CN109636029A - Power distribution network middle or short term voltage out-of-limit method for early warning based on big data - Google Patents
Power distribution network middle or short term voltage out-of-limit method for early warning based on big data Download PDFInfo
- Publication number
- CN109636029A CN109636029A CN201811500365.5A CN201811500365A CN109636029A CN 109636029 A CN109636029 A CN 109636029A CN 201811500365 A CN201811500365 A CN 201811500365A CN 109636029 A CN109636029 A CN 109636029A
- Authority
- CN
- China
- Prior art keywords
- limit
- month
- voltage
- data
- main reason
- 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.)
- Granted
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 10
- 238000007637 random forest analysis Methods 0.000 claims abstract description 40
- 230000001131 transforming effect Effects 0.000 claims abstract description 9
- 238000003066 decision tree Methods 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 26
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000015572 biosynthetic process Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000012502 risk assessment Methods 0.000 abstract description 3
- 230000004927 fusion Effects 0.000 abstract description 2
- 238000005457 optimization Methods 0.000 abstract description 2
- 235000013399 edible fruits Nutrition 0.000 description 10
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 4
- 230000009977 dual effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Power distribution network middle or short term voltage out-of-limit method for early warning based on big data.It is related to electric system early warning technology field.Propose a kind of clear logic, step orderly and can centering whether voltage out-of-limit in a short time carries out the power distribution network middle or short term voltage out-of-limit method for early warning based on big data that is good, effectively judging.The present invention passes through fusion distribution network voltage risk analysis various dimensions related data, realize that the separate unit distribution transforming middle or short term voltage out-of-limit under the influence of multiple factors is predicted using random forest technology, identify separate unit distribution transforming middle or short term voltage limit risk type, and out-of-limit risk probability is provided, effectively promote the optimization Governance Ability to the out-of-limit problem of middle or short term distribution network voltage.Have the advantages that on the whole clear logic, step orderly and can centering whether voltage out-of-limit in a short time carries out good, effective judgement.
Description
Technical field
The present invention relates to electric system early warning technology fields.
Background technique
Currently, research of the people to distribution network voltage control technology, develops correlation and is broadly divided into three phases: not considering
Traditional reactive power/voltage control stage of distributed generation resource, the distributed autonomous control stage for considering distributed generation resource and consideration point
The centralized Collaborative Control stage of cloth power supply.The grid company of various countries and research institution fully recognize idle configuration not
Shadow of the factors such as voltage fluctuation and distributed generation resource access caused by foot, burden with power fluctuation to distribution network voltage risk
It rings, and certain research has been made to the basic theory of voltage risk judgment.But matching by distribution automation system data driving
Network voltage risk analysis and anticipation technology, need further to study.Wherein, voltage risk refers to voltage fluctuation to normal
198V-242V except, there is voltage out-of-limit, to impact to operation of power networks.
Summary of the invention
The present invention in view of the above problems, propose a kind of clear logic, step orderly and can centering in a short time voltage whether
It is out-of-limit to carry out the power distribution network middle or short term voltage out-of-limit method for early warning based on big data that is good, effectively judging.
The technical solution of the present invention is as follows: being operated according to the following steps:
1), the influence factor of analysis and research voltage out-of-limit: by the scientific documents guidance of early period and finding, electricity is drafted
Out-of-limit correlative factor is pressed, capacity of distribution transform is specifically included that, holds with Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line
Amount, power factor (PF), power supply distance, bussed supply radius and climate temperature;
2) it, analyzes out-of-limit main reason: transferring the related data that the out-of-limit platform area of overvoltage once occurs, utilize correlation
Data establish the Logic Regression Models of voltage out-of-limit phenomenon Yu each relation factor:
Wherein p is of that month out-of-limit probability, and x is the correlative factor of a upper month voltage out-of-limit, i.e., is with the distribution transforming section time
It is no to cross the border as output variable, it is successively defeated as input variable using each influence factor fluctuation characteristic of transformer for the previous period
Enter in Logic Regression Models, be trained using Logic Regression Models and learn, it is out-of-limit to analyze each area for statistical correlation degree
Main reason;
It obtains, mean value, the mean value of power distribution voltage, the maximum of the maximum difference with Variable power, feeder line power of busbar voltage
Difference and out-of-limit relevance are maximum, are out-of-limit main reason;
3), by the data of main reason relevant to place distribution network voltage risk by extracting, pre-processing and being fused to
In distribution network voltage risk anticipation analysis mark sheet;
4), the following first month prediction:
4.1), training Random Forest model: the data of the main reason of a upper month voltage out-of-limit and this month are out-of-limit
In the data input Random Forest model of situation, several decision trees one are established;
4.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees one and are predicted, are obtained
Occurs most results in several results as the prediction result whether out-of-limit to next month voltage as a result, taking to several;
5), the following second month prediction:
5.1), training Random Forest model: by the data of the main reason of second month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees two are established;
5.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees two and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following second month voltage as a result, taking to several
Fruit;
6), the following third month prediction:
6.1), training Random Forest model: by the data of the main reason of month voltage out-of-limit of third before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees three are established;
6.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees three and are predicted, are obtained
Occurs most results in several results as to the whether out-of-limit prediction knot of the following third month voltage as a result, taking to several
Fruit;
7) it, predicts within following four month:
7.1), training Random Forest model: by the data of the main reason of four month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees four are established;
7.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees four and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following four month voltage as a result, taking to several
Fruit;
8) it, predicts within following five month:
8.1), training Random Forest model: by the data of the main reason of five month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees five are established;
8.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees five and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following five month voltage as a result, taking to several
Fruit;
9) it, predicts within following six month:
9.1), training Random Forest model: by the data of the main reason of six month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees six are established;
9.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees six and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following six month voltage as a result, taking to several
Fruit;
10), result is integrated: being counted to one to six month whether out-of-limit prediction result of voltage of future;It finishes.
Correlative factor in the step 2) according to voltage out-of-limit repeatedly establishes Logic Regression Models, and x is used as and matches each time
Varying capacity is supplied with Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line capacity, power factor (PF), power supply distance, bus
One in electric radius and climate temperature.
The present invention is realized more by fusion distribution network voltage risk analysis various dimensions related data using random forest technology
Separate unit distribution transforming middle or short term voltage out-of-limit prediction under the influence of weight factor, identifies separate unit distribution transforming middle or short term voltage limit risk type,
And out-of-limit risk probability is provided, effectively promote the optimization Governance Ability to the out-of-limit problem of middle or short term distribution network voltage.On the whole
Have the advantages that clear logic, step orderly and can centering whether voltage out-of-limit in a short time carries out good, effective judgement.
Detailed description of the invention
Flow diagram is predicted in this case of Fig. 1.
Specific embodiment
The present invention operates according to the following steps:
1), the influence factor of analysis and research voltage out-of-limit: by the scientific documents guidance of early period and finding, electricity is drafted
Out-of-limit correlative factor is pressed, capacity of distribution transform is specifically included that, holds with Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line
Amount, power factor (PF), power supply distance, bussed supply radius and climate temperature;
2) it, analyzes out-of-limit main reason: transferring the related data that the out-of-limit platform area of overvoltage once occurs, utilize correlation
Data establish the Logic Regression Models of voltage out-of-limit phenomenon Yu each relation factor:
Wherein p is of that month out-of-limit probability, and x is the correlative factor of a upper month voltage out-of-limit, i.e., is with the distribution transforming section time
It is no to cross the border as output variable, it is successively defeated as input variable using each influence factor fluctuation characteristic of transformer for the previous period
Enter in Logic Regression Models, be trained using Logic Regression Models and learn, it is out-of-limit to analyze each area for statistical correlation degree
Main reason;
It obtains, mean value, the mean value of power distribution voltage, the maximum of the maximum difference with Variable power, feeder line power of busbar voltage
Difference and out-of-limit relevance are maximum, are out-of-limit main reason;
3), by the data of main reason relevant to place distribution network voltage risk by extracting, pre-processing and being fused to
In distribution network voltage risk anticipation analysis mark sheet;The out-of-limit factor correlation acquisition Data Data quality of distribution transforming is to future anticipation model
It has a significant impact, needs to pre-process Raw data quality and cleaned;Power distribution voltage is greater than 0 less than 110 or greater than 330
Data point is set to invalid data, deletes the invalid power distribution voltage data of whole data;According to low-voltage overvoltage standard, to acquisition
Transformer situation of crossing the border is identified and is marked that mesolow is identified as -1 in data, is normally identified as 0, high pressure is identified as 1.
Based on the data after data prediction and cleaning, the anticipation of distribution network voltage risk and assistant analysis characteristic are calculated;Each moon matches
The fluctuation characteristics such as time variant voltage and power, busbar voltage, feeder line power, and related fixed attribute correlative factor, by structuring number
According to importing database purchase;
Pre- flow gauge is as shown in Figure 1;
4), the following first month prediction:
4.1), training Random Forest model: the data of the main reason of a upper month voltage out-of-limit and this month are out-of-limit
In the data input Random Forest model of situation, several decision trees one are established;
4.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees one and are predicted, are obtained
Occurs most results in several results as the prediction result whether out-of-limit to next month voltage as a result, taking to several;With
Mode is extracted using to sample and variable dual random when the training of machine forest model, constructs short-run decision tree several different,
It is prejudged from different dimensions to whether power distribution voltage crosses the border, last according to the minority is subordinate to the majority, principle realization is pre- to voltage out-of-limit
Sentence, and obtains its out-of-limit probability;
5), the following second month prediction:
5.1), training Random Forest model: by the data of the main reason of second month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees two are established;
5.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees two and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following second month voltage as a result, taking to several
Fruit;
6), the following third month prediction:
6.1), training Random Forest model: by the data of the main reason of month voltage out-of-limit of third before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees three are established;
6.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees three and are predicted, are obtained
Occurs most results in several results as to the whether out-of-limit prediction knot of the following third month voltage as a result, taking to several
Fruit;
7) it, predicts within following four month:
7.1), training Random Forest model: by the data of the main reason of four month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees four are established;
7.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees four and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following four month voltage as a result, taking to several
Fruit;
8) it, predicts within following five month:
8.1), training Random Forest model: by the data of the main reason of five month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees five are established;
8.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees five and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following five month voltage as a result, taking to several
Fruit;
9) it, predicts within following six month:
9.1), training Random Forest model: by the data of the main reason of six month voltage out-of-limit before this month and
In the data input Random Forest model of of that month out-of-limit situation, several decision trees six are established;
9.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees six and are predicted, are obtained
Occurs most results in several results as the prediction knot whether out-of-limit to the following six month voltage as a result, taking to several
Fruit;
10), result is integrated: being counted to one to six month whether out-of-limit prediction result of voltage of future;It finishes.
It needs to pre-process training data before model training, the out-of-limit situation distribution of distribution transforming is obvious uneven, and it is first right to need
Data distribution is modified, and considers that examinee produces environmental samples distribution asymmetry, normal voltage and the voltage ratio that crosses the border in training sample
Example is set as 10:1, owes example-based approach equilibrium data using normal transformer.There are dimension gaps for each dimension data of characteristic table, will
Hough transformation is between 0-1.Training set and test set: it uses and randomly selects and predict two ways month by month.
It realizes the early warning of middle or short term voltage out-of-limit, needs to consider machine learning time span problem, model prejudges time span
It should be consistent with model training time span.In conjunction with actual production environment, time span select 1 month it is relatively reasonable, i.e., with
Cross the border situation and front 1 month (or 2-6 months) of this month is trained, and is realized using of that month data to (or 2-6 1 month following
A month) out-of-limit early warning, each moon prediction result is integrated, to realize middle or short term voltage out-of-limit early warning.In actual use, by
The month where month and prediction result where main reason in input is closer, and the accuracy of prediction is higher, therefore, each
The moon is both needed to predict the following half a year.
Mode is extracted using to sample and variable dual random when Random Forest model training, constructs several different determine
Plan tree, different decision trees prejudge from different dimensions to whether power distribution voltage crosses the border, last root as the expert of different field
According to the minority is subordinate to the majority, principle is realized to voltage out-of-limit anticipation, and obtains its out-of-limit probability.Random Forest model needs training 6
It is secondary, respectively obtain the anticipation result and anticipation probability of each moon step-length of 1-6, and accordingly it is comprehensive obtain it is following cross the border within 6 months situation and
Probability.
Correlative factor in the step 2) according to voltage out-of-limit repeatedly establishes Logic Regression Models, and x is used as and matches each time
Varying capacity is supplied with Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line capacity, power factor (PF), power supply distance, bus
One in electric radius and climate temperature.
Claims (2)
1. the power distribution network middle or short term voltage out-of-limit method for early warning based on big data, which is characterized in that operated according to the following steps:
1) it, the influence factor of analysis and research voltage out-of-limit: by the scientific documents guidance of early period and finding, drafts voltage and gets over
The correlative factor of limit, specifically include that capacity of distribution transform, with Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line capacity,
Power factor (PF), power supply distance, bussed supply radius and climate temperature;
2) it, analyzes out-of-limit main reason: transferring the related data that the out-of-limit platform area of overvoltage once occurs, utilize related data
Establish the Logic Regression Models of voltage out-of-limit phenomenon Yu each relation factor:
Whether wherein p is of that month out-of-limit probability, and x is the correlative factor of a upper month voltage out-of-limit, i.e., sent out with the distribution transforming section time
Life is crossed the border as output variable, is sequentially input and is patrolled as input variable using each influence factor fluctuation characteristic of transformer for the previous period
In volume regression model, it is trained and is learnt using Logic Regression Models, statistical correlation degree, out-of-limit main in each area of analysis
The origin cause of formation;
Obtain, the mean value of busbar voltage, the mean value of power distribution voltage, the maximum difference with Variable power, feeder line power maximum difference
It is maximum with out-of-limit relevance, it is out-of-limit main reason;
3), by the data of main reason relevant to place distribution network voltage risk by extracting, pre-processing and be fused to distribution
In net voltage risk anticipation analysis mark sheet;
4), the following first month prediction:
4.1), training Random Forest model: by the data of the main reason of a upper month voltage out-of-limit and of that month out-of-limit situation
Data input Random Forest model in, establish several decision trees one;
4.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees one and are predicted, if obtaining
It is dry to occur most results in several results as the prediction result whether out-of-limit to next month voltage as a result, taking;
5), the following second month prediction:
5.1), training Random Forest model: by the data of the main reason of second month voltage out-of-limit and this month before this month
In the data input Random Forest model of out-of-limit situation, several decision trees two are established;
5.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees two and are predicted, if obtaining
It is dry to occur most results in several results as the prediction result whether out-of-limit to the following second month voltage as a result, taking;
6), the following third month prediction:
6.1), training Random Forest model: by the data of the main reason of third before this month month voltage out-of-limit and this month
In the data input Random Forest model of out-of-limit situation, several decision trees three are established;
6.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees three and are predicted, if obtaining
It is dry most results occur as to the whether out-of-limit prediction result of the following third month voltage as a result, taking in several results;
7) it, predicts within following four month:
7.1), training Random Forest model: by the data of the main reason of four month voltage out-of-limit and this month before this month
In the data input Random Forest model of out-of-limit situation, several decision trees four are established;
7.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees four and are predicted, if obtaining
It is dry to occur most results in several results as the prediction result whether out-of-limit to the following four month voltage as a result, taking;
8) it, predicts within following five month:
8.1), training Random Forest model: by the data of the main reason of five month voltage out-of-limit and this month before this month
In the data input Random Forest model of out-of-limit situation, several decision trees five are established;
8.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees five and are predicted, if obtaining
It is dry to occur most results in several results as the prediction result whether out-of-limit to the following five month voltage as a result, taking;
9) it, predicts within following six month:
9.1), training Random Forest model: by the data of the main reason of six month voltage out-of-limit and this month before this month
In the data input Random Forest model of out-of-limit situation, several decision trees six are established;
9.2) it, predicts: the data of the main reason of of that month voltage out-of-limit being inputted in all decision trees six and are predicted, if obtaining
It is dry to occur most results in several results as the prediction result whether out-of-limit to the following six month voltage as a result, taking;
10), result is integrated: being counted to one to six month whether out-of-limit prediction result of voltage of future;It finishes.
2. the power distribution network middle or short term voltage out-of-limit method for early warning according to claim 1 based on big data, which is characterized in that
Correlative factor in the step 2) according to voltage out-of-limit repeatedly establishes Logic Regression Models, each time x as capacity of distribution transform, match
Variable power, power distribution voltage, busbar voltage, feeder line power, feeder line capacity, power factor (PF), power supply distance, bussed supply radius and
One in climate temperature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811500365.5A CN109636029B (en) | 2018-12-10 | 2018-12-10 | Power distribution network medium-short term voltage out-of-limit early warning method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811500365.5A CN109636029B (en) | 2018-12-10 | 2018-12-10 | Power distribution network medium-short term voltage out-of-limit early warning method based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109636029A true CN109636029A (en) | 2019-04-16 |
CN109636029B CN109636029B (en) | 2020-07-24 |
Family
ID=66072300
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811500365.5A Active CN109636029B (en) | 2018-12-10 | 2018-12-10 | Power distribution network medium-short term voltage out-of-limit early warning method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109636029B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110266000A (en) * | 2019-06-17 | 2019-09-20 | 国网江苏省电力有限公司 | A kind of out-of-limit analysis of causes method of distribution network voltage, system and storage medium |
CN110739698A (en) * | 2019-11-20 | 2020-01-31 | 国网山东省电力公司潍坊市寒亭区供电公司 | 10kV bus voltage and public distribution transformer outlet voltage allocation method and system |
CN117614132A (en) * | 2023-11-27 | 2024-02-27 | 广州航海学院 | Distribution transformer voltage out-of-limit portrait method and device for power distribution network |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107666148A (en) * | 2017-08-10 | 2018-02-06 | 国网浙江宁波市鄞州区供电公司 | Line fault analysis method based on distribution transforming power cut signal |
CN108022001A (en) * | 2017-09-20 | 2018-05-11 | 河海大学 | Short term probability density Forecasting Methodology based on PCA and quantile estimate forest |
CN108123436A (en) * | 2017-12-01 | 2018-06-05 | 国网浙江省电力公司绍兴供电公司 | Voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm |
-
2018
- 2018-12-10 CN CN201811500365.5A patent/CN109636029B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107666148A (en) * | 2017-08-10 | 2018-02-06 | 国网浙江宁波市鄞州区供电公司 | Line fault analysis method based on distribution transforming power cut signal |
CN108022001A (en) * | 2017-09-20 | 2018-05-11 | 河海大学 | Short term probability density Forecasting Methodology based on PCA and quantile estimate forest |
CN108123436A (en) * | 2017-12-01 | 2018-06-05 | 国网浙江省电力公司绍兴供电公司 | Voltage out-of-limit prediction model based on principal component analysis and multivariate regression algorithm |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110266000A (en) * | 2019-06-17 | 2019-09-20 | 国网江苏省电力有限公司 | A kind of out-of-limit analysis of causes method of distribution network voltage, system and storage medium |
CN110266000B (en) * | 2019-06-17 | 2022-07-19 | 国网江苏省电力有限公司 | Power distribution network voltage out-of-limit reason analysis method, system and storage medium |
CN110739698A (en) * | 2019-11-20 | 2020-01-31 | 国网山东省电力公司潍坊市寒亭区供电公司 | 10kV bus voltage and public distribution transformer outlet voltage allocation method and system |
CN110739698B (en) * | 2019-11-20 | 2023-07-28 | 国网山东省电力公司潍坊市寒亭区供电公司 | Method and system for allocating 10kV bus voltage and public distribution transformer outlet voltage |
CN117614132A (en) * | 2023-11-27 | 2024-02-27 | 广州航海学院 | Distribution transformer voltage out-of-limit portrait method and device for power distribution network |
CN117614132B (en) * | 2023-11-27 | 2024-06-11 | 广州航海学院 | Distribution transformer voltage out-of-limit portrait method and device for power distribution network |
Also Published As
Publication number | Publication date |
---|---|
CN109636029B (en) | 2020-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106779087B (en) | A kind of general-purpose machinery learning data analysis platform | |
WO2021073462A1 (en) | 10 kv static load model parameter identification method based on similar daily load curves | |
CN106845717B (en) | Energy efficiency evaluation method based on multi-model fusion strategy | |
CN109840541A (en) | A kind of network transformer Fault Classification based on XGBoost | |
CN104820707B (en) | One kind being based on the architectonic B/S patterns automatic volume group method of computer realm | |
CN107918830B (en) | Power distribution network running state evaluation method based on big data technology | |
CN111429027A (en) | Regional power transmission network operation multidimensional analysis method based on big data | |
CN109636029A (en) | Power distribution network middle or short term voltage out-of-limit method for early warning based on big data | |
CN106779277B (en) | Classified evaluation method and device for network loss of power distribution network | |
CN104657718A (en) | Face recognition method based on face image feature extreme learning machine | |
CN112613536B (en) | Near infrared spectrum diesel fuel brand recognition method based on SMOTE and deep learning | |
CN109614488A (en) | Distribution network live line work condition distinguishing method based on text classification and image recognition | |
CN104820724B (en) | Text class educational resource knowledge point forecast model preparation method and application method | |
CN114092832A (en) | High-resolution remote sensing image classification method based on parallel hybrid convolutional network | |
CN105512808A (en) | Power system transient stability assessment method based on big data | |
CN108334894B (en) | Unsupervised machine learning-based transformer oil temperature abnormity identification method | |
CN106597154B (en) | Transformer fault diagnosis method for improving based on DAG-SVM | |
CN113837464A (en) | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention | |
CN112200263B (en) | Self-organizing federal clustering method applied to power distribution internet of things | |
CN106650959A (en) | Power distribution network repair ability assessment method based on improved grey clustering | |
CN104077493A (en) | Method for constructing state evaluation index system of electric relaying protection system | |
CN110705859A (en) | PCA-self-organizing neural network-based method for evaluating running state of medium and low voltage distribution network | |
CN114266297A (en) | Semantic knowledge base of thermal power equipment, construction method and zero sample fault diagnosis method | |
CN114693087A (en) | Multi-scale energy consumption model of urban energy system and energy flow monitoring method thereof | |
CN112330191A (en) | Education teaching evaluation system based on artificial intelligent blackboard and evaluation method thereof |
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 |