Low-voltage active power distribution network user phase sequence identification and control method based on carrier communication

Abstract

The application provides a low-voltage active power distribution network user phase sequence identification and control method based on carrier communication, and relates to the technical field of low-voltage power distribution network power quality treatment. First, a special carrier communication network is arranged in a low-voltage power distribution area to be identified, and operation parameter data of the power distribution area are synchronously collected based on the network; after the data are pretreated, a voltage-power phase sequence mapping model is constructed; the model is trained by using the pretreated data, and a phase sequence mapping matrix is extracted from solidified parameters of the trained model; based on the matrix, the phase sequence categories to which all users belong are determined, and three-phase unbalance degrees are calculated; when the unbalance degrees exceed a preset threshold, a load adjustment scheme is generated, and the phase sequence categories to which the users belong are remotely adjusted by using the special carrier communication network. In the case that no additional prediction calculation is needed, the identification accuracy is improved, the efficiency and accuracy of user phase sequence identification are considered, and the control precision of user phase sequence control is improved.

Description

Technical Field

[0001] This invention relates to the technical field of power quality management in low-voltage distribution networks, and more specifically, to a method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication. Background Technology

[0002] With the increasing penetration of distributed photovoltaic (PV) power in low-voltage distribution networks, the complexity of the network topology and the uncertainty of power flow characteristics have significantly increased. This complexity and uncertainty, particularly the three-phase power imbalance caused by PV integration, pose challenges to the safe, high-quality, and economical operation of distribution substations. To effectively address these challenges, accurately identifying the phase sequence of each user within a low-voltage substation has become a crucial foundational task. Based on accurate phase sequence information, by systematically changing the connection phases of users or power sources, the three-phase load can be further adjusted to achieve load distribution, reduce three-phase current imbalance, and improve power quality.

[0003] Currently, user phase sequence identification mainly relies on manual on-site inspection, correlation analysis based on voltage curves, or algorithmic inference based on smart meter data. These methods suffer from drawbacks such as low efficiency and accuracy. Furthermore, even when phase sequence is identified using these methods, the control methods that rely on manual experience for three-phase load adjustment suffer from slow response, low efficiency, and difficulty in real-time optimization. Therefore, there is an urgent need for a technical solution that can achieve high precision, automation, and a closed-loop system from phase sequence identification to load control adjustment. Summary of the Invention

[0004] To address the problem that existing technologies cannot achieve closed-loop management of user phase sequence identification and load adjustment control in low-voltage active distribution networks, resulting in poor power quality, this invention proposes a low-voltage active distribution network user phase sequence identification and control method based on carrier communication. This method balances the efficiency and accuracy of user phase sequence identification, improves load adjustment efficiency, and enhances the control precision for user phase sequence control.

[0005] To achieve the above-mentioned technical effects, the technical solution of the present invention is as follows:

[0006] In the first aspect, this application proposes a method for phase sequence identification and control of users in a low-voltage active distribution network based on carrier communication, comprising the following steps:

[0007] S1. Deploy a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collect the operating parameter data of the distribution transformer area based on the dedicated carrier communication network;

[0008] S2. Using the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output, construct a voltage-power phase sequence mapping model;

[0009] S3. Preprocess the operating parameter data of the distribution station area, and use the preprocessed operating parameter data of the distribution station area to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model.

[0010] S4. Based on the trained voltage-power phase sequence mapping model, extract the model fixed parameters, and based on the model fixed parameters, extract the phase sequence mapping matrix;

[0011] S5. Based on the phase sequence mapping matrix, determine the phase sequence category to which all users in the distribution area belong;

[0012] S6. Calculate the three-phase imbalance of the distribution area based on the phase sequence category of all users and the user power corresponding to each phase sequence;

[0013] S7. Determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If yes, generate a load adjustment scheme based on the three-phase imbalance of the distribution network. Based on the load adjustment scheme, remotely adjust the phase sequence category of the user using the dedicated carrier communication network. If no, end.

[0014] In this technical solution, a dedicated carrier communication network is first deployed within the low-voltage distribution transformer area to be identified. Operating parameter data of the distribution transformer area is synchronously collected through this network. After preprocessing the data, a voltage-power phase sequence mapping model is constructed, using the operating parameter data as input and the user voltage as output. The model is then trained using the preprocessed data, and the phase sequence mapping matrix is ​​extracted from the fixed parameters of the trained model. Based on this matrix, the phase sequence category of all users is determined, and the three-phase imbalance is calculated. When the imbalance exceeds a preset threshold, a load adjustment scheme is generated, and the phase sequence category of the user is remotely adjusted using the dedicated carrier communication network. This improves the identification accuracy without requiring additional predictive calculations, balancing the efficiency and accuracy of user phase sequence identification, and enhancing the control precision of user phase sequence control.

[0015] Preferably, the step of deploying a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collecting operating parameter data of the distribution transformer area based on the dedicated carrier communication network, includes:

[0016] Within the low-voltage distribution transformer area to be identified, power line carrier communication chips with data acquisition functions are deployed on the concentrators on the low-voltage side of the transformer and on the user's electricity meter side to construct a dedicated carrier communication network covering the distribution transformer area.

[0017] Keep the clocks of all power line carrier communication chips in a consistent state, and send data acquisition commands to all power line carrier communication chips synchronously to collect distribution area operating parameter data;

[0018] The operating parameter data of the distribution transformer substation includes: three-phase voltage on the low-voltage side of the substation substation, user power, and photovoltaic inverter power; the three-phase voltage on the low-voltage side of the substation substation includes phase A voltage. Phase B voltage and C-phase voltage User power includes user active power. and user reactive power Photovoltaic inverter power includes the active power of the photovoltaic inverter. and reactive power of photovoltaic inverters .

[0019] Preferably, the process of constructing the voltage-power phase sequence mapping model is as follows:

[0020] generate random matrix , Represents the number of users, for a random matrix Each column is processed to obtain the initial phase sequence mapping matrix;

[0021] Based on the initial phase sequence mapping matrix and the three-phase voltage on the low-voltage side of the distribution transformer, the contribution components of the three-phase voltage on the low-voltage side of the distribution transformer to the predicted user voltage are calculated, and denoted as the head-end contribution vector. The expression for evaluation satisfies:

[0022]

[0023] in, This indicates the three-phase voltage on the low-voltage side of the distribution transformer; Represents the initial phase sequence mapping matrix;

[0024] Based on the preset three-layer sensor parameters, the contribution components of user power and photovoltaic inverter power to the predicted user voltage are calculated and denoted as the power contribution vector. Satisfies the expression:

[0025]

[0026] in, These are the weight matrix parameters for the 1st, 2nd, and 3rd layers of the perceptron, respectively. These are the bias vector parameters for the first, second, and third layers of the perceptron, respectively. These are the activation functions for the 1st, 2nd, and 3rd layers of the perceptron, respectively. ;

[0027] Then the predicted user voltage of the distribution station area satisfy:

[0028] .

[0029] Preferably, the training voltage-power phase sequence mapping model includes:

[0030] S31. Using the preprocessed operating parameter data of the distribution substation as input to the voltage-power phase sequence mapping model, obtain the predicted user voltage output by the voltage-power phase sequence mapping model. ;

[0031] S32: Predicted User Voltage Based on Model Output and the actual user voltage collected Calculate the loss function value in the training voltage-power phase sequence mapping model; the expression for the loss function in the training voltage-power phase sequence mapping model is:

[0032]

[0033] in, Indicates the number of samples collected. Represents the sample sequence;

[0034] S33. Train the voltage-power phase sequence mapping model based on the Adam optimization algorithm. During the training process, update the parameters of the voltage-power phase sequence mapping model, including the phase sequence mapping matrix and all weight matrix parameters. and all bias vector parameters ;

[0035] S34. Determine if the loss function value is less than or equal to a preset threshold. If yes, complete the training of the voltage-power phase sequence mapping model, extract the final phase sequence mapping matrix from the trained voltage-power phase sequence mapping model. Each column of the final phase sequence mapping matrix corresponds to a user, and the three elements in each column represent the membership degree or probability of the user belonging to phases A, B, and C, respectively. Determine the phase of each user based on the final phase sequence mapping matrix. If not, return to S31.

[0036] Preferably, the calculation of the three-phase imbalance of the distribution substation based on the phase sequence category of all users and the user power corresponding to each phase sequence includes:

[0037] Calculate the average three-phase active power load based on the active power of all users and their phase sequence category. The expression is:

[0038]

[0039] in, This represents the sum of the active power of all users belonging to phase A. This represents the sum of the active power of all users belonging to phase B. This represents the sum of the active power of all users belonging to phase C;

[0040] Based on the phase sequence category of all users and the average value of the three-phase active power load, calculate the three-phase imbalance of the distribution network. The expression is:

[0041] .

[0042] Preferably, the load adjustment scheme is generated based on the three-phase imbalance of the distribution network, including:

[0043] S51. Based on the active power of all users and their phase sequence category, calculate the active power of phases A, B, and C respectively. , , The phase with the highest active power is designated as the phase to be removed, and the phase with the lowest active power is designated as the phase to be removed.

[0044] S52. From all users belonging to the removed phase, select users who meet the preset switching constraints to form a candidate set;

[0045] S53. Order , Indicates the user's active power order and executes S54;

[0046] S54. Sort the users in the candidate set according to their active power from largest to smallest. ;

[0047] S55. Based on the sorted order, select the users in the current candidate set. Switch to the shifted phase and calculate the new three-phase imbalance. ;

[0048] S56. Determine the new three-phase imbalance. If the new three-phase imbalance is less than the original three-phase imbalance, and if so, the new three-phase imbalance is used as the current three-phase imbalance, and S57 is executed; otherwise, the users in the current candidate set are selected. Restore to the shifted-out phase, let The value is increased by 1, and the process returns to S55; the original three-phase imbalance includes the preset three-phase imbalance value and the three-phase imbalance value under the previous user's active power sequence.

[0049] S57. Determine whether the current three-phase imbalance is less than the preset threshold. If yes, record this switching operation in the load adjustment scheme, integrate all switching operation records, and generate a load adjustment scheme; if not, then... The value is increased by 1, this switching operation is recorded in the load adjustment plan, and S58 is executed;

[0050] S58. Judgment Does it exceed If so, integrate all switching operation records to generate a load adjustment plan; otherwise, return to S55.

[0051] Preferably, a load adjustment scheme is generated based on the three-phase imbalance of the distribution network, and the phase sequence category of the user is remotely adjusted using the dedicated carrier communication network, including:

[0052] The generated load adjustment scheme is compiled into control commands, which are then sent to the commutation switch via the dedicated carrier communication network. The commutation switch receives and verifies the control commands before completing the user's commutation operation.

[0053] The results of the control command execution are fed back to the distribution master station through the dedicated carrier communication network to update the phase topology records of the distribution substation.

[0054] Secondly, this application also proposes a low-voltage active distribution network user phase sequence identification and control system based on carrier communication, the system comprising:

[0055] The distribution transformer substation operation parameter data acquisition unit is used to deploy a dedicated carrier communication network covering the distribution transformer substation within the low-voltage distribution transformer substation to be identified, and to synchronously acquire the distribution transformer substation operation parameter data based on the dedicated carrier communication network.

[0056] The voltage-power phase sequence mapping model construction unit is used to construct a voltage-power phase sequence mapping model by taking the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output.

[0057] The voltage-power phase sequence mapping model training unit is used to preprocess the operating parameter data of the distribution substation, and use the preprocessed operating parameter data of the distribution substation to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model.

[0058] The phase sequence mapping matrix acquisition unit is used to extract model-fixed parameters based on the trained voltage-power phase sequence mapping model, and extract the phase sequence mapping matrix based on the model-fixed parameters.

[0059] The user phase sequence category confirmation unit is used to determine the phase sequence category of all users in the distribution area based on the phase sequence mapping matrix.

[0060] The distribution area three-phase unbalance calculation unit is used to calculate the three-phase unbalance of the distribution area based on the phase sequence category of all users and the corresponding user power.

[0061] The user phase sequence control unit is used to determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If so, it generates a load adjustment scheme based on the three-phase imbalance of the distribution network and remotely adjusts the phase sequence category of the user using the dedicated carrier communication network. If not, it terminates the user phase sequence control.

[0062] Thirdly, this application also proposes a computer device, which includes a memory, a processor, and a computer program stored in the memory that can be run on the processor. The processor executes the computer program to realize a low-voltage active distribution network user phase sequence identification and control method based on carrier communication.

[0063] Fourthly, this application also proposes a computer storage medium storing a computer program, the computer program including program instructions, which, when executed by a computer, cause the computer to execute a low-voltage active distribution network user phase sequence identification and control method based on carrier communication.

[0064] Compared with the prior art, the beneficial effects of the present invention are:

[0065] This invention proposes a method for phase sequence identification and control of users in low-voltage active distribution networks based on carrier communication. First, a dedicated carrier communication network is deployed within the low-voltage distribution area to be identified, and operating parameter data of the distribution area is synchronously collected based on this network. After preprocessing the data, a voltage-power phase sequence mapping model is constructed, with the operating parameter data as input and the user voltage as output. The model is trained using the preprocessed data, and the phase sequence mapping matrix is ​​extracted from the fixed parameters of the trained model. Based on this matrix, the phase sequence category of all users is determined, and the three-phase imbalance is calculated. When the imbalance exceeds a preset threshold, a load adjustment scheme is generated, and the phase sequence category of the user is remotely adjusted using the dedicated carrier communication network. This method improves the identification accuracy without requiring additional predictive calculations, balancing the efficiency and accuracy of user phase sequence identification, and improving the control precision of user phase sequence control. Attached Figure Description

[0066] Figure 1 This is a flowchart illustrating the low-voltage active distribution network user phase sequence identification and control method based on carrier communication proposed in Embodiment 1 of the present invention.

[0067] Figure 2 A flowchart illustrating the training voltage-power phase sequence mapping model proposed in Embodiment 2 of the present invention;

[0068] Figure 3 This is a schematic diagram illustrating the process of generating a load adjustment scheme based on the three-phase imbalance of the power distribution network proposed in Embodiment 2 of the present invention.

[0069] Figure 4This is a schematic diagram of the low-voltage distribution network simulation system proposed in Embodiment 3 of the present invention;

[0070] Figure 5 A schematic diagram illustrating the user active power curve proposed in Embodiment 3 of the present invention;

[0071] Figure 6 A schematic diagram illustrating the photovoltaic active power curve proposed in Embodiment 3 of the present invention;

[0072] Figure 7 This represents a heatmap of the phase sequence mapping matrix after training, as proposed in Embodiment 3 of the present invention.

[0073] Figure 8 This is a schematic diagram showing the three-phase unbalance curves of the low-voltage distribution network simulation system proposed in Embodiment 3 of the present invention at various data acquisition times.

[0074] Figure 9 This is a schematic diagram of the structure of a low-voltage active distribution network user phase sequence identification and control system based on carrier communication proposed in Embodiment 4 of the present invention;

[0075] Figure 10 This is a schematic diagram of the structure of the computer device proposed in Embodiment 5 of the present invention. Detailed Implementation

[0076] The accompanying drawings are for illustrative purposes only and should not be construed as limiting the scope of this patent.

[0077] To better illustrate this embodiment, some parts of the accompanying drawings may be omitted, enlarged, or reduced, and do not represent the actual dimensions;

[0078] It is understandable to those skilled in the art that some well-known details may be omitted from the accompanying drawings.

[0079] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0080] The positional relationships depicted in the accompanying drawings are for illustrative purposes only and should not be construed as limiting this patent.

[0081] Example 1

[0082] This embodiment proposes a low-voltage active distribution network user phase sequence identification and control method based on carrier communication. A flowchart illustrating this method can be found here. Figure 1 This includes the following steps:

[0083] S1. Deploy a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collect the operating parameter data of the distribution transformer area based on the dedicated carrier communication network;

[0084] S2. Using the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output, construct a voltage-power phase sequence mapping model;

[0085] S3. Preprocess the operating parameter data of the distribution station area, and use the preprocessed operating parameter data of the distribution station area to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model.

[0086] S4. Based on the trained voltage-power phase sequence mapping model, extract the model fixed parameters, and based on the model fixed parameters, extract the phase sequence mapping matrix;

[0087] S5. Based on the phase sequence mapping matrix, determine the phase sequence category to which all users in the distribution area belong;

[0088] S6. Calculate the three-phase imbalance of the distribution area based on the phase sequence category of all users and the user power corresponding to each phase sequence;

[0089] S7. Determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If yes, generate a load adjustment scheme based on the three-phase imbalance of the distribution network. Based on the load adjustment scheme, remotely adjust the phase sequence category of the user using the dedicated carrier communication network. If no, end.

[0090] Specifically, when the three-phase imbalance of the distribution transformer area does not exceed a preset threshold, the current phase sequence of the user is maintained, and the real-time operating parameter data of the distribution transformer area is collected through the dedicated carrier communication network. Based on the user's phase sequence category determined in step S5 and the real-time collected user power data, step S6 is executed to continuously monitor the three-phase imbalance of the distribution transformer area.

[0091] In this embodiment, a dedicated carrier communication network is first deployed within the low-voltage distribution transformer area to be identified. Operating parameter data of the distribution transformer area is synchronously collected based on this network. After preprocessing the data, a voltage-power phase sequence mapping model is constructed, using the operating parameter data as input and the user voltage as output. The model is trained using the preprocessed data, and the phase sequence mapping matrix is ​​extracted from the fixed parameters of the trained model. Based on this matrix, the phase sequence category of all users is determined, and the three-phase imbalance is calculated. When the imbalance exceeds a preset threshold, a load adjustment scheme is generated, and the phase sequence category of the user is remotely adjusted using the dedicated carrier communication network. This improves the identification accuracy without requiring additional predictive calculations, balancing the efficiency and accuracy of user phase sequence identification, and improving the control precision of user phase sequence control.

[0092] Example 2

[0093] In this embodiment, the step of deploying a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collecting operating parameter data of the distribution transformer area based on the dedicated carrier communication network, includes:

[0094] Within the low-voltage distribution transformer area to be identified, power line carrier communication chips with data acquisition functions are deployed on the concentrators on the low-voltage side of the transformer and on the user's electricity meter side to construct a dedicated carrier communication network covering the distribution transformer area.

[0095] Keep the clocks of all power line carrier communication chips in a consistent state, and send data acquisition commands to all power line carrier communication chips synchronously to collect distribution area operating parameter data;

[0096] The operating parameter data of the distribution transformer substation includes: three-phase voltage on the low-voltage side of the substation substation, user power, and photovoltaic inverter power; the three-phase voltage on the low-voltage side of the substation substation includes phase A voltage. Phase B voltage and C-phase voltage User power includes user active power. and user reactive power Photovoltaic inverter power includes the active power of the photovoltaic inverter. and reactive power of photovoltaic inverters .

[0097] Specifically, the control of the clocks of all power line carrier communication chips includes controlling all chips to perform synchronous acquisition through a network time synchronization and command broadcasting mechanism.

[0098] In this embodiment, the process of constructing the voltage-power phase sequence mapping model is as follows:

[0099] generate random matrix , Represents the number of users, for a random matrix Each column is processed to obtain the initial phase sequence mapping matrix; the row number 3 of the random matrix R represents the number of phase sequences corresponding to phases A, B, and C. In this embodiment, the random matrix... When processing each column of the random matrix, Perform the softmax function operation on each column.

[0100] Based on the initial phase sequence mapping matrix and the three-phase voltage on the low-voltage side of the distribution transformer, the contribution components of the three-phase voltage on the low-voltage side of the distribution transformer to the predicted user voltage are calculated, and denoted as the head-end contribution vector. The expression for evaluation satisfies:

[0101]

[0102] in, This indicates the three-phase voltage on the low-voltage side of the distribution transformer; Represents the initial phase sequence mapping matrix; , , Representing users respectively The probability of belonging to phase A, phase B, or phase C;

[0103] Based on the preset three-layer sensor parameters, the contribution components of user power and photovoltaic inverter power to the predicted user voltage are calculated and denoted as the power contribution vector. Satisfies the expression:

[0104]

[0105] in, These are the weight matrix parameters for the 1st, 2nd, and 3rd layers of the perceptron, respectively. These are the bias vector parameters for the first, second, and third layers of the perceptron, respectively. These are the activation functions for the 1st, 2nd, and 3rd layers of the perceptron, respectively. ,Will The power contribution vector is obtained by inputting the multilayer perceptron. ;

[0106] Then the predicted user voltage of the distribution station area satisfy:

[0107]

[0108] in,

[0109] Specifically, the activation function is the ReLU function, and its expression is:

[0110]

[0111] In this embodiment, the flowchart illustrating the training of the voltage-power phase sequence mapping model is shown below. Figure 2 ,include:

[0112] S31. Using the preprocessed operating parameter data of the distribution substation as input to the voltage-power phase sequence mapping model, obtain the predicted user voltage output by the voltage-power phase sequence mapping model. ;

[0113] S32: Predicted User Voltage Based on Model Output and the actual user voltage collected Calculate the loss function value in the training voltage-power phase sequence mapping model; the expression for the loss function in the training voltage-power phase sequence mapping model is:

[0114]

[0115] in, Indicates the number of samples collected. Represents the sample sequence;

[0116] S33. Train the voltage-power phase sequence mapping model based on the Adam optimization algorithm. During the training process, update the parameters of the voltage-power phase sequence mapping model, including the phase sequence mapping matrix and all weight matrix parameters. and all bias vector parameters ;

[0117] S34. Determine whether the loss function value is less than or equal to a preset threshold. If yes, complete the training of the voltage-power phase sequence mapping model. Extract the final phase sequence mapping matrix from the trained voltage-power phase sequence mapping model. Each column of the final phase sequence mapping matrix corresponds to a user, and the three elements in each column represent the membership degree or probability of the user belonging to phases A, B, and C, respectively. Determine the phase of each user based on the final phase sequence mapping matrix. In this embodiment, by selecting the phase corresponding to the element with the largest value in each column, the phase sequence affiliation of each user can be directly and deterministically identified. If not, return to S31.

[0118] Specifically, the preprocessing includes normalizing the operating parameter data of the distribution radio station area. The preprocessing process for the operating parameter data of the distribution radio station area is as follows:

[0119] Input data includes the three-phase voltage on the low-voltage side of the distribution transformer in the area. , , Active power of each electricity user With reactive power and the active power of photovoltaic inverters With reactive power Because voltage and power data have different dimensions and significant differences in their numerical ranges, normalization is required. The normalization expression is as follows:

[0120]

[0121] The same operation is performed on the operating parameter data of each distribution station area, where, Sample values ​​of operating parameter data for each distribution radio area. and These are the minimum and maximum values ​​of all samples in the data for this operating parameter, respectively. Normalized sample values

[0122] Specifically, the training of the voltage-power phase sequence mapping model based on the Adam optimization algorithm includes:

[0123] Calculate the parameters of each voltage-power phase sequence mapping model. First moment estimation and second-order moment estimation The voltage-power phase sequence mapping model parameters Including weight matrix parameters Bias vector parameters and the initial phase sequence mapping matrix Each element in; the calculation of the first moment estimate The expression is:

[0124]

[0125] in, Indicates the current iteration number. Indicates the first attenuation coefficient. This represents the gradient of each voltage-power phase sequence mapping model parameter in the current batch;

[0126] The second-order moment estimation The expression is:

[0127]

[0128] in, Indicates the second attenuation coefficient;

[0129] Estimation of the first moment respectively and second-order moment estimation The deviation correction is performed using the following expression:

[0130]

[0131]

[0132] in, This represents the corrected first-order moment estimate. This represents the corrected second-order moment estimate;

[0133] Update voltage-power phase sequence mapping model parameters The expression is:

[0134] .

[0135] In this embodiment, calculating the three-phase imbalance of the distribution area based on the phase sequence category of all users and the user power corresponding to each phase sequence includes:

[0136] Based on the active power of all users and their phase sequence category, the active power of all users in the same phase is summed to obtain the total load power of the three phases. , and The calculation formula is:

[0137]

[0138] in, This represents three phases: A, B, and C. Indicates belonging to The set of all users in each phase is used to calculate the average value of the three-phase active power load. The expression is:

[0139]

[0140] in, This represents the sum of the active power of all users belonging to phase A. This represents the sum of the active power of all users belonging to phase B. This represents the sum of the active power of all users belonging to phase C;

[0141] Based on the phase sequence category of all users and the average value of the three-phase active power load, calculate the three-phase imbalance of the distribution network. The expression is:

[0142] .

[0143] In this embodiment, a flowchart illustrating the process of generating a load adjustment scheme based on the three-phase imbalance of the distribution network is provided below. Figure 3 ,include:

[0144] S51. Based on the active power of all users and their phase sequence category, calculate the active power of phases A, B, and C respectively. , , The phase with the highest active power is designated as the phase to be removed, and the phase with the lowest active power is designated as the phase to be removed; that is, this step determines the phase with the heaviest load based on the current phase sequence and load. With the lightest load .

[0145] S52. From all users belonging to the removed phase, select users who meet the preset switching constraints to form a candidate set; specifically, from... Selected options can be safely switched to. Users in the same category constitute a candidate set. Filtering criteria may include constraints such as user load type and whether switching is allowed.

[0146] S53. Order , Indicates the user's active power order and executes S54;

[0147] S54. Sort the users in the candidate set according to their active power from largest to smallest. ;

[0148] S55. Based on the sorted order, select the users in the current candidate set. Switch to the shifted phase and calculate the new three-phase imbalance. Specifically, the candidate set Users are sorted by their active power from highest to lowest, and each candidate user is then switched to [the appropriate platform]. Phase, and calculate the new three-phase imbalance.

[0149] S56. Determine the new three-phase imbalance. If the new three-phase imbalance is less than the original three-phase imbalance, and if so, the new three-phase imbalance is used as the current three-phase imbalance, and S57 is executed; otherwise, the users in the current candidate set are selected. Restore to the shifted-out phase, let The value is increased by 1, and the process returns to S55; the original three-phase imbalance includes the preset three-phase imbalance value and the three-phase imbalance value under the previous user's active power sequence.

[0150] S57. Determine whether the current three-phase imbalance is less than the preset threshold. If yes, record this switching operation in the load adjustment scheme, integrate all switching operation records, and generate a load adjustment scheme; if not, then... The value is increased by 1, this switching operation is recorded in the load adjustment plan, and S58 is executed;

[0151] S58. Judgment Does it exceed If so, integrate all switching operation records to generate a load adjustment plan; otherwise, return to S55.

[0152] Specifically, the termination condition also includes reaching a preset maximum number of allowed switching times.

[0153] Specifically, when the load adjustment scheme is terminated, a load adjustment scheme consisting of a series of accepted switching operations is output. The scheme clearly lists the user identifier to be adjusted, the target phase to be switched, and the expected three-phase imbalance after adjustment. This scheme can be directly used as the input instruction set for subsequent remote control execution.

[0154] In this embodiment, a load adjustment scheme is generated based on the three-phase imbalance of the distribution network, and the phase sequence category of the user is remotely adjusted using the dedicated carrier communication network, including:

[0155] The generated load adjustment scheme is compiled into control commands, which are then sent to the commutation switch via the dedicated carrier communication network. The commutation switch receives and verifies the control commands before completing the user's commutation operation.

[0156] The results of the control command execution are fed back to the distribution master station through the dedicated carrier communication network to update the phase topology record.

[0157] Specifically, using the dedicated carrier communication network, control commands can be sent to the smart energy meter or load switch on the target user side. After receiving and verifying the command, the phase-switching switch automatically drives its internal switching elements to perform phase-line switching operations, completing the transfer of load from the current phase to the target phase. In this embodiment, the control command execution result includes execution failure and execution success.

[0158] Example 3

[0159] This embodiment uses a typical 49-node low-voltage distribution network for simulation analysis. The structure of the 49-node low-voltage distribution network simulation system is as follows: Figure 4 As shown, Figure 4 The low-voltage distribution network shown has four main branches, with a total of 28 users connected to a 500KVA distribution transformer. Node 28 is a three-phase user. Photovoltaic power is configured at user nodes 24, 25, 26, 28, 29, 30, 35, and 41, with node 28 configured as a three-phase photovoltaic system. The peak power of each single-phase user is set to 13.56kW, and the peak power of each single-phase photovoltaic system is set to 13.34kW.

[0160] This embodiment simulates 10 days of operational data, with one sampling point every 15 minutes, totaling 960 training samples. The user active power curve is set to a bimodal shape, and the power factor is fixed at 0.9; a schematic diagram of the user active power curve is shown below. Figure 5 As shown, Figure 5 The three curves in the figure represent the changes in the active power of users 22, 23, and 24 over a day.

[0161] In this embodiment, the photovoltaic active power curve is set to a single-peak type, and the power factor is fixed at 1; the schematic diagram of the photovoltaic active power curve is shown below. Figure 6 As shown, Figure 6 The three curves in the figure represent the changes in the active power of three photovoltaic users within a day.

[0162] In this embodiment, the heatmap of the trained phase sequence mapping matrix is ​​as follows: Figure 7 As shown in the figure, the lighter the color in a phase, the lower the probability that the user belongs to that phase, and the darker the color in a phase, the higher the probability that the user belongs to that phase. For example, in the figure, the color of user 22 in phase C is very dark, which means that user 22 has a high probability of belonging to phase C.

[0163] In this embodiment, the schematic diagram of the three-phase unbalance curves of the low-voltage distribution network simulation system at each acquisition time is as follows: Figure 8 As shown, Figure 8 The threshold for three-phase imbalance is set at 40%. Figure 8 The average unbalance at each sampling time was 37.24%, and the maximum was 82.14%. The three-phase unbalance exceeded the threshold 41 times, indicating an urgent need for phase sequence adjustment. The three-phase unbalance threshold was set at 40%, and the maximum number of adjustments was set at 50. The final load adjustment scheme is shown in Table 1.

[0164] Table 1

[0165]

[0166] Figure 8 The dashed lines represent the three-phase imbalance at each sampling time after load adjustment. It can be seen that the imbalance at each sampling time has decreased significantly, with an average of 19.72% and a maximum of 38.43%. The number of times the three-phase imbalance exceeded the threshold was 0.

[0167] Example 4

[0168] This embodiment proposes a low-voltage active distribution network user phase sequence identification and control system based on carrier communication. In this embodiment, the system is used to implement a low-voltage active distribution network user phase sequence identification and control method based on carrier communication. The structural diagram is shown below. Figure 9 As shown, it includes:

[0169] The distribution transformer substation operation parameter data acquisition unit is used to deploy a dedicated carrier communication network covering the distribution transformer substation within the low-voltage distribution transformer substation to be identified, and to synchronously acquire the distribution transformer substation operation parameter data based on the dedicated carrier communication network.

[0170] The voltage-power phase sequence mapping model construction unit is used to construct a voltage-power phase sequence mapping model by taking the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output.

[0171] The voltage-power phase sequence mapping model training unit is used to preprocess the operating parameter data of the distribution substation, and use the preprocessed operating parameter data of the distribution substation to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model.

[0172] The phase sequence mapping matrix acquisition unit is used to extract model-fixed parameters based on the trained voltage-power phase sequence mapping model, and extract the phase sequence mapping matrix based on the model-fixed parameters.

[0173] The user phase sequence category confirmation unit is used to determine the phase sequence category of all users in the distribution area based on the phase sequence mapping matrix.

[0174] The distribution area three-phase unbalance calculation unit is used to calculate the three-phase unbalance of the distribution area based on the phase sequence category of all users and the corresponding user power.

[0175] The user phase sequence control unit is used to determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If so, it generates a load adjustment scheme based on the three-phase imbalance of the distribution network and remotely adjusts the phase sequence category of the user using the dedicated carrier communication network. If not, it terminates the user phase sequence control.

[0176] Example 5

[0177] In this embodiment, a computer device is proposed, comprising a memory 101, a processor 102, and a computer program stored in the memory 101 that can be executed by the processor. The processor 102 executes the computer program to implement a low-voltage active distribution network user phase sequence identification and control method based on carrier communication. A schematic diagram of the device is shown below. Figure 10 As shown.

[0178] In this embodiment, a computer storage medium is also proposed, on which a computer program is stored. The computer program includes program instructions, which, when executed by a computer, cause the computer to execute a low-voltage active distribution network user phase sequence identification and control method based on carrier communication.

[0179] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for phase sequence identification and control of users in low-voltage active distribution networks based on carrier communication, characterized in that, Includes the following steps: S1. Deploy a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collect the operating parameter data of the distribution transformer area based on the dedicated carrier communication network; S2. Using the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output, construct a voltage-power phase sequence mapping model; S3. Preprocess the operating parameter data of the distribution substation, and use the preprocessed operating parameter data of the distribution substation to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model. S4. Based on the trained voltage-power phase sequence mapping model, extract the model fixed parameters, and based on the model fixed parameters, extract the phase sequence mapping matrix; S5. Based on the phase sequence mapping matrix, determine the phase sequence category to which all users in the distribution area belong; S6. Calculate the three-phase imbalance of the distribution area based on the phase sequence category of all users and the user power corresponding to each phase sequence; S7. Determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If yes, generate a load adjustment scheme based on the three-phase imbalance of the distribution network. Based on the load adjustment scheme, remotely adjust the phase sequence category of the user using the dedicated carrier communication network. If no, end.

2. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 1, characterized in that, The process involves deploying a dedicated carrier communication network covering the low-voltage distribution transformer area to be identified, and synchronously collecting operating parameter data of the distribution transformer area based on this dedicated carrier communication network, including: Within the low-voltage distribution transformer area to be identified, power line carrier communication chips with data acquisition functions are deployed on the concentrators on the low-voltage side of the transformer and on the user's electricity meter side to construct a dedicated carrier communication network covering the distribution transformer area. Keep the clocks of all power line carrier communication chips in a consistent state, and send data acquisition commands to all power line carrier communication chips synchronously to collect distribution area operating parameter data; The operating parameter data of the distribution transformer substation includes: three-phase voltage on the low-voltage side of the substation substation, user power, and photovoltaic inverter power; the three-phase voltage on the low-voltage side of the substation substation includes phase A voltage. Phase B voltage and C-phase voltage User power includes user active power. and user reactive power Photovoltaic inverter power includes the active power of the photovoltaic inverter. and reactive power of photovoltaic inverters .

3. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 2, characterized in that, The process of constructing the voltage-power phase sequence mapping model is as follows: generate random matrix , Represents the number of users, for a random matrix Each column is processed to obtain the initial phase sequence mapping matrix; Based on the initial phase sequence mapping matrix and the three-phase voltage on the low-voltage side of the distribution transformer, the contribution components of the three-phase voltage on the low-voltage side of the distribution transformer to the predicted user voltage are calculated, and denoted as the head-end contribution vector. The expression for evaluation satisfies: in, This indicates the three-phase voltage on the low-voltage side of the distribution transformer; Represents the initial phase sequence mapping matrix; Based on the preset three-layer sensor parameters, the contribution components of user power and photovoltaic inverter power to the predicted user voltage are calculated and denoted as the power contribution vector. Satisfies the expression: in, These are the weight matrix parameters for the 1st, 2nd, and 3rd layers of the perceptron, respectively. These are the bias vector parameters for the first, second, and third layers of the perceptron, respectively. These are the activation functions for the 1st, 2nd, and 3rd layers of the perceptron, respectively. ; Then the predicted user voltage of the distribution station area satisfy: 。 4. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 3, characterized in that, The training voltage-power phase sequence mapping model includes: S31. Using the preprocessed operating parameter data of the distribution substation as input to the voltage-power phase sequence mapping model, obtain the predicted user voltage output by the voltage-power phase sequence mapping model. ; S32: Predicted User Voltage Based on Model Output and the actual user voltage collected Calculate the loss function value in the training voltage-power phase sequence mapping model; the expression for the loss function in the training voltage-power phase sequence mapping model is: in, Indicates the number of samples collected. Represents the sample sequence; S33. Train the voltage-power phase sequence mapping model based on the Adam optimization algorithm. During the training process, update the parameters of the voltage-power phase sequence mapping model, including the phase sequence mapping matrix and all weight matrix parameters. and all bias vector parameters ; S34. Determine if the loss function value is less than or equal to a preset threshold. If yes, complete the training of the voltage-power phase sequence mapping model, extract the final phase sequence mapping matrix from the trained voltage-power phase sequence mapping model. Each column of the final phase sequence mapping matrix corresponds to a user, and the three elements in each column represent the membership degree or probability of the user belonging to phases A, B, and C, respectively. Determine the phase of each user based on the final phase sequence mapping matrix. If not, return to S31.

5. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 4, characterized in that, The calculation of the three-phase imbalance of the distribution substation based on the phase sequence category of all users and the user power corresponding to each phase sequence includes: Calculate the average three-phase active power load based on the active power of all users and their phase sequence category. The expression is: in, This represents the sum of the active power of all users belonging to phase A. This represents the sum of the active power of all users belonging to phase B. This represents the sum of the active power of all users belonging to phase C; Based on the phase sequence category of all users and the average value of the three-phase active power load, calculate the three-phase imbalance of the distribution network. The expression is: 。 6. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 5, characterized in that, A load adjustment scheme is generated based on the three-phase imbalance of the distribution network, including: S51. Based on the active power of all users and their phase sequence category, calculate the active power of phases A, B, and C respectively. , , The phase with the highest active power is designated as the phase to be removed, and the phase with the lowest active power is designated as the phase to be removed. S52. From all users belonging to the removed phase, select users who meet the preset switching constraints to form a candidate set; S53. Order , Indicates the user's active power order and executes S54; S54. Sort the users in the candidate set according to their active power from largest to smallest. ; S55. Based on the sorted order, select the users in the current candidate set. Switch to the shifted phase and calculate the new three-phase imbalance. ; S56. Determine the new three-phase imbalance. If the new three-phase imbalance is less than the original three-phase imbalance, and if so, the new three-phase imbalance is used as the current three-phase imbalance, and S57 is executed; otherwise, the users in the current candidate set are selected. Restore to the shifted-out phase, let The value is increased by 1, and the process returns to S55; the original three-phase imbalance includes the preset three-phase imbalance value and the three-phase imbalance value under the previous user's active power sequence. S57. Determine whether the current three-phase imbalance is less than the preset threshold. If yes, record this switching operation in the load adjustment scheme, integrate all switching operation records, and generate a load adjustment scheme; if not, then... The value is increased by 1, this switching operation is recorded in the load adjustment plan, and S58 is executed; S58. Judgment Does it exceed If so, integrate all switching operation records to generate a load adjustment plan; otherwise, return to S55.

7. The method for user phase sequence identification and control in low-voltage active distribution networks based on carrier communication according to claim 6, characterized in that, Based on the three-phase imbalance of the distribution network, a load adjustment scheme is generated. Using the dedicated carrier communication network, the phase sequence category of the user is remotely adjusted, including: The generated load adjustment scheme is compiled into control commands, which are then sent to the commutation switch via the dedicated carrier communication network. The commutation switch receives and verifies the control commands before completing the user's commutation operation. The results of the control command execution are fed back to the distribution master station through the dedicated carrier communication network to update the phase topology records of the distribution substation.

8. A low-voltage active distribution network user phase sequence identification and control system based on carrier communication, characterized in that, The system is used to implement the method of any one of claims 1 to 7, comprising: The distribution transformer substation operation parameter data acquisition unit is used to deploy a dedicated carrier communication network covering the distribution transformer substation within the low-voltage distribution transformer substation to be identified, and to synchronously acquire the distribution transformer substation operation parameter data based on the dedicated carrier communication network. The voltage-power phase sequence mapping model construction unit is used to construct a voltage-power phase sequence mapping model by taking the operating parameter data of the distribution substation as input and the user voltage of the distribution substation as output. The voltage-power phase sequence mapping model training unit is used to preprocess the operating parameter data of the distribution substation, and use the preprocessed operating parameter data of the distribution substation to train the voltage-power phase sequence mapping model to obtain the trained voltage-power phase sequence mapping model. The phase sequence mapping matrix acquisition unit is used to extract model-fixed parameters based on the trained voltage-power phase sequence mapping model, and extract the phase sequence mapping matrix based on the model-fixed parameters. The user phase sequence category confirmation unit is used to determine the phase sequence category of all users in the distribution area based on the phase sequence mapping matrix. The distribution area three-phase unbalance calculation unit is used to calculate the three-phase unbalance of the distribution area based on the phase sequence category of all users and the corresponding user power. The user phase sequence control unit is used to determine whether the three-phase imbalance of the distribution substation exceeds a preset threshold. If so, it generates a load adjustment scheme based on the three-phase imbalance of the distribution network and remotely adjusts the phase sequence category of the user using the dedicated carrier communication network. If not, it terminates the user phase sequence control.

9. A computer device, characterized in that, The computer device includes a memory, a processor, and a computer program stored in the memory that can be executed by the processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that, It stores a computer program, which includes program instructions that, when executed by a computer, cause the computer to perform the method described in any one of claims 1 to 7.

Images