Big data analysis auxiliary power grid intelligent decision-making system and method

Abstract

The invention provides a big data analysis auxiliary power grid intelligent decision-making system and method. The method comprises the steps of monitoring real-time data in a power generation end of a power distribution network and a plurality of power supply lines in real time; performing data interpolation, abnormal value processing and data standardization preprocessing on the acquired data; calculating a phase angle between the power generation end of the power distribution network and the power supply line; calculating real-time voltage and real-time current between the power generation end of the power distribution network and the power supply line before the short-circuit fault occurs; constructing a transient balance equation after a short circuit occurs between the power generation end of the power distribution network and the power supply line, and solving a three-phase transient real-time current between the power generation end and the power supply line in a transient state after the short circuit occurs; and judging whether the three-phase current of the power distribution network is in respective short-circuit transient allowable threshold ranges or not so as to control whether to send a warning notification to a maintainer or not. According to the method, the big data technology is combined with deep learning and machine learning, so that accurate prediction and fault diagnosis and early warning of the power grid operation state are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart grids, and specifically relates to a big data analysis-assisted smart grid decision-making system and method. Background Art

[0002] With the increasing dependence of modern society on electricity and the continuous improvement of electricity quality, efficiency and safety, the power system is facing higher requirements and greater pressure. The traditional power system faces many challenges, such as imbalance between power supply and demand, energy waste, environmental pollution and other problems, and it is urgent to introduce advanced information and intelligent technologies to solve them.

[0003] Distribution network faults are mainly divided into short circuit faults and line break faults. Short circuit faults mainly refer to the direct connection between phases and between phases and the earth, which is a lateral fault. The main causes of short circuit faults are insulation damage of conductors, unpredictable natural damage, misoperation, etc. Short circuits can cause arc high temperatures at the short circuit point to burn out the equipment. The temperature increase caused by the thermal effect of the short circuit current accelerates insulation aging and even burns out the equipment. Short circuits can also cause the voltage of the distribution network to drop significantly, affecting the operation of electrical equipment. However, in the prior art, there is a lack of big data analysis-assisted intelligent decision-making methods and systems for power grids that can simultaneously predict the occurrence of short circuit faults on multiple lines in the distribution network and determine whether maintenance personnel need to arrive at the site immediately for maintenance. Summary of the invention

[0004] In view of the above-mentioned defects, the present invention provides a big data analysis-assisted power grid intelligent decision-making system and method. The big data analysis-assisted power grid intelligent decision-making system and method provided by the present invention combines big data technology with deep learning and machine learning. The system can process huge data sets and extract useful information from them, thereby realizing accurate prediction of power grid operation status and fault diagnosis and early warning.

[0005] The present invention provides the following technical solution: a big data analysis-assisted power grid intelligent decision-making method, the method is applicable to a distribution network with three-phase alternating current as a power generation end, the power supply capacity of the power generation end is infinite, the impedance of the power supply line between the power generation end and the power load and the two is zero, and the terminal voltage remains unchanged before and after a short circuit fault occurs; the method comprises the following steps:

[0006] S1. Real-time monitoring of real-time data in the power generation end of the distribution network and multiple power supply lines;

[0007] S2, perform data interpolation, outlier processing and data standardization preprocessing on the collected data;

[0008] S3, obtaining corresponding data from the data preprocessed in step S2, and calculating the phase angle Φ between the power generation end of the distribution network and the power supply line k,q; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current i k,p ;

[0009] S4, constructing a transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solving the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs;

[0010] S5, according to the return impedance angle when the distribution network is in a transient state after a short circuit fault occurs Determine whether the three-phase currents of the distribution network are within their respective short-circuit transient allowable thresholds, and then control whether to issue a warning notice to the maintenance personnel.

[0011] Furthermore, the step S2 includes the following steps:

[0012] S21, real-time monitoring of the voltage amplitude A between the kth power generation end and the qth power supply line of the distribution network k,q , construct the voltage amplitude data set matrix X:

[0013] p is the total number of generating terminals; all elements in X form the distribution network voltage amplitude data set Y;

[0014] S22. Construct data interpolation function A i，j :

[0015]

[0016] e-1∈{1, 2,...,p}, e+1∈{1, 2,...,p}, g-1∈{1, 2,...,q}, g+1∈{1, 2,...,q},

[0017] S23, the step S22 is performed through the data interpolation function A e,g The voltage amplitude A between the e-th generating terminal and the g-th power supply line is obtained e，g Add to the distribution network voltage amplitude data set Y formed in step S21 to form a distribution network generation end voltage amplitude interpolation data set Y′;

[0018] S24, performing wavelet transform on each element in the data set Y′ after interpolation of the voltage amplitude at the generating end of the distribution network obtained in step S23, and obtaining the wavelet transform A at time t in the frequency domain k，q (t):

[0019] S25, constructing a wavelet transform noise removal threshold function, removing the wavelet transform A in the frequency domain of each element in the data set Y′ after the voltage amplitude interpolation at the power generation end of the distribution network.k，q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y″.

[0020] Furthermore, the step S24 includes the following steps:

[0021] S241, the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the obtained distribution network power generation terminal voltage amplitude interpolation data set Y′ k，q [n], after the discrete time Fourier transform of the digital filter, the filtering result h(n) is obtained: N is the signal length;

[0022] Among them, DTFT{A k，q [n]} is the voltage amplitude A between the kth generating terminal and the qth power supply line k,q [n] Perform discrete-time Fourier transform, 2πf A is the angular frequency of the discrete-time signal h(n), f A is the frequency of the discrete-time signal h(n);

[0023] S242, construct the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the distribution network power generation terminal voltage amplitude interpolation data set Y′ k,q [n] Wavelet transform in frequency domain A k，q (t) is the mother wavelet σ(t) and the father wavelet ψ r (t):

[0024]

[0025] Where r is the total number of wavelet transforms; h r (n) is the voltage amplitude A between the kth generation terminal and the qth power supply line at discrete time n in the distribution network voltage amplitude data set Y by the digital filter k,q [n] Perform the rth filtering result;

[0026] S243, translate the mother wavelet and the father wavelet and perform scale transformation on the translated father wavelet:

[0027] σ l (t) = σ(tl);

[0028] ψ r，b，l (t) = ψ r (2 b tl);

[0029] Among them, l is a fixed translation factor, b is a fixed scale factor; σ l(t) is the result of mother wavelet translation, ψ r，b,l (t) is the result of scaling after the parent wavelet is translated;

[0030] S244, according to the mother wavelet and the father wavelet model constructed in step S242, the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the data set Y′ after the voltage amplitude interpolation of the power generation terminal of the distribution network k，q [n] Perform complete wavelet expansion to obtain the wavelet transform A at time t in the frequency domain k，q (t):

[0031]

[0032] Among them, γ(l) is the mother wavelet deformation coefficient of wavelet transform, ∈ r (b, l) are the deformation coefficients of the parent wavelet.

[0033] Furthermore, the wavelet transform noise removal threshold function constructed in step S25 is as follows:

[0034] S251, transform the wavelet transform A at time t in the frequency domain obtained in step S244 k,q Take the absolute value of each element in (t), sort them in ascending order, and then square them to get the wavelet transform A in the frequency domain at time t in the T time slot in the frequency domain k，q (t) recombination signal sequence: f(A k,q (t))=(sort| T (|A k，q (t)|)) 2 , where |A k，q (t)| is A k，q The absolute value of (t), sort| T (|A k，q (t)|) is the wavelet transform A at time t in the frequency domain within the T time slot in the frequency domain k，q (t) The absolute value results are sorted in ascending order from small to large; t = 1, 2, ..., T; each moment in the T time slot in the frequency domain and the discrete time signal length N in the step S21

[0035] S252, calculate the noise removal threshold of the wavelet transform at time t in the frequency domain:

[0036]

[0037] S253, calculating the risk coefficient function of the noise removal threshold of the wavelet transform in the frequency domain at time t obtained in S252;

[0038]

[0039] S254: The risk coefficient function obtained in step S253 is a concave function in the frequency domain, and the time t at which the risk coefficient function value is the minimum is taken. min , calculate t min The noise removal threshold of the wavelet transform in the frequency domain at time t As the wavelet transform noise removal threshold, the wavelet transform A in the frequency domain of each element in the data set Y′ after removing the voltage amplitude interpolation at the generation end of the distribution network is k，q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y″.

[0040] Furthermore, the S3 step includes the following steps:

[0041] S31, extracting the voltage amplitude value A of the voltage between the kth power generation terminal and the qth power supply line of the distribution network before the short circuit occurs in real time from the preprocessed data set k，q As sample data, calculate the phase angle Φ between the kth generating end of the distribution network and the qth power supply line before the short-circuit fault occurs. k，q :

[0042]

[0043] Among them, R k，q is the total resistance between the kth generating terminal and the qth power supply line, L k，q is the total inductance between the kth generating terminal and the qth power supply line; is the total resistance of the load that receives power from the kth generating terminal through the qth power supply line in the distribution network, is the total inductance of the load that receives power from the kth generating terminal through the qth power supply line in the distribution network;

[0044] S32, calculate the real-time voltage u between the kth generating terminal and the qth power supply line before the short-circuit fault occurs k，p :

[0045] u k，p =A k,q sin(ωt+δ k，p );

[0046] Where, ω is the sinusoidal frequency of the three-phase power supply; δ k，p is the sinusoidal phase between the kth generating terminal and the qth power supply line before the short-circuit fault occurs;

[0047] S33, calculating the real-time current i between the kth generating terminal and the qth power supply line before the short-circuit fault occurs:

[0048]

[0049] Among them, AI is the current amplitude between the kth generating terminal and the qth power supply line before the short circuit occurs, is the comprehensive impedance of the kth generating terminal and the qth power supply line and the load thereon before the short circuit occurs;

[0050] Furthermore, the S4 step includes the following steps:

[0051] S41. The transient equilibrium equation constructed is as follows:

[0052]

[0053] in, is the total transient real-time current after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network;

[0054] S42. Calculate the current amplitude value in a transient state after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network

[0055]

[0056] S43. Calculate the return impedance angle between the kth generation terminal of the distribution network and the qth power supply line when the two are in a transient state after a short circuit fault occurs.

[0057]

[0058] S44. Calculate the current amplitude between the kth generating terminal and the qth power supply line caused by the short circuit fault of the distribution network Decay Index:

[0059]

[0060] k a , k b and k c They are respectively the A-phase current attenuation coefficient, the B-phase current attenuation coefficient and the C-phase current attenuation coefficient after a short-circuit fault occurs in the distribution network;

[0061] S45, solving the linear first-order non-homogeneous differential equation of step S41 to obtain the transient real-time current i of phase A after a short-circuit fault occurs in the distribution network sa 、B phase transient real-time current i sb and C phase transient real-time current i sc :

[0062]

[0063] Among them, θ Ia is the transient real-time current phase offset angle of phase A, θ Ib is the transient real-time current phase offset angle of phase B, θ Ic is the transient real-time current phase offset angle of phase C,

[0064] Furthermore, the judgment criterion in step S5 is that when θ Io = ±90°, the instantaneous real-time current of phase o after a short-circuit fault occurs in the distribution network calculated in step S45 is the instantaneous maximum threshold value i of phase o. so，max ; When θ Io =0° or 180°, the transient real-time current of phase O calculated in step / 45 after a short-circuit fault occurs in the distribution network is the transient real-time current of phase A is the transient minimum threshold value i of phase A. so，min ; Wherein, o is a, b or c;

[0065] The transient real-time current i of phase o after a short-circuit fault occurs in the distribution network so In i so，min ≤i so <i so，max When the fault occurs, it is determined that the distribution network is within the safe life span that allows faults to occur.

[0066] The present invention also provides a big data analysis-assisted power grid intelligent decision-making system using the above method, including a power grid data acquisition module, a data preprocessing module, a pre-fault voltage and current calculation module, a three-phase transient real-time current calculation module and a fault prediction module;

[0067] The power grid data acquisition module is used to monitor the real-time data of the power generation end of the distribution network and multiple power supply lines;

[0068] Data preprocessing module, used for data interpolation, outlier processing and data standardization preprocessing of the collected data;

[0069] The pre-fault voltage and current calculation module is used to obtain the corresponding data from the pre-processed data in step S2 and calculate the phase angle Φ between the power supply line and the power supply end of the distribution network. k,q ; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current i k,p ;

[0070] The three-phase transient real-time current calculation module is used to construct the transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solve the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs;

[0071] The fault prediction module is used to predict the return impedance angle of the distribution network in a transient state after a short circuit fault occurs. Determine whether the three-phase currents of the distribution network are within their respective short-circuit transient allowable thresholds, and then control whether to issue a warning notice to the maintenance personnel.

[0072] The present invention also provides an electronic computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the above-mentioned big data analysis-assisted power grid intelligent decision-making method when executing the computer program.

[0073] The present invention also provides a storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of big data analysis assisting intelligent decision-making of the power grid are implemented as described above.

[0074] The beneficial effects of the present invention are:

[0075] 1. The present invention obtains data information such as voltage and current in the distribution network in real time, uses big data analysis to interpolate and supplement missing values, and further uses the joint processing of mother wavelet and father wavelet to remove noise. After the big data processing after data standardization preprocessing, the cloud big data is obtained again to build and combine deep learning and machine learning to build a transient analysis model of the power grid three-phase short-circuit fault. It can accurately analyze massive data and find that after a three-phase short-circuit fault in the distribution network occurs, it is necessary to immediately cut off the generator at the power generation end or quickly dispatch maintenance personnel for maintenance within the safe life time range of the distribution network power supply line, quickly identify abnormal situations, and take corresponding measures in time.

[0076] 2. The present invention utilizes information technology and intelligent technology to perform remote monitoring, fault diagnosis, and predictive analysis of the distribution network based on smart meters, thereby improving the safety, reliability, and efficiency of the power system.

[0077] 3. Compared with traditional monitoring methods that can only provide analysis of historical data, the present invention relies on big data technology to collect data in real time and further clean and standardize the data to monitor the operation status of the distribution network in real time. In addition, traditional monitoring methods can usually only provide monitoring of some indicators, while big data technology can comprehensively consider the data of all links in the whole life cycle before and after the failure occurs, providing comprehensive support for intelligent operation optimization and management decision-making.

[0078] 4. The present invention can realize data collection, transmission, cloud storage, processing and analysis of the power system through intelligent algorithms, artificial intelligence and other means, effectively optimize the operation and management of the power system, and improve the reliability, availability and economy of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] The present invention will be described in more detail below based on embodiments and with reference to the accompanying drawings, wherein:

[0080] Figure 1 A schematic diagram of the process flow of the big data analysis-assisted power grid intelligent decision-making method provided by the present invention;

[0081] Figure 2 This is a schematic diagram of the structure of the big data analysis-assisted power grid intelligent decision-making system provided by the present invention. DETAILED DESCRIPTION

[0082] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0083] The present invention provides a method for assisting intelligent decision-making of power grids with big data analysis. The method is applicable to a distribution network with three-phase alternating current as a power generation end, the power supply capacity of the power generation end is infinite, the impedance of the power supply line between the power generation end and the power load and the two is zero (the motor at the power generation end and the load at the power consumption end still have impedance formed by resistance and inductance), and the terminal voltage remains unchanged before and after a short-circuit fault occurs; the power generation end is a generator that generates three-phase alternating current;

[0084] like Figure 1 As shown, the big data analysis-assisted power grid intelligent decision-making method provided by the present invention includes the following steps:

[0085] S1. Real-time monitoring of real-time data in the power generation end of the distribution network and multiple power supply lines; preferably, this step is implemented by an AMI smart meter equipped at the power consumption end of each power supply line;

[0086] S2, perform data interpolation, outlier processing and data standardization preprocessing on the collected data;

[0087] S3, obtain the corresponding data from the data preprocessed in step S2, and calculate the phase angle Φ between the power generation end of the distribution network and the power supply line k,q ; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current i k,p ;

[0088] S4, constructing a transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solving the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs;

[0089] S5, according to the return impedance angle when the distribution network is in a transient state after a short circuit fault occurs Determine whether the three-phase current of the distribution network is within the respective short-circuit transient allowable threshold range. If so, the generator and power supply line of the distribution network are within the safe life span that allows faults to occur, waiting for the arrival of maintenance personnel. If not, it may lead to safety accidents such as fire and explosion, and then control whether to issue a warning notice to the maintenance personnel.

[0090] Various data in the power system are collected in real time through various sensors and monitoring equipment, covering key indicators such as current, voltage, and load. These data are stored in the database in a high-speed, large-capacity manner for subsequent processing and analysis. Therefore, in order to subsequently construct a short-circuit fault alarm model and make the safety life prediction of the entire distribution network power supply line and the power generation end more accurate, it is necessary to use data cleaning and preprocessing technology obtained by real-time monitoring in step S1 to ensure the data quality and accuracy used to construct the distribution network short-circuit fault model. Therefore, as a preferred embodiment of the present invention, step S2 includes the following steps:

[0091] S21, real-time monitoring of the voltage amplitude A between the kth power generation end and the qth power supply line of the distribution network k,q , construct the voltage amplitude data set matrix X:

[0092] p is the total number of generating terminals; all elements in X form the distribution network voltage amplitude data set Y;

[0093] S22. Due to various reasons, the recorded data often has missing values. Some relevant reasons include hardware failure, storage problems, unplanned maintenance, unreliable measurement data transmission and data corruption. Therefore, construct a data interpolation function A e，g :

[0094]

[0095] e-1∈{1, 2,...,p}, e+1∈{1, 2,...,p}, g-1∈{1, 2,...,q}, g+1∈{1, 2,...,q},

[0096] S23, step S22 is performed through the data interpolation function A e，g The voltage amplitude A between the e-th generating terminal and the g-th power supply line is obtained e，g Add to the distribution network voltage amplitude data set Y formed in step S21 to form a distribution network generation end voltage amplitude interpolation data set Y′;

[0097] S24, performing wavelet transform on each element of the data set Y′ after interpolation of the voltage amplitude at the generating end of the distribution network obtained in step S23, and obtaining the wavelet transform A at time t in the frequency domain k，q (t):

[0098] S25, constructing a wavelet transform noise removal threshold function, removing the wavelet transform A in the frequency domain of each element in the data set Y′ after the voltage amplitude interpolation at the power generation end of the distribution network. k,q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y″.

[0099] Through steps S21-S22, the missing voltage amplitude value A between the e-th power generation terminal and the g-th power supply line is first calculated. e，g According to the four points with it as the center point: the voltage amplitude value A between the e-1th generating terminal and the g-1th power supply line e-1，g-1 , the voltage amplitude value A between the e-1th generating terminal and the g+1th power supply line e-1，g+1 , the voltage amplitude value A between the e+1th generating terminal and the g-1th power supply line e+1，g-1 and the voltage amplitude value A between the e+1th generating end and the g+1th power supply line e+1，g+1 Calculate and obtain the voltage amplitude value A between the e-th point break and the g-th power supply line to be interpolated e，g , to integrate the data and ensure that there will be no defects such as inaccurate prediction results of the training model caused by data breakpoints and missing data during subsequent data analysis and modeling.

[0100] Since various conditions may occur during the data collection process of step S1, and the occurrence of harmonics caused by the mutual electromagnetic interaction of the power grid during the power transmission process may interfere with the noise of the interference-free data required for the subsequent model establishment, it is necessary to pre-process it, remove abnormal values, and then obtain standardized data of the prediction model that can accurately predict whether a short-circuit fault in the distribution network needs to be alarmed and immediately dispatch maintenance personnel. Therefore, as another preferred embodiment of the present invention, step S24 includes the following steps:

[0101] S241, the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the obtained distribution network power generation terminal voltage amplitude interpolation data set Y′ k，q [n], after the discrete time Fourier transform of the digital filter, the filtering result h(n) is obtained: N is the signal length;

[0102] Among them, DTFT{A k，q [n]} is the voltage amplitude A between the kth generating terminal and the qth power supply line k,q[n] Perform discrete-time Fourier transform, 2πf A is the angular frequency of the discrete-time signal h(n), f A is the frequency of the discrete-time signal h(n);

[0103] S242, construct the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the distribution network power generation terminal voltage amplitude interpolation data set Y′ k,q [n] Wavelet transform in frequency domain A k，q (t) is the mother wavelet σ(t) and the father wavelet ψ r (t):

[0104]

[0105] Where r is the total number of wavelet transforms; h r (n) is the voltage amplitude A between the kth generation terminal and the qth power supply line at discrete time n in the distribution network voltage amplitude data set Y by the digital filter k，q [n] Perform the rth filtering result;

[0106] S243, translate the mother wavelet and the father wavelet and perform scale transformation on the translated father wavelet:

[0107] σ l (t) = σ(tl);

[0108] ψ r，b，l (t) = ψ r (2 b tl);

[0109] Among them, l is a fixed translation factor, b is a fixed scale factor; σ l (t) is the result of mother wavelet translation, ψ r，b,l (t) is the result of scaling after the parent wavelet is translated;

[0110] S244, according to the model of the mother wavelet and the father wavelet constructed in step S242, the voltage amplitude A between the kth generating terminal and the qth power supply line at discrete time n in the data set Y′ after the voltage amplitude interpolation of the generating terminal of the distribution network k,q [n] Perform complete wavelet expansion to obtain the wavelet transform A at time t in the frequency domain k，q (t):

[0111]

[0112] Among them, γ(l) is the mother wavelet deformation coefficient of wavelet transform, ∈ r (b, l) are the deformation coefficients of the parent wavelet.

[0113] Fault detection in power systems is an important part of ensuring safe operation of the system. Compared with the traditional fault detection method which mainly relies on frequency domain analysis and has poor detection effect on transient faults, this application constructs a mother wavelet σ(t) through step S242 and performs a translation of I on the mother wavelet, σ l (t) The pre-processed voltage amplitude value is translated and passed through the parent wavelet ψ r (t), and then after the dual effects of translation factor and scale factor, ψ r，b,l (t) The pre-processed voltage amplitude value is simultaneously translated and scaled to extract the low-frequency information in the signal; through the father wavelet covering the entire signal domain and the mother wavelet capturing the local changes of the signal, they are interrelated and complemented to achieve the two-dimensional transformation of the discrete waveform signal, and finally obtain the wavelet transform A at time t in the frequency domain representing the approximate low-frequency signal and the detailed high-frequency signal at different resolutions k，q (t), using the wavelet transform A at time t in the frequency domain k,q (t) Constructing short-circuit fault analysis has good time domain resolution and can more accurately capture the characteristics of transient faults. Compared with the traditional Fourier transform, the present invention performs discrete time decomposition on the current waveform data collected in step S1 after discrete Fourier time transform, and then decomposes the collected voltage and current waveform signals through simultaneous two-dimensional transformation of the mother wavelet and the father wavelet. The instantaneous change or high-frequency noise of the waveform signal can be identified through the high-frequency sub-signal and then the high-frequency noise can be proposed. The low-frequency sub-signal obtained by the transformation and filtering of the father wavelet can obtain the slow change or basic trend of the waveform signal. Then, after the present invention is processed by steps S241-S244, features are extracted from the decomposed sub-signal, which has better local characteristics and can more accurately describe the transient characteristics of the signal. The noise is removed according to the extracted features, which is conducive to the subsequent analysis and evaluation of the distribution network short-circuit fault. The accuracy of the constructed model can be improved, and the noise in the signal can be effectively removed while retaining the key features of the signal.

[0114] Furthermore, the wavelet transform noise removal threshold function constructed in step S25 is as follows:

[0115] S25 1. Transform the frequency domain obtained in step S244 at time t into the wavelet transform A k , take the absolute value of each element in q(t), sort them in ascending order and square them, and get the wavelet transform A in the frequency domain at time t in the frequency domain within the T time slot k , q(t) recombination signal sequence: f(A k，q (t))=(sort| T (|A k，q (t)|)) 2 , where |A k，q(t)| is A k，q The absolute value of (t), sort| T (|A k，q (t)|) is the wavelet transform A at time t in the frequency domain within the T time slot in the frequency domain k , q(t) absolute value results are sorted in ascending order from small to large; t = 1, 2, ..., T; each moment in the T time slot in the frequency domain and the discrete time signal length N in step S21

[0116] S252, calculate the noise removal threshold of the wavelet transform at time t in the frequency domain:

[0117]

[0118] S253, calculating the risk coefficient function of the noise removal threshold of the wavelet transform at time t in the frequency domain obtained in S252;

[0119]

[0120] The risk coefficient function obtained in steps S254 and S253 is a concave function in the frequency domain. The time t at which the risk coefficient function value is the minimum is taken. min , calculate t min The noise removal threshold of the wavelet transform in the frequency domain at time t As the wavelet transform noise removal threshold, the wavelet transform A in the frequency domain of each element in the data set Y′ after removing the voltage amplitude interpolation at the generation end of the distribution network is k，q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y″.

[0121] The key technologies of smart grid monitoring based on big data analysis are the cornerstone of the intelligent development of power grids. Through the improvement and optimization of data collection, cleaning, mining, analysis, visualization and decision support, all-round monitoring and management of the power grid operation status can be achieved. The application of these key technologies will greatly improve the efficiency, reliability and security of power grid management, and promote the power industry to a new level of intelligence and digitization.

[0122] After a short circuit fault occurs, the three-phase AC power supply line is equivalent to a full three-phase grounding at the load power consumption end. Therefore, a transient state different from the normal state when no fault occurs occurs. The resistance and inductance of the load at the power consumption end of the power supply line are equivalent to 0. At this time, the three-phase current of the generator at the power generation end changes phase, and then the three-phase current value also changes. It is necessary to determine whether the transient instantaneous maximum value of the three-phase current is within the safe life threshold range that ensures that the power grid can wait for a period of time before maintenance, and then choose whether to issue a warning to the remote central control room, choose to immediately perform remote control to cut off the continued operation of the main power generation end, or immediately dispatch nearby maintenance personnel to perform immediate maintenance. Therefore, as another preferred embodiment of the present invention, step S3 includes the following steps:

[0123] S31, extracting the voltage amplitude value A of the voltage between the kth power generation terminal and the qth power supply line of the distribution network before the short circuit occurs in real time from the preprocessed data set (i.e., the reconstructed distribution network power generation terminal voltage amplitude denoised signal data set Y″ obtained in step S25) k，q As sample data, calculate the phase angle Φ between the kth generating end of the distribution network and the qth power supply line before the short-circuit fault occurs. k，q :

[0124]

[0125] Among them, R k，q is the total resistance between the kth generating terminal and the qth power supply line, L k，q is the total inductance between the kth generating terminal and the qth power supply line; is the total resistance of the load that receives power from the kth generating terminal through the qth power supply line in the distribution network, is the total inductance of the load receiving power from the kth generating end through the qth power supply line in the distribution network; the generating end is a generator generating three-phase alternating current;

[0126] S32, calculate the real-time voltage u between the kth generating terminal and the qth power supply line before the short-circuit fault occurs k，p :

[0127] u k，p =A k，q sin(ωt+δ k，p );

[0128] Where, ω is the sinusoidal frequency of the three-phase power supply; δ k，p is the sinusoidal phase between the kth generating terminal and the qth power supply line before the short-circuit fault occurs;

[0129] S33, calculating the real-time current i between the kth generating terminal and the qth power supply line before the short-circuit fault occurs:

[0130]

[0131] Among them, A I is the current amplitude between the kth generating terminal and the qth power supply line before the short circuit occurs, is the comprehensive impedance of the kth generating terminal and the qth power supply line and the load thereon before the short circuit occurs;

[0132] 6. The method for assisting power grid intelligent decision-making with big data analysis according to claim 5, characterized in that step S4 comprises the following steps:

[0133] S41. The transient equilibrium equation constructed is as follows:

[0134]

[0135] in, is the total transient real-time current after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network;

[0136] S42. Calculate the current amplitude value in a transient state after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network

[0137] Since the qth power supply line is in a three-phase grounding state after a three-phase short circuit occurs, the resistance and inductance on the qth power supply line are equivalent to 0;

[0138] S43. Calculate the return impedance angle between the kth generation terminal of the distribution network and the qth power supply line when the two are in a transient state after a short circuit fault occurs.

[0139]

[0140] S44. Calculate the current amplitude between the kth generating terminal and the qth power supply line caused by the short circuit fault of the distribution network Decay Index:

[0141]

[0142] k a , k b and k c They are respectively the A-phase current attenuation coefficient, the B-phase current attenuation coefficient and the C-phase current attenuation coefficient after a short-circuit fault occurs in the distribution network;

[0143] S45, solve the linear first-order non-homogeneous differential equation in step S41 to obtain the transient real-time current i of phase A after a short-circuit fault occurs in the distribution network sa、B phase transient real-time current i sb and C phase transient real-time current i sc :

[0144]

[0145] Among them, θ Ia is the transient real-time current phase offset angle of phase A, θ Ib is the transient real-time current phase offset angle of phase B, θ Ic is the transient real-time current phase offset angle of phase C,

[0146] The judgment criterion in step S5 is that when θ Io = ±90°, the distribution network calculated in step S45 will have a short circuit fault. The real-time transient current of the phase o is the maximum transient threshold i so，max ; When θ Io =0° or 180°, the transient real-time current of phase o after the short-circuit fault of the distribution network calculated in step S45 is the transient real-time current of phase A and the transient minimum threshold value i of phase A. so，min ; Wherein, o is a, b or c;

[0147] The transient real-time current i of phase o after a short-circuit fault occurs in the distribution network so In i so，min ≤i so <i so，max When the fault occurs, it is determined that the distribution network is within the safe life span that allows faults to occur.

[0148] That is, for the transient real-time current i of phase A after a short-circuit fault occurs in the distribution network sa , when δ k，p -Φ Is = ±90°, the transient real-time current of phase A after a short-circuit fault occurs in the distribution network calculated in step S45 is the maximum transient threshold value i of phase A. sa，max ; When δ k，p -Φ Is =0° or 180°, the transient real-time current of phase A after a short-circuit fault occurs in the distribution network calculated in step S45 is the minimum transient threshold value i of phase A. sa，min ;

[0149] For the transient real-time current i of phase B after a short-circuit fault in the distribution network sb , when δ k,p -Φ Is When -120°=±90°, the transient real-time current of phase B after a short-circuit fault occurs in the distribution network calculated in step S45 is the maximum transient threshold value i of phase B. sb,max ; When δ k,p-Φ Is When -120°=0° or 180°, the transient real-time current of phase B after a short-circuit fault occurs in the distribution network calculated in step S45 is the minimum transient threshold value i of phase B. sb,min ;

[0150] For the transient real-time current i of phase C after a short-circuit fault in the distribution network sc , when δ k，p -Φ Is When +120°=±90°, the transient real-time current of phase C after a short-circuit fault occurs in the distribution network calculated in step S45 is the maximum transient threshold value i of phase C. sc，max ; When δ k,p -Φ Is When +120°=0° or 180°, the transient real-time current of phase C after a short-circuit fault occurs in the distribution network calculated in step S45 is the minimum transient threshold value i of phase C. sc,min ;

[0151] The transient real-time current i of phase A after a short-circuit fault occurs in the distribution network sa , the transient real-time current of phase B and the transient real-time current of phase C are respectively in i sa，min ≤i sa <i sa，max 、i sb,min ≤i sb <i sb,max and i sc,min ≤i sc <i sc，max When the fault occurs, it is determined that the distribution network is within the safe life span that allows faults to occur.

[0152] like Figure 2 As shown, the big data analysis-assisted power grid intelligent decision-making system provided by the present invention adopts the above-mentioned method, including a power grid data acquisition module, a data preprocessing module, a pre-fault voltage and current calculation module, a three-phase transient real-time current calculation module and a fault prediction module;

[0153] A power grid data acquisition module, used for real-time monitoring of real-time data in the power generation end of the distribution network and multiple power supply lines; preferably, the power grid data acquisition module is an AMI smart meter equipped at the power consumption end of each power supply line;

[0154] Data preprocessing module, used for data interpolation, outlier processing and data standardization preprocessing of the collected data;

[0155] The pre-fault voltage and current calculation module is used to obtain the corresponding data from the pre-processed data in step S2 and calculate the phase angle Φ between the power supply line and the power supply end of the distribution network. k,q ; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current ik,p ;

[0156] The three-phase transient real-time current calculation module is used to construct the transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solve the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs;

[0157] The fault prediction module is used to predict the return impedance angle of the distribution network in a transient state after a short circuit fault occurs. Determine whether the three-phase current of the distribution network is within the respective short-circuit transient allowable threshold range. If so, the generator and power supply line of the distribution network are within the safe life span that allows faults to occur, waiting for the arrival of maintenance personnel. If not, it may lead to safety accidents such as fire and explosion, and then control whether to issue a warning notice to the maintenance personnel.

[0158] The memory stores a computer program that can be run by at least one processor, and the computer program is executed by at least one processor so that at least one processor can execute the above-mentioned big data analysis-assisted power grid intelligent decision-making method. The electronic device provided in this embodiment can be a personal computer, such as a desktop computer, an all-in-one computer, a laptop computer, a tablet computer, etc., and can also be a terminal device such as a mobile phone, a wearable device, a handheld computer, etc. The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0159] Components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one memory mentioned above, and a bus connecting different system components (including the memory and the processor).

[0160] The bus includes data bus, address bus and control bus.

[0161] The memory may include volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0162] The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0163] The processor executes various functional applications and data processing by running computer programs stored in the memory, such as the above-mentioned big data analysis-assisted power grid intelligent decision-making method.

[0164] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. Other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0165] The present embodiment also provides a computer storage medium, which stores a computer program, and the method described above can be implemented when the processor executes the computer program. Computer-readable media can be considered to be tangible and non-temporary. Non-limiting examples of non-temporary tangible computer-readable media include non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits or mask read-only memory circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital tapes or hard drives) and optical storage media (such as CDs, DVDs or Blu-ray discs), etc. The computer program includes processor executable instructions stored on at least one non-temporary tangible computer-readable medium. The computer program may also include or rely on stored data. The computer program may include a basic input / output system (BIOS) that interacts with the hardware of a special-purpose computer, a device driver that interacts with a specific device of a special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.

[0166] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0167] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

Claims

1. A method for intelligent decision-making of power grid assisted by big data analysis, the method is applicable to a distribution network with three-phase alternating current as the generating end, the power supply capacity of the generating end is infinite, the impedance of the power supply line between the generating end and the power load and the two is zero, and the terminal voltage remains unchanged before and after the short circuit fault occurs; characterized in that: The method comprises the following steps: S1. Real-time monitoring of real-time data in the power generation end of the distribution network and multiple power supply lines; S2, perform data interpolation, outlier processing and data standardization preprocessing on the collected data; S3, obtaining corresponding data from the data preprocessed in step S2, and calculating the phase angle Φ between the power generation end of the distribution network and the power supply line k,q ; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current i k,p ; S4, constructing a transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solving the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs; S5, according to the return impedance angle when the distribution network is in a transient state after a short circuit fault occurs Determine whether the three-phase currents of the distribution network are within their respective short-circuit transient allowable thresholds, and then control whether to issue a warning notification to the maintenance personnel.

2. The method for assisting power grid intelligent decision-making by big data analysis according to claim 1 is characterized in that: The S2 step includes the following steps: S21, real-time monitoring of the voltage amplitude A between the kth power generation end and the qth power supply line of the distribution network k,q , construct the voltage amplitude data set matrix X: k=1,2,…,p; p is the total number of generating terminals; all elements in X form the distribution network voltage amplitude data set Y; S22. Construct data interpolation function A e,g : S23, the step S22 is performed through the data interpolation function A e,g The voltage amplitude A between the e-th generating terminal and the g-th power supply line is obtained e,g Add to the distribution network voltage amplitude data set Y formed in step S21 to form a distribution network generation end voltage amplitude interpolation data set Y'; S24, performing wavelet transform on each element in the data set Y' after interpolation of the voltage amplitude at the generating end of the distribution network obtained in step S23, and obtaining the wavelet transform A at time t in the frequency domain k,q (t): S25, constructing a wavelet transform noise removal threshold function, removing the wavelet transform A in the frequency domain of each element in the data set Y' after the voltage amplitude interpolation at the power generation end of the distribution network. k,q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y''.

3. The method for assisting power grid intelligent decision-making by big data analysis according to claim 2 is characterized in that: The step S24 comprises the following steps: S241, the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the obtained distribution network power generation terminal voltage amplitude interpolation data set Y' k,q [n], after the discrete time Fourier transform of the digital filter, the filtering result h(n) is obtained: N is the signal length; Among them, DTFT{A k,q [n]} is the voltage amplitude A between the kth generating terminal and the qth power supply line k,q [n] Perform discrete-time Fourier transform, 2πf A is the angular frequency of the discrete-time signal h(n), f A is the frequency of the discrete-time signal h(n); S242, construct the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the distribution network power generation terminal voltage amplitude interpolation data set Y' k,q [n] Wavelet transform in frequency domain A k,q (t) is the mother wavelet σ(t) and the father wavelet ψ r (t): Where r is the total number of wavelet transforms; h r (n) is the voltage amplitude A between the kth generation terminal and the qth power supply line at discrete time n in the distribution network voltage amplitude data set Y by the digital filter k,q [n] Perform the rth filtering result; S243, translate the mother wavelet and the father wavelet and perform scale transformation on the translated father wavelet: s l (t)=σ(tl); ψ r,b,l (t)=ψ r (2 b tl); Among them, l is a fixed translation factor, b is a fixed scale factor; σ l (t) is the result of mother wavelet translation, ψ r,b,l (t) is the result of scaling after the parent wavelet is translated; S244, according to the mother wavelet and the father wavelet model constructed in step S242, the voltage amplitude A between the kth power generation terminal and the qth power supply line at discrete time n in the data set Y' after the voltage amplitude interpolation of the power generation terminal of the distribution network k,q [n] Perform complete wavelet expansion to obtain the wavelet transform A at time t in the frequency domain k,q (t): Among them, γ(l) is the mother wavelet deformation coefficient of wavelet transform, ∈ r (b,l) is the deformation coefficient of the parent wavelet.

4. The method for assisting power grid intelligent decision-making by big data analysis according to claim 3 is characterized in that: The wavelet transform noise removal threshold function constructed in step S25 is as follows: S251, transform the wavelet transform A at time t in the frequency domain obtained in step S244 k,q Take the absolute value of each element in (t), sort them in ascending order, and square them to get the wavelet transform A at time t in the frequency domain within the T time slot in the frequency domain. k,q (t) recombination signal sequence: f(A k,q (t))=(sort| T |A k,q (t)|)) 2 , where |A k,q (t)| is A k,q The absolute value of (t), sort| T (|A k,q (t)|) is the wavelet transform A at time t in the frequency domain within the T time slot in the frequency domain k,q (t) The absolute value results are sorted in ascending order; t = 1, 2, ..., T; each moment in the T time slot in the frequency domain and the discrete time signal length N in the step S21 S252, calculate the noise removal threshold of the wavelet transform at time t in the frequency domain: S253, calculating the risk coefficient function of the noise removal threshold of the wavelet transform in the frequency domain at time t obtained in S252; S254: The risk coefficient function obtained in step S253 is a concave function in the frequency domain, and the time t at which the risk coefficient function value is the minimum is taken. min , calculate t min The noise removal threshold of the wavelet transform in the frequency domain at time t As the wavelet transform noise removal threshold, the wavelet transform A in the frequency domain of each element in the data set Y' after removing the voltage amplitude interpolation at the power generation end of the distribution network is removed. k,q The noise signal of (t) is then subjected to inverse wavelet transform to obtain the reconstructed distribution network generation end voltage amplitude denoised signal data set Y''.

5. The method for assisting power grid intelligent decision-making by big data analysis according to claim 1 is characterized in that: The S3 step includes the following steps: S31, extracting the voltage amplitude value A of the voltage between the kth power generation terminal and the qth power supply line of the distribution network before the short circuit occurs in real time from the preprocessed data set k,q As sample data, calculate the phase angle Φ between the kth generating end of the distribution network and the qth power supply line before the short-circuit fault occurs. k,q : Among them, R k,q is the total resistance between the kth generating terminal and the qth power supply line, L k,q is the total inductance between the kth generating terminal and the qth power supply line; is the total resistance of the load that receives power from the kth generating terminal through the qth power supply line in the distribution network, is the total inductance of the load that receives power from the kth generating terminal through the qth power supply line in the distribution network; S32, calculate the real-time voltage u between the kth generating terminal and the qth power supply line before the short-circuit fault occurs k,p : you k,p =A k,q sin(ωt+δ k,p ); Where, ω is the sinusoidal frequency of the three-phase power supply; δ k,p is the sinusoidal phase between the kth generating terminal and the qth power supply line before the short-circuit fault occurs; S33, calculating the real-time current i between the kth generating terminal and the qth power supply line before the short-circuit fault occurs: Among them, A I is the current amplitude between the kth generating terminal and the qth power supply line before the short circuit occurs, is the comprehensive impedance of the kth generating terminal and the qth power supply line and the load thereon before the short circuit occurs; 6. The method for assisting power grid intelligent decision-making by big data analysis according to claim 5 is characterized in that: The S4 step includes the following steps: S41. The transient equilibrium equation constructed is as follows: in, is the total transient real-time current after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network; S42. Calculate the current amplitude value in a transient state after a short circuit occurs between the kth generating terminal and the qth power supply line of the distribution network S43. Calculate the return impedance angle between the kth generation terminal of the distribution network and the qth power supply line when the two are in a transient state after a short circuit fault occurs. S44. Calculate the current amplitude between the kth generating terminal and the qth power supply line caused by the short circuit fault of the distribution network Decay Index: k a , k b and k c They are respectively the A-phase current attenuation coefficient, the B-phase current attenuation coefficient and the C-phase current attenuation coefficient after a short-circuit fault occurs in the distribution network; S45, solving the linear first-order non-homogeneous differential equation of step S41 to obtain the transient real-time current i of phase A after a short-circuit fault occurs in the distribution network sa , B phase transient real-time current i sb and C phase transient real-time current i sc : Among them, θ Ia is the transient real-time current phase offset angle of phase A, θ Ib is the transient real-time current phase offset angle of phase B, θ Ic is the transient real-time current phase offset angle of phase C, 7. The method for assisting power grid intelligent decision-making by big data analysis according to claim 6 is characterized in that: The judgment criterion in step S5 is that when θ Io = ±90°, the instantaneous real-time current of phase o after a short-circuit fault occurs in the distribution network calculated in step S45 is the instantaneous maximum threshold value i of phase o. so,max ; When θ Io =0° or 180°, the transient real-time current of phase O calculated in step S45 after a short-circuit fault occurs in the distribution network is the transient real-time current of phase A is the transient minimum threshold value i of phase A. so,min ; Wherein, o is a, b or c; The transient real-time current i of phase o after a short-circuit fault occurs in the distribution network so In i so,min ≤i so so,max When the fault occurs, it is determined that the distribution network is within the safe life span that allows faults to occur.​ 8. A big data analysis-assisted power grid intelligent decision-making system using the method described in any one of claims 1 to 7, characterized in that: It includes a power grid data acquisition module, a data preprocessing module, a pre-fault voltage and current calculation module, a three-phase transient real-time current calculation module and a fault prediction module; The power grid data acquisition module is used to monitor the real-time data of the power generation end of the distribution network and multiple power supply lines; Data preprocessing module, used for data interpolation, outlier processing and data standardization preprocessing of the collected data; The pre-fault voltage and current calculation module is used to obtain the corresponding data from the pre-processed data in step S2 and calculate the phase angle Φ between the power supply line and the power supply end of the distribution network. k,q ; Calculate the real-time voltage u between the power supply line and the power supply end of the distribution network before the short-circuit fault occurs k,p , real-time current i k,p ; The three-phase transient real-time current calculation module is used to construct the transient balance equation after a short circuit occurs between the power generation end and the power supply line of the distribution network, and solve the three-phase transient real-time current between the power generation end and the power supply line in the transient state after the short circuit occurs; The fault prediction module is used to predict the return impedance angle of the distribution network in a transient state after a short circuit fault occurs. Determine whether the three-phase currents of the distribution network are within their respective short-circuit transient allowable thresholds, and then control whether to issue a warning notification to the maintenance personnel.

Images