CN103778486A - Power distribution network load predication method - Google Patents
Power distribution network load predication method Download PDFInfo
- Publication number
- CN103778486A CN103778486A CN201410071486.8A CN201410071486A CN103778486A CN 103778486 A CN103778486 A CN 103778486A CN 201410071486 A CN201410071486 A CN 201410071486A CN 103778486 A CN103778486 A CN 103778486A
- Authority
- CN
- China
- Prior art keywords
- data
- month
- load
- value
- error
- 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
Images
Classifications
-
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power distribution network load predication method. The method includes that month load value data within M years before a predicated month is revised to obtain first revision data, wherein M is a positive integer larger than or equal to 1; month load value data of the same month as the predicated month is obtained from the first revision data, and the month load predication value is calculated through a gray method; based on the error data of N months before the predicated month, error predication value is calculated through the gray method, wherein N is a positive integer larger than or equal to 1; the month load predication value is revised based on the error predication value, load predication value of the predicated month is obtained, and the technical problem in the existing month load predication method of being poor in predication accuracy, slow in predication and low in predication efficiency is solved. A technical effect that the month load predication is finished fast, correctly and efficiently is achieved.
Description
Technical field
The present invention relates to technical field of power systems, relate in particular to a kind of power distribution network load forecasting method.
Background technology
Load Prediction In Power Systems is the basis of Economical Operation of Power Systems, all of crucial importance to Power System Planning and operation.Load prediction according to the time of prediction can be divided into for a long time, mid-term and short-term load forecasting.Monthly load prediction belongs to load prediction a middle or short term, most important for fuel planning buying, scheduled overhaul, electricity transaction, income assessment etc.
Gray prediction method is as the modern Forecasting Methodology of one, and the fast precision of speed is high, in annual gas load prediction, has obtained good application.But gray prediction method is poor to cyclical variation data prediction effect, therefore seldom application in moon load prediction.At present, generally adopt in two ways for monthly load prediction: on the basis of classical Forecasting Methodology, carry out monthly coefficient correction, the method prediction accuracy is poor; Adopt neural network, the modern Forecasting Methodology such as genetic algorithm, can obtain higher precision of prediction, but predetermined speed is slow.Power distribution network load prediction is guaranteeing, under the prerequisite of accuracy requirement, computing velocity is had to higher requirement.Therefore, need the high-speed fast Forecasting Methodology of a kind of precision, to realize the load prediction of the power distribution network moon.
Present inventor realizing in the process of invention technical scheme in the embodiment of the present application, finds that above-mentioned technology at least exists following technical matters:
In the prior art, on the basis of classical Forecasting Methodology, carry out monthly coefficient correction and adopt the modern Forecasting Methodologies such as neural network, genetic algorithm to predict because existing monthly load forecasting method mainly adopts, because monthly leveling factor method algorithm is simple, and the data fluctuations of power distribution network is large, discreteness is strong, data have cycle variability, and monthly coefficient is unfixing, causes the method prediction accuracy poor; And the modern Forecasting Methodology calculation of complex such as employing neural network, genetic algorithm, the speed of convergence of algorithm own is slow, need to carry out repeatedly iterative computation, so predetermined speed is slow, so existing monthly load forecasting method exists prediction accuracy poor, predetermined speed is slower, the technical matters that forecasting efficiency is lower.
Summary of the invention
The invention provides a kind of power distribution network load forecasting method, having solved existing monthly load forecasting method exists prediction accuracy poor, predetermined speed is slower, and the technical matters that forecasting efficiency is lower has realized the technique effect that completes fast, accurately and efficiently monthly load prediction.
For solving the problems of the technologies described above, the embodiment of the present application provides a kind of power distribution network load forecasting method, and described method comprises:
Moon load value data in M before predicted month are revised, obtained first and revise data, wherein M is more than or equal to 1 positive integer;
Revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value;
Based on the error information of the described predicted month top n moon, adopt gray method error of calculation predicted value, wherein N is more than or equal to 1 positive integer;
Based on described error prediction value, moon load prediction value is revised, obtained described predicted month load prediction value.
Further, described moon load value data in M before predicted month are revised, are obtained first and revise data and specifically comprise:
Judge whether the moon load value data in the front M of described predicted month are bad data;
If bad data, revises described bad data, obtain revised data;
If normal data, does not revise.
Further, describedly judge whether the moon load value data in M are that bad data specifically comprises before described predicted month:
Utilize formula (1)
, calculate when the average of relatives value that load days with the first two months is loaded then, wherein X (i, j) is moon load data to be judged, and i represents month, and j represents the time;
Utilize formula (2)
, calculate the average of relatives value that same month the previous year loads with the previous year, the first two months was loaded;
If K (i, j) > 1.2K (i, j-1), or K (i, j) <0.8 K (i, j-1), this month load value data are bad data.
Further, if described bad data is revised described bad data, obtain revised data and be specially: if bad data utilizes formula (3)
described bad data is revised, obtained revised data.
Further, describedly revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value and specifically comprise:
Obtain with the described predicted month same month 5 days load value data, i.e. X (i, j-5), X (i, j-4), X (i, j-3), X (i, j-2), X (i, j-1);
The data of acquisition are carried out to smoothing processing, obtain described month load prediction value X (i, j) according to grey GM (1,1) model.
Further, the described error information based on the described predicted month top n moon, adopts gray method error of calculation predicted value specifically to comprise:
Obtain first 12 months error informations of described predicted month,
(i-12),
(i-11),
(i-10),
(i-9),
(i-8),
(i-7),
(i-6),
(i-5),
(i-4),
(i-3),
(i-2),
(i-1);
The data of acquisition are carried out to smoothing processing, obtain error prediction value according to described grey GM (1,1) model
(i).
Further, described error information is relative error data.
Further, describedly based on described error prediction value, moon load prediction value is revised, obtained described predicted month load prediction value and be specially: utilize formula (4) based on described error prediction value
moon load prediction value is revised, obtained described predicted month load prediction value.
Further, described the data of acquisition are carried out to smoothing processing, according to grey GM (1,1) model obtain described month load prediction value X (i, j) be specially: utilize formula (5)
to described X (i, j-4), described X (i, j-3), described X (i, j-2) carries out smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
Further, described the data of acquisition are carried out to smoothing processing, obtain error prediction value according to described grey GM (1,1) model
(i) be specially: utilize formula (6)
the 2nd to the 11st error information in first 12 months error informations of the described predicted month of described acquisition carried out to smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
The one or more technical schemes that provide in the embodiment of the present application, at least have following technique effect or advantage:
First the moon load value data in M before predicted month are revised owing to having adopted, obtained first and revise data, wherein M is more than or equal to 1 positive integer, then revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value, then the error information based on the described predicted month top n moon, adopts gray method error of calculation predicted value, and wherein N is more than or equal to 1 positive integer, finally based on described error prediction value, moon load prediction value is revised, obtain the technical scheme of described predicted month load prediction value, adopted and utilized historical same month data to predict of that month data, eliminate the cycle variability of data, utilize historical error amount to predict of that month error amount, and data are revised, and to load prediction and the prediction of error is all adopted to gray prediction method, and Double Grey Prediction method predetermined speed is fast, accurately high, and adopt the moon to identify and revise the technological means of bad data than mode, exist prediction accuracy poor so efficiently solve existing monthly load forecasting method, predetermined speed is slower, the technical matters that forecasting efficiency is lower, and then realize fast, accurately, complete efficiently the technique effect of monthly load prediction.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of power distribution network load forecasting method in the embodiment of the present application one;
Fig. 2 is bad data identification schematic diagram in power distribution network load forecasting method in the embodiment of the present application one;
Fig. 3 is historical data schematic diagram in power distribution network load forecasting method in the embodiment of the present application one;
Fig. 4 is power distribution network load forecasting method schematic flow sheet in the embodiment of the present application one.
Embodiment
The invention provides a kind of power distribution network load forecasting method, having solved existing monthly load forecasting method exists prediction accuracy poor, predetermined speed is slower, and the technical matters that forecasting efficiency is lower has realized the technique effect that completes fast, accurately and efficiently monthly load prediction.
Technical scheme during the application implements is for solving the problems of the technologies described above.General thought is as follows:
Adopted and first the moon load value data in M before predicted month have been revised, obtained first and revise data, wherein M is more than or equal to 1 positive integer, then revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value, then the error information based on the described predicted month top n moon, adopts gray method error of calculation predicted value, and wherein N is more than or equal to 1 positive integer, finally based on described error prediction value, moon load prediction value is revised, obtain the technical scheme of described predicted month load prediction value, adopted and utilized historical same month data to predict of that month data, eliminate the cycle variability of data, utilize historical error amount to predict of that month error amount, and data are revised, and to load prediction and the prediction of error is all adopted to gray prediction method, and Double Grey Prediction method predetermined speed is fast, accurately high, and adopt the moon to identify and revise the technological means of bad data than mode, exist prediction accuracy poor so efficiently solve existing monthly load forecasting method, predetermined speed is slower, the technical matters that forecasting efficiency is lower, and then realize fast, accurately, complete efficiently the technique effect of monthly load prediction.
In order better to understand technique scheme, below in conjunction with Figure of description and concrete embodiment, technique scheme is described in detail.
Embodiment mono-:
In embodiment mono-, a kind of power distribution network load forecasting method is provided, please refer to Fig. 1-Fig. 4, described method comprises:
S10, revises the moon load value data in M before predicted month, obtains first and revises data, and wherein M is more than or equal to 1 positive integer.
Wherein, in the embodiment of the present application, described moon load value data in M before predicted month are revised, are obtained first and revise data and specifically comprise:
Judge whether the moon load value data in the front M of described predicted month are bad data;
If bad data, revises described bad data, obtain revised data;
If normal data, does not revise.
Wherein, in the embodiment of the present application, please refer to Fig. 2, describedly judge whether the moon load value data in M are that bad data specifically comprises before described predicted month:
Utilize formula (1)
, calculate when the average of relatives value that load days with the first two months is loaded then, wherein X (i, j) is moon load data to be judged, and i represents month, and j represents the time;
Utilize formula (2)
, calculate the average of relatives value that same month the previous year loads with the previous year, the first two months was loaded;
If K (i, j) > 1.2K (i, j-1), or K (i, j) <0.8 K (i, j-1), this month load value data are bad data.
In actual applications, please refer to Fig. 2, i-2 the previous year month load value is X(i-2, j-1), data X(i-2, j) be i-2 in the same year month load value, by that analogy.
Wherein, in the embodiment of the present application, if described bad data is revised described bad data, obtain revised data and be specially: if bad data utilizes formula (3)
described bad data is revised, obtained revised data.
In actual applications, suppose that M equals 5, the data in first 5 years of predicted month are historical data.This historical data comprise in 5 years each month load value and every month the previous year predicted value and actual value between absolute error.Historical data correction is only for month load value wherein, and absolute error value does not need to revise.
The embodiment of the present application enters step S20 after the step S10, revises the moon load value data that obtain data with the described predicted month same month from described first, utilizes gray method to calculate a month load prediction value.
Wherein, in the embodiment of the present application, please refer to Fig. 3, describedly revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value and specifically comprise:
Obtain with the described predicted month same month 5 days load value data, i.e. X (i, j-5), X (i, j-4), X (i, j-3), X (i, j-2), X (i, j-1);
The data of acquisition are carried out to smoothing processing, obtain described month load prediction value X (i, j) according to grey GM (1,1) model.
After step S20, the embodiment of the present application enters step S30, based on the error information of the described predicted month top n moon, adopts gray method error of calculation predicted value, and wherein N is more than or equal to 1 positive integer
Wherein, in the embodiment of the present application, the described error information based on the described predicted month top n moon, adopts gray method error of calculation predicted value specifically to comprise:
Obtain first 12 months error informations of described predicted month,
(i-12),
(i-11),
(i-10),
(i-9),
(i-8),
(i-7),
(i-6),
(i-5),
(i-4),
(i-3),
(i-2),
(i-1);
The data of acquisition are carried out to smoothing processing, obtain error prediction value according to described grey GM (1,1) model
(i).
Wherein, in the embodiment of the present application, described error information is relative error data.
After step S30, the embodiment of the present application enters step S40, based on described error prediction value, moon load prediction value is revised, and obtains described predicted month load prediction value.
Wherein, in the embodiment of the present application, describedly based on described error prediction value, moon load prediction value is revised, obtained described predicted month load prediction value and be specially: utilize formula (4) based on described error prediction value
moon load prediction value is revised, obtained described predicted month load prediction value.
Wherein, in the embodiment of the present application, described the data of acquisition are carried out to smoothing processing, according to grey GM (1,1) model obtain described month load prediction value X (i, j) be specially: utilize formula (5)
to described X (i, j-4), described X (i, j-3), described X (i, j-2) carries out smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
Wherein, in the embodiment of the present application, described the data of acquisition are carried out to smoothing processing, obtain error prediction value according to described grey GM (1,1) model
(i) be specially: utilize formula (6)
the 2nd to the 11st error information in first 12 months error informations of the described predicted month of described acquisition carried out to smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
In actual applications, described grey GM (1,1) model is a kind of gray model that commonly use, better simply, it is only to comprise by one the model that the univariate differential equation forms, be GM (1, special case n), comparatively conventional in prediction, just do not repeat at this.
In actual applications, please refer to Fig. 4, Fig. 4 is power distribution network load forecasting method schematic flow sheet in the embodiment of the present application one, first the historical load Data Collection of power distribution network is got up, then historical data is revised, in revised data, filter out the historical data with the predicted month same month, the front some months error informations of predicted month are filtered out, some months error informations before that obtain and the historical data predicted month same month and predicted month are carried out respectively to gray method predicted month load, and utilize gray method prediction error data, then load with the error information correction moon, finally obtain final month load prediction value.
Introduce for example the power distribution network load forecasting method in the embodiment of the present application below, in actual applications, utilize the moon load data in certain province somewhere year Dec in January, 2006 to 2011 to carry out emulation experiment, wherein the load data in year Dec in January, 2006 to 2010 is as historical data, be used for setting up forecast model, the data in January, 2011 to Dec, as test set, are used for checking prediction effect.Predict the outcome as shown in table 1:
Table 1
Technical scheme in above-mentioned the embodiment of the present application, at least has following technique effect or advantage:
First the moon load value data in M before predicted month are revised owing to having adopted, obtained first and revise data, wherein M is more than or equal to 1 positive integer, then revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value, then the error information based on the described predicted month top n moon, adopts gray method error of calculation predicted value, and wherein N is more than or equal to 1 positive integer, finally based on described error prediction value, moon load prediction value is revised, obtain the technical scheme of described predicted month load prediction value, adopted and utilized historical same month data to predict of that month data, eliminate the cycle variability of data, utilize historical error amount to predict of that month error amount, and data are revised, and to load prediction and the prediction of error is all adopted to gray prediction method, and Double Grey Prediction method predetermined speed is fast, accurately high, and adopt the moon to identify and revise the technological means of bad data than mode, exist prediction accuracy poor so efficiently solve existing monthly load forecasting method, predetermined speed is slower, the technical matters that forecasting efficiency is lower, and then realize fast, accurately, complete efficiently the technique effect of monthly load prediction.
Although described the preferred embodiments of the present invention, once those skilled in the art obtain the basic creative concept of cicada, can make other change and modification to these embodiment.So claims are intended to be interpreted as comprising preferred embodiment and fall into all changes and the modification of the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (10)
1. a power distribution network load forecasting method, is characterized in that, described method comprises:
Moon load value data in M before predicted month are revised, obtained first and revise data, wherein M is more than or equal to 1 positive integer;
Revise the moon load value data that obtain data with the described predicted month same month from described first, utilize gray method to calculate a month load prediction value;
Based on the error information of the described predicted month top n moon, adopt gray method error of calculation predicted value, wherein N is more than or equal to 1 positive integer;
Based on described error prediction value, moon load prediction value is revised, obtained described predicted month load prediction value.
2. method according to claim 1, is characterized in that, described moon load value data in M before predicted month is revised, and obtains first and revises data and specifically comprise:
Judge whether the moon load value data in the front M of described predicted month are bad data;
If bad data, revises described bad data, obtain revised data;
If normal data, does not revise.
3. method according to claim 2, is characterized in that, describedly judges whether the moon load value data in M are that bad data specifically comprises before described predicted month:
Utilize formula (1)
, calculate when the average of relatives value that load days with the first two months is loaded then, wherein X (i, j) is moon load data to be judged, and i represents month, and j represents the time;
Utilize formula (2)
, calculate the average of relatives value that same month the previous year loads with the previous year, the first two months was loaded;
If K (i, j) > 1.2K (i, j-1), or K (i, j) <0.8 K (i, j-1), this month load value data are bad data.
4. method according to claim 3, is characterized in that, if described bad data is revised described bad data, obtains revised data and is specially: if bad data utilizes formula (3)
described bad data is revised, obtained revised data.
5. method according to claim 3, is characterized in that, describedly revises the moon load value data that obtain data with the described predicted month same month from described first, utilizes gray method to calculate a month load prediction value and specifically comprises:
Obtain with the described predicted month same month 5 days load value data, i.e. X (i, j-5), X (i, j-4), X (i, j-3), X (i, j-2), X (i, j-1);
The data of acquisition are carried out to smoothing processing, obtain described month load prediction value X (i, j) according to grey GM (1,1) model.
6. method according to claim 3, is characterized in that, the described error information based on the described predicted month top n moon adopts gray method error of calculation predicted value specifically to comprise:
Obtain first 12 months error informations of described predicted month,
(i-12),
(i-11),
(i-10),
(i-9),
(i-8),
(i-7),
(i-6),
(i-5),
(i-4),
(i-3),
(i-2),
(i-1);
The data of acquisition are carried out to smoothing processing, obtain error prediction value according to described grey GM (1,1) model
(i).
7. method according to claim 6, is characterized in that, described error information is relative error data.
8. method according to claim 7, is characterized in that, describedly based on described error prediction value, moon load prediction value is revised, and obtains described predicted month load prediction value and is specially: utilize formula (4) based on described error prediction value
moon load prediction value is revised, obtained described predicted month load prediction value.
9. method according to claim 5, is characterized in that, described the data of acquisition is carried out to smoothing processing, according to grey GM (1,1) model obtain described month load prediction value X (i, j) be specially: utilize formula (5)
to described X (i, j-4), described X (i, j-3), described X (i, j-2) carries out smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
10. method according to claim 6, is characterized in that, described the data of acquisition is carried out to smoothing processing, obtains error prediction value according to described grey GM (1,1) model
(i) be specially: utilize formula (6)
the 2nd to the 11st error information in first 12 months error informations of the described predicted month of described acquisition carried out to smoothing processing, and wherein said grey GM (1,1) model is Classical Grey color model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410071486.8A CN103778486A (en) | 2014-02-28 | 2014-02-28 | Power distribution network load predication method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410071486.8A CN103778486A (en) | 2014-02-28 | 2014-02-28 | Power distribution network load predication method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103778486A true CN103778486A (en) | 2014-05-07 |
Family
ID=50570694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410071486.8A Pending CN103778486A (en) | 2014-02-28 | 2014-02-28 | Power distribution network load predication method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103778486A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106611950A (en) * | 2015-10-21 | 2017-05-03 | 中国电力科学研究院 | Prediction load correction method in real-time scheduling plan |
| CN108292860A (en) * | 2015-12-10 | 2018-07-17 | 三菱电机株式会社 | Power control unit, operating plan formulating method and program |
| CN109063889A (en) * | 2018-06-20 | 2018-12-21 | 南瑞集团有限公司 | A kind of load power prediction technique of active distribution network |
| CN110245796A (en) * | 2019-06-12 | 2019-09-17 | 国网北京市电力公司 | Regional space load forecasting method and system and equipment based on internet fuzzy message Modifying model |
| WO2020075019A1 (en) * | 2018-10-09 | 2020-04-16 | International Business Machines Corporation | Prediction model enhancement |
| CN116131360A (en) * | 2023-01-31 | 2023-05-16 | 成都安美科能源管理有限公司 | Hybrid energy control method and control device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831488A (en) * | 2012-08-17 | 2012-12-19 | 华北电力大学 | Power load forecasting process based on improved grey forecasting method |
-
2014
- 2014-02-28 CN CN201410071486.8A patent/CN103778486A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102831488A (en) * | 2012-08-17 | 2012-12-19 | 华北电力大学 | Power load forecasting process based on improved grey forecasting method |
Non-Patent Citations (3)
| Title |
|---|
| 严磊 等: "基于双重灰色模型的中期电力负荷预测", 《电气应用》 * |
| 孟思齐 等: "基于灰色生成的卡尔曼滤波短期负荷预测", 《电力系统及其自动化学报》 * |
| 尹金良: "基于负荷预测的配电网络重构", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106611950A (en) * | 2015-10-21 | 2017-05-03 | 中国电力科学研究院 | Prediction load correction method in real-time scheduling plan |
| CN106611950B (en) * | 2015-10-21 | 2019-03-19 | 中国电力科学研究院 | A kind of prediction loading correcting method of Real-Time Scheduling in the works |
| CN108292860A (en) * | 2015-12-10 | 2018-07-17 | 三菱电机株式会社 | Power control unit, operating plan formulating method and program |
| CN109063889A (en) * | 2018-06-20 | 2018-12-21 | 南瑞集团有限公司 | A kind of load power prediction technique of active distribution network |
| WO2020075019A1 (en) * | 2018-10-09 | 2020-04-16 | International Business Machines Corporation | Prediction model enhancement |
| CN112823364A (en) * | 2018-10-09 | 2021-05-18 | 国际商业机器公司 | Predictive model enhancement |
| GB2593604A (en) * | 2018-10-09 | 2021-09-29 | Ibm | Prediction model enhancement |
| US11257001B2 (en) | 2018-10-09 | 2022-02-22 | International Business Machines Corporation | Prediction model enhancement |
| CN110245796A (en) * | 2019-06-12 | 2019-09-17 | 国网北京市电力公司 | Regional space load forecasting method and system and equipment based on internet fuzzy message Modifying model |
| CN116131360A (en) * | 2023-01-31 | 2023-05-16 | 成都安美科能源管理有限公司 | Hybrid energy control method and control device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103778486A (en) | Power distribution network load predication method | |
| CN103235553B (en) | Method for automatically compensating numerical control machining size error based on fractional order | |
| CN103020711A (en) | Classifier training method and classifier training system | |
| CN105988930A (en) | Test case generation method and device | |
| CN109086936B (en) | Production system resource allocation method, device and equipment for intelligent workshop | |
| CN102521080A (en) | Computer data recovery method for electricity-consumption information collecting system for power consumers | |
| CN110009419A (en) | Improvement time series electricity sales amount prediction technique and system based on Economic Climate method | |
| CN112597610B (en) | Optimization method, device and equipment for lightweight design of mechanical arm structure | |
| CN111105065A (en) | Rural water supply system and method based on machine learning | |
| CN104463381A (en) | Building energy consumption predication method based on KPCA and WLSSVM | |
| CN103345718A (en) | Second-hand house price assessment method | |
| CN104182800A (en) | Intelligent predicting method for time sequence based on trend and periodic fluctuation | |
| WO2017049428A1 (en) | Spinning reserve capacity optimization method based on cost-performance ratio of reserve object | |
| CN111461443A (en) | Optimal design method and system for wind power plant, electronic device and storage medium | |
| CN109214610B (en) | Saturated power load prediction method based on long-term and short-term memory neural network | |
| CN105389637A (en) | Effective workday construction method for monthly electricity consumption prediction model | |
| CN109919357A (en) | A kind of data determination method, device, equipment and medium | |
| CN110059865B (en) | Resource optimization processing method and device | |
| CN112101612A (en) | Prediction method of town gas usage, storage medium and terminal equipment | |
| CN107705200A (en) | Current account is layered the methods of figuring interest and device, computer equipment and storage medium | |
| CN104933210A (en) | Method for processing body-in-white rigidity optimization result file | |
| CN103002053A (en) | Profit maximization scheduling method and system of cloud computing | |
| CN114399078A (en) | Load day-ahead prediction and ultra-short-term prediction collaborative prediction method and system | |
| CN103752621B (en) | Automatic interchange and transfer method for emergency specification change materials of hot rolling line | |
| CN108509984A (en) | Activation value quantifies training method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140507 |