CN104268660A - Trend recognition method for electric power system predication-like data - Google Patents
Trend recognition method for electric power system predication-like data Download PDFInfo
- Publication number
- CN104268660A CN104268660A CN201410539260.6A CN201410539260A CN104268660A CN 104268660 A CN104268660 A CN 104268660A CN 201410539260 A CN201410539260 A CN 201410539260A CN 104268660 A CN104268660 A CN 104268660A
- Authority
- CN
- China
- Prior art keywords
- trend
- time
- data
- period
- time series
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000005070 sampling Methods 0.000 claims abstract description 11
- 230000003247 decreasing effect Effects 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 10
- 230000001174 ascending effect Effects 0.000 claims description 5
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract 1
- 230000008859 change Effects 0.000 description 9
- 230000002354 daily effect Effects 0.000 description 6
- 230000003203 everyday effect Effects 0.000 description 5
- 230000007774 longterm Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 206010003830 Automatism Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000714 time series forecasting 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
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to a trend recognition method for electric power system predication-like data. The method includes the following steps that the predication-like data are read; discretization is performed on the predication-like data to form time sequence data equal in time interval; the time sequence sampling period, the minimum value, the time point of the minimum value, the maximum value and the time point of the maximum value and the fluctuation range of the time sequence data are determined; a time frame fluctuation threshold is determined; on the basis of the time frame fluctuation threshold, the time sequence data are divided into various trend time frames; whether all the time sequence data are recognized or not is judged; all the trend time frames are judged, the trend time frame smaller than the minimum value of the time frames serves as an invalid time frame, and the invalid frame and the adjacent time frame are merged; trend time frames available within the sampling period of electric power system optimal control are formed. The method analyzes the result of the electric power system predication-like data to recognize a load or power generation increasing trend and a load or power decreasing trend, and therefore trend recognition information needed by optimal control is formed.
Description
Technical field
The present invention relates to a kind of discrimination method of technical field of power dispatching automation, specifically relate to the trend identify method of a kind of electric system prediction class data.
Background technology
At present, generally get with manual read the trend that typical load curve analyzes load prediction data in electric system, for local load character, in conjunction with the load trend checked, determine load lifting trend.Or adopt typical load trend, as load lifting trend.For the trend identify of wind-powered electricity generation and photovoltaic in electric system, be then relatively determining by generated output in some cycles.
Electrical network is subject to the impact of Different factor every day, and the predicted data of every day is the load/generating predicted value provided according to time series, wherein affected because have: trend factor, periodic factors, seasonal factor, enchancement factor.Time series forecasting data show stochastic volatility usually, but in a time period, time series still may show to a much higher value or the more gradual change of low value or movement.Seasonal effect in time series gradual change is referred to as time series trend.Usually there is different load variations trend in the different time periods in various places in the load of a day.Although the load variations trend of every day all changes, every day, the fluctuation of load variations had feature local separately, and had certain periodicity.Wind-powered electricity generation in new forms of energy and photovoltaic generation are also along with local weather conditions, daytime change and have certain periodic law.
From the angle of area power grid, need to avoid discrete device frequently to regulate in power grid control, and the key avoiding discrete device frequently to regulate makes the adjustment of discrete device consistent with the variation tendency of load.Typically, the load variations of a day has obvious peak valley feature two peak two paddy or three peak three paddy.Load climb the peak period, along with the rising of burden with power, load or burden without work also rises thereupon, and line voltage has a declining tendency, and regional voltage control system only should allow to cut reactance, throws electric capacity, upshift position, then should carry out inverse operation in the landslide period of load.The adjustment situation of area tune voltage control system reflects that the frequent adjustment of reactive voltage conditioning equipment is because the control strategy of system is not consistent with the variation tendency of load mostly, namely carries out contrary operation because of the change of load after causing discrete device to adjust in the short period.Therefore can consider to utilize short-term or ultra-short term result, filter small size load fluctuation, predict the roughly variation tendency of one day internal loading, and then the time is divided into multiple period, such as four ~ six periods, and determine that the reactive voltage of corresponding period regulates direction according to the load general morphologictrend of this period.
The trend of exerting oneself of new forms of energy is determined by the randomness of new forms of energy and electric system self-characteristic, understands this characteristic and all have great importance for solving the safety of wind-electricity integration electric system, stable operation and the quality of power supply etc.The trend identify of the predicted data of exerting oneself of new forms of energy directly affects the benefit of economic load dispatching, and the correctness improving identification can reduce margin capacity, reduce exert oneself adjustment and start-stop unit outside the plan temporarily.
Along with the fast development of economy, electric system scale is increasing, and automaticity becomes more and more higher.The thing followed is the requirement of the control of the electric system that improve dispatching automation field.In order to meet and adapt to the control overflow of electric system, must predict that accurate trend identify is carried out in class data such as load prediction, wind-powered electricity generation prediction, photovoltaic prediction etc. to electric system, so that according to these identification trend in electrical network analysis control system, analytical calculation, meets reliability and the accuracy requirement of power grid control.
Summary of the invention
For the deficiencies in the prior art, the object of this invention is to provide the trend identify method of a kind of electric system prediction class data, the result of the method to electric system prediction class data is analyzed, carry out the identification of load or generating rising tendency and reduction trend, form the trend identify information met needed for optimal control.
The object of the invention is to adopt following technical proposals to realize:
The invention provides the trend identify method of a kind of electric system prediction class data, its improvements are, described method comprises the steps:
(1) prediction class data are read;
(2) sliding-model control is carried out, the time series data of formation time interval equalization to prediction class data;
(3) the time series sampling period of time series data, the minimum value of time series data and time point, the maximal value of time series data and the fluctuating range (representing time series data size and variation tendency thereof by curve form) of time point and time series data thereof is determined;
(4) period fluctuation threshold is determined;
(5) based on period fluctuation threshold, time series data is divided into each trend period;
(6) whether identification is complete to judge time series data;
(7) each trend period is differentiated, is less than the period of period minimum the trend period as inactive time period, merges with attached adjacent time interval;
(8) form electric power system optimization and control the trend period available in the sampling period.
Further, in described step (3), by scanning time series data, the time series sampling period in acquisition time series data, the minimum value of time series data and time point, the maximal value of time series data and the fluctuating range basic feature information of time point and time series data thereof.
Further, in described step (4), by fluctuation threshold, the mark whether deterministic trend turns to; Described fluctuation threshold is determined by the component type of power grid control or control system feature.
Further, in described step (5), the trend period comprises ascending sequence and decreasing sequence;
From the curve fluctuation minimum value time and being initial default trend with ascendant trend analysis time data, turn to when fluctuation tendency and fluctuate lower than one of this period maximal value threshold value time time series be an ascending sequence;
From curve fluctuation maximal value time be current trend analysis data with downtrending, turn to when fluctuation tendency and fluctuate higher than of this period minimum threshold value time time series be a decreasing sequence.Further, in described step (6), when time series arrives last data, check whether analyze data reaches time series data maximum, if no, then turnaround time sequence data first data start analyze, until the minimum value place of curve.
Further, in described step (7), described period minimum is defaulted as 30 minutes, by component type or the decision of control system feature of power grid control.
Compared with the prior art, the beneficial effect that the present invention reaches is:
The trend of traditional prediction class data be by manually specify or simple before and after load data contrast and judge.The method of manually specifying can not carry out the adjustment of trend identify automatically according to prediction class data variation.Simple front and back Data Comparison is comparatively responsive to load data fluctuation problem, and bad to trend subsection efect.
The trend identify method being applicable to the prediction class data of electric system provided by the invention, power prediction class data are converted into time series data according to corresponding time point, the Long-term change trend of per a period of time is obtained by analyzing data variation, then the time span for each Long-term change trend merges according to actual requirement, forms electrical network and controls available tendency information in real time.
By the time series to predicted data, and the analysis to data variation, can Fast Identification load/variation tendency of exerting oneself and affiliated period, and then merge and eliminate the trend fluctuation of partly fluctuating and causing, finally obtain load/trend of the exerting oneself period meeting electric power system control and require.
Technical scheme provided by the invention is according to time series data, in conjunction with electric system feature, for the trend identify of electric system prediction class data, solve the difficulty of Classical forecast data trend identification, like this by real-time prediction class data, the trend period can be formed, the trend of electric system current and on the horizon is effectively identified.The process of identification has the effect of filtering data fluctuations simultaneously.So can treatment and analysis invalid trend period timely and effectively.
Accompanying drawing explanation
Fig. 1 is certain actual area power grid daily load prediction data trend result curve figure mono-of specific embodiment provided by the invention;
Fig. 2 is certain actual area power grid daily load prediction data trend result curve figure bis-of specific embodiment provided by the invention;
Fig. 3 is the process flow diagram of the trend identify method of electric system provided by the invention prediction class data.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in further detail.
The invention provides a kind of trend identify method being applicable to the prediction class data of electric system, power prediction class data are converted into time series data according to corresponding time point, the Long-term change trend of per a period of time is obtained by analyzing data variation, then the time span for each Long-term change trend merges according to actual requirement, forms electrical network and controls available tendency information in real time.
By the time series to predicted data, and the analysis to data variation, identification can be carried out fast to load/variation tendency of exerting oneself and affiliated period, then the trend fluctuation by causing partly fluctuating is carried out merging and is eliminated, and final acquisition meets load/trend of exerting oneself period that electric power system control requires.
Its technological difficulties are:
1. in trend analysis, how to pick out the numerical value change that short-time fluctuations factor or trend factor cause.
2. the effective trend how separated needed for power grid control for a period of time sequence area is interval.
The present invention is applicable to power dispatching automation field, is applicable to, to the identification of electrical network prediction class data analysis, to determine the operation of power networks trend in following a period of time, meet the demand that electrical network controls class application in real time.
The process flow diagram of the trend identify method of electric system prediction class data as shown in Figure 3, comprises the steps:
(1) prediction class data are read: the prediction class data (being generally a day predicted data) reading electric system certain hour section.
(2) sliding-model control is carried out, the time series data of formation time interval equalization to prediction class data; Be about to prediction class data time seriesization and form the average serialized data of collection density.
(3) time series data is scanned, determine the time series sampling period of time series data, the minimum value of time series data and time point, the maximal value of time series data and the fluctuating range (representing time series data size and variation tendency thereof by curve form) of time point and time series data thereof;
(4) determine period fluctuation threshold, judge that fluctuation threshold that trend turns to is as the mark being whether a fluctuation period.
By fluctuation threshold, the mark whether deterministic trend turns to.Fluctuation threshold is usually by component type or the decision of control system feature of power grid control.Such as, electric system AVC (in automatism voltage control) for fluctuation the period usually with 15% of fluctuating range for threshold is (when trend takes a turn for the worse, and changed 15% think may for next section), fluctuation tendency allows switching capacitive reactance device more than 25%.
(5) based on period fluctuation threshold, time series data is divided into each trend period, comprises rise period and decline the period:
From the curve minimum time and being initial default trend with ascendant trend analysis time data, when fluctuation tendency turn to and lower than this period maximal value one fluctuation threshold value time, then this section of time series is an ascending sequence.
Be current trend analysis data from the curve maximum time and with downtrending, when fluctuation tendency turn to and higher than this period minimum one fluctuation threshold value time, then this section of time series is a decreasing sequence.
(6) whether identification is complete to judge time series data: when time series arrives last data, checks whether analyze data reaches time series data maximum.If no, then turnaround time data first data start to analyze, until the minimum value place of curve.
(7) differentiate each trend period, the period being less than period minimum (being defaulted as 30 minutes) the trend period, as inactive time period, merges with attached adjacent time interval; Because the control of power system device needs the stationarity requirement considering to have one section of transformation period and implementation in implementation, period minimum is determined by the component type of power grid control or control system feature.
(8) carry out identification to load trend to complete, by Load Time Series data, be divided into the data segment of different trend, form electric power system optimization and control the trend period available in the sampling period.
Embodiment
Fig. 1 and Fig. 2 shows certain actual area power grid daily load prediction data.Be described as follows shown in table 1 to Fig. 1:
Certain actual area power grid daily load prediction data one of table 1
| Period | Action |
| Period 19:00-03:00 | Load declines, and allows adjust and mend, and allows to transfer the files |
| Period 03:00-12:15 | Load rises, and allows adjust and mend, and allows to transfer the files |
| Period 12:15-14:45 | Load declines, and allows adjust and mend, and forbids transferring the files |
| Period 14:45-19:00 | Load rises, and allows adjust and mend, and forbids transferring the files |
Be described as follows shown in table 2 to Fig. 2:
Certain actual area power grid daily load prediction data one of table 2
| Period | Action |
| Period 22:45-05:30 | Load declines, and allows adjust and mend, and allows to transfer the files |
| Period 05:30-12:15 | Load rises, and allows adjust and mend, and allows to transfer the files |
| Period 12:15-14:30 | Load declines, and allows adjust and mend, and forbids transferring the files |
| Period 14:30-19:15 | Load rises, and allows adjust and mend, and forbids transferring the files |
| Period 19:15-20:45 | Load declines, and forbids adjusting and mends, forbidding transferring the files |
| Period 20:45-22:45 | Load rises, and forbids adjusting and mends, forbidding transferring the files |
Wherein, Fig. 1 and Fig. 2 horizontal ordinate is the time sequential value (sampling period is 15 minutes, has 96 sampled points every day) of corresponding electrical network daily load, and ordinate is system loading number (unit is megawatt).
Relatively can be found out by identification result and actual schedule experience, the present invention effectively can carry out trend identify for the predicted data provided, and the difference for trend effectively can instruct the control of controllable device in electric system.Secondly, the trend identify result after the maximum short-time fluctuations occurred according to the 68th moment (namely 16: 45) of Fig. 2, the trend identify deviation that this technology can effectively avoid data fluctuations to cause in the process of identification trend.
Finally should be noted that: above embodiment is only in order to illustrate that technical scheme of the present invention is not intended to limit; although with reference to above-described embodiment to invention has been detailed description; those of ordinary skill in the field still can modify to the specific embodiment of the present invention or equivalent replacement; these do not depart from any amendment of spirit and scope of the invention or equivalent replacement, are all applying within the claims of the present invention awaited the reply.
Claims (6)
1. a trend identify method for electric system prediction class data, it is characterized in that, described method comprises the steps:
(1) prediction class data are read;
(2) sliding-model control is carried out, the time series data of formation time interval equalization to prediction class data;
(3) the time series sampling period of time series data, the minimum value of time series data and time point, the maximal value of time series data and the fluctuating range of time point and time series data thereof is determined;
(4) period fluctuation threshold is determined;
(5) based on period fluctuation threshold, time series data is divided into each trend period;
(6) whether identification is complete to judge time series data;
(7) each trend period is differentiated, is less than the period of period minimum the trend period as inactive time period, merges with attached adjacent time interval;
(8) form electric power system optimization and control the trend period available in the sampling period.
2. trend identify method as claimed in claim 1, it is characterized in that, in described step (3), by scanning time series data, the time series sampling period in acquisition time series data, the minimum value of time series data and time point, the maximal value of time series data and the fluctuating range basic feature information of time point and time series data thereof.
3. trend identify method as claimed in claim 1, is characterized in that, in described step (4), by fluctuation threshold, and the mark whether deterministic trend turns to; Described fluctuation threshold is determined by the component type of power grid control or control system feature.
4. trend identify method as claimed in claim 1, it is characterized in that, in described step (5), the trend period comprises ascending sequence and decreasing sequence;
From the curve fluctuation minimum value time and being initial default trend with ascendant trend analysis time data, turn to when fluctuation tendency and fluctuate lower than one of this period maximal value threshold value time time series be an ascending sequence;
From curve fluctuation maximal value time be current trend analysis data with downtrending, turn to when fluctuation tendency and fluctuate higher than of this period minimum threshold value time time series be a decreasing sequence.
5. trend identify method as claimed in claim 1, it is characterized in that, in described step (6), when time series arrives last data, check whether analyze data reaches time series data maximum, if no, then turnaround time sequence data first data start analyze, until the minimum value place of curve.
6. trend identify method as claimed in claim 1, it is characterized in that, in described step (7), described period minimum is defaulted as 30 minutes, by component type or the decision of control system feature of power grid control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410539260.6A CN104268660A (en) | 2014-10-13 | 2014-10-13 | Trend recognition method for electric power system predication-like data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410539260.6A CN104268660A (en) | 2014-10-13 | 2014-10-13 | Trend recognition method for electric power system predication-like data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268660A true CN104268660A (en) | 2015-01-07 |
Family
ID=52160180
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410539260.6A Pending CN104268660A (en) | 2014-10-13 | 2014-10-13 | Trend recognition method for electric power system predication-like data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268660A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109933607A (en) * | 2019-01-25 | 2019-06-25 | 四川眷诚天佑科技有限公司 | Periodical time series data processing method |
| CN110020935A (en) * | 2018-12-18 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of data processing, calculation method, device, equipment and medium |
| CN110889554A (en) * | 2019-11-27 | 2020-03-17 | 东南大学 | Power load fluctuation analysis and risk early warning method based on recurrence time interval analysis method |
| CN111539275A (en) * | 2020-04-14 | 2020-08-14 | 中南民族大学 | Electrical load classification method and system based on load characteristic visualization |
| WO2020252822A1 (en) * | 2019-06-18 | 2020-12-24 | 北京天泽智云科技有限公司 | Time series data processing method and apparatus |
| CN112149296A (en) * | 2020-09-17 | 2020-12-29 | 中国科学院地理科学与资源研究所 | Method for judging stability type of hydrological time sequence |
| CN112783251A (en) * | 2021-01-05 | 2021-05-11 | 黄山学院 | Transformer voltage tracking feedback automatic adjusting device and adjusting method thereof |
| CN115099544A (en) * | 2022-08-29 | 2022-09-23 | 江苏华维光电科技有限公司 | Smart power grid load prediction method based on signal denoising |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080030199A1 (en) * | 2006-08-04 | 2008-02-07 | Daqing Hou | Systems and methods for detecting high-impedance faults in a multi-grounded power distribution system |
| CN103646349A (en) * | 2013-09-27 | 2014-03-19 | 华北电力大学 | Power load curve segmented identification method |
| CN103795144A (en) * | 2013-11-22 | 2014-05-14 | 深圳供电局有限公司 | Fault recording data-based power system disturbance occurrence time identification method |
-
2014
- 2014-10-13 CN CN201410539260.6A patent/CN104268660A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080030199A1 (en) * | 2006-08-04 | 2008-02-07 | Daqing Hou | Systems and methods for detecting high-impedance faults in a multi-grounded power distribution system |
| CN103646349A (en) * | 2013-09-27 | 2014-03-19 | 华北电力大学 | Power load curve segmented identification method |
| CN103795144A (en) * | 2013-11-22 | 2014-05-14 | 深圳供电局有限公司 | Fault recording data-based power system disturbance occurrence time identification method |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110020935A (en) * | 2018-12-18 | 2019-07-16 | 阿里巴巴集团控股有限公司 | A kind of data processing, calculation method, device, equipment and medium |
| CN110020935B (en) * | 2018-12-18 | 2024-01-19 | 创新先进技术有限公司 | Data processing and calculating method, device, equipment and medium |
| CN109933607A (en) * | 2019-01-25 | 2019-06-25 | 四川眷诚天佑科技有限公司 | Periodical time series data processing method |
| CN109933607B (en) * | 2019-01-25 | 2023-10-03 | 微诺时代（北京）科技股份有限公司 | Periodic time series data processing method |
| WO2020252822A1 (en) * | 2019-06-18 | 2020-12-24 | 北京天泽智云科技有限公司 | Time series data processing method and apparatus |
| CN110889554A (en) * | 2019-11-27 | 2020-03-17 | 东南大学 | Power load fluctuation analysis and risk early warning method based on recurrence time interval analysis method |
| CN111539275A (en) * | 2020-04-14 | 2020-08-14 | 中南民族大学 | Electrical load classification method and system based on load characteristic visualization |
| CN112149296A (en) * | 2020-09-17 | 2020-12-29 | 中国科学院地理科学与资源研究所 | Method for judging stability type of hydrological time sequence |
| CN112149296B (en) * | 2020-09-17 | 2023-06-20 | 中国科学院地理科学与资源研究所 | Method for judging stability type of hydrologic time sequence |
| CN112783251A (en) * | 2021-01-05 | 2021-05-11 | 黄山学院 | Transformer voltage tracking feedback automatic adjusting device and adjusting method thereof |
| CN115099544A (en) * | 2022-08-29 | 2022-09-23 | 江苏华维光电科技有限公司 | Smart power grid load prediction method based on signal denoising |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104268660A (en) | Trend recognition method for electric power system predication-like data | |
| CN107423836B (en) | Short-term load prediction method based on body sensing temperature | |
| CN105305481B (en) | System and method for controlling power distribution network | |
| CN111625947B (en) | Distributed energy development scale prediction method, equipment and medium | |
| Sevlian et al. | Wind power ramps: Detection and statistics | |
| CN107491833B (en) | Photovoltaic power generation power prediction method and device | |
| Kariniotakis et al. | Evaluation of advanced wind power and load forecasting methods for the optimal management of isolated power systems | |
| CN103400217B (en) | Wind-powered electricity generation and conventional energy resources coordinated scheduling wind-powered electricity generation consistency network security analytical procedure | |
| CN111144654A (en) | Park energy management configuration method and device based on Internet of things | |
| Arévalo et al. | Smart monitoring method for photovoltaic systems and failure control based on power smoothing techniques | |
| CN104036356A (en) | Method for predicting future operating state of power grid by using fractal algorithm | |
| CN114914929A (en) | Transformer substation-based regional new energy online full-amount consumption method | |
| CN110135617A (en) | A kind of prediction technique of improvement short term under meteorological factor influence based on part throttle characteristics | |
| CN106203742B (en) | Power grid equipment energy-saving evaluation and type selection method based on energy-saving return rate | |
| CN104657787B (en) | A kind of wind power time series combination forecasting method | |
| CN103400304B (en) | Wind-powered electricity generation and conventional energy resources coordinated scheduling wind-powered electricity generation consistency rotate analytical procedure for subsequent use | |
| CN103280800A (en) | Method for forecasting super-short period wind power based on nonlinear fitting | |
| Majzoobi et al. | Leveraging microgrids for capturing uncertain distribution network net load ramping | |
| CN105976069A (en) | Regionalism-based prediction system and method for short-term power load of grid region at Guigang | |
| CN104156785A (en) | Generation schedule optimization method taking into consideration thermal power unit-driven coal mill start and stop | |
| Kumar et al. | Short-term wind power plant predicting with artificial neural network | |
| CN113487062A (en) | Power load prediction method based on periodic automatic encoder | |
| Femin et al. | Modeling the temporal variations in the output of large solar PV power plants | |
| CN105633946B (en) | A kind of high wind-powered electricity generation of extraction penetrates the modeling method of busbar day net active power Random-fuzzy feature | |
| Raj et al. | Evaluating The Ramping Trends And Noisy Fluctuations From Solar Power Imbalances |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150107 |