CN104866926B - Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis - Google Patents
Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis Download PDFInfo
- Publication number
- CN104866926B CN104866926B CN201510289912.XA CN201510289912A CN104866926B CN 104866926 B CN104866926 B CN 104866926B CN 201510289912 A CN201510289912 A CN 201510289912A CN 104866926 B CN104866926 B CN 104866926B
- Authority
- CN
- China
- Prior art keywords
- distribution network
- network failure
- time series
- factor
- prediction
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis that the present invention relates to a kind of, includes the following steps：1) outside weather data judge residing season during prediction during obtaining prediction, establish corresponding distribution network failure quantitative forecast regression model according to residing season, obtain by the number of faults under the influence of outside weather factor；2) distribution network failure quantitative forecast ARIMA models are established, are obtained by the number of faults under the influence of the other factors other than outside weather factor；3) number of faults that step 1) and step 2) obtain is summed up, obtains final Distribution Network Failure quantitative forecast value.Compared with prior art, the present invention has many advantages, such as that number of faults precision of prediction is high.
Description
Technical field
The present invention relates to distribution network failure quantitative forecast technical fields, and meteorologic factor and time are based on more particularly, to one kind
The distribution network failure quantitative forecasting technique of sequence analysis.
Background technology
With the development of China's economic society, requirement of the client to power supply reliability is higher and higher.Power distribution network is as entire
The end Network of electric system, complicated, in large scale, electric company will configure vast resources and solve power distribution network event daily
Barrier.It is horizontal to reach higher electric service, shorten the breakdown repair time as far as possible, electric company needs look-ahead subsequently several
It number of faults repairs resource to shift to an earlier date config failure.Therefore, realize that distribution network failure quantity is accurately short-term pre-
It surveys, it is horizontal to improving electric service, the repairing level of resources utilization is promoted, is of great significance.
Currently, being concentrated mainly on fault location and diagnosis, repairing task for the research in terms of distribution network failure both at home and abroad
Distribution, breakdown repair strategy and the optimization etc. for repairing flow and path, for distribution network failure quantitative forecast problem
It studies relatively fewer.
Invention content
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind being based on meteorologic factor
With the distribution network failure quantitative forecasting technique of time series analysis.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis, includes the following steps：
1) outside weather data judge residing season during prediction during obtaining prediction, are established according to residing season corresponding
Distribution network failure quantitative forecast regression model is obtained by the number of faults under the influence of outside weather factor；
2) distribution network failure quantitative forecast ARIMA models are established, are obtained by the other factors shadow other than outside weather factor
Number of faults under ringing；
3) number of faults that step 1) and step 2) obtain is summed up, obtains final Distribution Network Failure quantitative forecast
Value.
In step 1), the season includes winter, summer and spring and autumn, is judged according to outside weather data during prediction pre-
Residing season is specially during survey：
If lowest temperature average value was less than 10 DEG C in 7 days, it is determined as winter；
If highest temperature average value was higher than 26 DEG C in 7 days, it is determined as summer；
It is other, then it is spring and autumn.
In step 1), the distribution network failure quantitative forecast regression model includes winter prediction model, summer prediction model
With spring and autumn prediction model.
In the winter prediction model, using Distribution Network Failure quantity as dependent variable, using daily minimal tcmperature as independent variable；
In the spring and autumn prediction model, using Distribution Network Failure quantity as dependent variable, using daily mean temperature as independent variable；
It is certainly with daily maximum temperature and thunderstorm weather using Distribution Network Failure quantity as dependent variable in the summer prediction model
Variable.
The thunderstorm weather is entered in the form of dummy variable in summer prediction model, the dummy variable DThunderstormSpecially：
In the step 2), establishing distribution network failure quantitative forecast ARIMA models is specially：
201) sample failure amount time series and the corresponding outside weather data in set period of time are obtained, it will be described outer
Portion's meteorological data substitutes into distribution network failure quantitative forecast regression model, obtains by the sample failure under the influence of outside weather factor
Measure time series；
202) the sample failure amount time series under the influence of fault sample data are rejected by outside weather factor, is obtained
It obtains by the sample failure amount time series under the influence of the other factors other than outside weather factor；
203) whether the sample failure amount time series under the influence of using unit root test method to judge the other factors
Steadily, if so, thening follow the steps 204), if it is not, then being carried out to the sample failure amount time series under the influence of the other factors
Step 204) is executed after stationarity transformation；
204) required optimum prediction model is chosen according to the stable sample failure amount time series that step 203) obtains.
The prediction model includes AR models, MA models or ARIMA models.
Compared with prior art, the present invention has the following advantages：
(1) present invention establishes the distribution network failure quantitative forecast for Various Seasonal using innovative season criterion
The number of faults precision of regression model, prediction is high；
(2) present invention builds ARIMA time series predicting models for the remaining failure amount for rejecting meteorological factor influence,
The time series variation trend for capturing failure amount, is effectively predicted by the failure under the influence of the other factors other than outside weather factor
Quantity；
(3) present invention can accurately realize the short-term forecast of distribution network failure quantity degree of precision.
Description of the drawings
Fig. 1 is the flow diagram of the present invention；
Fig. 2 is Distribution Network Failure volume trends figure；
Fig. 3 is the correlativity schematic diagram of weather and failure amount；
Fig. 4 is the correlativity schematic diagram of wind-force and failure amount；
Fig. 5 is to divide season Regression Model Simulator result schematic diagram；
Fig. 6 is the failure amount sequence auto-correlation and partial autocorrelation figure for rejecting meteorological factor influence；
Fig. 7 is ARIMA (3,0,4) model autocorrelation of residuals and partial autocorrelation figure；
Fig. 8 is the fitting of total breakdown quantity and prediction case schematic diagram.
Specific implementation mode
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, give detailed embodiment and specific operating process, but protection scope of the present invention is not limited to
Following embodiments.
The distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis that the present embodiment provides a kind of, it is comprehensive
Closing multiple regression and the time series analysis means of using, structure divides the meteorological effect failure amount prediction model in season, temperature,
The quantitative relationship of the meteorologic factors such as weather and failure amount, and for the remaining failure amount for rejecting meteorological factor influence, build ARIMA
Time series predicting model captures the time series variation trend of failure amount.By the integrated application of above-mentioned model, realizes and match
The short-term forecast of electric network fault quantity degree of precision.
It causes the factor of Distribution Network Failure very much, can generally be divided into two classes：One kind is external environmental factor, such as temperature
The weather conditions such as degree, wind-force, sleet；Another kind of is the factor of equipment itself, for example, device type, manufacturer, performance parameter,
Run the time limit, maintaining etc..
External environmental factor relatively easily quantifies, and the influence factor of equipment itself because device type is various, derive from a wealth of sources,
Performance parameter differs, data accumulation scarcity etc., it is difficult to be refined and quantified, and then cannot be introduced into prediction model.Therefore, we
Selection uses compromise proposal, that is, first passes through regression model and determine influence of the outside weather factor to Distribution Network Failure quantity, pick later
Time series modeling is carried out except the number of faults that external meteorologic factor is explained, then to remaining unaccounted number of faults, is used
ARIMA methods are predicted, reverse operating is finally used, the event of number of faults and time series forecasting that meteorologic factor is explained
Barrier quantity sums up to get to final Distribution Network Failure quantitative forecast value.
The present embodiment reports data for repairment based on East China city distribution network failure, carries out distribution network failure quantity short-term forecast and grinds
Study carefully.The sample interval of the used data of the present embodiment is on December 31,1 day to 2014 January in 2014, and data acquisition is with day
Unit.Distribution Network Failure of the fault data in East China city electric power company's T CM systems reports record for repairment and (rejects client's wrong report and visitor
Family internal fault), meteorological data comes from China Meteorological Administration.The use of analysis software is Excel2007 and EViews8.
As shown in Figure 1, this approach includes the following steps：
Step S1, outside weather data judge residing season during prediction during obtaining prediction, are established according to residing season
Corresponding distribution network failure quantitative forecast regression model is obtained by the number of faults under the influence of outside weather factor；
Step S2, establishes distribution network failure quantitative forecast ARIMA models, obtain by other than outside weather factor it is other because
Number of faults under the influence of element；
Step S1 and step the S2 number of faults obtained are summed up, obtain final Distribution Network Failure quantity by step S3
Predicted value.
1, distribution network failure quantitative forecast regression model
Distribution Network Failure quantity have apparent season trend, as shown in Fig. 2, and under Various Seasonal temperature to number of faults
Influence form is different from direction, it is therefore desirable to divide the relationship of season research temperature factor and failure amount.The season include winter,
Summer and spring and autumn, residing season is specifically as shown in table 1 during judging prediction according to outside weather data during prediction：
Table 1 season judgment basis
(1) distribution network failure quantitative forecast regression model independent variable is chosen
According to the formation feature and practical experience of Distribution Network Failure, preliminary selected temperature, weather are (no rain, light rain, moderate rain, big
Rain, heavy rain, thunder shower), wind-force as influence number of faults meteorologic factor, analyze the correlativity of they and failure amount, choosing
Select has the meteorologic factor of significant correlation to enter prediction model with failure measurer.
1) correlation analysis of temperature factor and failure amount
Under Various Seasonal, the correlativity of temperature and failure amount is as shown in table 2.The absolute value of all related coefficients is more than
0.5, show that temperature has stronger correlation with failure amount, from the positive and negative as can be seen that winter and spring and autumn temperature of related coefficient
Lower failure is more, and summer temp is higher, and failure is more.
The related coefficient of table 2 temperature and failure amount
2) variance analysis that weather conditions influence failure amount
Weather conditions are qualitative variable, as shown in Figure 3 with the correlativity of failure amount.We are sentenced using variance analysis method
Whether the factor of breaking has significant correlation with failure amount.To no rain, light rain, moderate rain, heavy rain, (rainstorm weather only goes out within 2014 first
One day is now spent, data are incorporated to heavy rain scope) the failure amount under weather carries out single factor test variance point under 0.05 significance
Analysis, the results are shown in Table 3.The P-value=0.5857 ＞ 0.05 of group difference, show the days such as no rain, light rain, moderate rain, heavy rain
Influence of the gas factor to failure amount be not notable, is not considered in the prediction of consequent malfunction amount.
3 weather conditions of table (being free of thunderstorm weather) variance analysis
But thunderstorm weather is added in above-mentioned weather conditions, then carries out variance analysis, as shown in table 4, P-value substantially under
It is reduced to 0.0004,0.05 significance is much smaller than, shows that thunderstorm weather has a significant impact failure measurer, and during sample
Thunderstorm weather is only present in summer, therefore thunderstorm factor is considered in summer failure amount prediction model.
4 weather conditions of table (containing thunderstorm weather) variance analysis
3) variance analysis that wind-force factor influences failure amount
Wind-force factor is similarly qualitative variable, as shown in Figure 4 with the correlativity of failure amount.We to 3 grades and it is following, 4
Grade, 5 grades, 6-7 grade wind-force when failure amount carry out 0.05 significance under single factor test method analyze, the results are shown in Table 5.
P-value=0.2098 ＞ 0.05 show that influence of the wind-force to failure amount be not notable, are not examined in the prediction of consequent malfunction amount
Consider.
5 wind-force analysis of variance of table
(2) foundation of distribution network failure quantitative forecast regression model
Distribution network failure quantitative forecast regression model includes winter prediction model, summer prediction model and spring and autumn prediction mould
Type, wherein
In winter prediction model, using Distribution Network Failure quantity as dependent variable, using daily minimal tcmperature as independent variable；
In spring and autumn prediction model, using Distribution Network Failure quantity as dependent variable, using daily mean temperature as independent variable；
In summer prediction model, using Distribution Network Failure quantity as dependent variable, using daily maximum temperature and thunderstorm weather as independent variable.
Thunderstorm weather is entered in the form of dummy variable in summer prediction model, the dummy variable DThunderstormSpecially：
The regression result of distribution network failure quantitative forecast regression model is as shown in table 6.
Table 6 divides the distribution network failure quantitative forecast regression model in season
Based on regression result it is found that the Significance F values of three seaconal models are much smaller than 0.05, show to return
Equation is notable；The P-value of each regression parameter is respectively less than 0.05, shows influence of each independent variable to failure amount all very significantly；Three
The modified R 2 of a seaconal model is relatively low, shows that each independent variable is inadequate to the explanation degree of failure amount, reason is also equipment sheet
The other influences factor such as body does not enter model.Therefore, we carry out time series forecasting to the unaccounted failure amount of regression model,
To improve the precision of prediction of collective model.
2, distribution network failure quantitative forecast ARIMA models
ARIMA model full name autoregression difference moving average model(MA model)s, are a kind of famous Time Series Forecasting Methods.Its base
This thought is the data sequence predicted object over time and formed to be considered as a random sequence, with certain mathematical modulo
Type carrys out approximate description this sequence, this model after identified can from the past value of time series and now value come it is pre-
Survey future value；Its general literary style is ARIMA (p, d, q), and wherein p indicates that autoregressive process exponent number, d indicate that difference order, q indicate
Moving average process exponent number；Its general type is Xt=(α1Xt-1+α2Xt-2+…+αpXt-p)+(β1εt-1+β2εt-2+…+βqεt-q)；
Its modeling process generally comprises sequence stationary processing, Model Identification, model testing, models fitting and prediction.
In step S2, establishing distribution network failure quantitative forecast ARIMA models is specially：
201) sample failure amount time series and the corresponding outside weather data in set period of time are obtained, it will be described outer
Portion's meteorological data substitutes into distribution network failure quantitative forecast regression model, obtains by the sample failure under the influence of outside weather factor
Measure time series.
202) the sample failure amount time series under the influence of fault sample data are rejected by outside weather factor, is obtained
It obtains by the sample failure amount time series under the influence of the other factors other than outside weather factor, as shown in Figure 5.
203) whether the sample failure amount time series under the influence of using unit root test method to judge the other factors
Steadily, if so, thening follow the steps 204), if it is not, then being carried out to the sample failure amount time series under the influence of the other factors
Step 204) is executed after stationarity transformation.
We examine the steady of the failure amount sequence of the rejecting meteorologic factor of judgement as shown in Figure 5 by unit root (ADF)
Property.The results are shown in Table 7 for unit root test, and t statistics are -4.9371, less than facing under 1%, 5%, 10% significance
Dividing value shows that the sequence is a stable time series, without carrying out the transformation such as difference, i.e. d=0 by unit root test.
The failure amount sequence unit root that table 7 rejects meteorological factor influence is examined
204) required optimum prediction model is chosen according to the stable sample failure amount time series that step 203) obtains.
When choosing required optimum prediction model, sentenced by the partial correlation coefficient and auto-correlation coefficient of stationary time series
It is fixed.If the partial correlation coefficient of stationary time series is truncation, and auto-correlation coefficient is hangover, then can conclude that this sequence is suitble to
AR models；If the partial correlation coefficient of stationary time series is hangover, and auto-correlation coefficient is truncation, then can conclude that this sequence
It is suitble to MA models；If the partial correlation coefficient and auto-correlation coefficient of stationary time series are hangovers, this sequence is suitble to ARMA
Model.
The auto-correlation and partial autocorrelation figure of the failure amount sequence of above-mentioned rejecting meteorological factor influence are as shown in fig. 6, can see
Go out, auto-correlation coefficient obviously trails, PARCOR coefficients feature unobvious, it is believed that 1 rank truncation, it is also contemplated that hangover, because
We attempt the various combination of p, q for this, and using optimum criterion function method of fixing price, i.e. AIC criterion selects optimal models.Known by table 8,
When p=3, q=4, AIC obtains minimum value, still final selected ARIMA (3,0,4) model.
Table 8ARIMA models select
ARIMA (3,0,4) model is carried out using Eviews softwares to calculate, the results are shown in Table 9, removes the P-value of MA (2)
Outside=0.0563, slightly above 0.05, the P-value of other parameters is much smaller than 0.05, and it is good to show that each estimates of parameters has
Conspicuousness.
Table 9 ARIMA (3,0,4) model estimated result
It establishes distribution network failure quantitative forecast ARIMA models to need to verify model, judges that the information of former sequence is
No extraction is abundant, and it is white-noise process to be embodied in model residual error item.If model can be carried out follow-up pre- by examining
It surveys.Test to above-mentioned ARIMA (3,0,4) model residual error, obtain autocorrelation of residuals figure and partial autocorrelation figure (Fig. 7) and
Unit root test result (table 10).It can be seen that autocorrelation of residuals and PARCOR coefficients are in confidence interval, residual error list
The t statistics that position root is examined are much smaller than the critical value under each significance, and therefore, residual error passes through white noise verification, ARIMA
(3,0,4) model is effective, and final expression formula is：
Failure amountt=-0.3181 failure amountt-1+ 0.2586 failure amountt-2+ 0.8033 failure amountt-3+0.8882εt-1+
0.2047εt-2-0.6931εt-3-0.1846εt-4
The unit root test of table 10 ARIMA (3,0,4) model residual error
3, prediction result
The sample data of the present embodiment is predicted by the above method, fitting and the prediction result such as figure of prediction model
Shown in 8, it can be seen that model captures the basic trend of failure amount variation substantially, and overall fit situation is preferable.Model pair
The predicted value of first week distribution network failure amount in 2015 is respectively：1843、1925、1767、1533、1141、1509、1599.This
Invention prediction technique is horizontal to improving electric service, promotes distribution and repairs the level of resources utilization, has significance.
Claims (5)
1. a kind of distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis, which is characterized in that including
Following steps：
1) outside weather data judge residing season during prediction during obtaining prediction, and corresponding distribution is established according to residing season
Net number of faults predicts regression model, obtains by the number of faults under the influence of outside weather factor；
2) distribution network failure quantitative forecast ARIMA models are established, under the influence of obtaining by the other factors other than outside weather factor
Number of faults；
3) number of faults that step 1) and step 2) obtain is summed up, obtains final Distribution Network Failure quantitative forecast value；
In the step 2), establishing distribution network failure quantitative forecast ARIMA models is specially：
201) sample failure amount time series and the corresponding outside weather data in set period of time are obtained, by the external gas
Image data substitutes into distribution network failure quantitative forecast regression model, when obtaining by sample failure amount under the influence of outside weather factor
Between sequence；
202) the fault sample data reject by outside weather factor under the influence of sample failure amount time series, obtain by
Sample failure amount time series under the influence of other factors other than outside weather factor；
203) judge whether the sample failure amount time series under the influence of the other factors is steady using unit root test method,
If so, thening follow the steps 204), if it is not, then carrying out stationarity to the sample failure amount time series under the influence of the other factors
Step 204) is executed after transformation；
204) required optimum prediction model is chosen according to the stable sample failure amount time series that step 203) obtains.
2. the distribution network failure quantitative forecasting technique according to claim 1 based on meteorologic factor and time series analysis,
It is characterized in that, in step 1), the season includes winter, summer and spring and autumn, is sentenced according to outside weather data during prediction
Residing season is specially during disconnected prediction：
If lowest temperature average value was less than 10 DEG C in 7 days, it is determined as winter；
If highest temperature average value was higher than 26 DEG C in 7 days, it is determined as summer；
It is other, then it is spring and autumn.
3. the distribution network failure quantitative forecasting technique according to claim 1 based on meteorologic factor and time series analysis,
It is characterized in that, in step 1), the distribution network failure quantitative forecast regression model includes winter prediction model, summer prediction mould
Type and spring and autumn prediction model.
4. the distribution network failure quantitative forecasting technique according to claim 3 based on meteorologic factor and time series analysis,
It is characterized in that, in the winter prediction model, using Distribution Network Failure quantity as dependent variable, using daily minimal tcmperature as independent variable；
In the spring and autumn prediction model, using Distribution Network Failure quantity as dependent variable, using daily mean temperature as independent variable；
In the summer prediction model, using Distribution Network Failure quantity as dependent variable, using daily maximum temperature and thunderstorm weather as independent variable.
5. the distribution network failure quantitative forecasting technique according to claim 4 based on meteorologic factor and time series analysis,
It is characterized in that, the thunderstorm weather is entered in the form of dummy variable in summer prediction model, the dummy variable DThunderstormSpecifically
For：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510289912.XA CN104866926B (en) | 2015-05-30 | 2015-05-30 | Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510289912.XA CN104866926B (en) | 2015-05-30 | 2015-05-30 | Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104866926A CN104866926A (en) | 2015-08-26 |
| CN104866926B true CN104866926B (en) | 2018-09-18 |
Family
ID=53912746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510289912.XA Active CN104866926B (en) | 2015-05-30 | 2015-05-30 | Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104866926B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105243449A (en) * | 2015-10-13 | 2016-01-13 | 北京中电普华信息技术有限公司 | Method and device for correcting prediction result of electricity selling amount |
| CN105426991A (en) * | 2015-11-06 | 2016-03-23 | 深圳供电局有限公司 | Method and system for predicting defect rate of transformer |
| CN107993033A (en) * | 2017-11-14 | 2018-05-04 | 广东电网有限责任公司物流服务中心 | A kind of Power Material Forecasting Methodology |
| CN109063924A (en) * | 2018-08-22 | 2018-12-21 | 国网湖南省电力有限公司 | Power distribution network based on meteorological data repairs work order quantitative forecasting technique |
| CN109657835A (en) * | 2018-10-31 | 2019-04-19 | 中国电力科学研究院有限公司 | A kind of power distribution network area fault number prediction technique and system |
| CN109469896B (en) * | 2018-12-28 | 2020-06-09 | 佛山科学技术学院 | Industrial boiler fault diagnosis method and system based on time series analysis |
| CN109800995A (en) * | 2019-01-30 | 2019-05-24 | 北京数介科技有限公司 | A kind of grid equipment fault recognition method and system |
| CN110570322B (en) * | 2019-09-17 | 2023-09-12 | 西北农林科技大学 | Agricultural meteorological index insurance rate calibrating method based on time sequence simulation |
| CN112015169B (en) * | 2020-10-19 | 2021-02-09 | 金税信息技术服务股份有限公司 | Method, device and equipment for monitoring and maintaining equipment running state of intelligent equipment box |
| CN112613638A (en) * | 2020-11-30 | 2021-04-06 | 国网北京市电力公司 | Distribution network fault quantity overall trend prediction method, prediction device and processor |
| CN112187554B (en) * | 2020-12-01 | 2021-03-19 | 北京蒙帕信创科技有限公司 | Operation and maintenance system fault positioning method and system based on Monte Carlo tree search |
-
2015
- 2015-05-30 CN CN201510289912.XA patent/CN104866926B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| 基于季节ARIMA模型的华北电网售电量预测研究;崔和瑞等;《华东电力》;20090131;第37卷(第1期);第70-72页 * |
| 气象因素对北京电网设备影响的统计规律及时空分布特征;段大鹏等;《高压电器》;20130731;第49卷(第7期);第75-79页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104866926A (en) | 2015-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104866926B (en) | Distribution network failure quantitative forecasting technique based on meteorologic factor and time series analysis | |
| CN110097297B (en) | Multi-dimensional electricity stealing situation intelligent sensing method, system, equipment and medium | |
| Mahsin et al. | Modeling rainfall in Dhaka division of Bangladesh using time series analysis | |
| CN105740975B (en) | A kind of equipment deficiency assessment and prediction technique based on data correlation relation | |
| CN109766234A (en) | Disk storage capacity prediction technique based on time series models | |
| CN109376924A (en) | A kind of method, apparatus, equipment and the readable storage medium storing program for executing of material requirements prediction | |
| Haiges et al. | Forecasting electricity generation capacity in Malaysia: an auto regressive integrated moving average approach | |
| CN107832927B (en) | 10kV line variable relation evaluation method based on grey correlation analysis method | |
| CN111160791A (en) | Abnormal user identification method based on GBDT algorithm and factor fusion | |
| CN112258337B (en) | Self-complement correction base station energy consumption model prediction method | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| CN114707739A (en) | Wind-solar output prediction and market risk management and control method and system based on big data | |
| CN115759708A (en) | Line loss analysis method and system considering power space-time distribution characteristics | |
| CN116523140A (en) | Method and device for detecting electricity theft, electronic equipment and storage medium | |
| CN114399076A (en) | Method for screening electricity stealing suspicion users based on big data analysis | |
| CN117474584A (en) | Electric power customer demand prediction and analysis system based on big data | |
| CN117934135A (en) | Network operation management method and device, electronic equipment and storage medium | |
| CN112950048A (en) | National higher education system health evaluation based on fuzzy comprehensive evaluation | |
| CN109598052A (en) | Intelligent electric meter life cycle prediction technique and device based on correlation analysis | |
| CN116231624A (en) | Photovoltaic module output power prediction method for evaluating economic benefit of photovoltaic power station | |
| Andrei et al. | Saving and economic growth: An empirical analysis for Euro area countries | |
| CN116756505B (en) | Photovoltaic equipment intelligent management system and method based on big data | |
| CN108710999A (en) | The confidence level automatic evaluation method of shared resource under a kind of environment based on big data | |
| CN118280069A (en) | GIS-based power grid disaster monitoring and early warning system | |
| CN116069674B (en) | Security assessment method and system for grade assessment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |