CN108761227A - A kind of high ferro power quality data processing system - Google Patents
A kind of high ferro power quality data processing system Download PDFInfo
- Publication number
- CN108761227A CN108761227A CN201810283553.0A CN201810283553A CN108761227A CN 108761227 A CN108761227 A CN 108761227A CN 201810283553 A CN201810283553 A CN 201810283553A CN 108761227 A CN108761227 A CN 108761227A
- Authority
- CN
- China
- Prior art keywords
- power quality
- quality data
- vehicle
- cluster
- data
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention provides a kind of high ferro power quality data processing systems, including data acquisition unit, data pre-processing unit, normalization unit, cluster cell, outlier detection unit, power quality data library;Wherein data pre-processing unit according to when having a vehicle operation power quality data and high ferro in the run time of supply arm, filter out the power quality data for only having the operation of a vehicle on supply arm, and pre-process to power quality data;Cluster cell clusters the sample power quality data after being normalized, and the power quality data to obtain different automobile types is classified;Outlier detection unit carries out outlier detection to the power quality data after clustering processing, obtains abnormal point set and send in power quality data library to be stored.
Description
Technical field
The present invention relates to Power Quality Monitoring Technology fields, and in particular to a kind of high ferro power quality data processing system.
Background technology
Electrified high-speed railway locomotive belongs to non-linear and impact load, and negative phase-sequence and harmonic wave etc. are mainly brought to power grid
Power quality influences;Cause the power quality characteristic of power grid different when the locomotive operation of different automobile types simultaneously, especially harmonic wave is special
Property.These not only adversely affect miscellaneous equipment in power grid, but also the stability to self-operating and reliability composition prestige
The side of body.The electric locomotive of electric railway is the prodigious high-power single-phase rectification load of fluctuation, and since train was being run
The factors such as the various states of acceleration, coasting, braking in journey and line slope, turning radius, meteorological condition, driver operation
And on supply arm train quantity variation, traction load random fluctuation.Therefore, when carrying out the analysis of electrical energy measurement, it is necessary to
Fully take into account the part throttle characteristics of electric locomotive.Using the different straight electric locomotives of friendship-, the harmonic content generated is different.For
It is further to study the power quality characteristic after certain vehicle puts into operation, assess its influence brought to power grid, it is necessary to propose a kind of
High ferro power quality data processing system with power quality data analyzing processing function.
Invention content
In view of the above-mentioned problems, the present invention provides a kind of high ferro power quality data processing system.
The purpose of the present invention is realized using following technical scheme:
It provides a kind of high ferro power quality data processing system, including data acquisition unit, data pre-processing unit, returns
One changes unit, cluster cell, outlier detection unit, power quality data library;
Data acquisition unit obtains the power quality data of high ferro Traction Station by online electric energy quality monitor;
Data pre-processing unit according to when having a vehicle operation power quality data and high ferro supply arm run time,
The power quality data for only having the operation of a vehicle on supply arm is filtered out, and power quality data is pre-processed;
Normalization unit is directed to pretreated power quality data, calculates the run time and electric energy matter of a high ferro
The statistical value of figureofmerit, using high ferro in the run time of supply arm and the statistical value of power quality index as sample power quality
Data, and be normalized;
Cluster cell clusters the sample power quality data after being normalized, to obtain different automobile types
Power quality data is classified;
Outlier detection unit carries out outlier detection to the power quality data after clustering processing, obtains abnormal point set simultaneously
It is sent in power quality data library and is stored.
Preferably, the power quality data of the high ferro Traction Station includes that voltage deviation, electric current, negative-sequence current, frequency are inclined
Difference, active power, reactive power, electricity, harmonic wave, m-Acetyl chlorophosphonazo, phase angle, voltage fluctuation and flicker, tri-phase unbalance factor, voltage are temporary
It rises, voltage dip and short time voltage interrupt.
Preferably, the power quality data of the only vehicle operation includes active power, negative-sequence current and phase angle.
Preferably, the power quality data filtered out when only having a vehicle operation on supply arm, including:
(1) when there is power quality data when vehicle operation to be simultaneously greater than pre-set threshold value, then be considered as supply arm have vehicle when
It carves, supply arm is had and is ranked up to obtain the time series of vehicle period from front to back at the time of vehicle;
(2) according to there is vehicle time series, each continuous time span for having the vehicle period is calculated;
(3) size for judging each continuous time span and most short transit time for having a vehicle period, to continuously have the vehicle period into
Row divides;
(4) judge the size of each time span and longest transit time for continuously having the vehicle period, continuous there will be the vehicle period to draw
Be divided into the operation of more vehicles have vehicle period and an only vehicle operation have the vehicle period, and then obtain an only vehicle on supply arm
Power quality data when operation.
Beneficial effects of the present invention are:The Intelligent treatment to the power quality data of acquisition is realized, to study certain type
It provides the foundation to the power quality problem that power grid is brought in high ferro operational process.
Description of the drawings
Using attached drawing, the invention will be further described, but the embodiment in attached drawing does not constitute any limit to the present invention
System, for those of ordinary skill in the art, without creative efforts, can also obtain according to the following drawings
Other attached drawings.
Fig. 1 is the structural schematic block diagram of the high ferro power quality data processing system of an illustrative embodiment of the invention.
Reference numeral:
Data acquisition unit 1, data pre-processing unit 2, normalization unit 3, cluster cell 4, outlier detection unit 5,
Power quality data library 6.
Specific implementation mode
The invention will be further described with the following Examples.
Referring to Fig. 1, a kind of high ferro power quality data processing system provided in this embodiment, including data acquisition unit 1,
Data pre-processing unit 2, normalization unit 3, cluster cell 4, outlier detection unit 5, power quality data library 6;Data are adopted
Collect the power quality data that unit 1 obtains high ferro Traction Station by online electric energy quality monitor;Data pre-processing unit 2 according to
According to when having a vehicle operation power quality data and high ferro in the run time of supply arm, filter out and only have a vehicle on supply arm
The power quality data of operation, and power quality data is pre-processed;Normalization unit 3 is directed to pretreated electric energy matter
Data are measured, the statistical value of the run time and power quality index of a high ferro are calculated, by high ferro in the operation of supply arm
Between and power quality index statistical value as sample power quality data, and be normalized;Cluster cell 4 is to carrying out
Sample power quality data after normalized is clustered, and the power quality data to obtain different automobile types is classified;It is abnormal
Point detection unit 5 carries out outlier detection to the power quality data after clustering processing, obtains abnormal point set and sends electric energy
It is stored in quality database 6.
Wherein, the power quality data of the high ferro Traction Station include voltage deviation, electric current, negative-sequence current, frequency departure,
Active power, reactive power, electricity, harmonic wave, m-Acetyl chlorophosphonazo, phase angle, voltage fluctuation and flicker, tri-phase unbalance factor, voltage swell,
Voltage dip and short time voltage are interrupted.
Wherein, the power quality data of the only vehicle operation includes active power, negative-sequence current and phase angle.
In one embodiment, the power quality data filtered out when only having a vehicle operation on supply arm, including:
(1) when there is power quality data when vehicle operation to be simultaneously greater than pre-set threshold value, then be considered as supply arm have vehicle when
It carves, supply arm is had and is ranked up to obtain the time series of vehicle period from front to back at the time of vehicle;
(2) according to there is vehicle time series, each continuous time span for having the vehicle period is calculated;
(3) size for judging each continuous time span and most short transit time for having a vehicle period, to continuously have the vehicle period into
Row divides;
(4) judge the size of each time span and longest transit time for continuously having the vehicle period, continuous there will be the vehicle period to draw
Be divided into the operation of more vehicles have vehicle period and an only vehicle operation have the vehicle period, and then obtain an only vehicle on supply arm
Power quality data when operation.
The above embodiment of the present invention realizes the Intelligent treatment to the power quality data of acquisition, to study certain type high ferro
It provides the foundation to the power quality problem that power grid is brought in operational process.
In one embodiment, power quality data is pre-processed, is specifically included:To there are the electricity of 0 value or negative value
Energy qualitative data is pre-processed, and 0 value or negative value are replaced with preset substitution value.
The present embodiment can prevent 0 value in power quality data or negative value to subsequent power quality data clustering processing
It impacts.
In one embodiment, described pair be normalized after sample power quality data cluster, specifically
Including:
(1) power quality data of the set period of time of extraction sample power quality data is as a power quality data
Collection, is set as Y;
(2) in first time iteration, a unlabelled power quality data in power quality data collection Y is randomly choosed
As first cluster central point R1, calculate remaining power quality data and cluster central point R1Between similarity, if power quality
Data yiWith cluster central point R1Between similarity be more than setting similarity threshold, then by power quality data yiIt is assigned to this
Cluster central point R1, and be marked;
(3) iterations λ is enabled to add 1, a unlabelled power quality data in random selection power quality data collection Y
As another cluster central point Rλ+1, calculate remaining power quality data and cluster central point Rλ+1Between similarity;
If power quality data yjUnmarked and and Rλ+1Between similarity be more than setting similarity threshold, then will be electric
It can qualitative data yjIt is assigned to cluster central point Rλ+1, and be marked;
If power quality data yjIt is marked and meet reallocation condition, then by power quality data yjIt is assigned in the cluster
Heart point Rλ+1, and be marked, otherwise to power quality data yjAny operation is not made;
(4) (3) are repeated until iterations λ reaches the threshold value of setting or all power quality datas are all marked
Note executes (5);
(5) the cluster central point for updating each cluster is the mean value of all power quality datas in the cluster, is distributed in each non-cluster
Cluster of the heart point to where with the highest cluster central point of its similarity, when all cluster central points all no longer update, algorithm stops;
Wherein, set reallocation condition as:
S[D(yx,Rλ+1)-DT]×[D(yx,Rλ+1)-λD(yx,Rx0)]>0
In formula, D (yx,Rλ+1) indicate power quality data yxWith cluster central point Rλ+1Between similarity, DTFor the setting
Similarity threshold, S [D (yx,Rλ+1)-DT] it is the judgement value function set, as D (yx,Rλ+1)-DT>When 0, S [D (yx,
Rλ+1)-DT]=1, as D (yx,Rλ+1)-DTWhen≤0, S [D (yx,Rλ+1)-DT]=0;D(yx,Rx0) it is power quality data yxWith it
Similarity between the cluster central point distributed, λ are the adjustment factor of setting, and value range is (1,1.3).
The present embodiment sets the tool that clustering processing is carried out to the pretreated power quality data of data pre-processing unit
Body mechanism, the mechanism can quickly and easily complete the cluster of power quality data, need not preassign the number of cluster.
The present embodiment innovatively sets reallocation condition, by the power quality data weight that will meet reallocation condition
It is newly assigned in new cluster central point, enables to each power quality data that can distribute to the cluster most like with it,
Mode is clustered compared to traditional k-means, better Clustering Effect can be obtained.
Wherein, the similarity between power quality data and cluster central point may be used existing similarity function and be counted
It calculates, is measured for example, by using cosine similarity, Pearson correlation coefficient etc..
In a preferred embodiment, the calculation formula of the similarity between power quality data and cluster central point is set
For:
In formula, D (yx,Rk) indicate power quality data yxWith cluster central point RkBetween similarity, yxαIndicate power quality
Data yxα dimension attribute values, RkαIndicate cluster central point Rkα dimension attribute values, β be power quality data dimension, min tables
Show and be minimized, max expressions are maximized, f (yxα,Rkα) it is the comparison value function set, work as yxα=RkαWhen, f (yxα,Rkα)
=0, work as yxα≠RkαWhen, f (yxα,Rkα)=1.
The present embodiment innovatively sets the calculation formula of similarity, it is proposed that a kind of new measuring similarity mechanism,
The similarity obtained by the calculation formula weighs the similitude between two power quality datas, enables to similarity
Calculating is not influenced by the dimension of power quality data, to avoid any unnecessary data conversion so as to power quality
The cluster of data is simpler quick, improves the efficiency of high ferro power quality data processing system.
In one embodiment, outlier detection is carried out to the power quality data after clustering processing, specifically included:
(1) if there are the number threshold value that the power quality data number of a cluster is less than setting after cluster, which is regarded
For abnormal clusters, all power quality datas in abnormal clusters are considered as abnormal power quality data;
(2) similarity between the cluster central point of other normal clusters and the cluster central point of abnormal clusters is calculated;
(3) if there are the similarities between the cluster central point and the cluster central point of normal clusters of an abnormal clusters to be more than setting
Cluster similarity threshold then using the normal clusters as cluster to be detected, and is detected using the power quality data of the abnormal clusters to be checked
The power quality data in cluster is surveyed, if the power quality data collection of the abnormal clusters is combined into Yδ={ y1,y5,..,yδ, when to be detected
Power quality data y in clustercWhen meeting exceptional condition, by power quality data ycIt is considered as abnormal power quality data.
Wherein, set exceptional condition as:
In formula, ycαIndicate power quality data ycα dimension attribute values, yθαIndicate power quality data yθα dimension belong to
Property value, yθ∈Yδ, β is the dimension of power quality data, DtFor the similarity threshold of another setting,To set
The fixed function that gets the small value, whenWhen,WhenWhen, For the function that takes large values of setting, whenWhen,WhenWhen,
Due to comparatively loose between the power quality data in the smaller cluster of scale, and relative to other electric energy
Qualitative data is more isolated, therefore the data in the cluster of scale is smaller are usually considered as abnormal data in the prior art.Based on this,
The present embodiment carries out outlier detection to the power quality data after clustering processing, therefrom innovatively proposes for detecting electricity
Can qualitative data whether be abnormal exceptional condition, the exceptional condition is according to power quality data and the highest abnormal clusters of similarity
Power quality data mean value between similarity threshold judge whether the power quality data is abnormal power quality data,
Detection is enabled to not influenced by dimension, detection mode is simple and effective, has certain accuracy of detection, on the whole
Improve the data-handling efficiency and precision of high ferro power quality data processing system.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than the present invention is protected
The limitation of range is protected, although being explained in detail to the present invention with reference to preferred embodiment, those skilled in the art answer
Work as understanding, technical scheme of the present invention can be modified or replaced equivalently, without departing from the reality of technical solution of the present invention
Matter and range.
Claims (6)
1. a kind of high ferro power quality data processing system, characterized in that including data acquisition unit, data pre-processing unit,
Normalization unit, cluster cell, outlier detection unit, power quality data library;
Data acquisition unit obtains the power quality data of high ferro Traction Station by online electric energy quality monitor;
Data pre-processing unit according to when having a vehicle operation power quality data and high ferro in the run time of supply arm, screening
Go out on supply arm to only have the power quality data of vehicle operation, and power quality data is pre-processed;
Normalization unit is directed to pretreated power quality data, and the run time and power quality for calculating high ferro refer to
Target statistical value, using high ferro in the run time of supply arm and the statistical value of power quality index as sample power quality number
According to, and be normalized;
Cluster cell clusters the sample power quality data after being normalized, to obtain the electric energy of different automobile types
Qualitative data is classified;
Outlier detection unit carries out outlier detection to the power quality data after clustering processing, obtains abnormal point set and concurrently send
To being stored in power quality data library.
2. a kind of high ferro power quality data processing system according to claim 1, characterized in that the high ferro Traction Station
Power quality data include voltage deviation, it is electric current, negative-sequence current, frequency departure, active power, reactive power, electricity, humorous
Wave, m-Acetyl chlorophosphonazo, phase angle, voltage fluctuation and flicker, tri-phase unbalance factor, voltage swell, voltage dip and short time voltage are interrupted.
3. a kind of high ferro power quality data processing system according to claim 1, characterized in that an only vehicle
The power quality data of operation includes active power, negative-sequence current and phase angle.
4. a kind of high ferro power quality data processing system according to claim 1, characterized in that described to filter out power supply
Only have a power quality data when vehicle operation on arm, including:
It (1), then, will at the time of being considered as supply arm has vehicle when there is power quality data when vehicle operation to be simultaneously greater than pre-set threshold value
Supply arm has to be ranked up to obtain the time series of vehicle period at the time of vehicle from front to back;
(2) according to there is vehicle time series, each continuous time span for having the vehicle period is calculated;
(3) size for judging each time span and most short transit time for continuously having the vehicle period, to continuously there is the vehicle period to draw
Point;
(4) size for judging each continuous time span and longest transit time for having a vehicle period is by continuously there is vehicle Time segments division
The operation of more vehicles have vehicle period and an only vehicle operation have the vehicle period, and then show on supply arm that only having a vehicle runs
When power quality data.
5. according to a kind of high ferro power quality data processing system of claim 1-4 any one of them, characterized in that described right
Power quality data is pre-processed, and is specifically included:Described pair be normalized after sample power quality data carry out
Cluster, specifically includes:
(1) power quality data of the set period of time of extraction sample power quality data is as a power quality data collection,
It is set as Y;
(2) in first time iteration, a unlabelled power quality data conduct in power quality data collection Y is randomly choosed
First cluster central point R1, calculate remaining power quality data and cluster central point R1Between similarity, if power quality data
yiWith cluster central point R1Between similarity be more than setting similarity threshold, then by power quality data yiIt is assigned in the cluster
Heart point R1, and be marked;
(3) iterations λ is enabled to add 1, a unlabelled power quality data conduct in random selection power quality data collection Y
Another cluster central point Rλ+1, calculate remaining power quality data and cluster central point Rλ+1Between similarity;
If power quality data yjUnmarked and and Rλ+1Between similarity be more than setting similarity threshold, then by power quality
Data yjIt is assigned to cluster central point Rλ+1, and be marked;
If power quality data yjIt is marked and meet reallocation condition, then by power quality data yjIt is assigned to the cluster central point
Rλ+1, and be marked, otherwise to power quality data yjAny operation is not made;
(4) (3) are repeated until iterations λ reaches the threshold value of setting or all power quality datas have all been labeled, held
Row (5);
(5) the cluster central point for updating each cluster is the mean value of all power quality datas in the cluster, distributes each non-cluster central point
Cluster to where with the highest cluster central point of its similarity, when all cluster central points all no longer update, algorithm stops;
Wherein, set reallocation condition as:
S[D(yx,Rλ+1)-DT]×[D(yx,Rλ+1)-λD(yx,Rx0)]>0
In formula, D (yx,Rλ+1) indicate power quality data yxWith cluster central point Rλ+1Between similarity, DTFor the phase of the setting
Like degree threshold value, S [D (yx,Rλ+1)-DT] it is the judgement value function set, as D (yx,Rλ+1)-DT>When 0, S [D (yx,Rλ+1)-DT]
=1, as D (yx,Rλ+1)-DTWhen≤0, S [D (yx,Rλ+1)-DT]=0;D(yx,Rx0) it is power quality data yxWith it is its allocated
Similarity between cluster central point, λ are the adjustment factor of setting, and value range is (1,1.3).
6. according to a kind of high ferro power quality data processing system of claim 1-4 any one of them, characterized in that electric energy
Qualitative data is pre-processed, and is specifically included:To there are the power quality datas of 0 value or negative value to pre-process, by 0 value or bear
Value replaces with preset substitution value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810283553.0A CN108761227A (en) | 2018-04-02 | 2018-04-02 | A kind of high ferro power quality data processing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810283553.0A CN108761227A (en) | 2018-04-02 | 2018-04-02 | A kind of high ferro power quality data processing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108761227A true CN108761227A (en) | 2018-11-06 |
Family
ID=63980689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810283553.0A Pending CN108761227A (en) | 2018-04-02 | 2018-04-02 | A kind of high ferro power quality data processing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108761227A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109583599A (en) * | 2018-11-23 | 2019-04-05 | 广州供电局有限公司 | Abnormal state detection method |
CN110287256A (en) * | 2019-06-14 | 2019-09-27 | 南京邮电大学 | A kind of electric network data parallel processing system (PPS) and its processing method based on cloud computing |
CN112699113A (en) * | 2021-01-12 | 2021-04-23 | 上海交通大学 | Industrial manufacturing process operation monitoring system driven by time sequence data stream |
CN113421176A (en) * | 2021-07-16 | 2021-09-21 | 昆明学院 | Intelligent abnormal data screening method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103777091A (en) * | 2013-12-13 | 2014-05-07 | 国家电网公司 | High-speed rail electric energy quality monitoring data classification method based on K mean value |
US20150264683A1 (en) * | 2012-10-22 | 2015-09-17 | Lg Electronics Inc. | Method for configuring wireless frame of user equipment and user equipment, and method for configuring wireless frame of base station and base station |
CN106503086A (en) * | 2016-10-11 | 2017-03-15 | 成都云麒麟软件有限公司 | The detection method of distributed local outlier |
CN108508294A (en) * | 2018-03-29 | 2018-09-07 | 深圳众厉电力科技有限公司 | A kind of high ferro electric energy quality monitoring system |
-
2018
- 2018-04-02 CN CN201810283553.0A patent/CN108761227A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150264683A1 (en) * | 2012-10-22 | 2015-09-17 | Lg Electronics Inc. | Method for configuring wireless frame of user equipment and user equipment, and method for configuring wireless frame of base station and base station |
CN103777091A (en) * | 2013-12-13 | 2014-05-07 | 国家电网公司 | High-speed rail electric energy quality monitoring data classification method based on K mean value |
CN106503086A (en) * | 2016-10-11 | 2017-03-15 | 成都云麒麟软件有限公司 | The detection method of distributed local outlier |
CN108508294A (en) * | 2018-03-29 | 2018-09-07 | 深圳众厉电力科技有限公司 | A kind of high ferro electric energy quality monitoring system |
Non-Patent Citations (2)
Title |
---|
严宇平,萧展辉: "基于聚类分析的离群检测方法在电网数据质量管理中的应用研究", 《现代电子技术》 * |
钟庆,刘峰,王钢,力海峰: "电能质量监测数据中间距离法聚类分析", 《电力***及其自动化学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109583599A (en) * | 2018-11-23 | 2019-04-05 | 广州供电局有限公司 | Abnormal state detection method |
CN110287256A (en) * | 2019-06-14 | 2019-09-27 | 南京邮电大学 | A kind of electric network data parallel processing system (PPS) and its processing method based on cloud computing |
CN110287256B (en) * | 2019-06-14 | 2022-10-14 | 南京邮电大学 | Cloud computing-based power grid data parallel processing system and processing method thereof |
CN112699113A (en) * | 2021-01-12 | 2021-04-23 | 上海交通大学 | Industrial manufacturing process operation monitoring system driven by time sequence data stream |
CN113421176A (en) * | 2021-07-16 | 2021-09-21 | 昆明学院 | Intelligent abnormal data screening method |
CN113421176B (en) * | 2021-07-16 | 2022-11-01 | 昆明学院 | Intelligent screening method for abnormal data in student score scores |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108761227A (en) | A kind of high ferro power quality data processing system | |
CN103617568B (en) | Setting method for abnormal data determination threshold in steady-state power quality early-warning mechanism | |
CN113267692B (en) | Low-voltage transformer area line loss intelligent diagnosis and analysis method and system | |
Zhang et al. | State-of-health estimation of batteries in an energy storage system based on the actual operating parameters | |
CN108376262A (en) | A kind of analysis model construction method of wind power output typical characteristics | |
CN108508294A (en) | A kind of high ferro electric energy quality monitoring system | |
CN112712281B (en) | Cloud model-based energy storage working condition adaptability comprehensive evaluation method and system | |
CN103886518A (en) | Early warning method for voltage sag based on electric energy quality data mining at monitoring point | |
CN102157949A (en) | Small-signal stability prediction and decision support method | |
CN108957331A (en) | Battery performance detection method and battery performance detection system | |
CN112990627B (en) | Power quality evaluation method | |
CN111612326A (en) | Comprehensive evaluation method for power supply reliability of distribution transformer | |
CN112785060A (en) | Lean operation and maintenance level optimization method for power distribution network | |
CN114611842B (en) | Whole-county roof distributed photovoltaic power prediction method | |
CN108681802A (en) | A kind of electric vehicle electrically-charging equipment Information Interoperability evaluation method | |
CN113327052A (en) | Energy efficiency improvement-based comprehensive energy system energy efficiency assessment method and system | |
CN112014758B (en) | Method and system for analyzing battery performance based on event information of battery management system | |
Liu et al. | Research on the transformer area recognition method based on improved K-means clustering algorithm | |
CN109490622A (en) | A kind of electricity data calibration technology based on tri-state information | |
Zhang et al. | Power allocation method of battery energy storage system considering state balance in smoothing photovoltaic power fluctuations | |
CN115034922A (en) | Non-invasive industrial load monitoring method | |
CN112488360B (en) | Distribution variation routine analysis early warning method based on artificial intelligence | |
Zhang et al. | Clustering analysis of user load characteristics under new power system based on improved k-means clustering algorithm | |
CN111898871A (en) | Power grid power end data quality evaluation method, device and system | |
Yang et al. | Wind-storage combined system based on just-in-time-learning prediction model with dynamic error compensation |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181106 |
|
RJ01 | Rejection of invention patent application after publication |