CN104318322B - Festivals or holidays load forecasting method based on lunar date - Google Patents
Festivals or holidays load forecasting method based on lunar date Download PDFInfo
- Publication number
- CN104318322B CN104318322B CN201410536033.8A CN201410536033A CN104318322B CN 104318322 B CN104318322 B CN 104318322B CN 201410536033 A CN201410536033 A CN 201410536033A CN 104318322 B CN104318322 B CN 104318322B
- Authority
- CN
- China
- Prior art keywords
- red
- load
- day
- letter day
- holiday
- 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.)
- Expired - Fee Related
Links
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
Abstract
The present invention relates to a kind of festivals or holidays load forecasting method based on lunar date, belong to power-system short-term load forecasting technical field, the method comprising the steps of:S1:M days working days before n red-letter day and red-letter day are chosen with history of forming data, red-letter day load curve is predicted according to selected historical data, wherein, the working day does not include day off, and the red-letter day is Chinese Traditional Agricultural severe and migratory arthralgia day;S2:Holiday and the holiday of prediction load curve where choosing the non-date in red-letter day related to historical data, wherein, the holiday is the day off connected with red-letter day, and the selection of the holiday is the holiday that the distance red-letter day identical date intervals in history are selected according to the date intervals in holiday to be predicted and red-letter day;S3:Red-letter day load curve and holiday load curve are connected, overlapping region is smoothed, festivals or holidays curve prediction result is obtained.
Description
Technical field
The present invention relates to a kind of festivals or holidays load forecasting method based on lunar date, belong to power-system short-term load pre-
Survey technology field.
Background technology
Modern power network structure is increasingly sophisticated, Power System Interconnection is more and more wider, has gradually formed with remote, heavy load, great Qu
Bulk power grid with the characteristics of networking.Load prediction is an important field of research in modern power systems subject, is meeting society
Extremely important effect has all been played in terms of meeting demand and guarantee power grid security economical operation.With power system reform
Deepen constantly, the whole society increasingly improves to power network and whole power industry safety, the requirement of energy-conservation, economy, Efficient Operation.
Although in the only one day red-letter day of China, can be all adjusted substantially with adjacent weekend, one is formed 3 days or so
Small long holidays, relative to May Day, this Gregorian calendar red-letter day on New Year's Day, the Dragon Boat Festival, mid-autumn etc. China traditional festival there is stronger red-letter day
Lunar calendar attribute, both lunar calendar red-letter day this day where day be often whole holiday during load turning point.
Because Chinese tradition festivals or holidays (are commonly referred to as small long holidays, tradition section of the festivals or holidays comprising the China such as the Dragon Boat Festival, mid-autumn
Day and the day off being connected with the traditional festival, the day off are the holiday connected with traditional festival or formed after taking off
Holiday) social action of the people varies widely relative to normal day, festivals or holidays load level relatively normal day is born
Lotus level typically has decline by a relatively large margin, while shape difference is also very significantly, it is necessary to for festivals or holidays using uniqueness
Forecasting Methodology carries out festivals or holidays prediction, to improve festivals or holidays predictablity rate.
Electric load during festivals or holidays is typically relatively low, and load is easily by various random fluctuation factors and potential interference
The influence of factor so that some are for there is the Forecasting Methodology of good accuracy to be also difficult to the prediction knot being more satisfied with normal day
Really.
Current festivals or holidays Load Forecast Algorithm is mostly employed with reference to historical years holiday load and normal daily load phase
The range of decrease of ratio is come the Forecasting Methodology of the load level for following festivals or holidays of extrapolating, and such a method has two kinds of deficiencies:
1st, the load level before festivals or holidays generally requires manually to select a designated date, when the day is by external factor
When influence has sudden load change, there is into mistake in the load range of decrease for causing to calculate festivals or holidays;
2nd, the unified prediction in each day during traditional festivals or holidays load forecasting method carries out festivals or holidays, not in view of due to adjusting
Whole festivals or holidays load variations trend in the range of festivals or holidays where not caused red-letter day caused by the difference of different times is not
Together, although preferable, each daily load curve change that integral load level is predicted during ultimately resulting in the festivals or holidays for predicting and
Trend is not but right, or even the problems such as load recovers in advance occurs.
The content of the invention
It is an object of the invention to provide a kind of the scientific, intensive of achievable grid dispatching management, lean, and carry
The security of high operation of power networks, realizes the festivals or holidays load forecasting method based on lunar date of significant economic benefit.
To achieve the above object, the present invention is adopted the following technical scheme that:A kind of festivals or holidays load based on lunar date is pre-
Survey method, including step:
S1:M days working days before n red-letter day and red-letter day are chosen with history of forming data, according to selected history number
It is predicted that red-letter day load curve, wherein, the working day does not include day off, and the red-letter day is Chinese Traditional Agricultural severe and migratory arthralgia day;
S2:Holiday and the holiday of prediction load curve where choosing the non-date in red-letter day related to historical data, wherein, it is described
Holiday is the day off connected with red-letter day, and the selection of the holiday is to be gone through according to the selection of the date intervals in holiday to be predicted and red-letter day
The holiday of the distance red-letter day identical date intervals in history;
S3:Red-letter day load curve and holiday load curve are connected, overlapping region is smoothed, festivals or holidays are obtained
Curve prediction result.
Further, the step S1 is specifically included:
Choose m working days evidence before n red-letter day and red-letter day;
Load level before section is calculated, and the load level before section is calculated according to m days annual load levels, by the i-th (i=
1,2 ..., m) each day peak load P of dayimaxAverage, as the load level before section, calculation formula is:
The history red-letter day load level range of decrease is calculated, and calculates the peak load P on the day of the red-letter day in history each yearymaxBefore section
The ratio coefficient of load level is as load range of decrease coefficient, calculation formula:Y=1,2 ...,
n;
History Spring Festival holidays daily load per-unit curve, the load P by n red-letter day per moment pointytWith perunit base value PymaxCompare
Per-unit curve is obtained, calculation formula is:Lyt=Pyt/Pymax, y=1,2 ..., n, t=1,2 ..., b;
Spring Festival holidays preload level calculation is predicted, was calculated according to m days load levels before prediction year (n+1) section before the prediction Spring Festival holidays
Load level, (i=1,2 ..., m) each day peak load P (n+1) imax of day averages, are used as negative before section by i-th
Lotus level, calculation formula is:
Red-letter day load level predicts that the range of decrease system in each year constitutes sequence q1, q2..., qy(y=1,2 ..., n), by this
The red-letter day range of decrease coefficient in the prediction year that sequence is obtained by linear extrapolationAnd range of decrease coefficient and section preload by calculating
The red-letter day load level base value that level is predicted year is calculated, and calculation formula is:
Red-letter day per-unit curve is predicted, n red-letter day load per-unit curve is carried out smooth bent as prediction red-letter day in year perunit
Line, calculation formula is:
α is smoothing factor, can on (0,1) interval value;
Red-letter day load curve forecasting, predicts the outcome according to prediction red-letter day load level and is born with red-letter day per-unit curve prediction red-letter day
Lotus curve, calculation formula is:
Further, the step S2 specifically includes following steps:
S21:Choose holiday and red-letter day in related to historical data place holiday on non-date in red-letter day, rejecting historical law
Date intervals and holiday to be predicted and red-letter day date intervals incongruent time, historical data is reorganized, according to reorganization
Historical data, calculate the load level P of the holiday in non-red-letter day(n+1)maxAnd per-unit curve
S22:Load curve forecasting is carried out to the holiday in above-mentioned non-red-letter day, predicted the outcome and perunit according to prediction load level
Curve prediction holiday load curve, calculation formula is:
Further, the step S21 specifically includes following steps:
S211:Rule is determined during holiday where the non-date in red-letter day
The holiday in non-red-letter day and the day space before in red-letter day are calculated, -1 is designated as if section the previous day, if section one day after
For+1, by that analogy;
S212:Historical law incongruent time is rejected, historical data is reorganized
Rejected in n historical dates the time for not possessing Holiday Dates interval properties to be predicted, according to what is reorganized
Historical data, calculates the load level P of non-holiday in red-letter day(n+1)maxAnd per-unit curve
Further, algorithm is used when carrying out curve perunit and prediction, respectively before b point curves in the step S3
Respectively extend k time point afterwards, form the curve of b+2k point, the curve that predicts the outcome on two adjacent dates just has 2k point to exist
It is to overlap on time dimension;Go the average value of overlapping value to be predicted the outcome for the final of each curve, carry out curve smoothing and linking
To obtain festivals or holidays curve.
Further, the red-letter day load curve and holiday load curve use 96 point curves.
By such scheme, the present invention at least has advantages below:Scheduling unit can be improved by the Forecasting Methodology of the present invention
Door controls the ability of power network, improves the scheduling level of whole power network, realizes the scientific, intensive of grid dispatching management, lean
Change, improve the security of operation of power networks, realize significant economic benefit.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, below with presently preferred embodiments of the present invention and coordinate accompanying drawing describe in detail as after.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the festivals or holidays load forecasting method of the invention based on lunar date.
Embodiment
With reference to the accompanying drawings and examples, the embodiment to the present invention is described in further detail.Implement below
Example is used to illustrate the present invention, but is not limited to the scope of the present invention.
Fig. 1 is referred to, a kind of festivals or holidays load forecasting method based on lunar date shown in the present embodiment includes step
S1 to S3.
S1:M days working days before n red-letter day and red-letter day are chosen with history of forming data, according to selected history number
It is predicted that red-letter day load curve, wherein, the working day does not include day off, and the red-letter day is the biography of the China such as the Dragon Boat Festival, mid-autumn
Unite lunar calendar red-letter day.Herein it should be noted that:What the day off was formed comprising red-letter day, normal holiday at weekend and after taking off
Holiday and such as May Day, Gregorian calendar red-letter day on New Year's Day, the working day that working day is formed for the normal day of duty or after taking off.The step
Specifically include:
S11:M working days evidence before n lunar calendar red-letter day and lunar calendar red-letter day is chosen, wherein, n, m can be by artificial
Setting.For example, current date is on May 30th, 2014, the Dragon Boat Festival is on June 2nd, 2014 (lunar calendar early May five), and the Dragon Boat Festival has a holiday or vacation
For on May 31st, 2014, on June 1st, 2014, on June 2nd, 2014, wherein, on June 2nd, 2014 is needs the Chinese agriculture chosen
Severe and migratory arthralgia day, on May 31st, 2014, on June 1st, 2014 are holiday, i.e. day off, are not included in selected working day, institute
The working day of selection is a few days ago working day on May 31st, 2014.
S12:Load level before section is calculated
The load level before section is calculated according to annual m days load levels, (i=1,2 ..., m) each day of day is most by i-th
Big load PimaxAverage, as the load level before section, calculation formula is:
S13:The history red-letter day load level range of decrease is calculated
Calculate the peak load P on the day of the red-letter day in history each yearymaxRatio coefficient with the load level before section is as negative
Lotus range of decrease coefficient, calculation formula is:Y=1,2 ..., n;
S14:History Spring Festival holidays daily load per-unit curve
Load P by n red-letter day per moment pointytWith perunit base value Pymax(using history each year in above-mentioned steps S13
Red-letter day on the day of peak load) compared to per-unit curve is obtained, calculation formula is:Lyt=Pyt/Pymax, y=1,2 ..., n, t=
1,2 ..., 96.
S15:Predict Spring Festival holidays preload level calculation
The load level predicted before the Spring Festival holidays is calculated according to m days load levels before prediction year (n+1) section, by i-th (i=1,
2 ..., m) each day peak load P of day(n+1)imaxAverage, as the load level before section, calculation formula is:
S16:Red-letter day load level is predicted
The range of decrease system in each year constitutes sequence q1, q2..., qy(y=1,2 ..., n), linear extrapolation is passed through by the sequence
The red-letter day range of decrease coefficient in the prediction year obtainedAnd the range of decrease coefficient and section preload level by calculating are predicted year
Red-letter day load level base value calculate, calculation formula is:
S17:Red-letter day per-unit curve is predicted
N red-letter day load per-unit curve is carried out smoothly as prediction red-letter day in year per-unit curve, calculation formula is:α is smooth
Coefficient, can on (0,1) interval value;
S18:Red-letter day load curve forecasting
Predicted the outcome according to prediction red-letter day load level and predict red-letter day load curve, calculation formula with red-letter day per-unit curve
For:
In this step S1, the part order between each step can be exchanged, and such as step S17 is placed on before step S15.
S2:Holiday and the holiday of prediction load curve where choosing the non-date in red-letter day related to historical data, wherein, it is described
Holiday is the day off connected with red-letter day, and the selection of the holiday is to be gone through according to the selection of the date intervals in holiday to be predicted and red-letter day
The holiday of the distance red-letter day identical date intervals in history.The step is specifically included:
S21:Choose holiday and red-letter day in related to historical data place holiday on non-date in red-letter day, rejecting historical law
Date intervals and holiday to be predicted and red-letter day date intervals incongruent time, historical data is reorganized, according to reorganization
Historical data, calculate the load level P of non-holiday in red-letter day(n+1)maxAnd per-unit curveStep S21 is in detail:
S211:Rule is determined during holiday where the non-date in red-letter day
The holiday in non-red-letter day and the day space before in red-letter day are calculated, -1 is designated as if section the previous day, if section one day after
Be designated as+1, by that analogy, for example, on June 2nd, 2014 be the Dragon Boat Festival, holiday be on May 31st, 2014, on June 1st, 2014, its
In, it is designated as on May 31st, 2014 being designated as -2 on June 1st, -2,2014;
S212:Historical law incongruent time is rejected, historical data is reorganized
The time for not possessing Holiday Dates interval properties to be predicted is rejected in n historical dates.For example, prediction is included in year
Holiday before one red-letter day, then need to reject in historical years, red-letter day is the historical years of first day, it is the 2nd day to retain red-letter day
Later all times.According to the historical data reorganized, the load level P of non-holiday in red-letter day is calculated(n+1)maxAnd perunit
Curve
S22:Carry out the holiday load curve forecasting in non-red-letter day
Predicted the outcome according to prediction load level and predict holiday load curve with per-unit curve, calculation formula is:
S3:Red-letter day load curve and holiday load curve are connected, overlapping region is smoothed, festivals or holidays are obtained
Curve prediction result.The purpose of this step is:Because the load curve in each day is independent prediction, but load has continuation in itself
And continuity, it is therefore desirable to the progress that predicted the outcome to each day is smooth and is connected.
Algorithm is used when carrying out curve perunit and prediction in the step S4, is respectively extended before and after 96 point curves respectively
At k time point, the curve of 96+2k point is formed, the curve that predicts the outcome on two adjacent dates just has 2k point in time dimension
It is to overlap on degree;Go the average value of overlapping value to be predicted the outcome for the final of each curve, carry out curve smoothing and linking to obtain
Red-letter day curve.
In the present embodiment, the red-letter day load curve and holiday load curve use 96 point curves.Really, at other
In embodiment, in addition to selecting 96 point curves, it is also an option that other curves.
Illustrate the beneficial effect that the method for the present invention is brought with instantiation below.
Carry out load forecast work reduction grid company operating cost and improve before power equipment operational efficiency
Carry;It is that grid company adapts to requirement of the market economy, it is ensured that corporate investment returns and improved the element task of effectiveness of operation.Electric power is needed
Ask and whether accurate predict the outcome, not only have influence on power grid security reliable power supply, and have influence on the production warp of enterprises of managing electric wire netting
Seek decision-making and effectiveness of operation.
In electric power under the big situation of market development, power network short-term load forecasting is not only safe, the economy of power system
Operation provides safeguard, and is also layout operation plan, power supply plan, the basis of trading program under market environment.At the same time, electric power
The introducing in market to the accuracy of load prediction, real-time, reliability and it is intelligent propose higher requirement, current electricity at different levels
Short-term load forecasting is all classified as an important performance assessment criteria of various regions work by net company.
Short-term load forecasting is that power system improves security, the important means of economy.Load prediction is from known
The constraints such as electric load change and meteorology influential on this set out, and explore between power load and major influence factors
Inner link and development and change rule, advance prediction is made to following power load.In order to predict electricity needs exactly.
By taking 129,200,000 kilowatts of load level as an example, load prediction precision improves one percentage point, the direct benefit of generation
It can calculate as follows:
Unit:Wan Yuan, ten thousand kilowatt hours
Project | Reduce electric quantity loss | Reduce electricity charge loss | Reduce quality loss | Reduce power purchase loss | Save Electricity Investment |
Ration the power supply | 15504 | 9302 | 155040 | ||
Investment | 723520 | ||||
Power purchase | 46512 |
Wherein:Ration the power supply by 20 days, daily 6 hours, electricity price for industrial uses was calculated according to 0.6 yuan/kwh, 10 yuan/kwh of the output value;Investment
Calculated by the 5000 yuan/kw that generates electricity, 600 yuan/kw of power network;Power purchase valency presses 0.3 yuan/kwh, 4 months time, calculates within daily 10 hours.
By above table, from the point of view of direct economic benefit angle, this Forecasting Methodology contributes to grid company more reasonable
Ground arrangement, distribute supply of electric power ability rationally, effectively implement ordered electric, reduce power networks risk, while ensuring to realize enterprise
The maximization of industry, social benefit.
In summary, the ability that power network is controlled by traffic department is improved by above-mentioned Forecasting Methodology, improves whole power network
Scheduling level, can realize the scientific, intensive of grid dispatching management, lean, improve the security of operation of power networks, realize
Significant economic benefit.
Described above is only the preferred embodiment of the present invention, is not intended to limit the invention, it is noted that for this skill
For the those of ordinary skill in art field, without departing from the technical principles of the invention, can also make it is some improvement and
Modification, these improvement and modification also should be regarded as protection scope of the present invention.
Claims (5)
1. a kind of festivals or holidays load forecasting method based on lunar date, it is characterised in that:Including step:
S1:M days working days before n red-letter day and red-letter day are chosen with history of forming data, it is pre- according to selected historical data
Red-letter day load curve is surveyed, wherein, the working day does not include day off, and the red-letter day is Chinese Traditional Agricultural severe and migratory arthralgia day;
S2:Holiday and the holiday of prediction load curve where choosing the non-date in red-letter day related to historical data, wherein, the holiday
For the day off connected with red-letter day, the selection of the holiday is to be selected according to the date intervals in holiday to be predicted and red-letter day in history
Apart from the holiday of the red-letter day identical date intervals;
S3:Red-letter day load curve and holiday load curve are connected, overlapping region is smoothed, festivals or holidays curve is obtained
Predict the outcome;
The step S1 is specifically included:
Choose m working days evidence before n red-letter day and red-letter day;
Load level before the history Spring Festival holidays is calculated, and the m days load levels annual according to history calculate the load water before the history Spring Festival holidays
It is flat, by the i-th (i=1,2 ..., m) the peak load P of dayimaxAverage, as the load level before the history Spring Festival holidays, calculate public
Formula is:
The history red-letter day load level range of decrease is calculated, and calculates the peak load P on the day of the red-letter day in history each yearymaxWith the load before section
The ratio coefficient of level is as load range of decrease coefficient, calculation formula: Y=1,2 ..., n;
History Spring Festival holidays daily load per-unit curve, by load P of the n red-letter day per moment point tytOn the day of red-letter day in history each year
Peak load PymaxCompared to acquisition per-unit curve, calculation formula is:Lyt=Pyt/Pymax, y=1,2 ..., n, t=1,2 ..., b;b
=96;
Spring Festival holidays preload level calculation is predicted, the load before the prediction Spring Festival holidays is calculated according to m days load levels before the section in prediction year n+1
Level, by the i-th (i=1,2 ..., m) the peak load P of day(n+1)imaxAverage, as the load level before the prediction Spring Festival holidays,
Calculation formula is:
Red-letter day load level predicts that the range of decrease coefficient in each year constitutes sequence q1, q2..., qy(y=1,2 ..., n), the sequence is led to
Cross the red-letter day range of decrease coefficient that linear extrapolation obtains prediction yearAnd the prediction year range of decrease coefficient by calculating and the prediction Spring Festival holidays
The red-letter day load level base value that preload level is predicted year is calculated, and calculation formula is:
Red-letter day per-unit curve is predicted, n red-letter day load per-unit curve is carried out to smooth be used as and predicts red-letter day in year per-unit curve, meter
Calculating formula is: α
For smoothing factor, can on (0,1) interval value;
Red-letter day load curve forecasting, predicts the outcome bent with per-unit curve red-letter day, load prediction red-letter day according to prediction red-letter day load level
Line, calculation formula is:
2. the festivals or holidays load forecasting method according to claim 1 based on lunar date, it is characterised in that:The step
S2 specifically includes following steps:
S21:Holiday where the non-date in red-letter day related to historical data is chosen, the date in holiday and red-letter day in historical law is rejected
Interval and holiday to be predicted and red-letter day date intervals incongruent time, historical data is reorganized, according to going through for reorganizing
History data, calculate the load level Q of the holiday in non-red-letter day(n+1)maxAnd per-unit curve
S22:Load curve forecasting is carried out to the holiday in above-mentioned non-red-letter day, predicted the outcome and per-unit curve according to prediction load level
Holiday load curve is predicted, calculation formula is:
3. the festivals or holidays load forecasting method according to claim 2 based on lunar date, it is characterised in that:The step
S21 specifically includes following steps:
S211:Rule is determined during holiday where the non-date in red-letter day
The holiday in non-red-letter day and the day space before in red-letter day are calculated, -1 is designated as if section the previous day, is+1 one day after if section,
By that analogy;
S212:Historical law incongruent time is rejected, historical data is reorganized
Rejected in n historical dates the time for not possessing Holiday Dates interval properties to be predicted, according to the history reorganized
Data, calculate the load level Q of non-holiday in red-letter day(n+1)maxAnd per-unit curve
4. the festivals or holidays load forecasting method according to claim 1 based on lunar date, it is characterised in that:The step
Algorithm is used when carrying out curve perunit and prediction in S3, respectively the k time point of each extension before and after b point curves, forms b+
The curve of 2k point, the curve that predicts the outcome on two adjacent dates just has 2k point to be coincidence on time dimension;Take weight
The average value of folded value predicts the outcome for the final of each curve, carries out curve smoothing and linking to obtain festivals or holidays curve.
5. the festivals or holidays load forecasting method according to claim 1 based on lunar date, it is characterised in that:The red-letter day
Load curve and holiday load curve use 96 point curves.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410536033.8A CN104318322B (en) | 2014-10-11 | 2014-10-11 | Festivals or holidays load forecasting method based on lunar date |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410536033.8A CN104318322B (en) | 2014-10-11 | 2014-10-11 | Festivals or holidays load forecasting method based on lunar date |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104318322A CN104318322A (en) | 2015-01-28 |
CN104318322B true CN104318322B (en) | 2017-07-28 |
Family
ID=52373550
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410536033.8A Expired - Fee Related CN104318322B (en) | 2014-10-11 | 2014-10-11 | Festivals or holidays load forecasting method based on lunar date |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104318322B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107256435B (en) * | 2016-06-30 | 2024-02-02 | 国网江苏省电力公司南通供电公司 | Fixed value correction method based on predicted value of daily electricity quantity of station area |
CN108009938B (en) | 2016-11-02 | 2021-12-03 | 中国电力科学研究院 | System load clustering and load period pattern recognition method based on shape |
CN107507030A (en) * | 2017-08-22 | 2017-12-22 | 北京京东尚科信息技术有限公司 | The method and apparatus of information prediction |
CN108053074A (en) * | 2017-12-26 | 2018-05-18 | 中国电力科学研究院有限公司 | A kind of computational methods and system of power consumption contributive rate |
CN110309399A (en) * | 2018-02-06 | 2019-10-08 | 北京嘀嘀无限科技发展有限公司 | Scene information method for pushing and device based on date classification |
CN110378630A (en) * | 2018-04-12 | 2019-10-25 | 长沙行深智能科技有限公司 | Part method is sent based on festivals or holidays preferential pre- |
CN110334739A (en) * | 2019-06-05 | 2019-10-15 | 深圳供电局有限公司 | A kind of two-part component load forecasting method and device |
CN110598912B (en) * | 2019-08-21 | 2024-01-09 | 广东工业大学 | Electricity sales prediction method for electricity sales company during spring festival |
CN111445070B (en) * | 2020-03-26 | 2023-08-08 | 华润电力技术研究院有限公司 | Load curve generation method and related equipment |
CN113408101B (en) * | 2021-05-19 | 2024-01-12 | 南方电网科学研究院有限责任公司 | Load sequence simulation method and device |
CN113705929A (en) * | 2021-09-15 | 2021-11-26 | 中国南方电网有限责任公司 | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion |
CN117353349B (en) * | 2023-12-04 | 2024-03-29 | 珠海科创储能科技有限公司 | Power supply state control method of energy storage system, storage medium and electronic equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010193605A (en) * | 2009-02-18 | 2010-09-02 | Tokyo Electric Power Co Inc:The | Load estimating method of power distribution section and power distribution system control method |
CN103123665A (en) * | 2012-07-31 | 2013-05-29 | 上海交通大学 | Short-term power load forecasting method based on fuzzy clustering similar day |
CN103854068A (en) * | 2013-12-06 | 2014-06-11 | 国家电网公司 | Method for forecasting residential quarter short-term loads |
-
2014
- 2014-10-11 CN CN201410536033.8A patent/CN104318322B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010193605A (en) * | 2009-02-18 | 2010-09-02 | Tokyo Electric Power Co Inc:The | Load estimating method of power distribution section and power distribution system control method |
CN103123665A (en) * | 2012-07-31 | 2013-05-29 | 上海交通大学 | Short-term power load forecasting method based on fuzzy clustering similar day |
CN103854068A (en) * | 2013-12-06 | 2014-06-11 | 国家电网公司 | Method for forecasting residential quarter short-term loads |
Non-Patent Citations (4)
Title |
---|
冀南电网春节假日期间电力负荷预测方法;东明辰,杨同贺;《华北电力技术》;19970225(第2期);第6-8页 * |
基于神经元网络和模糊专家系统的电力短期负荷预测;王欣,王巍;《沈阳工程学院学报(自然科学版)》;20101015;第6卷(第4期);第318-320页 * |
山西电网节假日短期负荷预测研究与分析;候亮,李焱;《山西广播电视大学学报》;20060910(第5期);第90-91页 * |
重大节日期间电网日负荷预测方法的研究;陈志业,王贵保;《华北电力学院学报》;19920701(第2期);第25-30页 * |
Also Published As
Publication number | Publication date |
---|---|
CN104318322A (en) | 2015-01-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104318322B (en) | Festivals or holidays load forecasting method based on lunar date | |
CN107301472A (en) | Distributed photovoltaic planing method based on scene analysis method and voltage-regulation strategy | |
CN106485417A (en) | Photovoltaic plant based on dynamic self-adapting task scheduling strategy moves O&M method | |
Shukla et al. | Allocation of optimal distributed generation using GA for minimum system losses in radial distribution networks | |
CN103942613B (en) | Method for grid and province two-stage real-time generation schedule coordinative optimization under generalized tie line mode | |
CN106355285B (en) | Power load prediction method based on parameter correction | |
CN103745291B (en) | Based on the multiple target ordered electric sort method of electrical characteristics | |
CN103544537B (en) | Based on the cumulative short-term load forecasting method of comprehensive subnet of reliability forecasting assessment | |
CN105552971B (en) | Small power station and the subregion consumption method of large medium-size station group coordination optimization | |
CN106447073A (en) | Power purchase transaction method based on uncertainty factors and provincial load prediction | |
CN106779442A (en) | Have a power failure the generation method and device planned | |
CN106815684A (en) | The method of the ordered electric that becomes more meticulous management | |
Lin et al. | Fuzzy multi-objective forest biomass-to-biofuel facility location problem with social consideration | |
CN102567645A (en) | Method for counting equipment of power grid and computing transmission losses on basis of on-line theoretical transmission loss computation | |
Ghamkhari | Transactive energy versus demand response in cutting wholesale electricity prices | |
CN113746105A (en) | Optimal control method, device, equipment and storage medium for power demand response | |
Harish et al. | Do rural residential electricity consumers cross-subside their urban counterparts? Exploring the inequity in supply in the Indian power sector | |
CN104252647B (en) | Electro-load forecast method based on anti-distance weighting interpolation method | |
CN105701729A (en) | An electric quantity prediction method based on electric power business indexes | |
CN106530138A (en) | Electricity peak averting scheduling method and device | |
Liu et al. | A decision-making model for efficient fair electricity rationing under major power outrage emergencies | |
Györi et al. | Evaluation of Deep Learning-based prediction models in Microgrids | |
Meisenzahl et al. | District Battery for Optimized Use of Photovoltaic Energy | |
Senatla et al. | A mini-integrated resource plan for a commercial entity in Gauteng Province: planning for energy autonomous businesses | |
Nikiforov et al. | Some aspects of the problem of energy efficiency and energy saving in Russia |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170728 Termination date: 20181011 |
|
CF01 | Termination of patent right due to non-payment of annual fee |