Method and device for analyzing carrying capacity of double-loop power distribution network and electronic equipment

Abstract

The application discloses a kind of double-chain ring power distribution network carrying capacity analysis method, device and electronic equipment, it is related to power distribution network technical field, wherein, method includes: obtaining the distributed photovoltaic power data, the distributed wind power data, the operating state of independent energy storage and the load of distribution network load corresponding to double-chain ring power distribution network;Distributed photovoltaic power data, distributed wind power data, the operating state of independent energy storage and load are respectively extracted features, and a variety of feature data are obtained;Multiple feature data are input into neural network model, and the carrying capacity of double-chain ring power distribution network is calculated based on neural network model.Such, under the premise of ensuring the safety and reliability of power distribution network, the access of distributed new energy, energy storage, load is optimized, and the multi-element interaction ability of source, network, load and storage is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution networks, and particularly relates to a carrying capacity analysis method and device for a double-loop power distribution network and an electronic device. BACKGROUND

[0002] In the existing double-loop power distribution network, due to the small scale of distributed new energy itself and the strong uncertainty, the analysis of the carrying capacity of the local power grid is often ignored when the distributed energy and independent energy storage are accessed, which leads to uneven distribution of power flow, and the light load and heavy load of the main transformer and line often occur. Therefore, how to accurately quantify the output prediction of the distributed power supply, and cooperate with the independent energy storage on the power grid side to suppress the output fluctuation of the new energy, increase the inertia response of the new energy unit, quickly respond to the load demand, and improve the carrying capacity of the local power grid have become problems that must be solved in the power system. SUMMARY

[0003] Therefore, the present application provides a carrying capacity analysis method and device for a double-loop power distribution network and an electronic device, which solves the problem of uneven distribution of power flow caused by the access of distributed energy and independent energy storage, and the light load and heavy load of the main transformer and line often occur.

[0004] In one aspect, the present application provides a carrying capacity analysis method for a double-loop power distribution network, which comprises the following steps.

[0005] Obtaining distributed photovoltaic power data, distributed wind power data, the operating state of independent energy storage, and the load of the power distribution network corresponding to the double-loop power distribution network;

[0006] Extracting features from the distributed photovoltaic power data, the distributed wind power data, the operating state of the independent energy storage, and the load to obtain a plurality of feature data;

[0007] Inputting the plurality of feature data into a neural network model, and calculating the carrying capacity of the double-loop power distribution network based on the neural network model; wherein, the calculation process of the carrying capacity considers the bus voltage deviation rate, line power loss, system frequency deviation rate, and load rate of the double-loop power distribution network.

[0008] In one aspect, the present application provides a carrying capacity analysis device for a double-loop power distribution network, which comprises the following steps.

[0009] The obtaining module is configured to obtain distributed photovoltaic power data, distributed wind power data, the operating state of independent energy storage, and the load of the power distribution network corresponding to the double-loop power distribution network;

[0010] The feature extraction module is configured to extract features from the distributed photovoltaic power data, the distributed wind power data, the operating state of the independent energy storage, and the load quantity respectively to obtain a plurality of feature data.

[0011] The calculation module is configured to input the plurality of feature data into the neural network model and calculate the carrying capacity of the double-loop power distribution network based on the neural network model, wherein the calculation process of the carrying capacity considers the bus voltage deviation rate, the line power loss, the system frequency deviation rate, and the load rate of the double-loop power distribution network.

[0012] In a possible embodiment, the double-loop power distribution network comprises a first transformer substation bus, a second transformer substation bus, and N switch stations, where N is an integer greater than or equal to 1; each switch station comprises a first switch station bus and a second switch station bus, and the first switch station bus and the second switch station bus are connected through a tie switch; the first transformer substation bus, the N first switch station buses, and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; and the first transformer substation bus, the N second switch station buses, and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; the distributed photovoltaic and the independent energy storage are connected to the first switch station bus through the tie switch, and the distributed wind power and the distribution network load are connected to the second switch station bus through the tie switch.

[0013] In a possible embodiment, the first transformer substation bus comprises a first bus section and a second bus section, and the second transformer substation bus comprises a third bus section and a fourth bus section; wherein the first bus section and the second bus section, and the third bus section and the fourth bus section are connected based on tie switches respectively; the first bus section, the N first switch station buses, and the third bus section are connected in a chain shape, and each interface is provided with a tie switch; and the second bus section, the N second switch station buses, and the fourth bus section are connected in a chain shape, and each interface is provided with a tie switch.

[0014] In a possible embodiment, the calculation module is configured to: after multiplying the feature vectors corresponding to the plurality of feature data by a first layer weight matrix of the neural network model and adding a first bias vector, obtain a first layer calculation result based on an activation function calculation; after multiplying the first layer calculation result by a second layer weight matrix of the neural network model and adding a second bias vector, obtain a second layer calculation result based on an activation function calculation; and after multiplying the second layer calculation result by a third layer weight matrix of the neural network model and adding a third bias vector, obtain the carrying capacity of the double-loop power distribution network based on an activation function calculation.

[0015] In a possible embodiment, a model formula of the neural network model is as follows:

[0016] C y= σ (W3·σ (W2·σ (W1·F+b1)+b2)+b3) ;

[0017] wherein, C y is a bearing capacity predicted by the neural network model, σ is an activation function, F is a feature vector corresponding to the plurality of feature data, W1, W2 and W3 are respectively a first layer weight matrix, a second layer weight matrix and a third layer weight matrix of the neural network model, and b1, b2 and b3 are respectively a first bias vector, a second bias vector and a third bias vector of the neural network model.

[0018] In a possible embodiment, the apparatus further includes:

[0019] a training module configured to train a preset network model based on a preset loss function to obtain the neural network model, wherein the preset loss function is:

[0020]

[0021] wherein, C y,i is a bearing capacity predicted by the neural network model for an i-th training sample in n training samples, n is an integer greater than or equal to 1, C actual,i is an actual bearing capacity corresponding to the i-th training sample, and a calculation process of the actual bearing capacity considers bus voltage deviation rate, line power loss, system frequency deviation rate and load rate.

[0022] In a possible embodiment, a calculation formula of the actual bearing capacity is:

[0023]

[0024] wherein, V d is a bus voltage deviation rate, V dmax is a maximum allowed value of the bus voltage deviation rate; P loss is a power loss of the line, P rated is a rated power of the power distribution network system, P lmax is a maximum allowed value of a ratio of the line power loss to the rated power of the power distribution network system; f d is a frequency deviation rate of the power distribution network system, f dmax is a maximum allowed value of the frequency deviation rate of the power distribution network system; L f is a load rate, L fmax is a maximum allowed value of the load rate.

[0025] In one aspect, an electronic device is provided, which includes a processor and a memory, wherein the memory stores program code which, when executed by the processor, causes the processor to perform any of the methods for analyzing a bearing capacity of a double-loop power distribution network.

[0026] In an aspect, the present application provides a computer readable storage medium comprising program code for causing an electronic device to perform any of the above-mentioned methods for analyzing the carrying capacity of a double-loop power distribution network when the storage medium is run on the electronic device.

[0027] The present application has the following advantages:

[0028] The embodiments of the present application provide a method and device for analyzing the carrying capacity of a double-loop power distribution network and an electronic device. Due to the inherent characteristics of distributed energy, independent energy storage and regional load, different characteristic curves are obtained in different time periods of each year, each month and each day. By statistically analyzing the characteristic data of distributed photovoltaic, distributed wind power, independent energy storage and user load of the double-loop power distribution network, the optimal solution of multi-element interaction carrying capacity is obtained by iterative calculation based on the characteristic data and a neural network model, so that the access of distributed new energy, energy storage and load is optimized under the premise of ensuring the safety and reliability of the power distribution network, the multi-element interaction capability of source, network, load and storage is improved, the new energy consumption capacity, voltage qualification rate and power grid loss and other power grid technical indexes of the regional power distribution network are optimized to the greatest extent, and the problems of low carrying capacity and poor multi-element interaction capability of the traditional power distribution network are solved.

[0029] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be learned from the practice of the present application. The purpose and other advantages of the present application can be achieved and obtained by the structure specifically pointed out in the written description, claims and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings needed to be used in the embodiment or related art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to the provided drawings without creating any creative labor.

[0031] Figure 1 The step flow chart of the method for analyzing the carrying capacity of a double-loop power distribution network in the embodiments of the present application;

[0032] Figure 2 The structure example diagram of a double-loop power distribution network in the embodiments of the present application;

[0033] Figure 3 The structure schematic diagram of the carrying capacity analysis device of a double-loop power distribution network in the embodiments of the present application;

[0034] Figure 4 The hardware composition structure schematic diagram of an electronic device in the embodiments of the present application. DETAILED DESCRIPTION

[0035] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. The embodiments in the present application and the features in the embodiments can be combined with each other in a non-conflicting manner. Moreover, although a logical sequence is shown in the flowchart, in some cases, the steps shown or described can be performed in an order different from the order shown.

[0036] The terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0037] The design idea of the embodiments of the present application will be briefly introduced as follows:

[0038] In the existing double-loop distribution network, due to the small installed capacity of the distributed new energy and the strong uncertainty, the analysis of the carrying capacity of the local power grid is often ignored for the access of the distributed energy and independent energy storage, which leads to uneven distribution of power flow, and the light load and heavy load of the main transformer and line often occur. Therefore, how to accurately quantify the output prediction of the distributed power supply, and cooperate with the independent energy storage on the power grid side to suppress the output fluctuation of the new energy, increase the inertia response of the new energy unit, quickly respond to the load demand, and improve the carrying capacity of the local power grid have become problems that must be solved in the power system.

[0039] In view of this, embodiments of this application provide a method, apparatus, and electronic equipment for carrying capacity analysis of a dual-chain ring distribution network. Since distributed energy resources, independent energy storage, and regional loads have inherent characteristics, they exhibit different characteristic curves at different times of the year, month, and day. By statistically analyzing the characteristic data of distributed photovoltaic, distributed wind power, independent energy storage, and user loads in a dual-chain ring distribution network area, and using a neural network model for iterative calculation based on the characteristic data, the optimal solution for the multi-element interactive carrying capacity is obtained. This achieves the optimization of the access of distributed new energy, energy storage, and loads while ensuring the safety and reliability of the distribution network, improving the multi-element interactive capability of sources, grid, load, and storage, and maximizing the optimization of the regional distribution network's new energy absorption capacity, voltage qualification rate, grid losses, and other grid technical indicators. This solves the problems of low carrying capacity and poor multi-element interactive capability in traditional distribution networks.

[0040] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0041] like Figure 1 The diagram shown is a flowchart of the carrying capacity analysis method for a double-chain distribution network provided in this application embodiment, including the following steps:

[0042] S101, obtain the distributed photovoltaic power data, distributed wind power data, independent energy storage operation status and distribution network load corresponding to the dual-chain ring distribution network;

[0043] The double-chain distribution network includes a first substation busbar, a second substation busbar, and N switching stations, where N is an integer greater than or equal to 1. Each switching station includes a first switching station busbar and a second switching station busbar, connected by tie switches. The first substation busbar, the N first switching station buses, and the second substation busbar are linked in a chain, with each interface equipped with a tie switch. Furthermore, the first substation busbar, the N second switching station buses, and the second substation busbar are linked in a chain, with each interface equipped with a tie switch. Distributed photovoltaic power and independent energy storage are connected to the first switching station busbar via tie switches, while distributed wind power and distribution network loads are connected to the second switching station busbar via tie switches.

[0044] Optionally, the first substation bus includes a first bus section and a second bus section, and the second substation bus includes a third bus section and a fourth bus section; wherein the first bus section and the second bus section, and the third bus section and the fourth bus section are connected based on the tie switches respectively; then, the first bus section, the N first switch station buses, and the third bus section are connected in a chain shape, and each interface is provided with a tie switch; and the second bus section, the N second switch station buses, and the fourth bus section are connected in a chain shape, and each interface is provided with a tie switch.

[0045] For example, referring to Figure 2 , a structure example diagram of a double-loop power distribution network. In Figure 2 , it includes A substation 20kV bus, B substation 20kV bus, and 20kV switch station 1, 20kV substation 2, and 20kV substation 3. Among them, the A substation 20kV bus and the B substation 20kV bus are respectively segmented, and tie switches are arranged between the segmented buses; the 20kV switch station 1 is connected to the distributed photovoltaic 1, the independent energy storage 1, the distributed wind power 1, and the distribution network load 1; the 20kV switch station 2 is connected to the distributed photovoltaic 2, the independent energy storage 2, the distributed wind power 2, and the distribution network load 2; the 20kV switch station 3 is connected to the distributed photovoltaic 3, the independent energy storage 3, the distributed wind power 3, and the distribution network load 3. Above, tie switches are arranged at the connection points of each switch station, which can play a protective and isolating role.

[0046] Further, the operation data of the double-loop power distribution network is obtained, including distributed photovoltaic power data, distributed wind power data, independent energy storage operation state, and load of distribution network. Among them, since the distributed photovoltaic, the distributed wind power, the independent energy storage, and the distribution network load have their own inherent characteristics, they have different characteristic curves in different time periods of each year, each month, and each day. Therefore, after obtaining the operation data of the double-loop power distribution network, according to the characteristic curve of the operation data, the collaborative strategy between the distributed photovoltaic, the distributed wind power, the independent energy storage, and the distribution network load can be analyzed, such as wind-solar complementary strategy and multi-element interactive carrying capacity analysis. Hereinafter, the multi-element interactive carrying capacity analysis is taken as an example for description.

[0047] S102, feature extraction is performed on the distributed photovoltaic power data, the distributed wind power data, the independent energy storage operation state, and the load respectively, to obtain a plurality of feature data;

[0048] In the embodiments of the present application, the distributed photovoltaic power data refers to the output curve of the distributed photovoltaic power over time, and the statistical time length can include years, months, days, hours, etc.; the distributed wind power data refers to the output curve of the distributed wind power over time, and the statistical time length can include years, months, days, hours, etc.; the operating state of the independent energy storage refers to the charging and discharging state of the independent energy storage over time, and the statistical time length can include years, months, days, hours, etc.; and the load amount refers to the load change curve over time, and the statistical time length can include years, months, days, hours, etc.

[0049] Further, feature extraction is performed on the distributed photovoltaic power data, the distributed wind power data, the operating state of the independent energy storage, and the load amount, respectively, including:

[0050] Based on the spatio-temporal correlation feature and the Bi-directional Long Short-Term Memory (B-LSTM) model, feature extraction is performed on the distributed photovoltaic power data to obtain a distributed photovoltaic power feature data curve. The B-LSTM model is Bayesianized by adding a Dropout layer to enhance the generalization ability of the model.

[0051] Based on the combination model of Variational Mode Decomposition (VMD) and Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), feature extraction is performed on the distributed wind power data to obtain a distributed wind power feature data curve. The VMD is used for decomposing the wind power sequence, the CNN is used for feature extraction, and the LSTM is used for time series prediction.

[0052] Based on the Adaptive Neuro-Fuzzy Inference System (ANFIS) model, feature extraction is performed on the operating state of the independent energy storage to obtain an independent energy storage charging and discharging feature data curve.

[0053] Based on the model of Variational Mode Decomposition (VMD) and Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), an attention mechanism is introduced to perform feature extraction on the distribution network load data to obtain a load feature data curve.

[0054] In S103, a plurality of feature data is input into a neural network model, and the carrying capacity of the double-loop distribution network is calculated based on the neural network model.

[0055] In the embodiment of the present application, the neural network model is a three-layer neural network, each layer of the neural network has a corresponding weight matrix and bias vector, and the carrying capacity of the double-loop distribution network is calculated based on the neural network model, comprising:

[0056] After multiplying the feature vectors corresponding to the plurality of feature data and the first layer weight matrix of the neural network model by the first bias vector, the first layer calculation result is obtained based on the activation function calculation;

[0057] After multiplying the first layer calculation result and the second layer weight matrix of the neural network model by the second bias vector, the second layer calculation result is obtained based on the activation function calculation;

[0058] After multiplying the second layer calculation result and the third layer weight matrix of the neural network model by the third bias vector, the carrying capacity of the double-loop distribution network is obtained based on the activation function calculation.

[0059] Optionally, the model formula of the neural network model is:

[0060] C y =σ(W3·σ(W2·σ(W1·F+b1)+b2)+b3) (1)

[0061] In formula (1), C y is the carrying capacity predicted by the neural network model, σ is the activation function, F is the feature vector corresponding to the plurality of feature data, W1, W2, and W3 are the first layer weight matrix, the second layer weight matrix, and the third layer weight matrix of the neural network model, respectively, and b1, b2, and b3 are the first bias vector, the second bias vector, and the third bias vector of the neural network model, respectively. Among them, the dimensions of W1, W2, W3 and b1, b2, b3 correspond to the input and output of the neural network level they are in; F=[F1, F2, F3, F4], F1 is the distributed photovoltaic output power, F2 is the distributed wind power output, F3 is the running state of independent energy storage, and F4 is the distribution network load.

[0062] Optionally, the activation function in formula (1) is a ReLU function or a sigmoid function, which is used to increase the nonlinearity of the network, so that the network can learn and perform more complex tasks.

[0063] It should be noted that before inputting the plurality of feature data into the neural network model, it also includes:

[0064] Based on the preset loss function, the preset network model is trained, and after the training is completed, the neural network model is obtained, and the preset loss function is:

[0065]

[0066] In formula (2), C y,i is the bearing capacity predicted by the neural network model for the i-th training sample in n training samples, n is an integer greater than or equal to 1, C actual,i is the actual bearing capacity corresponding to the i-th training sample, the calculation process of the bearing capacity considers the bus voltage deviation rate, line power loss, system frequency deviation rate and load rate of the double-loop power distribution network, and the actual bearing capacity can be calculated by means of power system simulation software.

[0067] Optionally, the calculation formula of the actual bearing capacity is:

[0068]

[0069] In formula (3), V d is the bus voltage deviation rate, V dmax is the maximum allowable value of the bus voltage deviation rate; P loss is the power loss of the line, P rated is the rated power of the distribution network system, P lmax is the maximum allowable value of the ratio of the line power loss to the rated power of the distribution network system; f d is the frequency deviation rate of the distribution network system, f dmax is the maximum allowable value of the frequency deviation rate of the distribution network system; L f is the load rate, L fmax is the maximum allowable value of the load rate, wherein:

[0070]

[0071] P loss = I 2 × R (5)

[0072]

[0073] In formula (4), V actual is the actual voltage, V e is the rated voltage.

[0074] In formula (5), I is the line current, and R is the equivalent resistance of the line.

[0075] In formula (6), P actual is the actual output power of the distribution network system.

[0076] Since the power grid frequency will also be disturbed when the distributed photovoltaic, distributed wind power or the sudden access of the distribution network load, if the accessed load is too large, or the distributed photovoltaic, distributed wind power suddenly increases the output, it will affect the power grid frequency, thereby causing the power grid frequency to deviate, if the power grid frequency fluctuates too much, there will be a risk of power grid splitting, therefore, the above calculation process of the actual carrying capacity also considers the system frequency characteristics.

[0077] Based on the above formulas (2)-(7), the training process of the preset network model can be constrained to make the model converge, and the trained neural network model is obtained, in the training process, the calculation of the actual carrying capacity considers the bus voltage deviation rate of the double-loop distribution network, line power loss, system frequency deviation rate and load rate, so that the prediction result of the final neural network model also considers the bus voltage deviation rate, line power loss, system frequency deviation rate and load rate, thereby making the calculation result of the carrying capacity ensure the safe operation of the distribution network system.

[0078] In a possible embodiment, after obtaining the carrying capacity of the double-loop distribution network through the trained neural network model, the carrying capacity is further corrected, including:

[0079] The carrying capacity calculation result is imported into an Electrical Transient Analysis Program (ETAP) model, and simulation verification is performed through the ETAP model, if the verification result is passed, the result is directly output, if the verification result is not passed, the neural network model parameters are adjusted, and iterative calculation is continued until the ETAP model is verified.

[0080] The ETAP model is a power system simulation model, the simulation parameters of which are all taken from the actual operation data of the above double-loop distribution network, so that the calculation result is reliable.

[0081] After determining the carrying capacity of the double-loop distribution network, based on the carrying capacity, the collaborative strategy adjustment between the distributed photovoltaic, distributed wind power, independent energy storage and distribution network load in the double-loop distribution network can be performed. Further, it is helpful to achieve balanced and efficient use of electricity under the premise of distribution safety, avoid energy waste, and achieve flexible balance between power generation, power consumption and energy storage.

[0082] Based on the above double-loop power distribution network carrying capacity analysis method, due to the inherent characteristics of distributed energy, independent energy storage and district load, there are different characteristic curves in different time periods of each year, each month and each day. By statistically obtaining the characteristic data of the distributed photovoltaic, distributed wind power, independent energy storage and user load of the double-loop power distribution network district, the optimal solution of the multi-element interaction carrying capacity is obtained by iterative calculation based on the characteristic data using a neural network model, thereby realizing the optimization of the access of distributed new energy, energy storage and load under the premise of ensuring the safety and reliability of the power distribution network, improving the multi-element interaction capability of the source, network, load and storage, and optimizing the new energy consumption capacity, voltage qualification rate and power grid loss and other power grid technical indicators of the district power distribution network to the greatest extent, and solving the problems of low carrying capacity and poor multi-element interaction capability of the traditional power distribution network.

[0083] Based on the same inventive concept, the embodiments of the present application also provide a double-loop power distribution network carrying capacity analysis device, as shown in Figure 3 The device comprises:

[0084] The acquisition module 301 is configured to acquire distributed photovoltaic power data, distributed wind power data, independent energy storage operation state and power grid load of the double-loop power distribution network.

[0085] The feature extraction module 302 is configured to perform feature extraction on the distributed photovoltaic power data, distributed wind power data, independent energy storage operation state and load, respectively, to obtain a plurality of characteristic data.

[0086] The calculation module 303 is configured to input the plurality of characteristic data into a neural network model and calculate the carrying capacity of the double-loop power distribution network based on the neural network model; wherein the calculation process of the carrying capacity considers the bus voltage deviation rate, line power loss, system frequency deviation rate and load rate of the double-loop power distribution network.

[0087] In one possible embodiment, the double-loop power distribution network comprises a first transformer substation bus, a second transformer substation bus and N switch stations, N being an integer greater than or equal to 1; the switch station comprises a first switch station bus and a second switch station bus, and the first switch station bus and the second switch station bus are connected through a tie switch; the first transformer substation bus, N first switch station buses and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; and the first transformer substation bus, N second switch station buses and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; the distributed photovoltaic and the independent energy storage are connected to the first switch station bus through the tie switch, and the distributed wind power and the power grid load are connected to the second switch station bus through the tie switch.

[0088] In a possible embodiment, the first substation bus includes a first bus section and a second bus section, and the second substation bus includes a third bus section and a fourth bus section; the first bus section and the second bus section are connected based on a tie switch, and the third bus section and the fourth bus section are connected based on a tie switch; the first bus section, the N first switch station buses, and the third bus section are connected in a chain shape, and each interface is provided with a tie switch; and the second bus section, the N second switch station buses, and the fourth bus section are connected in a chain shape, and each interface is provided with a tie switch.

[0089] In a possible embodiment, the computing module 303 is configured to: obtain a first layer calculation result by performing calculation based on an activation function after multiplying a feature vector corresponding to the plurality of feature data and a first layer weight matrix of the neural network model and adding a first bias vector; obtain a second layer calculation result by performing calculation based on an activation function after multiplying the first layer calculation result and a second layer weight matrix of the neural network model and adding a second bias vector; and obtain the carrying capacity of the double-loop power distribution network by performing calculation based on an activation function after multiplying the second layer calculation result and a third layer weight matrix of the neural network model and adding a third bias vector.

[0090] In a possible embodiment, a model formula of the neural network model is as follows:

[0091] C y = σ (W3·σ (W2·σ (W1·F+b1)+b2)+b3) ;

[0092] wherein, C y is the carrying capacity predicted by the neural network model, σ is an activation function, F is a feature vector corresponding to the plurality of feature data, W1, W2, and W3 are respectively a first layer weight matrix, a second layer weight matrix, and a third layer weight matrix of the neural network model, and b1, b2, and b3 are respectively a first bias vector, a second bias vector, and a third bias vector of the neural network model.

[0093] In a possible embodiment, the apparatus further includes:

[0094] a training module configured to train a preset network model based on a preset loss function to obtain the neural network model, the preset loss function being as follows:

[0095]

[0096] wherein, C y,i is the carrying capacity predicted by the neural network model for an i-th training sample in n training samples, n is an integer greater than or equal to 1, and C actual,iis the actual carrying capacity corresponding to the ith training sample, and the calculation process of the actual carrying capacity considers bus voltage deviation rate, line power loss, system frequency deviation rate and load rate.

[0097] In a possible embodiment, the calculation formula of the actual carrying capacity is as follows:

[0098]

[0099] wherein, V d is the bus voltage deviation rate, V dmax is the maximum allowable value of the bus voltage deviation rate; P loss is the power loss of the line, P rated is the rated power of the distribution network system, P lmax is the maximum allowable value of the ratio of the line power loss to the rated power of the distribution network system; f d is the frequency deviation rate of the distribution network system, f dmax is the maximum allowable value of the frequency deviation rate of the distribution network system; L f is the load rate, L fmax is the maximum allowable value of the load rate.

[0100] The technical effects of the carrying capacity analysis device of the double-loop distribution network are described in the method part, and will not be repeated here.

[0101] In some possible implementations, the carrying capacity analysis device of the double-loop distribution network according to the present application can at least include a processor and a memory. The memory stores program codes, and when the program codes are executed by the processor, the processor executes the steps in the carrying capacity analysis method of the double-loop distribution network according to various exemplary embodiments of the present application described in the present specification. For example, the processor can execute the steps shown in Figure 1 .

[0102] Based on the same inventive concept, the present application also provides an electronic device, which can realize the functions of the foregoing carrying capacity analysis device of the double-loop distribution network, and refer to Figure 4 , the electronic device comprises:

[0103] at least one processor 401 and a memory 402 connected with the at least one processor 401, and the specific connection medium between the processor 401 and the memory 402 is not limited in the present application, Figure 4 in which the connection between the processor 401 and the memory 402 through the bus 400 is taken as an example. The bus 400 is represented by a thick line in Figure 4 , and the connection modes between other components are only schematically illustrated and are not limited. The bus 400 can be divided into an address bus, a data bus, a control bus and the like, and for the convenience of representation, Figure 4Only one bus is shown for each bus interface for simplicity, but there can be a plurality of buses. Generally, the bus allows data to be passed between each element of the data processing system 400. The processor 401 can be implemented as one or more central processing units (CPUs), microprocessors, microcontrollers, digital signal processors, dedicated circuitry, or any combination thereof. The processor 401 can be a general purpose processor or a special purpose processor.

[0104] In the embodiments of the present application, the memory 402 stores instructions executable by the at least one processor 401, and the at least one processor 401 can execute the method of analyzing the carrying capacity of the double-loop power distribution network discussed above by executing the instructions stored in the memory 402. The processor 401 can implement the functions of the modules of the apparatus shown in the embodiments of the present application. Figure 4 The functions of the modules of the apparatus shown in the embodiments of the present application.

[0105] The processor 401 is the control center of the apparatus, and can connect each part of the entire control device through various interfaces and lines, and process data and perform various functions of the apparatus by running or executing the instructions stored in the memory 402 and calling the data stored in the memory 402, thereby monitoring the entire apparatus.

[0106] In a possible design, the processor 401 can include one or more processing units, and the processor 401 can integrate an application processor and a modem processor, where the application processor mainly processes operating systems, user interfaces, and application programs, and the modem processor mainly processes wireless communication. It can be understood that the modem processor can also not be integrated into the processor 401. In some embodiments, the processor 401 and the memory 402 can be implemented on the same chip, and in some embodiments, they can also be implemented on separate chips respectively.

[0107] The processor 401 can be a general purpose processor, such as a central processing unit (CPU), a digital signal processor, an application specific integrated circuit, a field programmable gate array, or other programmable logic device, a discrete gate or transistor logic component, a discrete hardware component, and can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general purpose processor can be a microprocessor or any conventional processor. The steps of the method of analyzing the carrying capacity of the double-loop power distribution network disclosed in the embodiments of the present application can be directly embodied as execution by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0108] The memory 402, as a non-volatile computer readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules. The memory 402 can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. The memory 402 is any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but is not limited thereto. The memory 402 in the embodiments of the present application can also be a circuit or any other device capable of realizing a storage function, used for storing program instructions and / or data.

[0109] By designing and programming the processor 401, the code corresponding to the carrying capacity analysis method of the double-loop power distribution network introduced in the foregoing embodiments can be fixed into the chip, so that the chip can execute the steps of the carrying capacity analysis method of the double-loop power distribution network of the embodiments shown in the running time. Figure 1 How to design and program the processor 401 is a technology known to those skilled in the art, which will not be described here.

[0110] Based on the same inventive concept, the embodiments of the present application also provide a storage medium storing computer instructions, when the computer instructions run on a computer, the computer instructions make the computer execute the carrying capacity analysis method of the double-loop power distribution network discussed above.

[0111] In some possible implementations, various aspects of the carrying capacity analysis method of the double-loop power distribution network provided by the present application can also be implemented in the form of a program product, which includes program codes, when the program product runs on a device, the program codes are used to make the control device execute the steps in the carrying capacity analysis method of the double-loop power distribution network according to various exemplary embodiments of the present application described above in the specification.

[0112] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0113] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0114] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0116] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for carrying capacity analysis of a double-loop power distribution network, characterized by, The method comprises: obtaining distributed photovoltaic power data, distributed wind power data, operating state of independent energy storage and load of the distribution network corresponding to the double-loop distribution network; extracting features of the distributed photovoltaic power data, the distributed wind power data, the operating state of the independent energy storage and the load to obtain multiple feature data; The preset network model is trained based on a preset loss function to obtain a neural network model, and the preset loss function is: ; wherein, Cy,i is a bearing capacity predicted by the neural network model for an i-th training sample in n training samples, n is an integer greater than or equal to 1, Cactual,i is an actual bearing capacity corresponding to the i-th training sample, a calculation process of the actual bearing capacity considers bus voltage deviation rate, line power loss, system frequency deviation rate and load rate, and a calculation formula of the actual bearing capacity is: ; wherein, V d is the bus voltage deviation rate, V dmax is a maximum allowable value of the bus voltage deviation rate; P loss is the line power loss, P rated is a rated power of a power distribution network system, P lmax is a maximum allowable value of a ratio of the line power loss to the rated power of the power distribution network system; f d is a power distribution network system frequency deviation rate, f dmax is a maximum allowable value of the power distribution network system frequency deviation rate; L f is a load rate, L fmax is a maximum allowable value of the load rate; inputting the multiple feature data into the neural network model and calculating the carrying capacity of the double-loop distribution network based on the neural network model.

2. The method of claim 1, wherein, The double-loop distribution network comprises a first transformer substation bus, a second transformer substation bus and N switch stations, N being an integer greater than or equal to 1; the switch station comprises a first switch station bus and a second switch station bus, and the first switch station bus and the second switch station bus are connected through a tie switch; the first transformer substation bus, the N first switch station buses and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; and the first transformer substation bus, the N second switch station buses and the second transformer substation bus are connected in a chain shape, and each interface is provided with a tie switch; the distributed photovoltaic and the independent energy storage are connected to the first switch station bus through the tie switch, and the distributed wind power and the distribution network load are connected to the second switch station bus through the tie switch.

3. The method of claim 2, wherein, The first transformer substation bus comprises a first bus section and a second bus section, and the second transformer substation bus comprises a third bus section and a fourth bus section; wherein the first bus section and the second bus section, and the third bus section and the fourth bus section are connected based on the tie switch respectively; the first bus section, the N first switch station buses and the third bus section are connected in a chain shape, and each interface is provided with a tie switch; and the second bus section, the N second switch station buses and the fourth bus section are connected in a chain shape, and each interface is provided with a tie switch.

4. The method of claim 1, wherein, The calculation of the carrying capacity of the double-loop distribution network based on the neural network model comprises: after multiplying the feature vectors corresponding to the multiple feature data by the first layer weight matrix of the neural network model and adding the first bias vector, a first layer calculation result is obtained based on an activation function; after multiplying the first layer calculation result by the second layer weight matrix of the neural network model and adding the second bias vector, a second layer calculation result is obtained based on the activation function; after multiplying the second layer calculation result by the third layer weight matrix of the neural network model and adding the third bias vector, the carrying capacity of the double-loop distribution network is obtained based on the activation function.

5. The method of claim 4, wherein, A model formula of the neural network model is: C y = The device comprises: ( W 3∙ an acquisition module configured to acquire distributed photovoltaic power data, distributed wind power data, operating state of independent energy storage and load of the distribution network corresponding to the double-loop distribution network; ( W 2∙ a feature extraction module configured to extract features of the distributed photovoltaic power data, the distributed wind power data, the operating state of the independent energy storage and the load to obtain multiple feature data; ( W 1∙ F + b 1)+ b 2)+ b 3); wherein, C y a bearing capacity predicted by the neural network model, ​ an activation function, F a feature vector corresponding to the plurality of feature data, W 1、 W 2、 W 3 are respectively a first layer weight matrix, a second layer weight matrix, and a third layer weight matrix of the neural network model, b 1、 b 2、 b 3 are respectively a first bias vector, a second bias vector, and a third bias vector of the neural network model.

6. A device for analyzing the carrying capacity of a double-loop power distribution network, characterized by ​ ​ ​ A calculation module is configured to train a preset network model based on a preset loss function to obtain a neural network model, wherein the preset loss function is: ; wherein, Cy,i is a bearing capacity predicted by the neural network model for an i-th training sample in n training samples, n is an integer greater than or equal to 1, Cactual,i is an actual bearing capacity corresponding to the i-th training sample, a calculation process of the actual bearing capacity considers bus voltage deviation rate, line power loss, system frequency deviation rate and load rate, and a calculation formula of the actual bearing capacity is: ; wherein, V d is a bus voltage deviation rate, V dmax is a maximum allowable value of the bus voltage deviation rate; P loss is a line power loss, P rated is a power distribution network system rated power, P lmax is a maximum allowable value of a ratio of the line power loss to the power distribution network system rated power; f d is a power distribution network system frequency deviation rate, f dmax is a maximum allowable value of the power distribution network system frequency deviation rate; L f is a load rate, L fmax is a maximum allowable value of the load rate; and the multiple feature data are input into the neural network model, and a bearing capacity of the double-loop power distribution network is calculated based on the neural network model.

7. An electronic device, comprising: The application discloses a computer readable storage medium, which comprises a processor and a memory, wherein the memory stores program codes, and when the program codes are executed by the processor, the processor executes the method in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The application discloses a computer readable storage medium, which comprises program codes, and when the storage medium is executed on an electronic device, the program codes are used for making the electronic device execute the method in any one of claims 1-5.

Images