A system and method for energy saving and loss reduction of power distribution network of power grid company based on big data

Abstract

The present invention relates to the field of big data technology. The present invention discloses a big data-based energy-saving and loss-reduction system and method for a power grid company's distribution network. The system and method include: a power load data acquisition module, a neural network load prediction module, a load level classification and matching module, a power grid reactive power correction and compensation module, a distribution network reconstruction network loss judgment module, and an energy-saving and loss-reduction effect output module. The system outputs the power load data of the current day as a variable according to a neural network model, predicts the power load of the power grid company for the next day, classifies the power load results into load levels, issues energy-saving and loss-reduction instructions, performs reactive power correction and compensation or distribution network reconstruction on the power grid company's distribution network based on the energy-saving and loss-reduction instructions, measures the power grid load after reactive power correction and compensation or the power grid load after distribution network reconstruction, judges the energy-saving and loss-reduction effect, and helps the power grid company optimize power grid operation and achieve more efficient energy management.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically to a big data-based energy-saving and loss-reduction system and method for a power grid company's distribution network. Background Art

[0002] With the rapid development of social economy and the continuous improvement of people's living standards, the demand for electricity has shown an increasing trend year by year. In order to meet the growing demand for electricity, the structure of the distribution network has become more and more complex. This complexity is not only reflected in the scale and scope of the distribution network, but also in its internal structure and operation mode. Therefore, big data technology has been rapidly developed and widely used. Big data technology has the advantages of processing massive data, mining data value, and realizing data-driven decision-making. In the power industry, big data technology can be applied to real-time monitoring, data analysis, fault diagnosis and other aspects of the distribution network, providing strong technical support for energy saving and loss reduction of the distribution network.

[0003] In the power grid company's distribution network energy-saving and loss reduction system, the application of big data technology can achieve real-time monitoring and analysis of the power grid operation status. However, some big data-based energy-saving and loss reduction systems lack a clear division of warning levels, resulting in deficiencies in the system in risk identification and processing. In the process of risk identification, a single parameter adjustment method is usually used to reconstruct the distribution network. When reconstructing the distribution network, there is a lack of effective network loss estimation and judgment mechanism, and the reconstruction effect is difficult to quantify and evaluate, resulting in unclear energy-saving and loss reduction effects. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a power grid company distribution network energy-saving and loss reduction system based on big data to solve the problems existing in the above-mentioned background technology.

[0005] The present invention provides the following technical solution: a big data-based power grid company distribution network energy-saving and loss-reduction system, comprising: a power load data acquisition module, a neural network load forecasting module, a load level classification and matching module, a power grid reactive power correction and compensation module, a distribution network reconstruction network loss judgment module, and an energy-saving and loss-reduction effect output module;

[0006] The power load data acquisition module collects the power load data of the power grid company for n times at the same time interval through the power load measuring instrument;

[0007] The neural network load forecasting module uses the current day's power load data as a variable to output the neural network model and forecast the power load of the power grid company for the next day.

[0008] The load level classification and matching module classifies the power load results based on the predicted power load results, and issues energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results;

[0009] The grid reactive power correction and compensation module receives the energy-saving and loss-reduction instruction, calculates the reactive power compensation capacity based on the reactive power compensation capacity calculation mathematical model, and performs reactive power correction and compensation on the power distribution network of the power grid company;

[0010] The distribution network reconstruction network loss judgment module receives the energy-saving and loss-reduction instruction to reconstruct the distribution network of the power grid company, and judges whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction;

[0011] The energy-saving and loss-reduction effect output module measures the grid load after reactive power correction compensation or the grid load after distribution network reconstruction, compares the grid load with the grid load predicted by the neural network load prediction module, judges the energy-saving and loss-reduction effect, and outputs the judgment result to the grid terminal.

[0012] Preferably, the neural network load forecasting module includes an input layer, a hidden layer and an output layer, and the input layer inputs the current day's power load data sequence {x1, x2, x3, ..., x n}, the hidden layer performs neural network processing on the sequence to obtain the hidden layer daily power load data sequence {s1, s2, s3, ..., s n}, the output layer outputs the predicted next day power load data sequence {z1, z2, z3, ..., z n}, calculate the mean of the predicted next day's power load data series to predict the next day's power load of the power grid company. The calculation formula is: Where Z represents the predicted value of the power load of the power grid company for the next day.

[0013] Preferably, in the load level division matching module, the predicted value of the power load of the power grid company for the next day is compared with the preset judgment interval. If the predicted value of the power load of the power grid company for the next day is less than the minimum value of the preset judgment interval, the matching result is a zero-level warning. If the predicted value of the power load of the power grid company for the next day is within the judgment interval, the matching result is a first-level warning. If the predicted value of the power load of the power grid company for the next day is greater than the maximum value of the preset judgment interval, the matching result is a second-level warning.

[0014] Preferably, in the reactive power correction and compensation module of the power grid, when the matching result is a first-level warning, the reactive power compensation capacity is calculated based on the reactive power compensation capacity calculation mathematical model upon receiving the energy-saving and loss-reduction instruction. The specific content of the reactive power correction and compensation for the power grid company's distribution network is as follows: the transmitting end voltage and the receiving end voltage of the transmission line are input into the reactive power compensation capacity calculation mathematical model to calculate the reactive power compensation capacity. The reactive power compensation capacity calculation mathematical model is expressed as: Where P represents reactive compensation capacity, V b Represents the voltage at the receiving end of the transmission line, V a represents the voltage at the sending end of the transmission line, Z c represents the corrected equivalent reactance of the transmission line, θ ab represents the angle between the transmitting end and the receiving end of the transmission line, and pγ represents the power correction factor;

[0015] The grid reactive power correction and compensation module performs reactive power compensation on the grid company's distribution network based on the reactive compensation capacity obtained by the reactive compensation capacity calculation mathematical model. The reactive compensation capacity P represents the reactive power compensation value.

[0016] Preferably, the calculation of the reactive power compensation capacity is based on the correction processing of the transmission line, specifically as follows: the equivalent reactance of the transmission line is corrected according to the angle between the reactive power compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line, and the corrected equivalent reactance of the transmission line is calculated. The calculation formula is: Z e =Z c ×sinθ ab -H s ×Z c 2 × sinθ1sinθ2, where Z c represents the corrected equivalent reactance of the transmission line, Z c Represents the transmission line wave impedance, H s represents the susceptance of the transmission line, θ1 represents the angle between the reactive power compensation device and the transmitting end of the transmission line, and θ2 represents the angle between the reactive power compensation device and the receiving end of the transmission line;

[0017] The power factor of the transmission line is corrected based on the angle between the reactive compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line. The power correction factor of the transmission line is calculated using the formula: Pγ=cosθ ab -H s ×Z c ×sinθ1cosθ2, where pγ represents the power correction factor.

[0018] Preferably, in the distribution network reconstruction network loss judgment module, when the matching result is a level 2 warning, the specific contents of receiving the energy-saving and loss-reduction instruction to reconstruct the distribution network of the power grid company and judging whether the distribution network reconstruction is completed based on the estimated network loss before and after the reconstruction are as follows:

[0019] When the matching result is a Level 2 warning, the network loss before the distribution network reconstruction is estimated. The power grid company's distribution network energy-saving and loss reduction system automatically reconstructs the distribution network and estimates the network loss after the reconstruction.

[0020] Based on the estimated network loss values ​​before and after the distribution network reconstruction, it is judged whether the distribution network reconstruction is completed. If the judgment result is that the distribution network reconstruction is completed, the energy-saving and loss reduction effect output module is entered. If the judgment result is that the distribution network reconstruction is not completed, the distribution network of the power grid company continues to be reconstructed.

[0021] Preferably, the specific content of estimating the network loss before and after the distribution network reconstruction is as follows:

[0022] Divide the power distribution network of the power grid company into distribution nodes, where the total number of distribution nodes is M, where m=1, 2, 3, ..., M, and m represents the distribution node number;

[0023] After receiving the energy-saving and loss-reduction instruction, the network loss before the distribution network reconstruction is estimated. The calculation formula is: Where Ta represents the estimated value of network loss before distribution network reconstruction, R m Represents the output resistance value of each distribution node, W m Indicates the active power output value of each distribution node, ΔW m Indicates the active power loss value of each distribution node, Q m Indicates the reactive power output value of each distribution node, ΔQ m Indicates the reactive power loss value of each distribution node, U m Indicates the output voltage value of each distribution node; after receiving the energy-saving and loss-reduction instruction and performing the distribution network reconstruction, the network loss after the distribution network reconstruction is estimated. The calculation formula is: Where Tb represents the estimated value of network loss after distribution network reconstruction, λ represents the distribution network reconstruction coefficient, I m Indicates the output current value of each distribution node, U mmax Indicates the voltage upper limit of each distribution node, U mmin Represents the voltage lower limit of each distribution node, r m Indicates the output resistance value of each distribution node.

[0024] Preferably, the specific content of judging whether the distribution network reconstruction is completed based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction is: establishing a judgment model based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction, the expression of the judgment model is: D = Tb-Ta, D represents the output value of the judgment model, when the output value of the judgment model is greater than the preset threshold, the judgment result is that the distribution network reconstruction is completed, when the output value of the judgment model is less than or equal to the preset threshold, the judgment result is that the distribution network reconstruction is not completed.

[0025] Preferably, the energy saving and loss reduction effect output module measures the power load data after reactive power correction and compensation on the power grid company's distribution network to obtain the power load data sequence {z a1 , za2 , z a3 ,...,z an}, calculate the power load after reactive power correction compensation of the power grid company, the calculation formula is: Where Za represents the power load after reactive power correction compensation of the power grid company; the power load data after the power grid company's distribution network is reconstructed is measured to obtain the power load data sequence after the distribution network is reconstructed {z b1 , z b2 , z b3 ,...,z bn}, calculate the power load after the power grid company's distribution network is restructured. The calculation formula is: Where Zb represents the power load after the grid company's distribution network reconstruction. The energy-saving and loss-reduction effect is judged based on the power load after the grid company's reactive power correction compensation and the power load after the grid company's distribution network reconstruction, and the judgment result is output to the grid terminal.

[0026] A method for energy saving and loss reduction of a power distribution network of a power grid company based on big data, comprising the following steps:

[0027] Step S01: using a power load meter to collect power load data of a power grid company for n times at the same time interval;

[0028] Step S02: using the current day's power load data as a variable to output the neural network model according to the neural network model, and predicting the power load of the power grid company for the next day;

[0029] Step S03: classifying the power load result based on the predicted power load result, and issuing energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results;

[0030] Step S04: receiving the energy-saving and loss-reduction instruction, calculating the reactive compensation capacity based on the reactive compensation capacity calculation mathematical model, and performing reactive correction compensation on the power grid company's distribution network;

[0031] Step S05: Receiving the energy-saving and loss-reduction instruction, reconfiguring the distribution network of the power grid company, and determining whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction;

[0032] Step S06: Measure the grid load after reactive power correction compensation or the grid load after distribution network reconstruction, compare the grid load with the grid load predicted by the neural network load prediction module, judge the energy saving and loss reduction effect, and output the judgment result to the grid terminal.

[0033] The technical effects and advantages of the present invention are as follows:

[0034] The present invention is provided with a power load data acquisition module, a neural network load prediction module, a load level division and matching module, a power grid reactive power correction and compensation module, a distribution network reconstruction network loss judgment module and an energy-saving and loss reduction effect output module. According to the neural network model, the power load data of the day is used as a variable to output the neural network model, the power load of the power grid company for the next day is predicted, and the power load results are divided into load levels, and energy-saving and loss reduction instructions are issued. Based on the energy-saving and loss reduction instructions, reactive power correction and compensation or distribution network reconstruction is performed on the power grid company's distribution network, and the power grid load after reactive power correction and compensation or the power grid load after distribution network reconstruction is measured to judge the energy-saving and loss reduction effect, thereby helping the power grid company to optimize power grid operation and achieve more efficient energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a flow chart of a power grid company's distribution network energy-saving and loss-reduction system based on big data.

[0036] Figure 2 This is a flow chart of a method for energy saving and loss reduction in the distribution network of a power grid company based on big data. DETAILED DESCRIPTION

[0037] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely examples. The present invention involves a power grid company distribution network energy-saving and loss reduction system and method based on big data, and is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] like Figure 1 As shown, the present invention provides a power grid company distribution network energy-saving and loss-reduction system based on big data, including: a power load data acquisition module, a neural network load forecasting module, a load level classification and matching module, a power grid reactive power correction and compensation module, a distribution network reconstruction network loss judgment module, and an energy-saving and loss-reduction effect output module;

[0039] The power load data acquisition module collects the power load data of the power grid company for n times at the same time interval through the power load measuring instrument;

[0040] The neural network load forecasting module uses the current day's power load data as a variable to output the neural network model and forecast the power load of the power grid company for the next day.

[0041] The load level classification and matching module classifies the power load results based on the predicted power load results, and issues energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results;

[0042] The grid reactive power correction and compensation module receives the energy-saving and loss-reduction instruction, calculates the reactive power compensation capacity based on the reactive power compensation capacity calculation mathematical model, and performs reactive power correction and compensation on the power distribution network of the power grid company;

[0043] The distribution network reconstruction network loss judgment module receives the energy-saving and loss-reduction instruction to reconstruct the distribution network of the power grid company, and judges whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction;

[0044] The energy-saving and loss-reduction effect output module measures the grid load after reactive power correction and compensation or the grid load after distribution network reconstruction, compares the grid load with the grid load predicted by the neural network load prediction module, determines the energy-saving and loss-reduction effect, and outputs the judgment result to the grid terminal

[0045] In this embodiment, it should be specifically explained that the neural network load forecasting module includes an input layer, a hidden layer and an output layer. The input layer inputs the current day power load data sequence {x1, x2, x3, ..., x n}, where x n The hidden layer processes the sequence through a neural network to obtain the hidden layer's daily power load data sequence {s1, s2, s3, ..., s n}, where s n =a s ×x n , s n represents the daily power load value output in the hidden layer, a s represents the hidden layer conversion coefficient; the output layer outputs the predicted next day power load data sequence {z1, z2, z3, ..., z n}, where z n =a z ×s n , z n represents the next day's power load forecast value output by the output layer, a z Represents the output layer conversion coefficient; the power load of the power grid company on the next day is predicted by averaging the predicted next day's power load data sequence. The calculation formula is: Where Z represents the predicted value of the power load of the power grid company for the next day.

[0046] In this embodiment, it should be specifically explained that, in the load level division and matching module, the predicted value of the power load of the power grid company for the next day is compared with the preset judgment interval. If the predicted value of the power load of the power grid company for the next day is less than the minimum value of the preset judgment interval, the matching result is a zero-level warning. If the predicted value of the power load of the power grid company for the next day is within the judgment interval, the matching result is a first-level warning. If the predicted value of the power load of the power grid company for the next day is greater than the maximum value of the preset judgment interval, the matching result is a second-level warning.

[0047] The zero-level warning does not adjust the power grid company's distribution network, the first-level warning performs reactive power correction and compensation on the power grid company's distribution network, and the second-level warning reconstructs the power grid company's distribution network.

[0048] In this embodiment, it should be specifically explained that, in the power grid reactive power correction and compensation module, when the matching result is a first-level warning, the reactive power compensation capacity is calculated based on the reactive power compensation capacity calculation mathematical model upon receiving the energy-saving and loss-reduction instruction. The specific content of the reactive power correction and compensation for the power grid company's distribution network is as follows: the transmitting end voltage and the receiving end voltage of the transmission line are input into the reactive power compensation capacity calculation mathematical model to calculate the reactive power compensation capacity. The reactive power compensation capacity calculation mathematical model is expressed as: Where P represents reactive compensation capacity, V b Represents the voltage at the receiving end of the transmission line, V a represents the voltage at the sending end of the transmission line, Z e represents the corrected equivalent reactance of the transmission line, θ ab represents the angle between the transmitting end and the receiving end of the transmission line, and pγ represents the power correction factor;

[0049] The grid reactive power correction and compensation module performs reactive power compensation on the grid company's distribution network based on the reactive compensation capacity obtained by the reactive compensation capacity calculation mathematical model. The reactive compensation capacity P represents the reactive power compensation value.

[0050] In this embodiment, it should be specifically explained that the calculation of the reactive compensation capacity is based on the correction processing of the transmission line, and the specific contents are as follows:

[0051] The equivalent reactance of the transmission line is corrected based on the angle between the reactive compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line. The corrected equivalent reactance of the transmission line is calculated using the following formula: Z e =Z c ×sinθ ab -H s ×Z c 2 × sinθ1sinθ2, where Z e represents the corrected equivalent reactance of the transmission line, Z cRepresents the transmission line wave impedance, H s represents the susceptance of the transmission line, θ1 represents the angle between the reactive compensation device and the transmitting end of the transmission line, and θ2 represents the angle between the reactive compensation device and the receiving end of the transmission line;

[0052] The power factor of the transmission line is corrected based on the angle between the reactive compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line. The power correction factor of the transmission line is calculated using the formula: Pγ=cosθ ab -H s ×Z C ×sinθ1cosθ2, where pγ represents the power correction factor.

[0053] In this embodiment, it should be specifically explained that, in the distribution network reconstruction network loss judgment module, when the matching result is a level 2 warning, the specific contents of receiving the energy-saving and loss-reduction instruction to reconstruct the distribution network of the power grid company and determining whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction are as follows:

[0054] When the matching result is a Level 2 warning, the network loss before the distribution network reconstruction is estimated. The power grid company's distribution network energy-saving and loss reduction system automatically reconstructs the distribution network and estimates the network loss after the reconstruction.

[0055] Based on the estimated network loss values ​​before and after the distribution network reconstruction, it is judged whether the distribution network reconstruction is completed. If the judgment result is that the distribution network reconstruction is completed, the energy-saving and loss reduction effect output module is entered. If the judgment result is that the distribution network reconstruction is not completed, the distribution network of the power grid company continues to be reconstructed.

[0056] In this embodiment, it should be specifically explained that the specific contents of estimating the network loss before and after the distribution network reconstruction are as follows:

[0057] Divide the power distribution network of the power grid company into distribution nodes, where the total number of distribution nodes is M, where m=1, 2, 3, ..., M, and m represents the distribution node number;

[0058] After receiving the energy-saving and loss-reduction instruction, the network loss before the distribution network reconstruction is estimated. The calculation formula is: Where Ta represents the estimated value of network loss before distribution network reconstruction, R m Represents the output resistance value of each distribution node, W m Indicates the active power output value of each distribution node, ΔW m Indicates the active power loss value of each distribution node, Q m Indicates the reactive power output value of each distribution node, ΔQ m Indicates the reactive power loss value of each distribution node, U mIndicates the output voltage value of each distribution node; after receiving the energy-saving and loss-reduction instruction and performing the distribution network reconstruction, the network loss after the distribution network reconstruction is estimated. The calculation formula is: Where Tb represents the estimated value of network loss after distribution network reconstruction, λ represents the distribution network reconstruction coefficient, I m Indicates the output current value of each distribution node, U mmax Indicates the voltage upper limit of each distribution node, U mmin Represents the voltage lower limit of each distribution node, r m Indicates the output resistance value of each distribution node.

[0059] In this embodiment, it should be specifically explained that the specific content of judging whether the distribution network reconstruction is completed based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction is: establishing a judgment model based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction, the expression of the judgment model is: D = Tb-Ta, D represents the output value of the judgment model, when the output value of the judgment model is greater than the preset threshold value, the judgment result is that the distribution network reconstruction is completed, when the output value of the judgment model is less than or equal to the preset threshold value, the judgment result is that the distribution network reconstruction is not completed.

[0060] In this embodiment, it should be specifically explained that the energy saving and loss reduction effect output module measures the power load data after reactive power correction and compensation of the power grid company's distribution network to obtain the power load data sequence after reactive power correction and compensation {z a1 , z a2 , z a3 ,...,z an}, calculate the power load after reactive power correction compensation of the power grid company, the calculation formula is: Where Za represents the power load after reactive power correction compensation of the power grid company; the power load data after the power grid company's distribution network is reconstructed is measured to obtain the power load data sequence after the distribution network is reconstructed {z b1 , z b2 , z b3 ,...,z bn}, calculate the power load after the power grid company's distribution network is restructured. The calculation formula is: Where Zb represents the power load after the grid company's distribution network reconstruction. The energy saving and loss reduction effect is determined based on the power load after reactive power correction and compensation and the power load after the grid company's distribution network reconstruction, and the judgment result is output to the grid terminal.

[0061] When reactive power correction and compensation is performed on the power grid company's distribution network, the power load Za after reactive power correction and compensation is compared with the predicted value Z of the power load of the power grid company for the next day. If Z-Za is greater than a preset threshold, it is judged that the energy saving and loss reduction effect is obvious. Otherwise, it is judged that the energy saving and loss reduction effect is not obvious, and the judgment result is output to the power grid terminal;

[0062] When the power grid company's distribution network is reconstructed, the power load Zb after the power grid company's distribution network reconstruction is compared with the predicted value Z of the power grid company's power load for the next day. If Z-Zb is greater than the preset threshold, it is judged that the energy-saving and loss-reduction effect is obvious. Otherwise, it is judged that the energy-saving and loss-reduction effect is not obvious, and the judgment result is output to the power grid terminal.

[0063] like Figure 2 As shown, in this embodiment, it should be specifically explained that a method for energy saving and loss reduction of a power distribution network of a power grid company based on big data includes the following steps:

[0064] Step S01: using a power load meter to collect power load data of a power grid company for n times at the same time interval;

[0065] Step S02: using the current day's power load data as a variable to output the neural network model according to the neural network model, and predicting the power load of the power grid company for the next day;

[0066] Step S03: classifying the power load result based on the predicted power load result, and issuing energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results;

[0067] Step S04: receiving the energy-saving and loss-reduction instruction, calculating the reactive compensation capacity based on the reactive compensation capacity calculation mathematical model, and performing reactive correction compensation on the power grid company's distribution network;

[0068] Step S05: Receiving the energy-saving and loss-reduction instruction, reconfiguring the distribution network of the power grid company, and determining whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction;

[0069] Step S06: Measure the grid load after reactive power correction compensation or the grid load after distribution network reconstruction, compare the grid load with the grid load predicted by the neural network load prediction module, judge the energy saving and loss reduction effect, and output the judgment result to the grid terminal.

[0070] In this embodiment, it should be specifically explained that the difference between this embodiment and the prior art lies in that this embodiment is provided with a power load data acquisition module, a neural network load prediction module, a load level classification and matching module, a power grid reactive power correction and compensation module, a distribution network reconstruction network loss judgment module, and an energy-saving and loss reduction effect output module. According to the neural network model, the power load data of the day is output as a variable to the neural network model, the power load of the power grid company for the next day is predicted, the power load results are classified into load levels, and energy-saving and loss reduction instructions are issued, thereby achieving accurate prediction and real-time adjustment of the power grid load, thereby effectively reducing the loss of the power grid;

[0071] Based on the energy-saving and loss-reduction instructions, the power grid company's distribution network is subjected to reactive power correction and compensation or distribution network reconstruction, and the grid load after reactive power correction and compensation or the grid load after distribution network reconstruction is measured to judge the energy-saving and loss-reduction effect, monitor and manage the grid load in real time, and respond to grid load changes in a timely manner, thereby reducing unnecessary energy waste, ensuring the safe and stable operation of the power grid, and achieving more efficient energy management.

[0072] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0073] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A big data-based energy-saving and loss-reduction system for power grid companies' distribution networks, characterized by: include: Power load data acquisition module, neural network load forecasting module, load level classification and matching module, grid reactive power correction and compensation module, distribution network reconstruction network loss judgment module, and energy-saving and loss reduction effect output module; The power load data acquisition module collects the power load data of the power grid company for n times at the same time interval through the power load measuring instrument; The neural network load forecasting module uses the current day's power load data as a variable to output the neural network model and forecast the power load of the power grid company for the next day. The load level classification and matching module classifies the power load results based on the predicted power load results, and issues energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results; The grid reactive power correction and compensation module receives the energy-saving and loss-reduction instruction, calculates the reactive power compensation capacity based on the reactive power compensation capacity calculation mathematical model, and performs reactive power correction and compensation on the power distribution network of the power grid company; In the power grid reactive power correction and compensation module, when the matching result is a first-level warning, the reactive power compensation capacity is calculated based on the reactive power compensation capacity calculation mathematical model upon receiving the energy-saving and loss-reduction instruction. The specific contents of the reactive power correction and compensation for the power grid company's distribution network are as follows: the voltage at the transmitting end and the voltage at the receiving end of the transmission line are input into the reactive power compensation capacity calculation mathematical model to calculate the reactive power compensation capacity; The distribution network reconstruction network loss judgment module receives the energy-saving and loss-reduction instruction to reconstruct the distribution network of the power grid company, and judges whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction; In the distribution network reconstruction network loss judgment module, when the matching result is a level 2 warning, the energy-saving and loss-reduction instruction is received to reconstruct the distribution network of the power grid company, and the specific contents of judging whether the distribution network reconstruction is completed based on the estimated network loss before and after the reconstruction are as follows: When the matching result is a Level 2 warning, the network loss before the distribution network reconstruction is estimated. The power grid company's distribution network energy-saving and loss reduction system automatically reconstructs the distribution network and estimates the network loss after the reconstruction. Based on the estimated network loss value before and after the distribution network reconstruction, it is judged whether the distribution network reconstruction is completed. If the judgment result is that the distribution network reconstruction is completed, the energy saving and loss reduction effect output module is entered. If the judgment result is that the distribution network reconstruction is not completed, the distribution network of the power grid company is continued to be reconstructed; The energy-saving and loss-reduction effect output module measures the grid load after reactive power correction compensation or the grid load after distribution network reconstruction, compares the grid load with the grid load predicted by the neural network load prediction module, judges the energy-saving and loss-reduction effect, and outputs the judgment result to the grid terminal.

2. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: The neural network load forecasting module includes an input layer, a hidden layer and an output layer. The input layer inputs the current day's power load data sequence {x1, x2, x3, ..., x n }, the hidden layer performs neural network processing on the sequence to obtain the hidden layer daily power load data sequence {s1, s2, s3, ..., s n }, the output layer outputs the predicted next day power load data sequence {z1, z2, z3, ..., z n }, calculate the mean of the predicted next day's power load data series to predict the next day's power load of the power grid company. The calculation formula is: Where Z represents the predicted value of the power load of the power grid company for the next day.

3. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: In the load level division and matching module, the predicted value of the power load of the power grid company for the next day is compared with the preset judgment interval. If the predicted value of the power load of the power grid company for the next day is less than the minimum value of the preset judgment interval, the matching result is a zero-level warning. If the predicted value of the power load of the power grid company for the next day is within the judgment interval, the matching result is a first-level warning. If the predicted value of the power load of the power grid company for the next day is greater than the maximum value of the preset judgment interval, the matching result is a second-level warning.

4. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: In the grid reactive power correction and compensation module, the reactive power compensation capacity calculation mathematical model is expressed as: Where P represents reactive compensation capacity, V b Represents the voltage at the receiving end of the transmission line, V a represents the voltage at the sending end of the transmission line, Z e represents the corrected equivalent reactance of the transmission line, θ ab represents the angle between the transmitting end and the receiving end of the transmission line, and pγ represents the power correction factor; The grid reactive power correction and compensation module performs reactive power compensation on the grid company's distribution network based on the reactive compensation capacity obtained by the reactive compensation capacity calculation mathematical model. The reactive compensation capacity P represents the reactive power compensation value.

5. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 4 is characterized by: The calculation of the reactive power compensation capacity is based on the correction processing of the transmission line, and the specific contents are as follows: The equivalent reactance of the transmission line is corrected based on the angle between the reactive compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line. The corrected equivalent reactance of the transmission line is calculated using the following formula: Z e =Z c ×sinθ ab -H s ×Z c 2 × sinθ1sinθ2, where Z e Represents the corrected equivalent reactance of the transmission line, Z c Represents the transmission line wave impedance, H s represents the susceptance of the transmission line, θ1 represents the angle between the reactive compensation device and the transmitting end of the transmission line, and θ2 represents the angle between the reactive compensation device and the receiving end of the transmission line; The power factor of the transmission line is corrected based on the angle between the reactive compensation device and the transmitting end of the transmission line and the angle between the receiving end of the transmission line. The power correction factor of the transmission line is calculated using the formula: Pγ=cosθ ab -H s ×Z c ×sinθ1cosθ2, where pγ represents the power correction factor.

6. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: The specific contents of estimating the network loss before and after the distribution network reconstruction in the distribution network reconstruction network loss judgment module are as follows: Divide the power distribution network of the power grid company into distribution nodes, where the total number of distribution nodes is M, where m=1, 2, 3, ..., M, and m represents the distribution node number; After receiving the energy-saving and loss-reduction instruction, the network loss before the distribution network reconstruction is estimated. The calculation formula is: Where Ta represents the estimated value of network loss before distribution network reconstruction, R m Represents the output resistance value of each distribution node, W m Indicates the active power output value of each distribution node, ΔW m Indicates the active power loss value of each distribution node, Q m Indicates the reactive power output value of each distribution node, ΔQ m Indicates the reactive power loss value of each distribution node, U m Indicates the output voltage value of each distribution node; After receiving the energy-saving and loss-reduction instruction and performing the distribution network reconstruction, the network loss after the distribution network reconstruction is estimated. The calculation formula is: Where Tb represents the estimated value of network loss after distribution network reconstruction, λ represents the distribution network reconstruction coefficient, I m Indicates the output current value of each distribution node, U mmax Indicates the voltage upper limit of each distribution node, U mmin Represents the voltage lower limit of each distribution node, r m Indicates the output resistance value of each distribution node.

7. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: The specific content of judging whether the distribution network reconstruction is completed based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction is as follows: a judgment model is established based on the estimated network loss value before the distribution network reconstruction and the estimated network loss value after the distribution network reconstruction. The expression of the judgment model is: D = Tb-Ta, D represents the output value of the judgment model. When the output value of the judgment model is greater than a preset threshold, the judgment result is that the distribution network reconstruction is completed. When the output value of the judgment model is less than or equal to the preset threshold, the judgment result is that the distribution network reconstruction is not completed.

8. The big data-based energy-saving and loss-reduction system for power distribution networks of power grid companies according to claim 1 is characterized by: The energy-saving and loss-reduction effect output module measures the power load data after reactive power correction and compensation on the power grid company's distribution network to obtain a power load data sequence after reactive power correction and compensation {z a1 , z a2 , z a3 ,...,z an }, calculate the power load after reactive power correction compensation of the power grid company, the calculation formula is: Where Za represents the power load after reactive power correction compensation of the power grid company; the power load data after the power grid company's distribution network is reconstructed is measured to obtain the power load data sequence after the distribution network is reconstructed {z b1 , z b2 , z b3 ,...,z bn }, calculate the power load after the power grid company's distribution network is restructured. The calculation formula is: Where Zb represents the power load after the grid company's distribution network reconstruction. The energy-saving and loss-reduction effect is judged based on the power load after the grid company's reactive power correction compensation and the power load after the grid company's distribution network reconstruction, and the judgment result is output to the grid terminal.

9. A method for energy saving and loss reduction in a power grid company's distribution network based on big data, for using the power grid company's distribution network energy saving and loss reduction system based on big data according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step S01: using a power load meter to collect power load data of a power grid company for n times at the same time interval; Step S02: using the current day's power load data as a variable to output the neural network model according to the neural network model, and predicting the power load of the power grid company for the next day; Step S03: classifying the power load result based on the predicted power load result, and issuing energy-saving and loss-reduction instructions to the power grid company's distribution network according to the classification results; Step S04: receiving the energy-saving and loss-reduction instruction, calculating the reactive compensation capacity based on the reactive compensation capacity calculation mathematical model, and performing reactive correction compensation on the power grid company's distribution network; Step S05: Receiving the energy-saving and loss-reduction instruction, reconfiguring the distribution network of the power grid company, and determining whether the distribution network reconstruction is completed based on the estimated network losses before and after the reconstruction; Step S06: Measure the grid load after reactive power correction compensation or the grid load after distribution network reconstruction, compare the grid load with the grid load predicted by the neural network load prediction module, judge the energy saving and loss reduction effect, and output the judgment result to the grid terminal.

Images