CN114050613B - Online identification and tracing method and system for power grid voltage transient event - Google Patents
Online identification and tracing method and system for power grid voltage transient event Download PDFInfo
- Publication number
- CN114050613B CN114050613B CN202111435044.3A CN202111435044A CN114050613B CN 114050613 B CN114050613 B CN 114050613B CN 202111435044 A CN202111435044 A CN 202111435044A CN 114050613 B CN114050613 B CN 114050613B
- Authority
- CN
- China
- Prior art keywords
- transient event
- delta
- load
- voltage
- change rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000001052 transient effect Effects 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000013598 vector Substances 0.000 claims abstract description 27
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 230000008859 change Effects 0.000 claims description 79
- 230000006870 function Effects 0.000 claims description 41
- 238000003860 storage Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000007175 bidirectional communication Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/48—Controlling the sharing of the in-phase component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/50—Controlling the sharing of the out-of-phase component
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an online identification and tracing method and system of a power grid voltage transient event, wherein the method comprises the steps of acquiring real-time power data acquired at a power grid monitoring point; capturing a transient event based on real-time power data, and acquiring the duration time of the transient event and power parameters corresponding to the transient event; extracting transient event load characteristics, which comprise overall characteristics and local characteristics; determining key information area blocks of the overall features and the local features, and constructing feature vectors according to the features of the key information area blocks to serve as fingerprint features; based on the fingerprint characteristics of the load types corresponding to the transient event and fingerprint libraries corresponding to various loads, the load types corresponding to the current voltage transient event are identified, and the invention further comprises identification of a sag source. Aiming at the voltage transient event, the method realizes on-line monitoring and identification, effectively identifies the cause and source of the sag, and lays a foundation for the subsequent accurate and efficient establishment of measures.
Description
Technical Field
The invention belongs to the technical field of voltage sag, and particularly relates to an online identification and tracing method and system for a power grid voltage transient event.
Background
Voltage sag is the most common power quality problem in the industry, which refers to the phenomenon that the effective value of voltage suddenly drops and then quickly recovers. Most voltage sags are accidental emergency events, the occurrence frequency is high, and the accident reasons are not easy to find out. The voltage dip is more than 30% deep and less than 1 second in duration. Along with the improvement of the automation degree of a factory and the large-scale use of novel sensitive loads, when equipment is stopped due to disturbance of power supply voltage, serious stopping and production stopping losses are caused.
The traditional voltage sag management monitoring in the market mainly adopts a localized monitoring device, and the device can generally record and simply analyze and calculate the voltage sag of a monitoring point, does not identify the reason of the voltage sag, can not rapidly judge the reason of the fault and rapidly decide when the voltage sag is not realized, often causes the expansion of accidents, and causes larger loss to power grids and enterprises.
Disclosure of Invention
The invention aims at the identification of voltage sag reasons, namely the tracing problem of load types, and provides an online identification and tracing method and system of a power grid voltage transient event. The method disclosed by the invention has the advantages that the transient event is captured in real time, the fingerprint characteristics of the current transient event are constructed by utilizing the data of the transient event, and on the basis of the fingerprint characteristics, the cause of sag/sag is rapidly and efficiently identified, namely, which type of load is determined to correspond, and finally, the online identification of the cause of sag/sag is realized, so that the foundation is laid for timely and rapid appointed decision.
In one aspect, the invention provides an online identification and tracing method for a transient event of a power grid voltage, which comprises the following steps:
step 1: acquiring real-time power data acquired at a power grid monitoring point;
step 2: capturing a transient event based on the real-time power data in the step 1, wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are obtained;
step 3: extracting transient event load characteristics based on the data in the step 2, wherein the transient event load characteristics comprise overall characteristics and local characteristics, and the transient event load characteristics in the overall characteristics are functions or parameters changing with time;
step 4: determining key information area blocks of the overall features and the local features, constructing feature vectors according to the features of the key information area blocks, and taking the feature vectors as fingerprint features of load types corresponding to transient events;
step 5: and identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
Optionally, the overall feature is defined by: some or all parameter combinations in each subharmonic value (THD 1, THD2, THD3, …), power factor cos phi, positive and negative sequence component voltage change rate function delta U/delta t, active change rate function delta P/delta t, reactive change rate function delta Q/delta t, active power P, reactive power Q;
the local features include at least: the correlation Δp/Δu between the active power variation and the voltage variation, and the correlation Δq/Δu between the reactive power variation and the voltage variation.
Optionally, the key information areas of the active power P, the reactive power Q and the power factor cos phi are: maximum, and/or minimum, and/or average, and/or statistics under confidence probabilities;
the key information areas for the respective subharmonic values (THD 1, THD2, THD3, …) are: statistics of harmonic times, harmonic content percentages and absolute values of current of each subharmonic, wherein the statistics are maximum values, minimum values, average values and/or statistical values under confidence probability;
the key information areas of the positive and negative sequence component voltage change rate function delta U/delta t, the active change rate function delta P/delta t and the reactive change rate function delta Q/delta t are as follows: slope, and/or inflection point, and/or peak;
the key information areas of the correlation deltaP/deltaU between the active power variation and the voltage variation and the correlation deltaQ/deltaU between the reactive power variation and the voltage variation are as follows: maximum, and/or minimum, and/or average, and/or confidence probability distribution interval, and/or slope, and/or inflection point value.
Optionally, in step 5, the load type corresponding to the current voltage transient event is identified, and the fingerprint feature of the current voltage transient event is input into a constructed load type identification model to obtain a load type identification result;
the method comprises the steps of adopting a deep learning algorithm DBN of a layered pre-training mechanism, and training a network by utilizing fingerprint libraries corresponding to various loads to obtain a load type identification model.
Optionally, step 5 is to calculate a similar distance between the fingerprint feature of the current voltage transient event and a fingerprint library corresponding to various loads, and determine the load type corresponding to the current voltage transient event according to the size of the similar distance.
Optionally, the method further comprises: the voltage sag source is identified as follows:
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the external voltage change causes the active and reactive power change of the load;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the voltage sag source is the load or a similar area thereof.
In a second aspect, the present invention provides a system based on the above-mentioned method for online identification and tracing, which includes:
the data acquisition module is used for acquiring the acquired real-time power data;
the transient event capturing and parameter acquiring module is used for capturing a transient event based on the real-time power data, wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are acquired;
the feature extraction module is used for extracting transient event load features, wherein the transient event load features comprise overall features and local features, and the transient event load features in the overall features are functions or parameters which change with time; the key information area block is used for determining the overall characteristics and the local characteristics, and constructing a characteristic vector according to the characteristics of the key information area block, wherein the characteristic vector is used as a fingerprint characteristic of a load type corresponding to a transient event;
the load type identification module is used for identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
Optionally, the system further comprises: the sag source tracing module is used for identifying a voltage sag source;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the external voltage change causes the active and reactive power change of the load;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the source of the voltage sag is the load or a similar area thereof.
In a third aspect, the present invention provides an electronic terminal, comprising:
one or more processors;
a memory storing one or more computer programs;
the processor invokes a computer program to implement:
an online identification and tracing method for a power grid voltage transient event.
In a fourth aspect, the present invention provides a readable storage medium storing a computer program, the computer program being invoked by a processor to implement:
an online identification and tracing method for a power grid voltage transient event.
Advantageous effects
1. The method for on-line identification and tracing of the power grid voltage transient event provided by the invention constructs the fingerprint characteristics of the current transient event by monitoring whether the transient event occurs and collecting the data of the transient event in real time, so that the load types corresponding to the current transient event are identified through the fingerprint libraries of various loads, on-line identification and tracing are realized, a foundation is laid for the subsequent rapid establishment of a sag accident strategy, and the safety of the power grid is further ensured.
2. The method provided by the invention considers the overall characteristics and the local characteristics, fuses the key characteristics in the overall characteristics and the local characteristics, and can more accurately express the sag characteristics based on the characteristic vector of the transient event constructed by the key characteristics, thereby improving the reliability of the load type identification result of the current voltage transient event.
3. In a further preferred scheme of the invention, a deep learning algorithm DBN of a layered pre-training mechanism is introduced to construct a load type recognition model, the DBN model consists of a plurality of limited Boltzmann machines (RBMs) and a layer of backward propagation neural network, and the load type recognition module constructed by the DBN model can be used for rapidly and accurately recognizing the load type of any transient event and fully mining the detailed information of fingerprint characteristics.
Drawings
FIG. 1 is a schematic diagram of a circuit provided by the present invention;
fig. 2 is a flow chart of an online identification and tracing method of a transient event of a power grid voltage, taking the transient event as an example.
Detailed Description
The method and the system for on-line identification and tracing of the transient event of the power grid voltage provided by the invention aim to realize on-line identification and tracing of the voltage sag/sag of the power grid, determine the load type corresponding to the captured transient event and lay a foundation for subsequent rapid strategy formulation. The invention will be further illustrated with reference to examples.
Example 1:
the embodiment provides an online identification and tracing method for a power grid voltage transient event, which comprises the following steps:
step 1: and acquiring real-time power data acquired at a power grid monitoring point.
In this embodiment, instantaneous value data and waveforms of three-phase voltage and current are collected, and basic current parameters of the three-phase power grid, such as effective values of three-phase voltage and current, three-phase active and reactive power, power factors and the like, are calculated. Wherein, which basic power parameters are calculated is determined based on the data required by the subsequent steps, such as which type or types of basic power parameters are required for the subsequent capturing of the transient event, and corresponding data are calculated. It should be noted that, on the basis of acquiring real-time data, which step of recalculating the basic power parameters is adaptively adjustable according to the actual working conditions.
Step 2: and (3) capturing a transient event based on the real-time power data in the step (1), wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are obtained.
In this embodiment, the technology for identifying the transient event may be implemented by using the existing technology, that is, the existing identification parameters and the discrimination criteria are used to identify whether the transient event occurs, so as to record the duration event of the transient event and the corresponding power parameters. The power parameters corresponding to the transient event are determined according to the transient event load characteristics required by the subsequent steps.
For example, the embodiment captures transient events such as voltage and current based on double sliding windows, and uses two single-chain table to realize column pairs, wherein one column is used for judging the voltage and current transient events, the length of the sliding window is 4-6 cycles, and when the variation of the head value and the tail value of the sliding window exceeds a certain threshold, the transient events are judged to occur; the other queue is used for storing corresponding three-phase power parameters when the transient event occurs, and the sliding window is 100 cycles.
Step 3: and (3) extracting transient event load characteristics based on the data in the step (2), wherein the transient event load characteristics comprise overall characteristics and local characteristics, and the transient event load characteristics in the overall characteristics are functions or parameters which change with time.
In this embodiment, the overall characteristics include the respective subharmonic values (THD 1, THD2, THD3, …), the power factor cos phi, the positive and negative sequence component voltage change rate function Δu/Δt, the active change rate function Δp/Δt, the reactive change rate Δq/Δt; the local correlation features include a correlation Δp/Δu between the amount of change in active power and the amount of change in voltage, and a correlation Δq/Δu between the amount of change in reactive power and the amount of change in voltage. The following matrix M is constructed by using the overall characteristics and the local characteristics:
the decomposition is expressed as:
M 1 the matrix represents the matrix of the overall feature construction, which contains functions that are all time-varying functions, M 1 The matrix represents the local features. It should be appreciated that the local and global features may be supplemented with other feature value additions in accordance with the techniques of the art in addition to the transient event load features noted above, and are not limited to combinations of the features described above.
Step 4: and determining key information area blocks of the overall features and the local features, constructing feature vectors according to the features of the key information area blocks, and taking the feature vectors as fingerprint features of load types corresponding to transient events.
In this embodiment, the key information area block is extracted according to the following rule:
(1) The active power P and the reactive power Q, cos phi can adopt the statistic maximum value, the minimum value, the average value and the statistic value of 95% confidence probability as one of the characteristic vector components.
(2) Each subharmonic value (THD 1, THD2, THD3, …) adopts the harmonic number and the harmonic content percentage of each subcurrent, and the statistics (the maximum value, the minimum value, the average value and the statistics of 95% confidence probability) of the absolute value of each subharmonic current as one of the components of the characteristic vector; exemplary nth current harmonics feature vectors are (n,%, max, min, AVG, [95%],A max ,A min ,A avg ,A 95％ )。
(3) The voltage change rate function delta U/delta t, the active change rate function delta P/delta t and the reactive change rate delta Q/delta t function curves have slopes, obvious inflection points and peaks, and the maximum value, the minimum value, the inflection points and the peaks of the slopes form one of key characteristic components of specific loads.
(4) The characteristic quantities of the maximum value, the minimum value, the average value, the 95% confidence probability distribution interval, the slope inflection point value and the like can be adopted as key characteristic components.
It should be understood that, in this embodiment, the key information on the load characteristics of each transient event summarized according to the actual working conditions, and in other possible embodiments, some key information may be selected for combination, which is not limited to the above-mentioned combination manner; in addition, in other possible embodiments, the key information of the two matrices may also be extracted by an existing algorithm.
After key features are obtained, the invention utilizes the data to construct feature vectors as fingerprint features of the transient event corresponding to the load types.
Step 5: and identifying the load type corresponding to the current voltage transient event/transient rise based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
Common sensitive loads include frequency converters, PLCs, contactors, etc. For example, the frequency converter comprises several steady-state characteristics and several transient event characteristics, wherein the steady-state characteristics comprise that the power factor is more than 0.9, the harmonic content is large (the harmonic content of 5 th order current is close to 20%, and the harmonic content of 7 th order current is close to 15%) and the harmonic content is 5/7/11/13; the dip characteristic includes that when DeltaU is less than 25%, deltaQ/DeltaU is about 0, deltaP/DeltaU is about 0, and when DeltaU is greater than 25%, the values of DeltaQ/DeltaU and DeltaP/DeltaU are larger. When the transient event characteristic value and the steady state characteristic value of the load accord with the characteristics of the frequency converter, the sensitive load can be considered as the frequency converter with high probability. Therefore, each type of load corresponds to the unique data characteristics, and the invention aims at the voltage transient event to acquire the characteristic vector of the transient event under various loads, thereby constructing a fingerprint library corresponding to various loads.
In order to identify the load type corresponding to the voltage transient event, the invention provides two possible ways as follows:
first kind:
in the embodiment, a deep learning algorithm DBN of a layered pre-training mechanism is introduced, the DBN consists of a plurality of limited Boltzmann machines (RBMs) and a layer of backward propagation neural network, feature vectors of various common sensitive loads are used as input of training data, a contrast divergence algorithm is used after preprocessing and normalizing, and a first RBM is fully trained to obtain initial features; and then training the next RBM by taking the initial characteristic values as training data to acquire advanced characteristics, and the like, finally obtaining a load type prediction result, and finely adjusting the whole DBN in a supervision mode through a back propagation algorithm.
Therefore, the invention introduces a deep learning algorithm DBN of a layered pre-training mechanism, and trains a network by utilizing fingerprint libraries corresponding to various loads to obtain a load type identification model; and further, inputting the fingerprint characteristics of the current voltage transient event into a constructed load type recognition model to obtain a load type recognition result when actual recognition is predicted.
It should be understood that the deep learning algorithm DBN is an existing algorithm, and the present invention does not make specific statements about the implementation thereof.
It should be understood that, considering that there are two situations of voltage sag and voltage sag, transient events for various loads can be divided into sag and sag events, and when a load type identification model is built, construction according to different working conditions can be considered.
Second kind:
in this embodiment, the fingerprint library of each type of load includes a plurality of feature vectors (fingerprint features) of the type of load, so that when the actual identification prediction is performed, the similar distance between the fingerprint feature of the current voltage transient event and each fingerprint feature in the fingerprint library of each type of load is calculated, and then the similar distance between the fingerprint feature of the current voltage transient event and the fingerprint library of each type of load is determined by adopting an average value or other modes, and finally, the type of load with the smallest similar distance is selected and regarded as the identified load type.
It should be understood that, considering that there are two situations of voltage sag and voltage sag, transient events for various loads can be divided into sag and sag events, and further, when a fingerprint library of each type of load is constructed, construction according to different conditions can be considered.
Step 6: the source of the voltage sag is further identified based on the identified load type.
If the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the active power and the reactive power of the load are changed due to external voltage change; if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the voltage sag source is the load or a similar area thereof.
According to the characteristics that the closer the sag source is to the load, the smaller the line impedance between the sag source and the load is, the larger the current change rate is, and the larger the change rates of delta P/delta t and delta Q/delta t of the load are. If the change rates of the delta P/delta t and the delta Q/delta t of the load are not large, confirming that the sag source is a node with higher voltage level of the load power supply network, which means that the active and reactive power changes of the load are caused by external voltage changes; if the delta P/delta t and delta Q/delta t change rate values of the load are very high, confirming that the sag source is the load or the vicinity thereof, which means that the load or other vicinity loads have short circuit grounding and other conditions, and the like, so that a voltage transient event occurs.
It should be appreciated that in this embodiment, in addition to identifying the load type, the source of the sag of the voltage sag is further identified; in other possible embodiments, step 6 may not be performed, which is not particularly limited by the present invention.
Based on the statement, the invention utilizes the real-time data of the power grid to judge whether the voltage transient event occurs in real time, if the voltage transient event occurs, the invention provides the data to construct the characteristic vector in real time, and finally identifies the corresponding load type based on the characteristic vector (fingerprint feature), thereby laying a foundation for the subsequent establishment of related measures.
Example 2:
the embodiment provides a system based on the above-mentioned online identification and tracing method, which comprises:
and the data acquisition module is used for acquiring the acquired real-time power data.
The transient event capturing and parameter acquiring module is used for capturing a transient event based on the real-time power data, wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are acquired;
the feature extraction module is used for extracting transient event load features, wherein the transient event load features comprise overall features and local features, and the transient event load features in the overall features are functions or parameters which change with time; the key information area block is used for determining the overall characteristics and the local characteristics, and constructing a characteristic vector according to the characteristics of the key information area block, wherein the characteristic vector is used as a fingerprint characteristic of a load type corresponding to a transient event;
the load type identification module is used for identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
And the sag source tracing module is used for identifying the voltage sag source. If the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the external voltage change causes the active and reactive power change of the load; if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the source of the voltage sag is the load or a similar area thereof.
In some embodiments, the system includes a remote communication module, where the remote communication module is configured to establish a communication protocol with an external device to implement a communication connection. In this embodiment, based on the MQTT standard protocol of the internet of things, the cloud server can be conveniently accessed, the traffic consumption is low, the traffic consumption is limited to the actual data transmitted by the user, all the data can be transmitted to the master station in real time, and reliable bidirectional communication with the master station is realized.
It should be understood that the implementation of the above modules may be implemented in software or hardware, or in both, such as by using a hardware acquisition device disposed on the power grid to acquire real-time power data of the power grid; the data processing subsystem is built in a software mode and is composed of a transient event capturing and parameter acquiring module, a characteristic extracting module, a load type identifying module, a sag source tracing module and a remote communication module, so that load type identification is realized; or the whole system is regarded as a system for communicating with the hardware acquisition equipment, and comprises a data acquisition module, a transient event capturing and parameter acquiring module, a characteristic extraction module, a load type identification module, a sag source tracing module and a remote communication module, wherein the load type identification is realized by utilizing the functions of the modules.
In this embodiment, as shown in fig. 1, a hardware acquisition device (monitoring module) is disposed at the main entrance of the user incoming line.
It should be understood that, in the specific implementation process of the above unit module, reference is made to the method content, the present invention is not specifically described herein, and the division of the functional module unit is merely a division of a logic function, and there may be another division manner when actually implemented, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted or not performed. Meanwhile, the integrated units can be realized in a hardware form or a software functional unit form.
Example 3:
the present embodiment provides an electronic terminal, which includes: one or more processors and a memory storing one or more computer programs. Wherein the processor invokes a computer program to implement:
the method for identifying and tracing the transient event c of the power grid voltage on line specifically comprises the following steps:
step 1: and acquiring real-time power data acquired at a power grid monitoring point.
Step 2: and (3) capturing a transient event based on the real-time power data in the step (1), wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are obtained.
Step 3: and (3) extracting transient event load characteristics based on the data in the step (2), wherein the transient event load characteristics comprise overall characteristics and local characteristics, and the transient event load characteristics in the overall characteristics are functions or parameters which change with time.
Step 4: and determining key information area blocks of the overall features and the local features, constructing feature vectors according to the features of the key information area blocks, and taking the feature vectors as fingerprint features of load types corresponding to transient events.
Step 5: and identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
Or further also performs:
step 6: the source of the voltage sag is further identified based on the identified load type.
For a specific implementation of each step, please refer to the description of the foregoing method.
It should be appreciated that in embodiments of the present invention, the processor may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf Programmable gate arrays (FPGAs) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include read only memory and random access memory and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store information of the device type.
Example 4:
the present embodiment provides a readable storage medium storing a computer program that is called by a processor to implement:
the method specifically comprises the following steps of an online identification and tracing method of a power grid voltage transient event:
step 1: and acquiring real-time power data acquired at a power grid monitoring point.
Step 2: and (3) capturing a transient event based on the real-time power data in the step (1), wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are obtained.
Step 3: and (3) extracting transient event load characteristics based on the data in the step (2), wherein the transient event load characteristics comprise overall characteristics and local characteristics, and the transient event load characteristics in the overall characteristics are functions or parameters which change with time.
Step 4: and determining key information area blocks of the overall features and the local features, constructing feature vectors according to the features of the key information area blocks, and taking the feature vectors as fingerprint features of load types corresponding to transient events.
Step 5: and identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
Or further also performs:
step 6: the source of the voltage sag is further identified based on the identified load type.
For a specific implementation of each step, please refer to the description of the foregoing method.
The readable storage medium is a computer readable storage medium, which may be an internal storage unit of the controller according to any one of the foregoing embodiments, for example, a hard disk or a memory of the controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the controller. Further, the readable storage medium may also include both an internal storage unit and an external storage device of the controller. The readable storage medium is used to store the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been output or is to be output.
Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a random access Memory (RAM, randomAccess Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.
It should be emphasized that the examples described herein are illustrative rather than limiting, and that this invention is not limited to the examples described in the specific embodiments, but is capable of other embodiments in accordance with the teachings of the present invention, as long as they do not depart from the spirit and scope of the invention, whether modified or substituted, and still fall within the scope of the invention.
Claims (8)
1. An online identification and tracing method for a power grid voltage transient event is characterized by comprising the following steps of: the method comprises the following steps:
step 1: acquiring real-time power data acquired at a power grid monitoring point;
step 2: capturing a transient event based on the real-time power data in the step 1, wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are obtained;
step 3: extracting transient event load characteristics based on the data in the step 2, wherein the transient event load characteristics comprise overall characteristics and local characteristics, and the transient event load characteristics in the overall characteristics are functions or parameters changing with time;
step 4: determining key information area blocks of the overall features and the local features, constructing feature vectors according to the features of the key information area blocks, and taking the feature vectors as fingerprint features of load types corresponding to transient events;
step 5: identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads;
the overall features are: some or all parameters in the subharmonic value, the power factor cos phi, the positive and negative sequence component voltage change rate function delta U/delta t, the active change rate function delta P/delta t, the reactive change rate function delta Q/delta t, the active power P and the reactive power Q are combined;
the local features include at least: a correlation Δp/Δu between the active power variation and the voltage variation, and a correlation Δq/Δu between the reactive power variation and the voltage variation;
the key information areas of the active power P, the reactive power Q and the power factor cos phi are as follows: maximum, and/or minimum, and/or average, and/or statistics under confidence probabilities;
the key information areas of each subharmonic value are: statistics of harmonic times, harmonic content percentages and absolute values of current of each subharmonic, wherein the statistics are maximum values, minimum values, average values and/or statistical values under confidence probability;
the key information areas of the positive and negative sequence component voltage change rate function delta U/delta t, the active change rate function delta P/delta t and the reactive change rate function delta Q/delta t are as follows: slope, and/or inflection point, and/or peak;
the key information areas of the correlation deltaP/deltaU between the active power variation and the voltage variation and the correlation deltaQ/deltaU between the reactive power variation and the voltage variation are as follows: maximum, and/or minimum, and/or average, and/or confidence probability distribution interval, and/or slope, and/or inflection point value.
2. The method according to claim 1, characterized in that: in the step 5, the load type corresponding to the current voltage transient event is identified, namely, the fingerprint characteristic of the current voltage transient event is input into a constructed load type identification model to obtain a load type identification result;
the method comprises the steps of adopting a deep learning algorithm DBN of a layered pre-training mechanism, and training a network by utilizing fingerprint libraries corresponding to various loads to obtain a load type identification model.
3. The method according to claim 1, characterized in that: and 5, calculating similar distances between the fingerprint characteristics of the current voltage transient event and fingerprint libraries corresponding to various loads, and determining the load type corresponding to the current voltage transient event according to the similar distances.
4. The method according to claim 1, characterized in that: further comprises: the voltage sag source is identified as follows:
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the external voltage change causes the active and reactive power change of the load;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the voltage sag source is the load or a similar area thereof.
5. A system based on the method of any one of claims 1-4, comprising:
the data acquisition module is used for acquiring the acquired real-time power data;
the transient event capturing and parameter acquiring module is used for capturing a transient event based on the real-time power data, wherein if the transient event is captured, the duration of the transient event and the power parameter corresponding to the transient event are acquired;
the feature extraction module is used for extracting transient event load features, wherein the transient event load features comprise overall features and local features, and the transient event load features in the overall features are functions or parameters which change with time; the key information area block is used for determining the overall characteristics and the local characteristics, and constructing a characteristic vector according to the characteristics of the key information area block, wherein the characteristic vector is used as a fingerprint characteristic of a load type corresponding to a transient event;
the load type identification module is used for identifying the load type corresponding to the current voltage transient event based on the fingerprint characteristics of the load type corresponding to the transient event and fingerprint libraries corresponding to various loads.
6. The system according to claim 5, wherein: further comprises: the sag source tracing module is used for identifying a voltage sag source;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset small change rate range, the voltage sag source is a node with a higher voltage level of the load power supply network, namely the external voltage change causes the active and reactive power change of the load;
if the active change rate function delta P/delta t and the reactive change rate delta Q/delta t are in a preset large change rate range, the source of the voltage sag is the load or a similar area thereof.
7. An electronic terminal, characterized in that: comprising the following steps:
one or more processors;
a memory storing one or more computer programs;
the processor invokes a computer program to implement:
the method of any one of claims 1-4.
8. A readable storage medium, characterized by: a computer program is stored, which is called by a processor to implement:
the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435044.3A CN114050613B (en) | 2021-11-29 | 2021-11-29 | Online identification and tracing method and system for power grid voltage transient event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111435044.3A CN114050613B (en) | 2021-11-29 | 2021-11-29 | Online identification and tracing method and system for power grid voltage transient event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114050613A CN114050613A (en) | 2022-02-15 |
| CN114050613B true CN114050613B (en) | 2023-10-27 |
Family
ID=80211702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111435044.3A Active CN114050613B (en) | 2021-11-29 | 2021-11-29 | Online identification and tracing method and system for power grid voltage transient event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114050613B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489066A (en) * | 2013-09-13 | 2014-01-01 | 深圳供电局有限公司 | Analysis method for monitoring information and data of highlight area of power quality transient state event |
| CN105305437A (en) * | 2015-11-18 | 2016-02-03 | 天津大学 | Tri-reliability matching and identification method of electric load |
| WO2016138750A1 (en) * | 2015-03-04 | 2016-09-09 | 江苏省电力公司常州供电公司 | Power quality disturbance source locating system and locating method |
| CN106483370A (en) * | 2016-10-21 | 2017-03-08 | 威胜集团有限公司 | Non-intrusion type household loads real-time identification method based on multi-feature fusion and device |
| CN107979086A (en) * | 2017-11-14 | 2018-05-01 | 国网江苏省电力公司电力科学研究院 | Voltage sag reason recognition methods based on EM algorithms and gradient boosted tree |
| CN110245584A (en) * | 2019-05-28 | 2019-09-17 | 全球能源互联网研究院有限公司 | A kind of voltage sag reason recognition methods and system |
| CN110907762A (en) * | 2019-12-10 | 2020-03-24 | 深圳供电局有限公司 | Non-invasive load matching identification method |
| CN112964960A (en) * | 2021-02-04 | 2021-06-15 | 国网上海市电力公司 | Multi-source data fusion power grid fault diagnosis method based on scheduling fault fingerprint database |
| CN112989133A (en) * | 2021-03-29 | 2021-06-18 | 广州水沐青华科技有限公司 | Graph data modeling power fingerprint identification method, storage medium and system for electrical equipment |
| CN113393121A (en) * | 2021-06-15 | 2021-09-14 | 贵州电网有限责任公司 | Non-invasive load identification method based on load power fingerprint characteristics |
| CN113673480A (en) * | 2021-09-03 | 2021-11-19 | 武汉盛帆电子股份有限公司 | Non-intrusive load identification method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9606154B2 (en) * | 2013-12-28 | 2017-03-28 | Intel Corporation | Electrical load identification during an on event using a support vector machine classifier |
| US10845397B2 (en) * | 2017-01-30 | 2020-11-24 | Wirepath Home Systems, Llc | Systems and methods for detecting load coupling and for detecting a load type |
-
2021
- 2021-11-29 CN CN202111435044.3A patent/CN114050613B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489066A (en) * | 2013-09-13 | 2014-01-01 | 深圳供电局有限公司 | Analysis method for monitoring information and data of highlight area of power quality transient state event |
| WO2016138750A1 (en) * | 2015-03-04 | 2016-09-09 | 江苏省电力公司常州供电公司 | Power quality disturbance source locating system and locating method |
| CN105305437A (en) * | 2015-11-18 | 2016-02-03 | 天津大学 | Tri-reliability matching and identification method of electric load |
| CN106483370A (en) * | 2016-10-21 | 2017-03-08 | 威胜集团有限公司 | Non-intrusion type household loads real-time identification method based on multi-feature fusion and device |
| CN107979086A (en) * | 2017-11-14 | 2018-05-01 | 国网江苏省电力公司电力科学研究院 | Voltage sag reason recognition methods based on EM algorithms and gradient boosted tree |
| CN110245584A (en) * | 2019-05-28 | 2019-09-17 | 全球能源互联网研究院有限公司 | A kind of voltage sag reason recognition methods and system |
| CN110907762A (en) * | 2019-12-10 | 2020-03-24 | 深圳供电局有限公司 | Non-invasive load matching identification method |
| CN112964960A (en) * | 2021-02-04 | 2021-06-15 | 国网上海市电力公司 | Multi-source data fusion power grid fault diagnosis method based on scheduling fault fingerprint database |
| CN112989133A (en) * | 2021-03-29 | 2021-06-18 | 广州水沐青华科技有限公司 | Graph data modeling power fingerprint identification method, storage medium and system for electrical equipment |
| CN113393121A (en) * | 2021-06-15 | 2021-09-14 | 贵州电网有限责任公司 | Non-invasive load identification method based on load power fingerprint characteristics |
| CN113673480A (en) * | 2021-09-03 | 2021-11-19 | 武汉盛帆电子股份有限公司 | Non-intrusive load identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| "基于深度学习的用电负荷辨识方法";潘世博 等;《中国新通信》;第23卷(第2期);第233-234页，图2、3 * |
| Robert Cox 等."Transient event detection for nonintrusive load monitoring and demand side management using voltage distortion".《Twenty-First Annual IEEE Applied Power Electronics Conference and Exposition, 2006. APEC '06》.2006,第1751-1757. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114050613A (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
| CN108198408B (en) | Self-adaptive anti-electricity-stealing monitoring method and system based on electricity information acquisition system | |
| CN106656669B (en) | A kind of device parameter abnormality detection system and method based on threshold adaptive setting | |
| CN109613324B (en) | Harmonic amplification detection method and device | |
| CN111371188A (en) | Real-time early warning system for abnormal power consumption data | |
| CN112784210A (en) | Load identification method based on multivariate Gaussian discrimination mode | |
| CN113687610B (en) | Method for protecting terminal information of GAN-CNN power monitoring system | |
| CN116231871A (en) | Power grid situation supervision method, system and storage medium based on digital twinning | |
| CN114050613B (en) | Online identification and tracing method and system for power grid voltage transient event | |
| Ismail et al. | Principal component regression with artificial neural network to improve prediction of electricity demand. | |
| CN113570473B (en) | Equipment fault monitoring method, device, computer equipment and storage medium | |
| CN111130098B (en) | Risk assessment method for power distribution network system with distributed power supplies | |
| CN112131069B (en) | Equipment operation monitoring method and system based on clustering | |
| Zhu et al. | Power system short‐term voltage stability assessment based on improved CatBoost with consideration of model confidence | |
| CN110704508A (en) | Intelligent production line abnormal data processing method and device | |
| Mishra et al. | An IoT Integrated Reliability Estimation of Wind Energy System | |
| CN117595464B (en) | Battery charger charging detection control method and system | |
| CN111651461B (en) | Energy storage operation monitoring method and system based on machine learning | |
| CN214150893U (en) | Modular terminal for classified recording of state data of power distribution equipment | |
| CN112731261B (en) | Fault detection method and device for electric energy metering equipment, computer equipment and medium | |
| CN114418792A (en) | Automatic analysis and management system for power utilization | |
| CN117390560A (en) | Concentrator energy consumption abnormality cause diagnosis method based on DBSCAN algorithm | |
| CN113850296A (en) | FCM algorithm-based terminal electricity stealing detection method, system, equipment and readable storage medium | |
| Zhan et al. | An industrial control intrusion detection method combining semi-supervised LDA and PSO-SVM | |
| CN116633021A (en) | Switch cabinet energy consumption monitoring method and system based on Internet of things |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |