A low-voltage substation line loss diagnosis method, system, device and storage medium

Abstract

A low-voltage substation line loss diagnosis method, system, device, and storage medium, including: collecting the voltage and current of nodes included in each level of branch boxes and metering boxes, calculating the electricity quantity, phase angle, fundamental wave current amplitude, and the odd harmonic current amplitudes of a set number; thereby calculating the weight of each node; calculating the total line loss of the substation area and all sectional line losses according to the electricity quantity and the corresponding normalized weights, and calculating all comprehensive sectional line loss rates in combination with the relative change rates corresponding to all line losses; constructing and training a line loss time series prediction model, inputting all the comprehensive sectional line loss rates at the current moment into the line loss time series prediction model to predict all the comprehensive sectional line loss rates at the next moment, and giving an early warning when there is a comprehensive sectional line loss rate exceeding the set line loss rate threshold among the predicted comprehensive sectional line loss rates at the next moment. The present invention accurately calculates the total line loss and sectional line losses, and predicts the comprehensive sectional line loss rates at the next moment, and can give an early warning in advance, greatly improving the on-site operation efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of line loss diagnosis, and particularly relates to a low-voltage substation area line loss diagnosis method, system, device and storage medium. Background Art

[0002] The line loss of the substation area is an important operation and technical index of power grid enterprises, which consists of two parts: technical line loss and management line loss. Due to the existence of technical line loss, the line loss of the substation area is generally within a certain range. If it exceeds the normal range, it belongs to abnormal line loss and needs to be manually investigated and managed.

[0003] CN119125667A provides a calculation method, device, electronic device and medium for the line loss of a low-voltage substation area. The method is applied to a three-phase IoT meter of a target low-voltage substation area, and includes: reading the power consumption of the three-phase IoT meter and the power consumption of each single-phase meter, and obtaining the electrical characteristic quantities of the target low-voltage substation area; calculating a first line loss result based on the power consumption of the three-phase IoT meter and the power consumption of each single-phase meter; inputting the electrical characteristic quantities into a pre-trained line loss calculation model to obtain a second line loss result; wherein, the line loss calculation model is trained based on a random forest model of an improved bat algorithm; and performing weighted calculation on the first line loss result and the second line loss result to obtain the line loss result of the target low-voltage substation area. However, this invention is affected by the data acquisition completeness rate and the clock synchronization rate, and the accuracy of the line loss calculation in the low-voltage substation area is not high; at the same time, it does not consider that the power supply network in the low-voltage substation area is intricate and there are many cable buried underground scenarios, involving various devices such as low-voltage lines, residential meter boxes, electric energy meters and current transformers. When front-line personnel face difficult substation areas such as high loss, negative loss, unreasonable deviation of the two rates, and suspected non-metered electricity consumption, the investigation difficulty is relatively large; and with the continuous increase in the penetration rate of new loads such as new energy vehicles, 5G base stations, and distributed photovoltaics, the complexity of power supply and consumption in the substation area increases, which further exacerbates the difficulty of line loss investigation and management work in the low-voltage substation area. Summary of the Invention

[0004] To solve the problems of difficult line loss measurement and calculation and low accuracy in the prior art, the present invention provides a low-voltage substation area line loss diagnosis device, method and system, which synchronously and real-timely measure the key electrical parameters of the substation area nodes through multiple node measurement units, comprehensively calculate and predict the line loss abnormal points, and improve the efficiency of line loss management in the substation area.

[0005] The present invention adopts the following technical solutions.

[0006] The first aspect of the present invention proposes a low-voltage substation area line loss diagnosis method, which is characterized by including the following contents:

[0007] Gradually investigate each branch box and the nodes included in the metering box from the outlet end of the substation area transformer to the metering box;

[0008] The voltage and current of the node are collected at the set time interval, and the electrical quantity, phase angle, fundamental current amplitude and the set number of odd harmonic current amplitudes of the node are calculated based on the voltage and current;

[0009] The weight of each node is calculated according to the phase angle of the node, the fundamental current amplitude and the amplitude of a set number of odd harmonic currents, and the weight is normalized;

[0010] Calculate the total line loss of the substation area and all segment line losses according to the power and the corresponding normalized weights, and calculate all comprehensive segment line loss rates according to the relative change rates of the total line loss of the substation area, all segment line losses and all line losses;

[0011] Construct and train a line loss time series prediction model, input all the comprehensive segmented line loss rates at this moment into the line loss time series prediction model to predict all the comprehensive segmented line loss rates at the next moment, and issue an early warning when the predicted comprehensive segmented line loss rate at the next moment exceeds the set line loss rate threshold; add all the comprehensive segmented line loss rates at this moment to the training set to update the line loss time series prediction model.

[0012] Preferably, the nodes included in the branch boxes and meter boxes at all levels from the transformer outlet to the meter box are specifically:

[0013] Each level of branch box contains several branch boxes, and each phase A, phase B, and phase C cable in front of the outlet terminal of each branch box serves as a node;

[0014] The A-phase, B-phase, and C-phase cables in each meter box each serve as a node.

[0015] Preferably, the weight of each node is calculated according to the phase angle of the node, the fundamental current amplitude and the set number of odd harmonic current amplitudes, and the weight is normalized, specifically as follows:

[0016] Weight The calculation formula is:

[0017]

[0018] in, , is the number of branch box levels; For the x indivual k The first branch box j The weight of the node, when k is equal to m +1, k The level branch box is a metering box; , j 1, 2, and 3 correspond to the nodes of phase A, phase B, and phase C respectively; is the fundamental current amplitude of the node; is the amplitude of the (2i + 1)-th harmonic current of the node; N is the set number of odd harmonic currents; is the phase angle of the node; , are both set sensitivity parameters; is the importance ratio of the set (2i + 1)-th harmonic current;

[0019] Dividing the weight of each node by the sum of the weights of all nodes gives the normalized weight.

[0020] Preferably, calculating the total line loss of the distribution transformer area and the sectional line loss according to the electricity quantity multiplied by the corresponding normalized weight, specifically:

[0021] The sectional line loss of the x -th k level branch box at this moment Specifically:

[0022]

[0023] Wherein, is the electricity quantity of the x -th k node of the j level branch box; is the normalized weight of the x -th k node of the j level branch box; is the electricity quantity of the x -th k node of the -th k +1 level branch box connected to the j -th is the normalized weight of the x -th k node of the -th k +1 level branch box connected to the j -th is the number of x -th k level branch boxes connected to the k +1 level branch box;

[0024] The total line loss is the sum of all sectional line losses.

[0025] Preferably, calculating the total line loss of the distribution transformer area and the sectional line loss according to the electricity quantity and the corresponding normalized weight, and calculating the comprehensive sectional line loss rate according to the total line loss of the distribution transformer area, all sectional line losses and the relative change rates corresponding to all line losses, specifically:

[0026] The integrated sectional line loss rate of the x th k -level branch box at this moment The calculation formula is:

[0027]

[0028] Among them, is the total line loss at this moment; is the relative change rate of the sectional line loss of the x th k -level branch box at this moment, which is equal to the difference between the sectional line losses of the x th k -level branch box at this moment and the previous moment divided by the sectional line loss of the x th k -level branch box at this moment; is the relative change rate of the total line loss at this moment, which is equal to the difference between the total line losses at this moment and the previous moment divided by the total line loss at this moment.

[0029] Preferably, the line loss time series prediction model adopts an echo state network, and the echo state network includes an input layer, a dynamic reservoir, and an output layer, and the dynamic reservoir is composed of neurons connected randomly and sparsely;

[0030] The dynamic reservoir state update function of the echo state network is:

[0031]

[0032] Among them, is the dynamic reservoir state vector at time step t; is the vector output by the input layer at time step t; is the dynamic reservoir state vector at time step t - 1; is the weight matrix from the input layer to the dynamic reservoir; is the weight matrix inside the dynamic reservoir; is the bias term inside the dynamic reservoir; is the non-linear activation function.

[0033] Preferably, all the integrated sectional line loss rates at this moment are added to the training set to update the line loss time series prediction model, and all the weight matrices of the echo state network are not updated and trained, and only the weight matrix of the output layer of the network is updated.

[0034] The second aspect of the present invention proposes a low-voltage substation area line loss diagnosis system using the method described in the first aspect of the present invention, including a plurality of node measurement units, a weight calculation unit, an integrated sectional line loss rate calculation unit, and a prediction unit, and is characterized in that:

[0035] The node measurement unit: It is installed on each node included in each branch box and metering box from the outlet end of the substation area transformer to the metering box; it is used to collect the voltage and current of the node at a set time interval, and calculate the electricity quantity, phase angle, fundamental wave current amplitude and the odd harmonic current amplitudes of a set number of nodes according to the voltage and current.

[0036] The weight calculation unit: It is used to calculate the weight of each node according to the phase angle, fundamental wave current amplitude and the odd harmonic current amplitudes of a set number of nodes, and normalize the weight.

[0037] The comprehensive sectional line loss rate calculation unit: It is used to calculate the total line loss of the substation area and all sectional line losses according to the electricity quantity and the corresponding normalized weights, and calculate all comprehensive sectional line loss rates according to the total line loss of the substation area, all sectional line losses and the relative change rates corresponding to all line losses.

[0038] The prediction unit: It is used to construct and train a line loss time series prediction model, input all the comprehensive sectional line loss rates at the current moment into the line loss time series prediction model to predict all the comprehensive sectional line loss rates at the next moment, and give an early warning when there is a comprehensive sectional line loss rate exceeding the set line loss rate threshold among the predicted comprehensive sectional line loss rates at the next moment; add all the comprehensive sectional line loss rates at the current moment to the training set to update the line loss time series prediction model.

[0039] Preferably, the node measurement unit is composed of a voltage measurement module, a current measurement module, a data storage module, a data communication module, a synchronous clock module, a power supply module and a microprocessor.

[0040] The voltage measurement module and the current measurement module synchronously measure the voltage and current at the node under the control of the microprocessor; the synchronous clock module provides clock information for the microprocessor; the microprocessor calculates the electricity quantity, phase angle, fundamental wave current amplitude and the odd harmonic current amplitudes of a set number of nodes according to the measured voltage and current; the data storage module is used to store the measured voltage and current values, as well as the calculated electricity quantity, phase angle, fundamental wave current amplitude and the odd harmonic current amplitudes of a set number of nodes; the data communication module is used for communication between the node measurement unit and the weight calculation unit and the comprehensive sectional line loss rate calculation unit.

[0041] Preferably, the voltage measurement module adopts a direct access method, directly connects the voltage measurement module with the measured node through a wire, and the wire is connected to the voltage measurement module using a banana plug or BNC interface, and the wire is connected to the measured node using an alligator clip or neodymium iron boron magnet.

[0042] The current measurement module adopts an open-type current clamp access method, clamps the open-type current clamp on the phase wire, and the lead wire of the open-type current clamp is connected to the current measurement module using a BNC interface.

[0043] A third aspect of the present invention provides a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the low-voltage substation line loss diagnosis method described in the first aspect of the present invention.

[0044] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the low-voltage substation line loss diagnosis method described in the first aspect of the present invention are used.

[0045] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention calculates various electrical parameters by collecting the voltage and current of each node; calculates the weight of each node according to the electrical parameters, and comprehensively adjusts the calculated power according to the operating state of each node in the low-voltage substation area, so as to adapt to the line loss detection in complex situations. Calculate the total line loss and sectional line loss according to the power and weight. Only need to install the node measurement and control unit, without other debugging, reducing the equipment installation and debugging time. Calculate the comprehensive sectional line loss rate through the total line loss, sectional line loss and their change rates, making the abnormal measurement results more accurate. Use the time series prediction model to predict the comprehensive sectional line loss rate at the next moment, which can give early warnings, greatly improve the on-site operation efficiency, save labor costs, add the comprehensive sectional line loss rate at this moment to the training set to update the model after prediction, complete online learning, and improve the accuracy of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flowchart of the low-voltage substation line loss diagnosis method;

[0047] Figure 2 Schematic diagram of the installation of the node measurement unit in the low-voltage distribution substation area;

[0048] Figure 3 Block diagram of the node measurement unit;

[0049] Figure 4 Installation example diagram of the node measurement unit in Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments described in this application are only a part of the embodiments of the present invention, rather than all embodiments. Based on the spirit of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0051] Such as Figure 1As shown in the figure, Embodiment 1 of the present invention proposes a method for diagnosing line loss in a low-voltage power distribution area, which is characterized by including the following steps:

[0052] Gradually inspect the nodes included in each branch box and metering box from the outlet end of the transformer in the power distribution area to the metering box;

[0053] Collect the voltage and current of the nodes at a set time interval, and calculate the power consumption, phase angle, fundamental current amplitude, and the amplitudes of a set number of odd harmonic currents of the nodes according to the voltage and current;

[0054] It should be noted that the power is calculated by multiplying the voltage and current, the power consumption is calculated by integrating the power over time, and the phase angle calculation formula is:

[0055]

[0056] Wherein, is the power; and are the effective values of the voltage and current, and is the phase angle.

[0057] The fundamental current amplitude and the amplitudes of a set number of odd harmonic currents are obtained by performing Fourier analysis on the measured current signal to obtain the amplitudes of the fundamental wave and each harmonic component.

[0058] Specifically, the set number in this embodiment is 2, that is, the amplitudes of the third and fifth harmonic currents are calculated;

[0059] Calculate the weight of each node according to the phase angle, fundamental current amplitude, and the amplitudes of a set number of odd harmonic currents of the node, and normalize the weight;

[0060] Calculate the total line loss of the power distribution area and the line losses of all segments according to the power consumption and the corresponding normalized weights, and calculate the comprehensive line loss rates of all segments according to the total line loss of the power distribution area, the line losses of all segments, and the relative change rates corresponding to all line losses;

[0061] Construct and train a line loss time series prediction model, input the comprehensive line loss rates of all segments at this moment into the line loss time series prediction model to predict the comprehensive line loss rates of all segments at the next moment, and give an early warning when there is a comprehensive line loss rate exceeding the set line loss rate threshold among the predicted comprehensive line loss rates at the next moment; add the comprehensive line loss rates of all segments at this moment to the training set to update the line loss time series prediction model.

[0062] Preferably, the nodes included in each branch box and metering box from the outlet end of the transformer in the power distribution area to the metering box are specifically:

[0063] Each level of branch box contains several branch boxes, and each of the A-phase, B-phase, and C-phase cables before the outgoing terminal of each branch box serves as 1 node;

[0064] Each of the A-phase, B-phase, and C-phase cables in each metering box serves as 1 node.

[0065] Specifically, the low-voltage distribution substation area of this embodiment is as Figure 2 shown, and each level of branch box includes first- and second-level branch boxes.

[0066] Preferably, calculate the weight of each node according to the phase angle, fundamental current amplitude, and the odd-harmonic current amplitudes of the set number, and normalize the weight. Specifically:

[0067] Weight The calculation formula is:

[0068]

[0069] Among them, , is the number of levels of the branch box; is the x th k weight of the j th node of the m -th level branch box. When k is equal to k +1, the , j -th level branch box is the metering box; , is the fundamental current amplitude of the node; is the 2i + 1-th harmonic current amplitude of the node; N is the set number of odd-harmonic currents; , are both set sensitivity parameters; is the importance ratio of the 2i + 1-th harmonic current;

[0070] Specifically, of this embodiment is set to 0.2; is set to 0.5; , are respectively set to 0.8 and 0.6.

[0071] Divide the weight of each node by the sum of the weights of all nodes to obtain the normalized weight.

[0072] Preferably, calculate the total line loss and sectional line loss of the substation area according to the electricity consumption multiplied by the corresponding normalized weight. Specifically:

[0073] At this moment, the x thk Section line loss of the primary branch box Specifically:

[0074]

[0075] Among them, is the power consumption of the x th k node of the j th primary branch box; is the weight of the x th k node of the j th primary branch box after normalization; is the power consumption of the x th k node of the th k +1 primary branch box connected to the j th primary branch box, is the weight of the x th k node of the th k +1 primary branch box connected to the j th primary branch box after normalization; is the number of x th k +1 primary branch boxes connected to the k th primary branch box;

[0076] The total line loss is the sum of all section line losses.

[0077] Preferably, the total line loss and section line loss of the distribution area are calculated according to the power consumption and the corresponding normalized weight, and the comprehensive section line loss rate is calculated according to the total line loss of the distribution area, all section line losses and the relative change rate corresponding to all line losses. Specifically:

[0078] The comprehensive section line loss rate of the x th k primary branch box at this moment The calculation formula is:

[0079]

[0080] Among them, is the total line loss at this moment; is the relative change rate of the section line loss of the x th k primary branch box at this moment, is equal to the difference between the section line loss of the x th k primary branch box at this moment and the previous moment divided by the section line loss of the x thk Section line loss of the primary branch box is the relative change rate of the total line loss at this moment, which is equal to the difference between the total line loss at this moment and the previous moment divided by the total line loss at this moment.

[0081] Preferably, the line loss time series prediction model adopts an echo state network, which includes an input layer, a dynamic reservoir, and an output layer. The dynamic reservoir is composed of neurons connected randomly and sparsely;

[0082] The state update function of the dynamic reservoir of the echo state network is:

[0083]

[0084] where, is the state vector of the dynamic reservoir at time step t; is the vector output by the input layer at time step t; is the state vector of the dynamic reservoir at time step t - 1; is the weight matrix from the input layer to the dynamic reservoir; is the weight matrix inside the dynamic reservoir; is the bias term inside the dynamic reservoir; is the non - linear activation function.

[0085] Preferably, when adding all the comprehensive section line loss rates at this moment to the training set to update the line loss time series prediction model, not all the weight matrices of the echo state network are updated and trained, but only the weight matrix of the output layer of the network is updated.

[0086] Embodiment 2 of the present invention proposes a low - voltage sub - area line loss diagnosis system using the method described in Embodiment 1 of the present invention, including several node measurement units, a weight calculation unit, a comprehensive section line loss rate calculation unit, and a prediction unit, characterized in that:

[0087] The node measurement unit: installed on each node included in each level of branch box and metering box from the outlet end of the sub - area transformer to the metering box; used to collect the voltage and current of the node at a set time interval, and calculate the electric quantity, phase angle, fundamental wave current amplitude, and the odd - harmonic current amplitudes of a set number of the node according to the voltage and current;

[0088] The weight calculation unit: used to calculate the weight of each node according to the phase angle, fundamental wave current amplitude, and the odd - harmonic current amplitudes of a set number of the node, and normalize the weight;

[0089] Comprehensive sectional line loss rate calculation unit: It is used to calculate the total line loss of the transformer substation area and all sectional line losses according to the electricity quantity and the corresponding normalized weights, and calculate all comprehensive sectional line loss rates according to the total line loss of the transformer substation area, all sectional line losses and the relative change rates corresponding to all line losses;

[0090] Prediction unit: It is used to construct and train a line loss time series prediction model, input all the comprehensive sectional line loss rates at this moment into the line loss time series prediction model to predict all the comprehensive sectional line loss rates at the next moment, and give an alarm when there is a comprehensive sectional line loss rate exceeding the set line loss rate threshold among the predicted comprehensive sectional line loss rates at the next moment; Add all the comprehensive sectional line loss rates at this moment to the training set to update the line loss time series prediction model.

[0091] Preferably, as Figure 3 shown, the node measurement unit is composed of a voltage measurement module, a current measurement module, a data storage module, a data communication module, a synchronous clock module, a power supply module and a microprocessor;

[0092] The voltage measurement module and the current measurement module synchronously measure the voltage and current at the node under the control of the microprocessor; The synchronous clock module provides clock information for the microprocessor; The microprocessor calculates the electricity quantity, phase angle, fundamental current amplitude and the amplitudes of a set number of odd harmonic currents according to the measured voltage and current; The data storage module is used to store the measured voltage and current values, as well as the calculated electricity quantity, phase angle, fundamental current amplitude and the amplitudes of a set number of odd harmonic currents; The data communication module is used for communication between the node measurement unit and the weight calculation unit and the comprehensive sectional line loss rate calculation unit.

[0093] As Figure 4 shown, preferably, the voltage measurement module adopts a direct connection method, directly connects the voltage measurement module to the measured node through a wire, and the connection between the wire and the voltage measurement module uses a banana plug or BNC interface, and the connection between the wire and the measured node uses an alligator clip or neodymium iron boron magnet;

[0094] The current measurement module adopts an open-type current clamp access method, clamps the open-type current clamp on the phase line, and the lead-out wire of the open-type current clamp is connected to the current measurement module using a BNC interface.

[0095] Embodiment 3 of the present invention proposes a device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the steps of using the low-voltage transformer substation area line loss diagnosis method described in Embodiment 1 of the present invention.

[0096] Embodiment 4 of the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor, uses the steps of the low-voltage substation area line loss diagnosis method described in Embodiment 1 of the present invention.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A method for diagnosing line loss in a low-voltage power distribution area, characterized in that, It includes the following contents: Gradually investigate the nodes included in each branch box and metering box from the outlet end of the substation area transformer to the metering box; Collect the voltage and current of the nodes at set time intervals, and calculate the power, phase angle, fundamental current amplitude, and odd harmonic current amplitudes of a set number of the nodes based on the voltage and current; Calculate the weight of each node based on the phase angle, fundamental current amplitude, and odd harmonic current amplitudes of a set number of the nodes, and normalize the weight; Calculate the total line loss of the substation area and all sectional line losses based on the power and the corresponding normalized weights, and calculate all comprehensive sectional line loss rates based on the total line loss of the substation area, all sectional line losses, and the relative change rates corresponding to all line losses; Construct and train a line loss time series prediction model, input all the comprehensive sectional line loss rates at this moment into the line loss time series prediction model to predict all the comprehensive sectional line loss rates at the next moment, and give an early warning when there are comprehensive sectional line loss rates exceeding the set line loss rate threshold among the predicted comprehensive sectional line loss rates at the next moment; add all the comprehensive sectional line loss rates at this moment to the training set to update the line loss time series prediction model.

2. A low-voltage substation area line loss diagnosis method according to claim 1, characterized in that: The nodes included in each branch box and metering box from the outlet end of the substation area transformer to the metering box are specifically: Each level of branch box includes several branch boxes, and each of the A-phase, B-phase, and C-phase cables in front of the outlet terminal of each branch box is used as 1 node; Each of the A-phase, B-phase, and C-phase cables in each metering box is used as 1 node.

3. A low-voltage substation area line loss diagnosis method according to claim 2, characterized in that: The method of calculating the weight of each node based on the phase angle, fundamental current amplitude, and odd harmonic current amplitudes of a set number of the nodes, and normalizing the weight is specifically: Weight The calculation formula is as follows: where k = {1, 2,..., m, m + 1}, and m is the number of branch box levels; is the weight of the j-th node of the x-th k-level branch box. When k equals m + 1, the k-level branch box is the metering box; j = {1, 2, 3}, and j corresponding to 1, 2, and 3 are the nodes of phase A, phase B, and phase C respectively; I1 is the fundamental wave current amplitude of the node; I 2i+1 is the (2i + 1)-th harmonic current amplitude of the node; N is the set number of odd harmonic currents; φ is the phase angle of the node; α and β are both set sensitivity parameters; γ 2i+1 is the set importance ratio of the (2i + 1)-th harmonic current; Dividing the weight of each node by the sum of the weights of all nodes gives the normalized weight.

4. A low-voltage substation area line loss diagnosis method according to claim 3, characterized in that: The method of calculating the total line loss of the substation area and all sectional line losses based on the power and the corresponding normalized weights is specifically: The sectional line loss of the x-th k-level branch box at this moment Specifically: Among them, W k,x,j is the power of the j-th node of the x-th k-level branch box; is the weight of the j-th node of the x-th k-level branch box after normalization; W k+1,x′,j is the power of the j-th node of the x'-th (k + 1)-level branch box connected to the x-th k-level branch box, is the weight of the j-th node of the x'-th (k + 1)-level branch box connected to the x-th k-level branch box after normalization; X' is the number of (k + 1)-level branch boxes connected to the x-th k-level branch box; The total line loss is the sum of all sectional line losses.

5. A low-voltage substation area line loss diagnosis method according to claim 4, characterized in that: The method of calculating the total line loss of the substation area and sectional line losses based on the power and the corresponding normalized weights, and calculating the comprehensive sectional line loss rate based on the total line loss of the substation area, all sectional line losses, and the relative change rates corresponding to all line losses is specifically: The comprehensive sectional line loss rate L of the x-th k-level branch box at this moment k,x The calculation formula is as follows: Among them, is the line loss of the bus at this moment; is the relative change rate of the sectional line loss of the x-th k-level branch box at this moment, which is equal to the difference between the sectional line loss of the x-th k-level branch box at this moment and the previous moment divided by the sectional line loss of the x-th k-level branch box at this moment; is the relative change rate of the bus line loss at this moment, which is equal to the difference between the bus line loss at this moment and the previous moment divided by the bus line loss at this moment.

6. A low-voltage substation area line loss diagnosis method according to claim 1, characterized in that: The line loss time series prediction model uses an echo state network, and the echo state network includes an input layer, a dynamic reservoir, and an output layer, and the dynamic reservoir is composed of neurons connected randomly and sparsely; The dynamic reservoir state update function of the echo state network is: x(t) = tanh(W in u(t)+W re x(t - 1)+b) where, \(x(t)\) is the dynamic reservoir state vector at time step \(t\); \(u(t)\) is the vector of the output of the input layer at time step \(t\); \(x(t - 1)\) is the dynamic reservoir state vector at time step \(t - 1\); \(W\) in is the weight matrix from the input layer to the dynamic reservoir; \(W\) re is the weight matrix inside the dynamic reservoir; \(b\) is the bias term inside the dynamic reservoir; \(\tanh(\cdot)\) is the non-linear activation function.

7. A low-voltage substation area line loss diagnosis method according to claim 6, characterized in that: When updating the line loss time series prediction model by adding all the comprehensive sectional line loss rates at this moment to the training set, the ownership weight matrices of the echo state network are not updated and trained, and only the weight matrix of the output layer of the network is updated.

8. A low-voltage substation area line loss diagnosis system using the method according to any one of claims 1-7, comprising a plurality of node measurement units, a weight calculation unit, a comprehensive sectional line loss rate calculation unit, and a prediction unit; characterized in that: The node measurement unit: is installed on each node included in each branch box and metering box between the outgoing line end of the substation area transformer and the metering box; is used to collect the voltage and current of the node at a set time interval, and calculate the electric quantity, phase angle, fundamental wave current amplitude, and the set number of odd harmonic current amplitudes of the node according to the voltage and current. The weight calculation unit: is used to calculate the weight of each node according to the phase angle, fundamental wave current amplitude, and the set number of odd harmonic current amplitudes of the node, and normalize the weight. The comprehensive sectional line loss rate calculation unit: is used to calculate the total line loss of the substation area and all sectional line losses according to the electric quantity and the corresponding normalized weight, and calculate all comprehensive sectional line loss rates according to the total line loss of the substation area, all sectional line losses, and the relative change rates corresponding to all line losses. The prediction unit: is used to construct and train a line loss time series prediction model, input all the comprehensive sectional line loss rates at this moment into the line loss time series prediction model to predict all the comprehensive sectional line loss rates at the next moment, and give an alarm when there is a comprehensive sectional line loss rate exceeding the set line loss rate threshold among the predicted comprehensive sectional line loss rates at the next moment; add all the comprehensive sectional line loss rates at this moment to the training set to update the line loss time series prediction model.

9. The low-voltage substation area line loss diagnosis system according to claim 8, characterized in that: The node measurement unit is composed of a voltage measurement module, a current measurement module, a data storage module, a data communication module, a synchronous clock module, a power supply module, and a microprocessor; The voltage measurement module and the current measurement module synchronously measure the voltage and current at the node under the control of the microprocessor; the synchronous clock module provides clock information for the microprocessor; The microprocessor calculates the electric quantity, phase angle, fundamental wave current amplitude, and the set number of odd harmonic current amplitudes according to the measured voltage and current; The data storage module is used to store the measured voltage and current values, as well as the calculated electric quantity, phase angle, fundamental wave current amplitude, and the set number of odd harmonic current amplitudes; The data communication module is used for communication between the node measurement unit and the weight calculation unit and the comprehensive sectional line loss rate calculation unit.

10. The low-voltage substation area line loss diagnosis system according to claim 9, characterized in that: The voltage measurement module adopts a direct access method, directly connects the voltage measurement module to the measured node through a wire, and the connection between the wire and the voltage measurement module uses a banana plug or BNC interface, and the connection between the wire and the measured node uses an alligator clip or neodymium iron boron magnet; The current measurement module adopts an open-type current clamp access method, clamps the open-type current clamp on the phase line, and the lead wire of the open-type current clamp is connected to the current measurement module using a BNC interface.

11. An apparatus, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the low-voltage substation line loss diagnosis method according to any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the steps of the low-voltage substation line loss diagnosis method according to any one of claims 1 to 9 are used.

Images