load demand and safety margin (generally 10%-20%). The formula is C 所需 =P 峰值负载 ×(1+redundancy coefficient), where P 峰值负载 For the predicted peak load, the redundancy factor is generally 0.1-0.2;

[0115] Adjust capacity requirements based on existing capacity and load transfer capabilities: If the existing capacity can partially meet the demand, only the shortfall will be supplemented; if the peak load can be reduced through load transfer, the transferred portion will be deducted from the demand calculation;

[0116] Output deployment capacity recommendations: recommended mobile transformer capacity for each potential high-load area (e.g. 300kVA, 500kVA, etc.);

[0117] S123. Taking load balancing, economy, flexibility and economy as optimization goals, construct a comprehensive objective function, determine constraints, and use an optimization algorithm to calculate a comprehensive score for each potential deployment area;

[0118] Load balancing goal: to solve the needs of high-load areas and reduce the load rate to a safe range (such as 60%-80%);

[0119] Economic goal: Minimize deployment costs, including transportation costs and equipment costs;

[0120] Flexibility goal: give priority to deployment locations that can serve multiple stations to improve resource utilization;

[0121] Emergency goals: Prioritize key areas (such as areas with high power supply importance);

[0122] S124. Determine the deployment priority of each potential deployment area according to the ranking result of the comprehensive scores;

[0123] Among them, the expression of the comprehensive objective function is:

[0124] f(x)=ω 1 ·L+ω 2 ·C-ω 3 ·F-ω 4 ·E

[0125] The formula for calculating the comprehensive score is:

[0126] U i =ω 1 ·L i +ω 2 ·C i +ω 3 ·F i +ω 4 ·E i

[0127] Where f(x) is the comprehensive objective function value, L, C, F, and E are load balancing objectives, economic objectives, flexibility objectives, and emergency objectives, respectively. 1 ,ω 2 ,ω 3 ,ω 4 are the load balancing target weight, the economic target weight, the flexibility target weight and the urgency target weight. In this embodiment, ω 1 ,ω 2 ,ω 3 ,ω 4 The values ​​of U are 0.4, 0.3, 0.2, and 0.1 respectively. i is the comprehensive score, L i , C i 、F i 、E i They are load balancing score, economy score, flexibility score and urgency score;

[0128] The goal of load balancing is to reduce the load rate of high-load areas to a safe range (such as 60%-80%) to improve system stability. The load balancing score measures the contribution of the deployment point to load optimization. The calculation formula is:

[0129]

[0130] The economic score measures the cost-effectiveness of the deployment point, including the minimization of transportation costs and equipment costs, and is calculated as:

[0131]

[0132] The flexibility score measures the ability of a deployment point to serve multiple areas and its adaptability to future load changes. The calculation formula is:

[0133]

[0134] The formula for calculating the urgency score is:

[0135]

[0136] In this embodiment, the power supply importance weight of ordinary substations is 1, the power supply importance weight of important substations (such as business districts and densely populated areas) is 1.5, and the power supply importance weight of key substations (such as hospitals and industrial parks) is 2;

[0137] Through the above steps, we can achieve efficient and accurate load forecasting (improve forecasting accuracy and provide a scientific basis for deployment decisions), reasonable regional screening and capacity planning (optimize deployment scope and reduce resource waste), optimize load balancing across the entire network (ensure global load distribution balance and improve distribution network operation stability), reduce operating costs and accident risks (reduce overload accidents and improve power supply reliability), and enhance the efficiency of subsequent steps (provide a solid data foundation for benefit calculation and optimized deployment).

[0138] S2. Build a load rate matrix of all substations and time nodes based on the predicted load demand, and obtain the distance cost matrix from each substation to other substations;

[0139] The method of constructing a load rate matrix of all substations and time nodes in combination with the predicted load demand and obtaining a distance cost matrix from each substation to other substations includes the following steps:

[0140] S21. Number each time period according to a preset time node, and obtain the transformer parameters of each substation (including load data at each time node, transformer no-load active loss, transformer capacity, transformer short-circuit active loss); specifically, in this embodiment, every fifteen minutes is used as a time node and each time period is numbered;

[0141] S22, obtaining the load data of each substation at each time node according to the predicted load demand, and generating a load rate matrix of each substation at each time node;

[0142] The rows in the load rate matrix are the area numbers, the columns are the time period numbers, and the content of each position in the matrix is ​​the load rate of the area at the time node, and the expression of the load rate is:

[0143]

[0144] In the formula, represents the load rate of the first mobile transformer in the s station at time t, It represents the calculated load of the transformer in the transformer area No. s at time t, S N，s Indicates the rated capacity of the transformer in the transformer area No. s;

[0145] S23, obtaining the distance cost from each substation to other substations, and constructing a distance cost matrix from each substation to other substations;

[0146] The rows in the route cost matrix are the starting points of the route, and the columns are the end points of the route. The content of each position in the matrix is ​​the route cost required from the starting site to the end site.

[0147] S3. Calculate the benefits of adding a mobile transformer to each area at each time node, and determine the initial deployment location of the mobile transformer based on the generated benefits combined with the potential deployment area and deployment priority;

[0148] The steps of respectively calculating the benefits generated by adding a mobile transformer to each area at each time node, and determining the deployment location of the initial mobile transformer according to the generated benefits combined with the potential deployment area and the deployment priority include the following steps:

[0149] S31. Based on the transformer loss formula, calculate the difference between the transformer loss of each substation at any time point and the transformer loss generated after adding a mobile transformer;

[0150] The transformer loss formula is:

[0151]

[0152] Where P loss，s，t It represents the transformer loss caused by adding a mobile transformer to the transformer area No. s at time t, ΔP k，s Indicates the short-circuit active power loss of the transformer in the s transformer area, RL s，t represents the load rate of transformer section s at time t, S N，sIndicates the rated capacity of the transformer in the transformer area No. s, ΔP 0，t Indicates the no-load active power loss of the mobile transformer in the s transformer area, ΔP k，t It represents the short-circuit active power loss of the mobile transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the transformer area No. s;

[0153] S32, selecting an initial station area according to the potential deployment area and the deployment priority, and obtaining the travel cost of moving from the initial station area to all other stations;

[0154] S33, constructing a revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the revenue model;

[0155] Specifically, the method of constructing a revenue model based on the transformer loss difference and the distance cost of moving from the initial substation to the remaining substations, and calculating the revenue generated by moving the mobile transformer to each substation based on the revenue model includes the following steps:

[0156] S331. Obtain the transformer loss cost parameters and weights during the use of the mobile transformer; obtain the cost parameters and weights during the production and movement of the mobile transformer;

[0157] Specifically, in this embodiment, the transformer loss cost parameters of the mobile hybrid distribution transformer are obtained during the use process, and based on multiple loss cost parameters, the loss cost-effectiveness of the transformer during use is calculated by weighted summation; the cost parameters of the mobile hybrid distribution transformer during the production and movement process are obtained, and based on multiple cost parameters, the cost-effectiveness of the movement process is calculated by weighted summation.

[0158] S332. Construct a revenue model based on the transformer loss cost parameters and weights during the use of the mobile transformer and the cost parameters and weights during the production and movement of the mobile transformer;

[0159] Among them, the expression of the revenue model is:

[0160] f ms =c 1 f 11 +c 2 f 12

[0161] In the formula, f ms represents the revenue value, c 1 Represents the weight coefficient of transformer loss, c 2 represents the cost weight coefficient of movement, f 11 represents the transformer loss cost parameter, f 12A parameter representing the cost of movement.

[0162] S34, based on the benefits generated by moving the mobile transformer to each substation, combined with the potential deployment area, determine the substation location where the mobile transformer should be deployed at the time node;

[0163] S35. Repeat steps S31-S34 to determine the deployment position of the mobile transformer in each time period.

[0164] In addition, in the process of determining the initial mobile transformer deployment location, if a minimum time for the mobile transformer to be deployed is specified, the following steps need to be added:

[0165] S31', determining the first time period deployment position of the mobile transformer to be deployed;

[0166] Specifically, the determining of the first time period deployment position of the mobile transformer to be deployed comprises the following steps:

[0167] S311', calculating the difference between the transformer loss of each area in the first time period and the transformer loss generated after adding a mobile transformer according to the transformer loss formula;

[0168] S312', selecting an initial station area according to the potential deployment area and deployment priority, and obtaining the distance cost of moving from the initial station area to all other stations;

[0169] S313', constructing a new revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the new revenue model;

[0170] Among them, the expression of the new profit model is:

[0171] f mm =c 1 f 21 +c 2 f 22

[0172] In the formula, f mm represents the new revenue value, c 1 Represents the weight coefficient of transformer loss, c 2 represents the cost weight coefficient of movement, f 21 represents the sum of transformer loss gains after the move, f 22 represents the sum of movement costs.

[0173] S32', repeating steps S31-S34 to obtain the substation location where the mobile transformer should be deployed at the time node, and determining whether the substation to be deployed at the time node is the same as the substation to be deployed in the previous time period. If so, repeating step S32' until the deployment position of the mobile transformer in each time period is determined. If not, executing step S33';

[0174] S33', determine the position where the mobile transformer should be deployed in the next period of time (including the same number of time nodes), and judge whether the position where the mobile transformer should be deployed at this time node is the same as the position where the mobile transformer should be deployed at the previous time node. If so, repeat step S32'; if not, update the deployment position.

[0175] S4. Update the load rate matrix after adding the initial mobile transformer, construct constraints and calculate the benefits of the remaining mobile transformers, and determine the deployment location of each mobile transformer in turn until all mobile transformers are deployed or meet the power supply needs.

[0176] The construction constraints include:

[0177] Node voltage constraints:

[0178]

[0179] In the formula, They represent the upper and lower limits of the voltage amplitude at node s, U s，t It is represented as the voltage amplitude of node i at time t;

[0180] Considering the safety transmission limit of line current, the branch current constraint is:

[0181]

[0182] In the formula, I ij，t represents the current flowing through branch ij at time t, Indicates the maximum value of the current allowed to flow through branch ij;

[0183] To ensure that the network is radial, the topology constraints are:

[0184]

[0185] In the formula, α ij represents the switch state of branch ij, z represents the number of network nodes, and Ω represents the set of distribution network branches;

[0186] Specifically, updating the load factor matrix after adding the initial mobile transformer includes the following steps:

[0187] Obtain the initial deployment position of the mobile transformer, and calculate the proportion of the load of the original transformer in each substation after the initial mobile transformer is deployed at the position; update the load rate matrix based on the proportion of the load of the original transformer in each substation;

[0188] The calculation formula for the load ratio is:

[0189]

[0190] The update formula of the load factor matrix is:

[0191]

[0192] In the formula, p represents the proportion of the original transformer load in each area, S N，s Indicates the rated capacity of the transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the s transformer area. It represents the load rate of the nth mobile transformer in the s station area at time t.

[0193] In order to facilitate understanding of the above technical solutions of the present invention, specific examples of the present invention in actual processes are described in detail below.

[0194] According to the above deployment method, 1228 substations in a certain area of ​​XX Province were selected to deploy 4 mobile hybrid distribution transformers to evaluate the feasibility of this method. The deployment positions of these 4 mobile hybrid distribution transformers were calculated using the MATLAB simulation platform. Figure 2 shown.

[0195] exist Figure 2 In the figure, the No. 1 mobile hybrid distribution transformer was deployed in the substations of No. 272, No. 907, No. 271, No. 1086, No. 907, and No. 1178 in different time periods; the No. 2 mobile hybrid distribution transformer was always deployed in the substation of No. 1018; the No. 3 mobile hybrid distribution transformer was deployed in the substations of No. 275, No. 272, No. 1086, No. 1178, and No. 271 in different time periods; the No. 4 mobile hybrid distribution transformer was deployed in the substations of No. 276, No. 1177, No. 1178, and No. 271. This reflects that each modular mobile transformer moves between different substations according to the grid demand and possible priority, proving the correctness and feasibility of this method.

[0196] In order to further prove the reliability of this method, this example selected the relatively typical substations No. 271, No. 272, No. 1018, and No. 1086 to draw a comparison chart of their load rates before and after the introduction of the mobile hybrid distribution transformer. At the same time, the following evaluation steps for mobile transformers were formulated:

[0197] Step 1: Data collection and organization. Before deploying mobile transformers to each substation area, collect historical load data and transformer data of each substation area.

[0198] Step 2: Determine the performance evaluation index. Determine the improvement of the load factor as the key performance evaluation index. The improvement of the load factor is measured by comparing the change in the load factor before and after the introduction of the mobile transformer.

[0199] Step 3: Evaluation of actual operation effect. Based on the collected data, the load rate change after the introduction of the mobile transformer is calculated for each substation area. For example, the load rate of substation area No. 271 fluctuated violently before the introduction of the mobile hybrid distribution transformer, but after the introduction of the mobile hybrid distribution transformer, the load rate decreased significantly; the load rate of substation area No. 272 ​​was high in the initial period, and then the load rate decreased, but after the introduction of the mobile hybrid distribution transformer, the load rate decreased significantly during the period of high load rate; the load rate of substation area No. 1086 was roughly in the form of a sawtooth wave, and the load rate after the introduction of the mobile hybrid distribution transformer was still in the form of a sawtooth wave, but the load rate decreased significantly; the load rate of substation area No. 1018 was also roughly in the form of a triangular wave, and the load rate decreased significantly after the introduction of the mobile hybrid distribution transformer. By deploying mobile hybrid distribution transformers, the load rates of these substation areas have been significantly reduced, which proves the effectiveness of this method in improving the load rate.

[0200] Step 4: Comprehensive performance analysis and feedback. Combined with various evaluation indicators, conduct a comprehensive analysis of the comprehensive performance of mobile transformers in different substation areas, and summarize their advantages and disadvantages under different power grid environments and load conditions. Feedback the evaluation results to relevant departments to provide a basis for the operation strategy, parameter setting and future optimization and upgrading of mobile transformers, and further improve their application effect and reliability in the power grid.

[0201] like Figure 3 As shown, through the above evaluation steps, it can be clearly seen that after the introduction of mobile hybrid distribution transformers, these substation areas have experienced positive changes in key performance indicators such as load rate, thus proving the feasibility and effectiveness of this method.

[0202] According to another embodiment of the present invention, Figure 4 and Figure 5As shown, a mobile hybrid distribution transformer is provided, which includes a movable transformer carrier trolley 1. In specific application, the movable transformer carrier trolley is a closed trolley. Wheels 2 are arranged at the bottom corners of the movable transformer carrier trolley 1, so that the transformer can be protected while providing flexible mobility for the transformer. A transformer body 3 is arranged inside the movable transformer carrier trolley 1, and a plurality of insulators 4 are arranged on the top of the transformer body 3. A high-voltage outlet line (10KV) 5 is arranged on the top of the insulator 4. A low-voltage outlet line (0.4KV) 6 is arranged at one end of the transformer body 3. An operable PEC module (power electronic converter, i.e., power electronic converter 7) connected thereto is arranged on one side of the transformer body 3. In specific application, the PEC module is connected to the transformer body through an electrical connection structure to provide it with a function of highly dynamic control of voltage, active power and reactive power.

[0203] In actual operation, the staff can move the transformer to the required scene by connecting the trolley with other power equipment. During on-site operation, the staff can directly operate the high-voltage outlet terminal on the top of the trolley and the low-voltage outlet terminal on the side to connect the mobile transformer to the grid. In addition, the staff can also operate the PEC module to make corresponding adjustments and handle voltage drops, sudden increases and other problems that may occur during operation to ensure the stable operation of the system.

[0204] Among them, the operable PEC module is specifically as follows: In a three-phase system of a distribution transformer, its single phase is analyzed, and the proposed single-phase hybrid distribution transformer is composed of a transformer winding, a PEC and a corresponding bypass switch. Among them, the secondary side of the transformer winding is divided into two parts: the main winding and the auxiliary winding; the PEC is mainly a power electronic converter. The input side of the PEC is connected to the auxiliary winding, and the output side forms a series system with the main winding and the load, that is, the single-phase HDT can achieve flexible regulation of the load voltage through the modulation of the converter.

[0205] To sum up, with the help of the above-mentioned technical scheme of the present invention, the portability and rapid deployment characteristics of the mobile distribution transformer make it an ideal choice for temporary or emergency power needs. At the same time, the present invention combines the mobile distribution transformer with power electronics, which not only utilizes the advantages of the mobile transformer, but also combines the advantages of the power electronic converter that can cope with voltage drops and sudden increases that may occur in practical applications; at the same time, the deployment method for the mobile hybrid distribution transformer provided by the present invention can quickly and accurately determine the optimal deployment position of the hybrid distribution transformer, so that when facing complex and changeable power grid loads, it is still possible to accurately predict power demand, ensure efficient use of energy, and significantly reduce energy waste caused by uneven power distribution, thereby saving the operation and maintenance costs of the power grid and improving the power supply reliability of the power grid; in addition, this flexible deployment capability can help local power grids manage loads more effectively and reduce management costs.

[0206] The technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes the steps described in the above method, and the storage medium, such as ROM / RAM, a disk, an optical disk, etc.

[0207] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for deploying a mobile hybrid distribution transformer in a distribution network, characterized in that: The following steps are involved: S1. Use machine learning algorithms to predict the future load demand of each substation at different time points, and determine the potential deployment area, deployment capacity and deployment priority of mobile transformers based on the predicted load demand; S2. Build a load rate matrix of all substations and time nodes based on the predicted load demand, and obtain the distance cost matrix from each substation to other substations; S3. Calculate the benefits of adding a mobile transformer to each area at each time node, and determine the initial deployment location of the mobile transformer based on the generated benefits combined with the potential deployment area and deployment priority; S4. Update the load rate matrix after adding the initial mobile transformer, construct constraints and calculate the benefits of the remaining mobile transformers, and determine the deployment location of each mobile transformer in turn until all mobile transformers are deployed or meet the power supply needs.

2. A method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 1, characterized in that: The method of using a machine learning algorithm to predict the load demand of each substation at different time nodes in the future and determining the potential deployment area, deployment capacity and deployment priority of the mobile transformer according to the predicted load demand includes the following steps: S11. Number all substations, obtain real-time load data, historical load data and weather data of each substation, and use machine learning algorithms to predict the load demand of each substation at different time nodes in the future; S12. Determine potential deployment areas and corresponding deployment capacities of mobile transformers according to the predicted load demand, and prioritize the potential deployment areas according to multi-objective optimization.

3. The method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 2, characterized in that: Determining the potential deployment area and the corresponding deployment capacity of the mobile transformer according to the predicted load demand, and prioritizing the potential deployment area according to the multi-objective optimization includes the following steps: S1 21. Determine the high-load area according to the comparison result of the predicted load demand and the preset load rate threshold, and take the high-load area and the station area where the load growth rate exceeds the preset growth threshold as the potential deployment area of ​​the mobile transformer; S122. Calculate the capacity of the mobile transformer in the potential deployment area using the predicted load demand, and adjust the capacity demand in combination with the existing capacity and load transfer capability to obtain the deployment capacity of each potential deployment area; S1 23. Taking load balancing, economy, flexibility and economy as optimization goals, construct a comprehensive objective function, determine the constraints, and use the optimization algorithm to calculate the comprehensive score of each potential deployment area; S124. Determine the deployment priority of each potential deployment area according to the ranking result of the comprehensive scores; Among them, the expression of the comprehensive objective function is: f(x)=ω1·L+ω2·C-ω3·F-ω4·E The formula for calculating the comprehensive score is: U i =ω1·L i +ω2·C i +ω3·F i +ω4·E i Where f(x) is the comprehensive objective function value, L, C, F, and E are the load balancing objective, economic objective, flexibility objective, and emergency objective, respectively; ω1, ω2, ω3, and ω4 are the weights of the load balancing objective, economic objective, flexibility objective, and emergency objective, respectively; and U i is the comprehensive score, L i , C i 、F i 、E i They are load balancing score, economy score, flexibility score and urgency score.

4. The method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 1, characterized in that: The method of constructing a load rate matrix of all substations and time nodes in combination with the predicted load demand and obtaining a distance cost matrix from each substation to other substations includes the following steps: S2 1. Number each time period according to the preset time node and obtain the transformer parameters of each substation; S22, obtaining the load data of each substation at each time node according to the predicted load demand, and generating a load rate matrix of each substation at each time node; The rows in the load rate matrix are the area numbers, the columns are the time period numbers, and the content of each position in the matrix is ​​the load rate of the area at the time node, and the expression of the load rate is: In the formula, represents the load rate of the first mobile transformer in the s station at time t, It represents the calculated load of the transformer in the transformer area No. s at time t, S N，s Indicates the rated capacity of the transformer in the transformer area No. s; S23, obtaining the distance cost from each substation to other substations, and constructing a distance cost matrix from each substation to other substations; The rows in the route cost matrix are the starting points of the route, and the columns are the end points of the route. The content of each position in the matrix is ​​the route cost required from the starting site to the end site.

5. The method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 1, characterized in that: The method of calculating the benefits generated by adding a mobile transformer to each area at each time node and determining the deployment location of the initial mobile transformer according to the generated benefits combined with the potential deployment area and the deployment priority includes the following steps: S3 1. Based on the transformer loss formula, calculate the difference between the transformer loss of each substation at any time point and the transformer loss generated after adding a mobile transformer; The transformer loss formula is: Where P loss，s，t It represents the transformer loss caused by adding a mobile transformer to the transformer area No. s at time t, ΔP k，s Indicates the short-circuit active power loss of the transformer in the s transformer area, RL s，t represents the load rate of transformer section s at time t, S N，s Indicates the rated capacity of the transformer in the transformer area No. s, ΔP 0，t Indicates the no-load active power loss of the mobile transformer in the s transformer area, ΔP k，t It represents the short-circuit active power loss of the mobile transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the transformer area No. s; S32, selecting an initial station area according to the potential deployment area and the deployment priority, and obtaining the travel cost of moving from the initial station area to all other stations; S33, constructing a revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the revenue model; S34, based on the benefits generated by moving the mobile transformer to each substation, combined with the potential deployment area, determine the substation location where the mobile transformer should be deployed at the time node; S35. Repeat steps S31-S34 to determine the deployment position of the mobile transformer in each time period.

6. A method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 5, characterized in that: The method of constructing a revenue model based on the transformer loss difference and the distance cost of moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the revenue model includes the following steps: S33 1. Obtain the transformer loss cost parameters and weights during the use of the mobile transformer; obtain the cost parameters and weights during the production and movement of the mobile transformer; S332. Construct a revenue model based on the transformer loss cost parameters and weights during the use of the mobile transformer and the cost parameters and weights during the production and movement of the mobile transformer; Among them, the expression of the revenue model is: in ms =c1f 11 +c2f 12 In the formula, f ms represents the benefit value, c1 represents the weight coefficient of transformer loss, c2 represents the weight coefficient of the cost generated by the movement, and f 11 represents the transformer loss cost parameter, f 12 A parameter representing the cost of movement.

7. A method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 6, characterized in that: In the process of determining the initial mobile transformer deployment location, if the minimum deployment time is set, the benefits generated by adding a mobile transformer to each substation at each time node are calculated respectively, and the initial mobile transformer deployment location is determined based on the generated benefits combined with the potential deployment area and deployment priority, including the following steps: S3 1', determining the first time period deployment position of the mobile transformer to be deployed; S32', repeat steps S31-S34 to obtain the location of the area where the mobile transformer should be deployed at the time node, and determine whether the area to be deployed at the time node is the same as the area to be deployed in the previous time period. If so, repeat step S32' until the deployment position of the mobile transformer in each time period is determined. If not, execute step S33'; S33', determine the position where the mobile transformer should be deployed in the next period of time, and judge whether the position where the mobile transformer should be deployed at this time node is the same as the position where the mobile transformer should be deployed at the previous time node. If so, repeat step S32'; if not, update the deployment position.

8. A method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 7, characterized in that: Determining the first time period deployment position of the mobile transformer to be deployed comprises the following steps: S3 11', calculate the difference between the transformer loss of each area in the first time period and the transformer loss generated after adding a mobile transformer according to the transformer loss formula; S312', selecting an initial station area according to the potential deployment area and deployment priority, and obtaining the distance cost of moving from the initial station area to all other stations; S313', constructing a new revenue model based on the transformer loss difference and the distance cost when moving from the initial transformer area to the remaining transformer areas, and calculating the revenue generated by moving the mobile transformer to each transformer area based on the new revenue model; Among them, the expression of the new profit model is: in mm =c1f 21 +c2f 22 In the formula, f mm represents the new benefit value, c1 represents the weight coefficient of transformer loss, c2 represents the cost weight coefficient of movement, and f 21 represents the sum of transformer loss gains after the move, f 22 represents the sum of movement costs.

9. The method for deploying a mobile hybrid distribution transformer in a distribution network according to claim 1, characterized in that: Updating the load factor matrix after adding the initial mobile transformer load factor includes the following steps: Obtain the initial deployment position of the mobile transformer, and calculate the proportion of the load of the original transformer in each substation after the initial mobile transformer is deployed at the position; update the load rate matrix based on the proportion of the load of the original transformer in each substation; The calculation formula for the load ratio is: The update formula of the load factor matrix is: In the formula, p represents the proportion of the original transformer load in each area, S N，s Indicates the rated capacity of the transformer in the transformer area No. s, S N，t Indicates the rated capacity of the mobile transformer in the s transformer area. It represents the load rate of the nth mobile transformer in the s station area at time t.

10. A mobile hybrid distribution transformer, deployed based on the method for deploying a mobile hybrid distribution transformer in a distribution network according to any one of claims 1 to 9, characterized in that: The mobile hybrid distribution transformer comprises a movable transformer carrier trolley (1), wheels (2) are arranged at the bottom corners of the movable transformer carrier trolley (1), a transformer body (3) is arranged inside the movable transformer carrier trolley (1), a plurality of insulators (4) are arranged on the top of the transformer body (3), a high-voltage outlet line (5) is arranged on the top of the insulator (4), a low-voltage outlet line (6) is arranged at one end of the transformer body (3), and a power electronic converter (7) connected to the transformer body (3) is arranged on one side.

Images