CN109816164A - A kind of Methods of electric load forecasting - Google Patents
A kind of Methods of electric load forecasting Download PDFInfo
- Publication number
- CN109816164A CN109816164A CN201910038483.7A CN201910038483A CN109816164A CN 109816164 A CN109816164 A CN 109816164A CN 201910038483 A CN201910038483 A CN 201910038483A CN 109816164 A CN109816164 A CN 109816164A
- Authority
- CN
- China
- Prior art keywords
- history
- data
- methods
- domain data
- electric load
- 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 44
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000015654 memory Effects 0.000 claims description 6
- 238000012731 temporal analysis Methods 0.000 claims description 6
- 238000000700 time series analysis Methods 0.000 claims description 6
- 241001123248 Arma Species 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims 1
- 238000012300 Sequence Analysis Methods 0.000 claims 1
- 238000005096 rolling process Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 5
- 230000005611 electricity Effects 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The present invention relates to a kind of Methods of electric load forecasting, comprising: step S100 obtains the history Power system load data D=[D of n history cycle of current period1,D2,…,Dn], wherein DiFor the Power system load data in the (n+1)th-i before current period periods, 1≤i≤n;Step S200 is based on the history Power system load data D, obtains history high frequency time domain data DH=[DH using frequency spectrum analysis method1,DH2,…,DHM]TWith history low-frequency time-domain data DL=[DL1,DL2,…,DLn];Step S300 predicts the Power system load data of current period according to the history high frequency time domain data DH and the history low-frequency time-domain data DLWherein pl is the low frequency predicted value obtained based on the history low-frequency time-domain data DL, the phjFor based on the history high frequency time domain data DHjThe high frequency predicted value of acquisition.
Description
Technical field
The present invention relates to power domain more particularly to a kind of prediction techniques of electric load.
Background technique
Load forecast can play critical work to departments such as planning, electricity consumption and scheduling in electric system
With.The external factors own profound such as electric load and the economic level of their location, the industrial structure, policies and regulations, meteorological condition
Complicated relationship, the characteristics of showing periodicity and randomness.On the one hand, there is certain regularity for the variation of electric load
And periodicity;On the other hand, it is influenced by various external factor, electric load embodies the fluctuation for being difficult to hold again.Patent
File CN106503851A discloses a kind of improved Short-Term Load Forecasting Method based on wavelet analysis, including chooses sample
Notebook data carries out pseudo- data monitoring to the sample data of selection and corrects, determines sample set and be normalized, and obtains more flat
Sliding, more accurate sample data and future position load correlation are stronger, but this method only accounts for Short-term characteristic, also not to work
Day is distinguished with nonworkdays with electrical feature.Patent application CN108549960A discloses a kind of 24 hours Electric Load Forecastings
Survey method is acquired and is pre-processed comprising data, and the validity feature gone out by Characteristic Entropy weight computing, combined window is chosen method and chosen
Input data of 24 hours power load situations as DBN network training in set time, determines DBN network structure and foundation
Network model is simultaneously predicted, however, this method also only accounts for Short-term characteristic, the also not electricity consumption to working day and nonworkdays
Feature distinguishes.Patent document CN108736474A discloses Methods of electric load forecasting and device, quasi- according to historical data
Conjunction obtains moment to be predicted corresponding first fit correlation model and the second fit correlation model, is obtained according to the model to be predicted
Moment corresponding first parameter factors and the second parameter factors;Further according to moment to be predicted in each history cycle corresponding load
Moment to be predicted corresponding load power normalized value is calculated in power, the first parameter factors and the second parameter factors.Most
Afterwards, it is obtained according to moment to be predicted in each history cycle corresponding load power normalized value utilization index smoothing algorithm to pre-
Survey moment to be predicted corresponding load power in the period.This method considers history feature, but model utilization index smoothing algorithm,
There is no memory unit, precision is limited, also not being distinguished with electrical feature to working day and nonworkdays.
Summary of the invention
In order to solve the above technical problems, the invention discloses a kind of Methods of electric load forecasting, comprising: step S100 is obtained
Take the history Power system load data D=[D of n history cycle of current period1,D2,…,Dn], wherein DiIt is before current period
The Power system load data in n+1-i period, 1≤i≤n;Step S200 is based on the history Power system load data D, uses frequency spectrum
Analysis method obtains history high frequency time domain data DH=[DH1,DH2,…,DHM]TWith history low-frequency time-domain data DL=[DL1,
DL2,…,DLn];Step S300, according to the history high frequency time domain data DH and the history low-frequency time-domain data DL, prediction is worked as
The Power system load data in preceding periodWherein pl is low to be obtained based on the history low-frequency time-domain data DL
Frequency predicted value, the phjFor based on the history high frequency time domain data DHjThe high frequency predicted value of acquisition.
Detailed description of the invention
Fig. 1 is a kind of flow chart of Methods of electric load forecasting of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, the present invention will be made further in conjunction with attached drawing
Detailed description.This description is to describe specific implementation consistent with the principles of the present invention by way of example, and not limitation
Mode, the description of these embodiments is detailed enough, so that those skilled in the art can practice the present invention, is not being taken off
Other embodiments can be used in the case where from scope and spirit of the present invention and can change and/or replace each element
Structure.Therefore, the following detailed description should not be understood from restrictive sense.
Fig. 1 is a kind of flow chart of Methods of electric load forecasting of the invention.As shown in Figure 1, this method comprises:
Step S100 obtains the history Power system load data D=[D of n history cycle of current period1,D2,…,Dn],
Wherein DiFor the Power system load data in the (n+1)th-i before current period periods, 1≤i≤n.According to the present invention, the electricity in the period
Power load data is the Power system load data of specified geography fence region, transformer and/or user in different cycles, wherein described
Geography fence region can be obtained according to the division for carrying out the other shapes such as rectangle to terrestrial coordinate system, the transformer and/or institute
Stating user can be specified transformer and/or designated user.The length in the period can customize setting, it is preferred that the length
Value range be [1 day, 100 days].Further, according to the present invention, the value of n can customize setting, it is preferable that the value of n
Range be [10,100], the customized setting of n value, can convenient for as needed obtain in the recent period or temporary electricity load characteristic and/or
Electric load feature when long-term or long, such as when n value is smaller, electric load feature in a short time can be got, if n value
Larger, then what is reflected is long-term electric load feature.Table 1 is totally 97 periods under the transformer Source of Gateway Meter that obtains of the present invention
Power system load data, wherein the length in the period be 1 day, and Power system load data unit be kwh (be limited to length, herein
Value provides partial data):
Table 1
D1 | D2 | ... | D97 |
2869.6 | 2899.2 | ... | 2444.8 |
Step S200 is based on the history Power system load data D, obtains history high frequency time domain number using frequency spectrum analysis method
According to DH=[DH1,DH2,…,DHM]TWith history low-frequency time-domain data DL=[DL1,DL2,…,DLn], wherein M is the frequency spectrum point
The analysis number of plies in analysis method, DHj=[DHj1,DHj2,…,DHjn]TFor the jth layer height obtained according to the frequency spectrum analysis method
Frequency component, DLkThe numerical value for being the first layer low frequency component that is obtained according to the frequency spectrum analysis method at the kth moment, DHjkFor jth
Numerical value of the layer high fdrequency component at the kth moment, 1≤j≤M, 1≤k≤n.According to one embodiment of present invention, the spectrum analysis
Method is Bartlett frequency spectrum analysis method, and in preferred one embodiment of the invention, the frequency spectrum analysis method is small
Wave conversion method.Further, the small wave converting method is become using the wavelet analysis that the small echos class functions such as symN, dbN carry out M layers
It changes, wherein the value range of M is [2,6], and the value range of N is [2,9], it is preferred that in the present invention, the wavelet transformation side
Method converts the Power system load data D wavelet analysis for carrying out M=3 layers using db5 wavelet function.Table 2 is right in the present invention
The Power system load data D carries out the data after 3 layers of wavelet transformation based on db5 wavelet function, and table 3 is of the invention to described
Power system load data D carries out the history high frequency time domain data DH after 3 layers of wavelet transformation based on db5 wavelet function, and table 4 is this hair
The bright history low-frequency time-domain data Power system load data D carried out after 3 layers of wavelet transformation based on db5 wavelet function
DL。
Table 2
k | 1 | 2 | ... | 97 |
DL | DL1=2819.7 | DL2=2823.7 | ... | DL97=2209.4 |
DH1 | DH1,1=70.3024 | DH1,2=23.71 | ... | DH1,97=117.1698 |
DH2 | DH2,1=0.4114 | DH2,2=35.0899 | ... | DH2,97=191.2215 |
DH3 | DH3,1=8.7486 | DH3,2=7.8881 | ... | DH3,97=-72.9452 |
Table 3
k | 1 | 2 | ... | 97 |
DH1 | DH1,1=70.3024 | DH1,2=23.71 | ... | DH1,97=117.1698 |
DH2 | DH2,1=0.4114 | DH2,2=35.0899 | ... | DH2,97=191.2215 |
DH3 | DH3,1=8.7486 | DH3,2=7.8881 | ... | DH3,97=-72.9452 |
Table 4
k | 1 | 2 | ... | 97 |
DL | DL1=2819.7 | DL2=2823.7 | ... | DL97=2209.4 |
Step S300, according to the history high frequency time domain data DH and the history low-frequency time-domain data DL, prediction is current
The Power system load data in periodWherein pl is the low frequency obtained based on the history low-frequency time-domain data DL
Predicted value, the phjFor based on the history high frequency time domain data DHjThe high frequency predicted value of acquisition.In an implementation of the invention
In mode,The i.e. described pl is the average value of the history low-frequency time-domain data DL, excellent in of the invention one
It selects in embodiment, pl is obtained based on conventional time series analysis prediction model and the history low-frequency time-domain data DL, wherein
The conventional time series analysis prediction model is autoregression model AR, Moving Average model M A, auto regressive moving average mould
Type ARMA and/or difference ARMA model ARIMA.Since the smoothed data of low frequency can be used to characterize for a long time
With electrical feature, and prolonged periodical power load data stabilization, fluctuate it is small, therefore using conventional time series analysis prediction
Model is predicted just to be able to satisfy requirement.
Further, according to embodiment of the present invention,In a preferred implementation of the invention
In mode, using the length in machine learning method in short-term memory network LSTM model to the history high frequency time domain data DHjInto
Capable prediction, the random fluctuation data of high frequency can be used for characterizing the use electrical feature of short time, in short-term using the length with memory unit
Memory network LSTM model predicts high frequency time domain data, can further improve the precision of prediction.Table 5 is institute of the present invention
Long memory network LSTM model in short-term is stated to high frequency time domain data DHjThe predicted value predicted, table 6 are tradition of the present invention
Predicted value of the Time Series Analysis Forecasting model to the history low-frequency time-domain data DL.
Table 5
ph1=35.5368 |
ph2=-65.5428 |
ph3=-62.7829 |
Table 6
Pl=2395 |
It therefore, can be with the Power system load data N=2395+ of the current period according to the data of table 5 and table 6
35.5368-65.5428-62.7829=2302.2.
By content disclosed above it is found that the power load of n history cycle before the current period that the present invention will acquire
Lotus data obtain low-frequency time-domain data and multiple high frequency time domain datas by Spectrum Conversion method, wherein utilize low-frequency time-domain number
According to stability characterize the long-term with electrical feature of transformer, geography fence region either user, use multiple high frequency time domains
The stochastic volatility of data is remembered to characterize short-term electrical feature of using further combined with passing logical Time Series Analysis Model and having
Recalling the length of unit, memory network LSTM model respectively counts it was predicted that being led to low-frequency time-domain data and high frequency time domain data in short-term
It crosses and is superimposed the Power system load data that every predicted value obtains current period, so that the electric load number of the current period finally obtained
It is higher according to accuracy.
In one embodiment of the invention, when the length in the period is one,Wherein, M is weight coefficient, and value range is [0,1], it is preferable that the value range of m is
[0.85,0.92].When the period is one, by using the workaday Power system load data mean value of history/non-work of history
The Power system load data mean value for making day is modified basic forecast value, and it is pre- to further improve current period Power system load data
The precision of measured value.
Preferably, in another embodiment of the present invention, a kind of load forecast server is also disclosed, it is described pre-
The available geography fence of server, transformer and/or the Power system load data of user, the server is surveyed further to go back
It, can be real when the computer program is performed including processor and the non-transient storage medium for being stored with computer program
Existing the above step S100- step S300.The load forecast is realized on the server, can save local storage money
Source and computing resource.
In addition, according to disclosed specification of the invention, other realizations of the invention are for those skilled in the art
Significantly.The various aspects of embodiment and/or embodiment can be used for system of the invention individually or with any combination
In method.Specification and example therein should be only be regarded solely as it is exemplary, the actual scope of the present invention and spirit by appended
Claims indicate.
Claims (10)
1. a kind of Methods of electric load forecasting characterized by comprising
Step S100 obtains the history Power system load data D=[D of n history cycle of current period1,D2,…,Dn], wherein Di
For the Power system load data in the (n+1)th-i before current period periods, 1≤i≤n;
Step S200 is based on the history Power system load data D, obtains history high frequency time domain data DH using frequency spectrum analysis method
=[DH1,DH2,…,DHM]TWith history low-frequency time-domain data DL=[DL1,DL2,…,DLn], wherein M is the spectrum analysis side
The analysis number of plies in method, DHj=[DHj1,DHj2,…,DHjn]TFor the high frequency division of jth layer obtained according to the frequency spectrum analysis method
Amount, DLkThe numerical value for being the first layer low frequency component that is obtained according to the frequency spectrum analysis method at the kth moment, DHjkIt is high for jth layer
Numerical value of the frequency component at the kth moment, 1≤j≤M, 1≤k≤n;
Step S300 predicts current period according to the history high frequency time domain data DH and the history low-frequency time-domain data DL
Power system load dataWherein pl is the low frequency prediction obtained based on the history low-frequency time-domain data DL
Value, the phjFor based on the history high frequency time domain data DHjThe high frequency predicted value of acquisition.
2. Methods of electric load forecasting according to claim 1, which is characterized in that the value range of M is [2,6], preferably
It is 3.
3. Methods of electric load forecasting according to claim 1, which is characterized in that the length in the period, which can customize, to be set
It sets, it is preferred that the value range of the length is [1 day, 100 days].
4. Methods of electric load forecasting according to claim 1, which is characterized in that the value of n can customize setting, preferably
Ground, the value range of n are [10,100].
5. Methods of electric load forecasting according to claim 1-4, which is characterized in that the frequency spectrum analysis method
For small wave converting method.
6. Methods of electric load forecasting according to claim 1, which is characterized in that in step S300, when based on tradition
Between sequence analysis prediction model and the history low-frequency time-domain data DL obtain pl;Preferably, the conventional time series analysis
Prediction model can be mobile for autoregression model, rolling average line model, ARMA model and/or difference autoregression
Averaging model.
7. Methods of electric load forecasting according to claim 1, which is characterized in that be based on the history high frequency time domain data
DHjPh is obtained with long memory network LSTM model in short-termj。
8. Methods of electric load forecasting according to claim 1-7, which is characterized in that when the length in the period
When being one,Wherein, M is weight coefficient, and value range is [0,1].
9. Methods of electric load forecasting according to claim 8, which is characterized in that the value range of the m be [0.85,
0.92]。
10. Methods of electric load forecasting according to claim 1, which is characterized in that the Power system load data is specified
The Power system load data of geography fence region, transformer and/or user in different cycles.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910038483.7A CN109816164A (en) | 2019-01-16 | 2019-01-16 | A kind of Methods of electric load forecasting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910038483.7A CN109816164A (en) | 2019-01-16 | 2019-01-16 | A kind of Methods of electric load forecasting |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816164A true CN109816164A (en) | 2019-05-28 |
Family
ID=66604406
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910038483.7A Pending CN109816164A (en) | 2019-01-16 | 2019-01-16 | A kind of Methods of electric load forecasting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816164A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116805782A (en) * | 2023-05-22 | 2023-09-26 | 国家电网有限公司华东分部 | New energy output scene generation method and device and computer equipment |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102427230A (en) * | 2011-12-19 | 2012-04-25 | 天津市电力公司 | Wind-light storage combined dispatching method and system used for distributed microgrid island operation |
CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
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 |
CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
CN103745272A (en) * | 2014-01-06 | 2014-04-23 | 国家电网公司 | Power short-term load predicating method based on fast periodic component extraction |
CN104376368A (en) * | 2014-08-19 | 2015-02-25 | 上海交通大学 | Wind power generation short-term load forecasting method and device based on frequency domain decomposition |
CN104820876A (en) * | 2015-05-21 | 2015-08-05 | 国家电网公司 | Short-term load forecasting method and system |
CN105335539A (en) * | 2014-08-08 | 2016-02-17 | 国家电网公司 | Data processing method and apparatus for power load |
CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
CN106485365A (en) * | 2016-10-25 | 2017-03-08 | 广东工业大学 | A kind of Load Prediction In Power Systems method and device |
CN106503851A (en) * | 2016-10-25 | 2017-03-15 | 国家电网公司 | A kind of improved Short-Term Load Forecasting Method based on wavelet analysises |
CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
CN107590557A (en) * | 2017-08-31 | 2018-01-16 | 河海大学 | Load forecasting method based on wavelet transformation and harmony search updated gray correlation analysis |
CN107729868A (en) * | 2017-11-01 | 2018-02-23 | 广西师范学院 | A kind of signal processing method based on wavelet analysis |
CN108022014A (en) * | 2017-12-05 | 2018-05-11 | 国网山东省电力公司济南供电公司 | A kind of Load Prediction In Power Systems method and system |
CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
-
2019
- 2019-01-16 CN CN201910038483.7A patent/CN109816164A/en active Pending
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102427230A (en) * | 2011-12-19 | 2012-04-25 | 天津市电力公司 | Wind-light storage combined dispatching method and system used for distributed microgrid island operation |
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 |
CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
CN103745272A (en) * | 2014-01-06 | 2014-04-23 | 国家电网公司 | Power short-term load predicating method based on fast periodic component extraction |
CN105335539A (en) * | 2014-08-08 | 2016-02-17 | 国家电网公司 | Data processing method and apparatus for power load |
CN104376368A (en) * | 2014-08-19 | 2015-02-25 | 上海交通大学 | Wind power generation short-term load forecasting method and device based on frequency domain decomposition |
CN104820876A (en) * | 2015-05-21 | 2015-08-05 | 国家电网公司 | Short-term load forecasting method and system |
CN105678398A (en) * | 2015-12-24 | 2016-06-15 | 国家电网公司 | Power load forecasting method based on big data technology, and research and application system based on method |
CN106485365A (en) * | 2016-10-25 | 2017-03-08 | 广东工业大学 | A kind of Load Prediction In Power Systems method and device |
CN106503851A (en) * | 2016-10-25 | 2017-03-15 | 国家电网公司 | A kind of improved Short-Term Load Forecasting Method based on wavelet analysises |
CN106529747A (en) * | 2017-01-04 | 2017-03-22 | 成都四方伟业软件股份有限公司 | Power load predicting method and system based on large data |
CN107590557A (en) * | 2017-08-31 | 2018-01-16 | 河海大学 | Load forecasting method based on wavelet transformation and harmony search updated gray correlation analysis |
CN107729868A (en) * | 2017-11-01 | 2018-02-23 | 广西师范学院 | A kind of signal processing method based on wavelet analysis |
CN108022014A (en) * | 2017-12-05 | 2018-05-11 | 国网山东省电力公司济南供电公司 | A kind of Load Prediction In Power Systems method and system |
CN108846517A (en) * | 2018-06-12 | 2018-11-20 | 清华大学 | A kind of probability short-term electric load prediction integrated approach of quantile |
CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
Non-Patent Citations (1)
Title |
---|
许元斌: "短期电力负荷组合预测分析方法研究", 自动化与仪器仪表, no. 3, pages 32 - 35 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116805782A (en) * | 2023-05-22 | 2023-09-26 | 国家电网有限公司华东分部 | New energy output scene generation method and device and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yu et al. | A systematic procedure to study the influence of occupant behavior on building energy consumption | |
CN111144468B (en) | Method and device for labeling power consumer information, electronic equipment and storage medium | |
CN106786519B (en) | A kind of method of Optimization Prediction power grid typical case's daily load | |
CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
CN107194502B (en) | Residential user power load prediction method | |
CN103793788B (en) | A kind of ordered electric management method | |
CN106410781A (en) | Power consumer demand response potential determination method | |
JP6498976B2 (en) | Estimation apparatus, estimation method, and computer program | |
CN103020459A (en) | Method and system for sensing multiple-dimension electric utilization activities | |
CN112330077B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
CN112488396A (en) | Wavelet transform-based electric power load prediction method of Holt-Winters and LSTM combined model | |
CN107423836A (en) | Short-term load forecasting method based on sendible temperature | |
CN104573857A (en) | Power grid load rate prediction method based on intelligent algorithm optimization and combination | |
CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
CN115238167A (en) | Power consumer refined portrait and management method considering load and social information | |
Wu et al. | Short-term wind power generation forecasting based on the SVM-GM approach | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
CN109816164A (en) | A kind of Methods of electric load forecasting | |
CN106096774A (en) | A kind of large area region Analyzing Total Electricity Consumption Forecasting Methodology based on gridding method | |
CN110991780A (en) | Electric energy quality evaluation method based on ordered weighted average operator | |
CN109214610A (en) | A kind of saturation Methods of electric load forecasting based on shot and long term Memory Neural Networks | |
CN113537578A (en) | Power consumer behavior prediction method | |
CN102880917B (en) | Method for predicting medium-term and long-term power load on basis of logarithmical load density growth curve | |
CN111859242A (en) | Household power energy efficiency optimization method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240319 |