CN112598157B - Prediction method and device of power load - Google Patents
Prediction method and device of power load Download PDFInfo
- Publication number
- CN112598157B CN112598157B CN202011364841.2A CN202011364841A CN112598157B CN 112598157 B CN112598157 B CN 112598157B CN 202011364841 A CN202011364841 A CN 202011364841A CN 112598157 B CN112598157 B CN 112598157B
- Authority
- CN
- China
- Prior art keywords
- load
- users
- user
- prediction
- predicting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000011217 control strategy Methods 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 description 4
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a method and a device for predicting a power load. The method for predicting the power load comprises the following steps: arranging the user loads in a preset historical time period according to a descending order; accumulating each of the user loads until the accumulated load exceeds a first predetermined percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users; predicting the key users to obtain a first load predicted value A (i, j); wherein i is the user number and j is the date; vectorizing the actual load of the general user to obtain a second load actual value B (i, j); and superposing the prediction of the key user and the vectorization of the general user to obtain total amount prediction results A (i, j + 1) and B (i, j + 1). Compared with the prior art, the embodiment of the invention improves the accuracy of power load prediction.
Description
Technical Field
The embodiment of the invention relates to the technical field of electric power, in particular to a method and a device for predicting an electric power load.
Background
With the great increase of the power consumption, the improvement of the power supply quality becomes an important target of a power supply enterprise, and the power distribution through a load prediction method becomes an important reference of the power distribution. The existing power load prediction method mainly comprises the steps of removing abnormal values after comparing load historical data, clustering, and finally establishing a load prediction mode according to the result of each cluster for prediction. Therefore, in the prior art, only the load composition is considered, and the influence of other uncertain factors on load prediction is not considered, so that the prior art only trains through historical data, and the prediction accuracy is influenced.
Disclosure of Invention
The embodiment of the invention provides a method and a device for predicting a power load, which are used for improving the accuracy of power load prediction.
In a first aspect, an embodiment of the present invention provides a method for predicting a power load, including:
arranging the user loads in a preset historical time period according to a descending order;
accumulating each of the user loads until the accumulated load exceeds a first predetermined percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users;
predicting the key users to obtain a first load predicted value A (i, j); wherein i is the user number and j is the date;
vectorizing the actual load of the general user to obtain a second load actual value B (i, j);
and superposing the prediction of the key user and the vectorization of the general user to obtain total amount prediction results A (i, j + 1) and B (i, j + 1).
According to the technical scheme, the key users are separated from the total amount of the power system, the prediction is independently carried out, the special rule of the key users is obtained, and finally the prediction results are superposed. Compared with the overall prediction of the power system, the historical data does not need to be modeled in a large quantity, but a mode of gradually eliminating the historical data by a total quantity-to-component method is adopted, so that the modeling of only data with trend changes is facilitated, and the accuracy of power load prediction is improved.
Optionally, after obtaining the first load prediction value a (i, j), the method further includes:
carrying out difference processing on the first load predicted value, and recording as (1-B) nA (i, j); wherein n is a positive integer;
performing stationarity test on the first load predicted value after difference;
if not, returning to the step of differential processing;
if the load is stable, obtaining an optimized predicted value S (i, t) according to the first load predicted value, and recording the optimized predicted value S (i, t) = A (i, t)/Mean [ A (i, t-3), A (i, t + 3) ], wherein t =1,2, … …, n;
a peak staggering model is invoked.
Alternatively, n ≧ 7.
Optionally, after obtaining the second load prediction value B (i, j), the method further includes:
vectorizing the actual load of the general user to obtain a temperature T (T);
summing the load demands of all users to obtain a total load demand value N (i, j);
judging whether the second load predicted value B (i, j) is larger than the total load demand value N (i, j);
if yes, calling a peak staggering model;
if not, the air temperature model is called.
Optionally, the air temperature model comprises:
acquiring input historical data;
fitting the historical data by adopting a fitting formula, wherein the fitting formula is as follows:
y(t)＝g(t)+s(t)+h(t)+et
wherein y (t) is a prediction term of the model; g (t) is a trend item and represents the variation trend of the time series on the non-period; s (t) is a term representing a period; h (t) is a holiday term; et is the error term;
and outputting the fitting parameters.
Optionally, the peak shift model comprises:
acquiring an input sequence Y and a parameter matrix X;
storing the predictive control strategy matrix to an expert system as a learning sample, and marking as X (j); wherein j represents the j day, automatically calling the scheme in the expert system according to the result, and directly calling the control strategy of j-1;
if the error is larger than a second preset percentage, selecting a historical optimal parameter X = argmax (Y); wherein argmax (f (x)) is a variable point x corresponding to f (x) taking the maximum value;
and if the error of the historical optimal parameters is larger than the second preset percentage, selecting the sequence Y of the latest historical similar day.
Optionally, the preset historical time period is: one, two or more days before the forecast date.
Optionally, the method for predicting the power load further comprises:
dividing users according to regions;
or dividing users according to industries;
alternatively, the users are divided by user type.
Optionally, the first preset percentage is greater than or equal to 50%.
In a second aspect, an embodiment of the present invention further provides a device for predicting a power load, including:
the sorting module is used for sorting the user loads in a preset historical time period according to a descending order;
the user dividing module is used for accumulating each user load until the accumulated load exceeds a first preset percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users;
the first load prediction module is used for predicting the key users to obtain first load prediction values A (i, j); wherein i is the user number and j is the date;
the second load processing module is used for vectorizing the actual load of the general user to obtain a second load actual value B (i, j);
and the total amount prediction module is used for superposing the prediction of the key user and the vectorization of the general user to obtain total amount prediction results A (i, j + 1) and B (i, j + 1). XX, … ….
According to the embodiment of the invention, key users are separated from the total amount of the power system and are independently predicted to obtain the own special rule, and finally, the prediction results are superposed. Compared with the overall prediction of the power system, the historical data does not need to be modeled in a large quantity, but a mode of gradually eliminating the historical data by a total quantity-to-component method is adopted, so that the modeling of only data with trend changes is facilitated, and the accuracy of power load prediction is improved.
Drawings
Fig. 1 is a schematic flowchart illustrating a method for predicting a power load according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a peak shift model according to a second embodiment of the present invention;
FIG. 3 is a schematic flow chart of an air temperature model according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a power load prediction apparatus according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
The embodiment of the invention provides a power load prediction method, which can be suitable for reference of power supply enterprises, and can be executed by a power load prediction device, wherein the power load prediction device can be configured in hardware equipment such as a power controller and the like.
Fig. 1 is a flowchart illustrating a method for predicting a power load according to an embodiment of the present invention. Referring to fig. 1, the method for predicting the power load includes the steps of:
and S110, arranging the user loads in the preset historical time period according to a descending order.
Wherein the preset historical time period is as follows: one day (yesterday), two or more days before the forecast date. Illustratively, the current day power load may be adaptively predicted based on the user load during the yesterday history period.
The user loads arranged in a descending order are classified in various manners, and if the users are divided according to the areas, the user loads in different areas are arranged in the descending order; if the users are divided according to the industries, the user loads of different industries are arranged according to the descending order; and if the users are divided according to the user types, the user loads of different user types are arranged according to a descending order.
S120, accumulating the load of each user until the accumulated load exceeds a first preset percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users.
Wherein, accumulating each user load means to add the user load ranked at the first position and the user load ranked at the second position, and then add the user load ranked at the third position, and so on. The first preset percentage is the percentage of the cumulative load to the total load of all users, the greater the cumulative user load, the greater the percentage. The user loads are arranged according to a descending order and are accumulated one by one until the accumulated load exceeds a first preset percentage, so that the user load which plays a main role in the total load, namely the key user load, can be obtained, and the corresponding user is the key user. Illustratively, the first preset percentage is equal to or greater than 50%, preferably, the first preset percentage is 75%.
S130, predicting the counterweight user to obtain a first load prediction value A (i, j); wherein i is the user number and j is the date.
The method comprises the following steps that key users are separated from the total amount of a power system, and change rule vectors of the key users can be obtained through independent prediction and are recorded as first change rule vectors A; accordingly, i is the user number, j is the date, and A (i, j) is the first load prediction value.
S140, carrying out difference processing on the first load predicted value, and recording as (1-B) n A (i, j); wherein n is a positive integer.
Wherein, the first step difference is (1-B), which represents A (i, j) -A (i, j-1), and the first load prediction value A (i, j) is processed by n steps and is marked as (1-B) n A (i, j); preferably, n ≧ 7, i.e., 7-order difference processing is performed on the first load prediction value A (i, j).
S150, performing stability test on the differential first load predicted value. If not, returning to S140; if so, go to step S160.
S160, obtaining an optimized predicted value S (i, t) according to the first load predicted value, and recording the optimized predicted value S (i, t) = A (i, t)/Mean [ A (i, t-3), A (i, t + 3) ], wherein t =1,2, … …, n; and performs S1B0.
S170, vectorizing the actual load of the general user to obtain a second load actual value B (i, j) and a temperature T (T).
And vectorizing the actual load of the general users, wherein the second actual load value of each general user is recorded as B (i, j), and the temperature is recorded as T (T).
And S180, summing the load demands of all the users to obtain a total load demand value N (i, j).
The load demands of all the users can be set as the current-day load demands of all the users according to needs, that is, the total load demand value N (i, j) is the sum of the current-day load demands of all the users.
And S190, judging whether the second load predicted value B (i, j) is larger than the total load demand value N (i, j). If yes, executing S1A0; otherwise, S1B0 is executed.
And S1A0, calling a peak staggering model.
And S1B0, calling an air temperature model.
S1C0, superposing prediction of key users and vectorization of general users to obtain total prediction results A (i, j + 1) and B (i, j + 1).
The total prediction results a (i, j + 1) and B (i, j + 1) are results generated by superimposing various prediction quantities.
Therefore, the embodiment of the invention separates the key users from the total amount of the power system, independently predicts the key users to obtain the own special rules, and finally superposes the prediction results. Compared with the overall prediction of the power system, the historical data does not need to be modeled in a large quantity, but a mode of gradually eliminating the historical data by a total quantity-to-component method is adopted, so that the modeling of only data with trend changes is facilitated, and the accuracy of power load prediction is improved.
Example two
On the basis of the first embodiment, the second embodiment further defines a peak offset model. Fig. 2 is a schematic flow chart of a peak shift model according to a second embodiment of the present invention. Referring to fig. 2, the peak shift model includes the following steps:
s210, acquiring an input sequence Y and a parameter matrix X.
S220, storing the predictive control strategy matrix to an expert system as a learning sample, and recording the learning sample as X (j); wherein j represents the j day, the scheme in the expert system is automatically called according to the result, and the control strategy of j-1 is directly called.
The system automatically stores the prediction control strategy matrix of the operator in an expert system as a learning sample, and the learning sample is recorded as X (j).
S230, if the error is larger than a second preset percentage, selecting a historical optimal parameter X = argmax (Y); here, argmax (f (x)) is a variable point x (or a set of x) corresponding to the maximum value of f (x).
The second predetermined percentage may be, for example, 2% to 5%. Illustratively, if the error is greater than 5%, the system may autonomously select the historically optimal parameter X = argmax (Y).
S240, if the error of the historical optimal parameters is larger than a second preset percentage, selecting the sequence Y of the latest historical similar day.
According to the embodiment of the invention, the prediction control strategy matrix is stored to the expert system as a learning sample by setting the peak staggering model, so that compared with the load prediction system in the prior art which needs to manually set a plurality of model parameters, the automatic parameter adjustment is realized; and load prediction with self-learning, self-organizing, self-adapting function and feedback mechanism is provided, and the accuracy of power load prediction is further improved.
EXAMPLE III
In addition to the first and second embodiments, the third embodiment further defines the air temperature model. Fig. 3 is a schematic flow chart of an air temperature model according to a third embodiment of the present invention. Referring to fig. 3, the air temperature model includes the following steps:
s310, acquiring input historical data.
S320, fitting the historical data by adopting a fitting formula, wherein the fitting formula is as follows:
y(t)＝g(t)+s(t)+h(t)+et
wherein y (t) is a prediction term of the model; g (t) is a trend item and represents the variation trend of the time series on a non-periodic time, namely a long-term trend; s (t) is a term representing a period, otherwise known as a seasonal term; illustratively, the predictive model may take two cycles: one is the change rule of the cycle of the week, namely Monday to Sunday, and the other is the change rule of the cycle of the year, namely within one year; h (t) is a holiday term, the law of the electric load of the holiday may be different from that of the ordinary times, and different holidays can be regarded as different models; et is the error term, otherwise known as the residue term.
And S330, outputting the fitting parameters.
According to the embodiment of the invention, the fitting formula of the air temperature model is set as the superposition of the trend term, the period term, the holiday term and the error term, the model prediction is carried out by considering the high complexity and uncertainty of the power consumption of the power consumer, and integrating the factors such as the trend, the period, the holiday and the like, the modeling parameters are adjusted in a self-adaptive manner, and the accuracy of the power load prediction is further improved.
Example four
An embodiment four of the present invention provides a power load prediction apparatus, which can perform the prediction method provided in any one of the first to third embodiments. Fig. 4 is a schematic structural diagram of a power load prediction apparatus according to a fourth embodiment of the present invention. Referring to fig. 4, the power load prediction apparatus includes: a ranking module 410, a user partitioning module 420, a first load prediction module 430, a second load prediction module 440, and a total prediction module 450.
The sorting module 410 is configured to sort the user loads in a preset historical time period in a descending order. The user dividing module 420 is configured to accumulate each user load until the accumulated load exceeds a first preset percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users. The first load prediction module 430 is configured to predict a key user to obtain a first load prediction value a (i, j); wherein i is the user number and j is the date. The second load prediction module 440 is configured to perform vectorization on the actual load of the general user to obtain a second load actual value B (i, j). The total amount prediction module 450 is configured to superimpose the prediction of the key users and the vectorization of the general users to obtain total amount prediction results a (i, j + 1) and B (i, j + 1).
In the embodiment of the invention, the key users are separated from the total amount of the power system by arranging the user dividing module 420, the first load prediction module 430 and the second load prediction module 440 are arranged to perform prediction independently to obtain the own special rule, and the total amount prediction module 450 is arranged to perform superposition of prediction results. Compared with the overall prediction of the power system, the historical data does not need to be modeled in a large quantity, but a mode of gradually eliminating the historical data by a total quantity-to-component method is adopted, so that the modeling of only data with trend changes is facilitated, and the accuracy of power load prediction is improved.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A method for predicting a power load, comprising:
arranging the user loads in a preset historical time period according to a descending order;
accumulating each of the user loads until the accumulated load exceeds a first predetermined percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users;
predicting the key users to obtain a first load predicted value A (i, j); wherein i is the user number and j is the date;
vectorizing the actual load of the general user to obtain a second load actual value B (i, j);
superposing the prediction of the key user and the vectorization of the general user to obtain total prediction results A (i, j + 1) and B (i, j + 1);
after obtaining the second load actual value B (i, j), the method further includes:
vectorizing the actual load of the general user to obtain a temperature T (T);
summing the load demands of all users to obtain a total load demand value N (i, j);
judging whether the second load actual value B (i, j) is larger than the total load demand value N (i, j);
if yes, calling a peak staggering model;
if not, the air temperature model is called.
2. The method for predicting a power load according to claim 1, further comprising, after obtaining the first load prediction value a (i, j):
performing difference processing on the first load predicted value, and recording the difference as (1-B) n A (i, j); wherein n is a positive integer;
performing stationarity test on the first load predicted value after difference;
if not, returning to the step of differential processing;
if the load is stable, obtaining an optimized predicted value S (i, t) according to the first load predicted value, and recording the optimized predicted value S (i, t) = A (i, t)/Mean [ A (i, t-3), A (i, t + 3) ], wherein t =1,2, … …, n;
and calling a peak staggering model.
3. The method for predicting a power load according to claim 2, wherein n is 7 or more.
4. The method of predicting an electric power load according to claim 1, wherein the air temperature model includes:
acquiring input historical data;
fitting the historical data by adopting a fitting formula, wherein the fitting formula is as follows:
y（t）=g（t）+s（t）+h（t）+et
wherein y (t) is a prediction term of the model; g (t) is a trend item and represents the variation trend of the time series on the non-period; s (t) is a term representing a period; h (t) is a holiday term; et is the error term;
and outputting the fitting parameters.
5. The method of predicting a power load according to claim 1 or 2, wherein the peak shift model includes:
acquiring an input sequence Y and a parameter matrix X;
storing the predictive control strategy matrix to an expert system as a learning sample, and recording as X (j); wherein j represents the j day, automatically calling the scheme in the expert system according to the result, and directly calling the control strategy of j-1;
if the error is larger than a second preset percentage, selecting a historical optimal parameter X = argmax (Y); wherein argmax (f (x)) is a variable point x corresponding to f (x) taking the maximum value;
and if the error of the historical optimal parameters is larger than the second preset percentage, selecting the sequence Y of the latest historical similar day.
6. The method of claim 1, wherein the predetermined historical period of time is: one, two or more days before the forecast date.
7. The method for predicting an electric load according to claim 1, further comprising:
dividing users according to regions;
or dividing users according to industries;
alternatively, the users are divided by user type.
8. The method according to claim 1, wherein the first predetermined percentage is equal to or greater than 50%.
9. An apparatus for predicting an electric load, comprising:
the sorting module is used for sorting the user loads in a preset historical time period according to a descending order;
the user dividing module is used for accumulating each user load until the accumulated load exceeds a first preset percentage; wherein, the accumulated users are marked as key users, and the rest users are marked as general users;
the first load prediction module is used for predicting the key users to obtain first load prediction values A (i, j); wherein i is the user number and j is the date;
the second load processing module is used for vectorizing the actual load of the general user to obtain a second load actual value B (i, j);
the total amount prediction module is used for superposing the prediction of the key users and the vectorization of the general users to obtain total amount prediction results A (i, j + 1) and B (i, j + 1);
the second load processing module is further configured to:
vectorizing the actual load of the general user to obtain a temperature T (T);
summing the load demands of all users to obtain a total load demand value N (i, j);
judging whether the second load actual value B (i, j) is larger than the total load demand value N (i, j);
if yes, calling a peak staggering model;
if not, the air temperature model is called.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364841.2A CN112598157B (en) | 2020-11-27 | 2020-11-27 | Prediction method and device of power load |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364841.2A CN112598157B (en) | 2020-11-27 | 2020-11-27 | Prediction method and device of power load |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112598157A CN112598157A (en) | 2021-04-02 |
| CN112598157B true CN112598157B (en) | 2023-03-24 |
Family
ID=75187224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011364841.2A Active CN112598157B (en) | 2020-11-27 | 2020-11-27 | Prediction method and device of power load |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112598157B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729689A (en) * | 2013-12-20 | 2014-04-16 | 华南理工大学 | Power grid electric quantity prediction method based on industry classifications and leading industry data |
| CN105701559A (en) * | 2015-12-31 | 2016-06-22 | 国网上海市电力公司 | Short-term load prediction method based on time sequence |
| CN108346009A (en) * | 2018-03-21 | 2018-07-31 | 深圳库博能源科技有限公司 | A kind of power generation configuration method and device based on user model self study |
| CN111222711A (en) * | 2020-01-16 | 2020-06-02 | 大连理工大学 | Index linkage analysis-based multi-objective optimization method for peak shaving scheduling of electric power system |
| CN111291782A (en) * | 2020-01-13 | 2020-06-16 | 上海交通大学 | Accumulated load prediction method based on information accumulation k-Shape clustering algorithm |
| CN111815060A (en) * | 2020-07-16 | 2020-10-23 | 广东电网有限责任公司 | Short-term load prediction method and device for power utilization area |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5998081B2 (en) * | 2013-03-08 | 2016-09-28 | 株式会社日立製作所 | Electric power demand adjustment system and demand adjustment execution system |
-
2020
- 2020-11-27 CN CN202011364841.2A patent/CN112598157B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729689A (en) * | 2013-12-20 | 2014-04-16 | 华南理工大学 | Power grid electric quantity prediction method based on industry classifications and leading industry data |
| CN105701559A (en) * | 2015-12-31 | 2016-06-22 | 国网上海市电力公司 | Short-term load prediction method based on time sequence |
| CN108346009A (en) * | 2018-03-21 | 2018-07-31 | 深圳库博能源科技有限公司 | A kind of power generation configuration method and device based on user model self study |
| CN111291782A (en) * | 2020-01-13 | 2020-06-16 | 上海交通大学 | Accumulated load prediction method based on information accumulation k-Shape clustering algorithm |
| CN111222711A (en) * | 2020-01-16 | 2020-06-02 | 大连理工大学 | Index linkage analysis-based multi-objective optimization method for peak shaving scheduling of electric power system |
| CN111815060A (en) * | 2020-07-16 | 2020-10-23 | 广东电网有限责任公司 | Short-term load prediction method and device for power utilization area |
Non-Patent Citations (1)
| Title |
|---|
| 采用面积灰关联决策的高斯过程回归概率短期负荷预测;黄南天 等;《电力系统自动化》;20181210;第42卷(第23期);正文第64-71页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112598157A (en) | 2021-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Umar et al. | Hybrid multiobjective genetic algorithms for integrated dynamic scheduling and routing of jobs and automated-guided vehicle (AGV) in flexible manufacturing systems (FMS) environment | |
| JP2004086896A (en) | Method and system for constructing adaptive prediction model | |
| CN107464023B (en) | Online learning method and equipment of life cycle prediction model | |
| EP2419796A1 (en) | Apparatus and method for model quality estimation and model adaptation in multivariable process control | |
| US8340789B2 (en) | System for monitoring and optimizing controllers for process performance | |
| KR101432436B1 (en) | Apparatus and method for prediction of influent flow rate and influent components using nearest neighbor method | |
| JP2015021934A (en) | Deterioration factor determination system, deterioration prediction system, deterioration factor determination method, and deterioration factor determination program | |
| CN112990587B (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| Lin et al. | A hybrid EA for reactive flexible job-shop scheduling | |
| CN112598157B (en) | Prediction method and device of power load | |
| Song et al. | Machine learning approach for determining feasible plans of a remanufacturing system | |
| Ahmadizar et al. | Minimizing makespan in a group shop with fuzzy release dates and processing times | |
| CN113268885A (en) | Transformer fault prediction method based on gray Markov model and electronic equipment | |
| Chiang et al. | Using a family of critical ratio-based approaches to minimize the number of tardy jobs in the job shop with sequence dependent setup times | |
| CN117196250A (en) | Water plant control method and control equipment | |
| JP4146610B2 (en) | Turbidity prediction system, turbidity control system and turbidity management system | |
| Parnianifard et al. | Robust simulation-optimization of dynamic-stochastic production/inventory control system under uncertainty using computational intelligence | |
| CN116822217A (en) | Man-machine double-resource constraint multi-target production scheduling method considering man-hour uncertainty | |
| WO2019167656A1 (en) | Prediction system, prediction method, and program | |
| CN107464015B (en) | Short-term load with fusing mechanism and electric quantity prediction method based on electricity utilization behavior | |
| CN116306214A (en) | Method and device for providing an ageing state model for determining the ageing state of an energy store | |
| Behroozsarand et al. | Optimal control of distillation column using non-dominated sorting genetic algorithm-ii | |
| JP4298581B2 (en) | Power demand forecasting device, power demand forecasting system, power demand forecasting program, recording medium, and power demand forecasting method | |
| Lipiec et al. | Health-aware fault-tolerant control of multiple cooperating autonoumous vehicles | |
| Liao et al. | Recurrent reinforcement learning for predictive overall equipment effectiveness |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |