CN114529071A - Method for predicting power consumption of transformer area - Google Patents
Method for predicting power consumption of transformer area Download PDFInfo
- Publication number
- CN114529071A CN114529071A CN202210128856.1A CN202210128856A CN114529071A CN 114529071 A CN114529071 A CN 114529071A CN 202210128856 A CN202210128856 A CN 202210128856A CN 114529071 A CN114529071 A CN 114529071A
- Authority
- CN
- China
- Prior art keywords
- data
- power consumption
- predicting
- sample
- model
- 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 35
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 238000009826 distribution Methods 0.000 claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000012417 linear regression Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract 1
- 230000005611 electricity Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000001932 seasonal effect Effects 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting the power consumption of a distribution room, which comprises the following steps: sample construction: acquiring a data sample, and establishing a training set and a test set according to the sample data; the construction characteristics are as follows: analyzing the data sample to construct a multi-dimensional feature; model training: training sample data of the training set by using a lightGBM model; and (3) model evaluation: and predicting the electric quantity of the test set by using the trained lightGBM model. According to the method for predicting the power consumption of the distribution room, trend changes of data in different time periods do not need to be considered, the lightGBM integrates a plurality of characteristics, influences of modeling of different types of data on model prediction accuracy are eliminated, the power consumption of common power consumption users is more accurately predicted, further optimization space is provided for prediction of the power consumption of large-power-consumption users, the method has good use value, the obtained data samples are accurate, repeated calibration and repeated verification are performed, the prediction accuracy is high, and good prospects are realized.
Description
Technical Field
The invention relates to the field of electric quantity prediction, in particular to a method for predicting the electric quantity used in a distribution room.
Background
With the development of society and the continuous improvement of the living standard of people, the demand on electric energy is more and more increased. Due to the simultaneity of electric energy production and consumption, the production of electric energy needs to be reasonably planned to meet the consumption;
the power consumption prediction is the forecast of the total amount of the load consumed electric energy of the electric power system in a period of time, the power consumption prediction is the key basis for the power grid company to make a production comprehensive plan and make an operation plan, a reasonable and accurate prediction conclusion can bring forward effect to the operation decision of the company, otherwise, the deviation of the operation strategy of the company can be caused, and therefore, the power consumption prediction in the future quarter or year is very important;
when the existing power consumption prediction method is used for predicting future power consumption data, temperature data needs to be predicted first, and the temperature data is related to seasonal changes and is easy to generate errors; and the holiday data need to distinguish the solar calendar from the lunar calendar, the lunar calendar and the holiday are distinguished every year, and errors are easy to occur when historical data are compared.
Disclosure of Invention
The invention mainly aims to provide a method for predicting the power consumption of a distribution room, which can effectively solve the problems in the background technology.
In order to achieve the purpose, the invention adopts the technical scheme that:
a power consumption prediction method for a distribution room comprises the following steps:
firstly, sample construction: acquiring a data sample, and establishing a training set and a test set according to the sample data;
secondly, constructing characteristics: analyzing the data sample to construct a multi-dimensional feature;
thirdly, training the model: training sample data of the training set by using a lightGBM model;
fourthly, model evaluation: and predicting the electric quantity of the test set by using the trained lightGBM model, and calibrating the lightGBM model.
Preferably, the step of obtaining the data sample in the step (i) includes the following steps:
determining a time window, and extracting the relevant data of the electric quantity of the station area in the past time window;
and II, performing data correction on the acquired data to obtain a data sample.
Preferably, the step of performing data correction on the acquired data in step ii is as follows:
the acquired power related data of the transformer area are sorted according to different projects;
constructing a linear regression equation of each project;
removing the data deviating from the linear regression equation by 8%;
and replacing the rejected data by the data in the linear regression equation.
Preferably, the data related to the power consumption of the distribution room acquired in step i includes data related to the power consumption of the distribution room users and related influence factors.
Preferably, the relevant impact factors include temperature, industry, holidays, and economic growth rate.
Preferably, in the step I, a time window is randomly extracted when a training set and a test set are established according to sample data, the obtained sample data is extracted, the data set formed after extraction is the training set and the test set, and the proportion of the training set to the test set is 2: 8.
Preferably, in the second step, the time length required to be observed is determined when the data sample is analyzed, and the multidimensional characteristic is constructed through the circular ratio, the same ratio, the mean value and the variance statistic.
Preferably, in the step III, the model training is performed by inputting the sample data into the lightGBM model and optimizing the parameters of the lightGBM model.
Preferably, in the step (iv), when the trained lightGBM model is used to predict the electricity quantity of the test set, the relevant influence factor data recorded in the test set is input, the electricity quantity within the time window is predicted, and the predicted electricity quantity is compared with the actual electricity quantity recorded in the test set.
Preferably, in the step (iv), the power consumptions at different time windows are predicted, and when the difference between the power consumptions predicted for the third time and the actual power consumptions recorded in the test set exceeds 10%, the training set and the test set are established again according to the sample data, and the model training and the model evaluation are performed again.
Compared with the prior art, the method for predicting the power consumption of the distribution room has the following beneficial effects:
firstly, the lightGBM model in the station area power consumption prediction method does not need to consider trend changes of data in different time periods, and the lightGBM integrates a plurality of characteristics, so that the influence of different types of data modeling on model prediction accuracy is eliminated;
secondly, the power consumption prediction method for the distribution room is more accurate in power consumption prediction of most users, more accurate in power consumption prediction of common power consumption users, and has a further optimized space for power consumption prediction of large-power-consumption users, and has a good use value;
thirdly, the data sample obtained by the method for predicting the power consumption of the transformer area is accurate, repeated calibration and repeated verification are carried out, the prediction accuracy is high, the using effect is good, and the method can be popularized and applied in a large scale.
Drawings
Fig. 1 is a flowchart of a power consumption prediction method for a distribution room according to the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
Examples
A power consumption prediction method for a distribution room comprises the following steps:
firstly, sample construction: acquiring a data sample, and establishing a training set and a test set according to the sample data;
acquiring a data sample comprises the following steps:
determining a time window, and extracting the relevant data of the electric quantity of the station area in the past time window;
and II, performing data correction on the acquired data to obtain a data sample.
And step II, correcting the acquired data as follows:
the acquired power related data of the transformer area are sorted according to different projects;
constructing a linear regression equation of each project;
removing the data deviating from the linear regression equation by 8%;
and replacing the rejected data by the data in the linear regression equation.
In a specific application scene, the acquired relevant data of the electric quantity of the transformer area are sorted according to different projects, namely the data of time windows of different years of the transformer area are classified according to the electric quantity and relevant influence factors;
for example, the item is the electricity consumption, and the electricity consumption data in the time window of different years of all the distribution areas are summarized together.
The acquired relevant data of the power consumption of the distribution area comprise power consumption data of users of the distribution area and relevant influence factors.
Relevant impact factors include temperature, industry, holidays, and economic growth rate.
In a specific application scenario, the relevant influence factors further include data such as people flow data.
In a specific application scenario, a time window is set, and is a time period of one distribution area every year, and distribution area electric quantity related data in the time window of the distribution area every year in the past are acquired when data are acquired.
And randomly extracting a time window when a training set and a test set are established according to sample data, extracting the obtained sample data, wherein the data set formed after extraction is the training set and the test set, and the ratio of the training set to the test set is 2: 8.
In a specific application scenario, the proportion of the training set and the test set can be adjusted, and when more data are acquired, the proportion of the training set can be increased.
Secondly, constructing characteristics: analyzing the data sample to construct a multi-dimensional feature;
and determining the time length required to be observed when analyzing the data sample, and constructing the multidimensional characteristics through the ring ratio, the homonymy, the mean value and the variance statistics.
In a specific application scenario, the multi-dimensional features can also be constructed by using the existing commonly used statistics.
Thirdly, training the model: training sample data of the training set by using a lightGBM model;
and inputting the sample data into the lightGBM model for model training during model training, and optimizing parameters of the lightGBM model.
Fourthly, model evaluation: using the trained lightGBM model to predict the electric quantity of the test set, and calibrating the lightGBM model;
inputting relevant influence factor data recorded in the test set when the trained lightGBM model is used for predicting the electric quantity of the test set, predicting the electric quantity in the time window, and comparing the predicted electric quantity with the actual electric quantity recorded in the test set;
and predicting the power consumption of different time windows, reestablishing a training set and a testing set according to the sample data when the difference between the power consumption predicted for the third time and the actual power consumption recorded in the testing set exceeds 10%, reestablishing model training and model evaluation, and predicting the power consumption by adopting a model with the difference between the power consumption and the actual power consumption recorded in the testing set being lower than 10%.
It should be noted that, in the model training, the time length to be observed is determined, then data is extracted, sample characteristics are constructed, the actual electric quantity is used as a prediction target and is input into the model together with the characteristics, model parameters are set, and the model is trained;
when the prediction method of the power consumption of the distribution room is used for predicting the power consumption at the next moment by using the data of the current moment and the two latest continuous moments;
in the method for predicting the power consumption of the distribution room, the lightGBM model does not need to consider trend changes of data in different time periods, and the lightGBM integrates a plurality of characteristics, so that the influence of different types of data modeling on the model prediction accuracy is eliminated;
the method for predicting the power consumption of the distribution room is more accurate in predicting the power consumption of most users and the power consumption of common power consumption users, has a further optimized space for predicting the power consumption of large-power consumption users, and has good use value;
the data sample obtained by the method for predicting the power consumption of the distribution room is accurate, repeated calibration and repeated verification are performed, the prediction accuracy is high, the using effect is good, and the method can be popularized and applied in a large scale.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A method for predicting power consumption of a distribution room is characterized by comprising the following steps: the method comprises the following steps:
firstly, sample construction: acquiring a data sample, and establishing a training set and a test set according to the sample data;
secondly, constructing characteristics: analyzing the data sample to construct a multi-dimensional feature;
thirdly, training the model: training sample data of the training set by using a lightGBM model;
fourthly, model evaluation: and predicting the electric quantity of the test set by using the trained lightGBM model, and calibrating the lightGBM model.
2. The method for predicting the power consumption of the distribution room as claimed in claim 1, wherein: the data sample acquisition method comprises the following steps:
determining a time window, and extracting the relevant data of the electric quantity of the station area in the past time window;
and II, performing data correction on the acquired data to obtain a data sample.
3. The method for predicting the power consumption of the distribution room as claimed in claim 2, wherein: and step II, correcting the acquired data as follows:
the acquired power related data of the transformer area are sorted according to different projects;
constructing a linear regression equation of each project;
removing the data deviating from the linear regression equation by 8%;
and replacing the rejected data by the data in the linear regression equation.
4. The method for predicting the power consumption of the distribution room according to claim 3, wherein: the relevant data of the electric quantity of the transformer area obtained in the step I comprise the electric quantity data of the users of the transformer area and relevant influence factors.
5. The method for predicting the power consumption of the distribution room as claimed in claim 4, wherein: the relevant impact factors include temperature, industry, holidays, and economic growth rate.
6. The method for predicting the power consumption of the distribution room as claimed in claim 5, wherein: randomly extracting a time window when a training set and a test set are established according to sample data, extracting the obtained sample data, wherein the data set formed after extraction is the training set and the test set, and the ratio of the training set to the test set is 2: 8.
7. The method for predicting the power consumption of the distribution room as claimed in claim 6, wherein: and secondly, determining the time length required to be observed when analyzing the data sample, and constructing the multidimensional characteristics through the statistics of the ring ratio, the homonymy, the mean value and the variance.
8. The method for predicting the power consumption of the distribution room according to any one of claims 7, wherein: and step three, inputting sample data into the lightGBM model for model training during model training, and optimizing parameters of the lightGBM model.
9. The method of claim 8, wherein the method comprises: and fourthly, inputting relevant influence factor data recorded in the test set when the trained lightGBM model is used for predicting the electric quantity of the test set, predicting the electric quantity in the time window, and comparing the predicted electric quantity with the actual electric quantity recorded in the test set.
10. The method of claim 9, wherein the method comprises: and fourthly, predicting the power consumption of different time windows, reestablishing the training set and the test set according to the sample data when the difference value of the power consumption predicted for three times and the actual power consumption recorded in the test set exceeds 10%, and reestablishing model training and model evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210128856.1A CN114529071A (en) | 2022-02-11 | 2022-02-11 | Method for predicting power consumption of transformer area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210128856.1A CN114529071A (en) | 2022-02-11 | 2022-02-11 | Method for predicting power consumption of transformer area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529071A true CN114529071A (en) | 2022-05-24 |
Family
ID=81623347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210128856.1A Pending CN114529071A (en) | 2022-02-11 | 2022-02-11 | Method for predicting power consumption of transformer area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529071A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823075A (en) * | 2023-08-29 | 2023-09-29 | 小象飞羊(北京)科技有限公司 | City data construction model, electronic equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201037A (en) * | 2011-06-14 | 2011-09-28 | 中国农业大学 | Agricultural disaster forecast method |
| CN107643252A (en) * | 2017-09-18 | 2018-01-30 | 中南大学 | The real-time buckle back scape non-linear correction method of oxygen concentration in a kind of Wavelength modulation spectroscopy detection vial |
| CN109785003A (en) * | 2019-01-17 | 2019-05-21 | 四川骏逸富顿科技有限公司 | A kind of Pharmaceutical retail industry medicine sales forecasting system and method |
| AU2020101475A4 (en) * | 2020-07-24 | 2020-08-27 | Cheng, Fang Miss | A Financial Data Analysis Method Based on Machine Learning Models |
| CN112465256A (en) * | 2020-12-08 | 2021-03-09 | 华中科技大学 | Building power consumption prediction method and system based on Stacking model fusion |
| CN113609115A (en) * | 2021-08-03 | 2021-11-05 | 招商局重庆交通科研设计院有限公司 | Data cleaning method for slope deformation monitoring data |
| CN113919558A (en) * | 2021-09-28 | 2022-01-11 | 三一重机有限公司 | Product sales prediction method and device |
| CN114021848A (en) * | 2021-11-24 | 2022-02-08 | 西安热工研究院有限公司 | Generating capacity demand prediction method based on LSTM deep learning |
-
2022
- 2022-02-11 CN CN202210128856.1A patent/CN114529071A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201037A (en) * | 2011-06-14 | 2011-09-28 | 中国农业大学 | Agricultural disaster forecast method |
| CN107643252A (en) * | 2017-09-18 | 2018-01-30 | 中南大学 | The real-time buckle back scape non-linear correction method of oxygen concentration in a kind of Wavelength modulation spectroscopy detection vial |
| CN109785003A (en) * | 2019-01-17 | 2019-05-21 | 四川骏逸富顿科技有限公司 | A kind of Pharmaceutical retail industry medicine sales forecasting system and method |
| AU2020101475A4 (en) * | 2020-07-24 | 2020-08-27 | Cheng, Fang Miss | A Financial Data Analysis Method Based on Machine Learning Models |
| CN112465256A (en) * | 2020-12-08 | 2021-03-09 | 华中科技大学 | Building power consumption prediction method and system based on Stacking model fusion |
| CN113609115A (en) * | 2021-08-03 | 2021-11-05 | 招商局重庆交通科研设计院有限公司 | Data cleaning method for slope deformation monitoring data |
| CN113919558A (en) * | 2021-09-28 | 2022-01-11 | 三一重机有限公司 | Product sales prediction method and device |
| CN114021848A (en) * | 2021-11-24 | 2022-02-08 | 西安热工研究院有限公司 | Generating capacity demand prediction method based on LSTM deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823075A (en) * | 2023-08-29 | 2023-09-29 | 小象飞羊(北京)科技有限公司 | City data construction model, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615226B (en) | Operation index abnormity monitoring method | |
| CN106408223A (en) | Short-term load prediction based on meteorological similar day and error correction | |
| CN104657788B (en) | Key industry electricity demand forecasting method based on Industrial Cycle index | |
| CN106682763B (en) | Power load optimization prediction method for large amount of sample data | |
| CN108229742A (en) | A kind of load forecasting method based on meteorological data and data trend | |
| CN111506618B (en) | Abnormal electricity consumption behavior analysis method combined with lightgbm-stacking algorithm | |
| CN113723844B (en) | Low-voltage station theoretical line loss calculation method based on ensemble learning | |
| CN114004296A (en) | Method and system for reversely extracting monitoring points based on power load characteristics | |
| CN112446534A (en) | Construction period prediction method and device for power transmission and transformation project | |
| CN111210170A (en) | Environment-friendly management and control monitoring and evaluation method based on 90% electricity distribution characteristic index | |
| CN112330065A (en) | Runoff forecasting method based on basic flow segmentation and artificial neural network model | |
| CN115688993A (en) | Short-term power load prediction method suitable for power distribution station area | |
| CN114529071A (en) | Method for predicting power consumption of transformer area | |
| CN110533247B (en) | Monthly power consumption prediction method adopting temperature data anomaly point compensation | |
| CN109325641A (en) | A kind of industrial efficiency management system and method | |
| CN110889565A (en) | Distribution network routing inspection period calculation method based on multi-dimensional matrix decision | |
| Gerossier et al. | A novel method for decomposing electricity feeder load into elementary profiles from customer information | |
| CN117559443A (en) | Ordered power utilization control method for large industrial user cluster under peak load | |
| CN102508997B (en) | Underground water model output uncertainty analysis method | |
| CN112200209A (en) | Poor user identification method based on day-to-day power consumption | |
| CN116611785A (en) | Power transmission and transformation project cost model construction method, system, equipment and medium based on big data | |
| CN114676931B (en) | Electric quantity prediction system based on data center technology | |
| CN116226720A (en) | High-reliability load abnormality identification repair method based on multidimensional data cross-validation | |
| CN115860797A (en) | Electric quantity demand prediction method suitable for new electricity price reform situation | |
| CN115470970A (en) | Electric quantity prediction method and system based on prophet-LightGBM combined model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220524 |
|
| RJ01 | Rejection of invention patent application after publication |