CN112613670A - Device and method for predicting power consumer demand based on weight distribution - Google Patents
Device and method for predicting power consumer demand based on weight distribution Download PDFInfo
- Publication number
- CN112613670A CN112613670A CN202011575395.XA CN202011575395A CN112613670A CN 112613670 A CN112613670 A CN 112613670A CN 202011575395 A CN202011575395 A CN 202011575395A CN 112613670 A CN112613670 A CN 112613670A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- database
- weight distribution
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000009826 distribution Methods 0.000 title claims abstract description 22
- 238000011161 development Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000009499 grossing Methods 0.000 claims description 14
- 230000001932 seasonal effect Effects 0.000 claims description 14
- 230000000007 visual effect Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000008521 reorganization Effects 0.000 claims description 3
- 238000013500 data storage Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/18—File system types
- G06F16/182—Distributed file systems
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a device and a method for predicting demand of power users based on weight distribution, which comprises a data acquisition module, a database, a deployment layer module and a development layer module, wherein the data acquisition module comprises a communication module, the communication module transmits acquired data to the database, the database is in signal connection with the deployment layer module, the deployment layer module is in signal connection with the development layer module, and the purpose of prediction is achieved by processing the acquired data. The invention achieves the purpose of providing simple and efficient data storage, reading, model development, deployment and monitoring schemes.
Description
Technical Field
The invention particularly relates to the technical field of power consumer demand prediction, and particularly relates to a device and a method for predicting power consumer demand based on weight distribution.
Background
The demand forecast with the monthly maximum power load as a core forecasting index refers to one of the components of demand declaration of power conducting users, and is also an important decision reference for measuring the production and operation conditions of power users. How are each economic indicator and power indicator increased on a par? How does the ring ratio grow? What are the economic production indicators developed and the level of the electric power consumption landscape? Besides mastering the characteristic values of each index in the current period, the development trend of each index is also known, so that a decision reference is provided for demand declaration. Most of the concern to the power consumer is how to make more accurate predictions of demand for the next period of time through interpretation of historical monthly demand data and external economic production data. In the current domestic power market environment, demand prediction is developed in a shorter time interval, and no direct application scene exists, so that short-term time series data prediction models such as LSTM are not suggested to be used in the technical demand.
Disclosure of Invention
The invention aims to provide a device and a method for predicting the demand of a power consumer based on weight distribution aiming at the defects of the prior art so as to achieve the aim of providing a simple and efficient data storage and reading scheme and a scheme for model development, deployment and monitoring.
The invention solves the problems through the following technical scheme:
a device for predicting demand of power users based on weight distribution comprises a data acquisition module, a database, a deployment layer module and a development layer module, wherein the data acquisition module comprises a communication module, the communication module transmits acquired data to the database, the database is in signal connection with the deployment layer module, the deployment layer module is in signal connection with the development layer module, and the purpose of prediction is achieved by processing the acquired data.
Preferably, the data acquisition module is set as an intelligent gateway.
Preferably, the database adopts HDFS to store data in a distributed manner, and the data in the database includes source data and processed data.
4. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 1, wherein: the deployment layer module comprises a data processing module, a model module and a visual interface, the data processing module processes the acquired source data and transmits the source data to the model module, and the model module transmits the data to the visual interface and the database after rechecking, decomposing and calculating the data.
Preferably, the model modules include seasonal structure models, exponential smoothing models, and PCA regression models.
Preferably, the development layer module adopts Jupyterhub, and developers develop the data processing module, the model module and the visual interface through development tools of the development layer module.
The invention also provides a method for predicting the demand of the power consumer based on weight distribution, which adopts a device for predicting the demand of the power consumer based on weight distribution and comprises the following steps:
step A1) a data acquisition module acquires special transformer energy data of a user side;
step A2) transmitting the collected data to a database in real time through a power carrier special line;
step A3) the data processing module reads the original data from the database and processes the original data;
step A4) the model module reads the data processed in the step A3), carries out load decomposition calculation according to the data, and finally transmits the calculation result to a visual interface and a database.
Preferably, the data processing module processes the raw data by data structure reorganization, data resampling, and data padding.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the invention provides a comprehensive prediction method which adopts a seasonal deconstruction model, an exponential smoothing model, a multivariate regression method based on principal component analysis and the like, can obtain the highest prediction precision, and has a comprehensive error of only 0.1% for a power supply block with a regional demand load of 200MW level. Meanwhile, the system model integrated scheduling and data acquisition processing method can detect the working strength of personnel in the economic development department in demand prediction to a greater extent, and obtain reliable results conveniently, thereby effectively improving the production efficiency.
Drawings
FIG. 1 is a block diagram of the apparatus of the present invention.
Fig. 2 is a system architecture diagram of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples, but the embodiments of the present invention are not limited thereto.
Example 1:
referring to fig. 1, a device for predicting demand of power consumers based on weight distribution includes a data acquisition module, a database, a deployment layer module and a development layer module, where the data acquisition module is configured as an intelligent gateway. The data acquisition module comprises a communication module, the communication module transmits acquired data to a database, the database adopts HDFS (Hadoop distributed file system) and stores the data in a distributed manner, the data in the database comprises source data and processed data, the database is in signal connection with the deployment layer module, the deployment layer module is in signal connection with the development layer module, and the purpose of prediction is achieved by processing the acquired data. The deployment layer module comprises a data processing module, a model module and a visual interface, the data processing module processes the acquired source data and transmits the source data to the model module, and the model module transmits the data to the visual interface and the database after rechecking, decomposing and calculating the data. The model modules include a seasonal structure model, an exponential smoothing model, and a PCA regression model. The development layer module adopts Jupyterhub, and developers develop the data processing module, the model module and the visual interface through a development tool of the development layer module.
The seasonal deconstruction model is a tool for analyzing time series containing seasonal changes, which resolves a time series into four factors: linear trends, seasonal variations, cyclic variations, and irregular factors. The relationship between the four factors and the original time series can be combined in two forms of a multiplication model and an addition model.
A multiplication model: y ist＝TCt×St×It
An addition model: y ist＝TCt+St+It
YtIs original sequence, TCtIs a trend cycle sequence, StAs a sequence of seasons、ItIs an irregular sequence.
The exponential smoothing model predicts the future value by using the weighted average of the past values of the sequence, wherein the recent data in the sequence is assigned with larger weight, and the future data is assigned with smaller weight. The reason is that in general, the effect of a variable on its subsequent behavior is gradually attenuated. Commonly used exponential smoothing methods are first exponential smoothing, second exponential smoothing, and third exponential smoothing. Cubic exponential smoothing (Holt-Winters algorithm) is a method proposed by Holt and Winters in the sixties of the last century to capture analysis for seasonal variations. The method is divided into a prediction equation and three smoothing equations, namely a horizontal part, a trend part and a seasonal part, and smoothing parameters a, beta and gamma are adopted.
There are two distinctions in seasonal components of the method. When the seasonal variation is generally fixed throughout the sequence, an additive approach may be used. When the seasonal variable varies proportionally with the level of the sequence, a multiplicative approach may be used.
In the multiplication model:
St+kt＝s+1，s+2，…，T
wherein: at denotes intercept, bt denotes slope, at + bt k denotes trend, and St is a seasonal factor of the multiplicative model, which can be derived from three smoothing equations.
The PCA regression model is influenced by fluctuation of economic influence factors, so that the fitting precision is limited, and the prediction error is large. The economic factor historical data can be subjected to dimensionality reduction through a principal component analysis method, the contribution degree of each economic factor to the electric quantity increase of the industry is extracted, and due to the fact that coupling relations exist among the economic factors in the extracted principal components and the economic factors are not independent, a nonlinear multiple high-order regression model is considered and utilized. And quantitatively calculating the association degree of different influence factors and the industry power consumption based on a principal component analysis method, and extracting the leading factor of the industry power increase. The analysis was developed according to the following:
pearson correlation coefficient analysis → principal component extraction → establishment of principal component equation → interpretation and evaluation
Modeling one to two factor indexes with larger influence factors, and performing expansion analysis by using a high-order equation.
With reference to fig. 2, in the invention, models of three prediction methods are all arranged in different Docker containers of a model module, and then weights of the three prediction methods are calculated, wherein the calculation process comprises the steps of calculating relative errors of predicted values of the different methods, calculating reciprocals of the relative errors, calculating sum of the reciprocals, calculating weights of the different methods, and finally calculating according to the weights to obtain a comprehensive predicted value.
A method for predicting the demand of an electric power consumer based on weight distribution is adopted, and the device for predicting the demand of the electric power consumer based on weight distribution comprises the following steps:
step A1) a data acquisition module acquires special transformer energy data of a user side;
step A2) transmitting the collected data to a database in real time through a power carrier special line;
step A3) the data processing module reads the original data from the database and processes the original data;
step A4) the model module reads the data processed in the step A3), carries out load decomposition calculation according to the data, and finally transmits the calculation result to a visual interface and a database.
The data processing module processes original data through data structure reorganization, data resampling and data filling.
The device and the method for predicting the demand of the power users based on weight distribution are applied to an actual scene, and by taking demand prediction and return measurement of load of a power supply area of an industrial park in a certain urban area in summer peak-to-peak summer in 2010-2019 of a certain place and city in east China as an example, the comprehensive precision provided by the prediction model is as shown in table 1:
TABLE 1
The invention provides a comprehensive prediction method which adopts a seasonal deconstruction model, an exponential smoothing model, a multivariate regression method based on principal component analysis and the like, can obtain the highest prediction precision, and has a comprehensive error of only 0.1% for a power supply block with a regional demand load of 200MW level. Meanwhile, the system model integrated scheduling and data acquisition processing method can detect the working strength of personnel in the economic development department in demand prediction to a greater extent, and obtain reliable results conveniently, thereby effectively improving the production efficiency.
Although the present invention has been described herein with reference to the illustrated embodiments thereof, which are intended to be preferred embodiments of the present invention, it is to be understood that the invention is not limited thereto, and that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure.
Claims (8)
1. An apparatus for predicting power consumer demand based on weight distribution, comprising: the device comprises a data acquisition module, a database, a deployment layer module and a development layer module, wherein the data acquisition module comprises a communication module, the communication module transmits acquired data to the database, the database is in signal connection with the deployment layer module, the deployment layer module is in signal connection with the development layer module, and the purpose of prediction is achieved by processing the acquired data.
2. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 1, wherein: the data acquisition module is set as an intelligent gateway.
3. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 1, wherein: the database adopts HDFS to store data in a distributed mode, and the data in the database comprises source data and processed data.
4. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 1, wherein: the deployment layer module comprises a data processing module, a model module and a visual interface, the data processing module processes the acquired source data and transmits the source data to the model module, and the model module transmits the data to the visual interface and the database after rechecking, decomposing and calculating the data.
5. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 4, wherein: the model modules include a seasonal structure model, an exponential smoothing model, and a PCA regression model.
6. The apparatus for forecasting electric power consumer demand based on weight distribution as claimed in claim 1, wherein: the development layer module adopts Jupyterhub, and developers develop the data processing module, the model module and the visual interface through a development tool of the development layer module.
7. A method for predicting the demand of a power consumer based on weight distribution is characterized in that: the device for predicting the demand of the power consumer based on the weight distribution, which is applied to any one of claims 1 to 4, comprises the following steps:
step A1) a data acquisition module acquires special transformer energy data of a user side;
step A2) transmitting the collected data to a database in real time through a power carrier special line;
step A3) the data processing module reads the original data from the database and processes the original data;
step A4) the model module reads the data processed in the step A3), carries out load decomposition calculation according to the data, and finally transmits the calculation result to a visual interface and a database.
8. The method for forecasting electric power consumer demand based on weight distribution as claimed in claim 7, wherein: the data processing module processes original data through data structure reorganization, data resampling and data filling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011575395.XA CN112613670A (en) | 2020-12-28 | 2020-12-28 | Device and method for predicting power consumer demand based on weight distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011575395.XA CN112613670A (en) | 2020-12-28 | 2020-12-28 | Device and method for predicting power consumer demand based on weight distribution |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613670A true CN112613670A (en) | 2021-04-06 |
Family
ID=75248060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011575395.XA Withdrawn CN112613670A (en) | 2020-12-28 | 2020-12-28 | Device and method for predicting power consumer demand based on weight distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613670A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516276A (en) * | 2021-04-09 | 2021-10-19 | 国网安徽省电力有限公司铜陵供电公司 | Medium-short term load prediction method based on data mining processing framework |
-
2020
- 2020-12-28 CN CN202011575395.XA patent/CN112613670A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516276A (en) * | 2021-04-09 | 2021-10-19 | 国网安徽省电力有限公司铜陵供电公司 | Medium-short term load prediction method based on data mining processing framework |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242391B (en) | Machine learning model training method and system for power load identification | |
| CN114004296A (en) | Method and system for reversely extracting monitoring points based on power load characteristics | |
| CN107741578B (en) | Original meter reading data processing method for remote calibration of running error of intelligent electric energy meter | |
| CN113011481B (en) | Electric energy meter function abnormality assessment method and system based on decision tree algorithm | |
| CN107832927B (en) | 10kV line variable relation evaluation method based on grey correlation analysis method | |
| CN103020459A (en) | Method and system for sensing multiple-dimension electric utilization activities | |
| CN112149873A (en) | Low-voltage transformer area line loss reasonable interval prediction method based on deep learning | |
| CN113554361B (en) | Comprehensive energy system data processing and calculating method and processing system | |
| CN116031887B (en) | Power grid simulation analysis calculation data generation method, system, equipment and medium | |
| CN114240086A (en) | Carbon emission monitoring method and device, storage medium and processor | |
| CN116632838B (en) | Method and device for analyzing electric energy supply of power generation enterprise | |
| CN103018611B (en) | Non-invasive load monitoring method and system based on current decomposition | |
| CN110866691A (en) | Staged and layered sampling method for isolated batch intelligent electric energy meters | |
| CN110968703B (en) | Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm | |
| CN115759708A (en) | Line loss analysis method and system considering power space-time distribution characteristics | |
| CN115859099A (en) | Sample generation method and device, electronic equipment and storage medium | |
| CN115965125A (en) | Power load prediction method based on deep learning | |
| CN113450031B (en) | Method and device for selecting intelligent energy consumption service potential transformer area of residents | |
| CN112613670A (en) | Device and method for predicting power consumer demand based on weight distribution | |
| CN106405224B (en) | Energy-saving diagnosis method and system based on mass electric energy data | |
| CN117559443A (en) | Ordered power utilization control method for large industrial user cluster under peak load | |
| CN110796392A (en) | Staged and layered sampling method for continuous batch intelligent electric energy meters | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN114662563A (en) | Industrial electricity non-invasive load decomposition method based on gradient lifting algorithm | |
| CN104933476A (en) | Power generation asset generating capacity prediction system and method and value estimation method |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210406 |