CN112561206A - Power grid load prediction method and device and power system - Google Patents
Power grid load prediction method and device and power system Download PDFInfo
- Publication number
- CN112561206A CN112561206A CN202011564615.9A CN202011564615A CN112561206A CN 112561206 A CN112561206 A CN 112561206A CN 202011564615 A CN202011564615 A CN 202011564615A CN 112561206 A CN112561206 A CN 112561206A
- Authority
- CN
- China
- Prior art keywords
- power consumption
- average human
- human power
- data
- relevant
- 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 60
- 230000005611 electricity Effects 0.000 claims abstract description 58
- 238000013507 mapping Methods 0.000 claims abstract description 28
- 230000008676 import Effects 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 230000006641 stabilisation Effects 0.000 claims description 3
- 238000011105 stabilization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 230000007774 longterm Effects 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a power grid load prediction method, a device and a power system, wherein the power grid load prediction method comprises the following steps: acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person; establishing a mapping relation model of the average human power consumption and relevant characteristics according to historical annual data and relevant characteristic information of the average human power consumption; determining a prediction result of the average human power consumption in the period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics; and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted. The power grid load prediction method fully considers the per-capita electricity consumption and the characteristic factors and the correlation among the characteristic factors, can realize the prediction of the medium and long term power grid load, and can achieve better prediction effect.
Description
Technical Field
The invention relates to the technical field of power control, in particular to a power grid load prediction method, a power grid load prediction device and a power system.
Background
In the electric power spot market, the power grid load prediction is a key link in the power distribution network planning and is an important calculation basis for the substation and power grid planning. The power grid load prediction method is generally divided into a short-term load prediction method and a medium-term load prediction method.
The existing load prediction methods include the following methods: time series method, industrial production value unit consumption method, elastic coefficient method, electricity consumption per person method, load utilization hour method and electricity comprehensive method. By these load prediction methods, prediction of annual power consumption, power load, power supply amount, and power supply load is performed. The average electricity consumption method is to calculate the electricity consumption according to the average annual electricity consumption and population number. The method is more suitable for predicting the medium and long term electric load of the plan. The per-capita electricity consumption is affected by various factors, such as per-capita GDP, fixed asset investment, and the like. When the existing electricity quantity method for the average person to use is used for predicting the electricity quantity, the relevance among the factors can be ignored, so that the existing electricity quantity method for the average person to use can cause larger errors, and a better prediction effect cannot be achieved.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus and a power system for predicting a grid load, which overcome the disadvantages of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme: a power grid load prediction method comprises the following steps:
acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person;
establishing a mapping relation model of the average human power consumption and relevant characteristics according to historical annual data and relevant characteristic information of the average human power consumption;
determining a prediction result of the average human power consumption in the period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics;
and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted.
Optionally, the related feature information includes one or more of the following items:
GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, import and export total, and per-capita import and export total.
Optionally, the establishing a mapping relationship model between the average human power consumption and the relevant characteristics according to the historical annual data of the average human power consumption and the relevant characteristic information specifically includes:
preprocessing historical annual data and relevant characteristic data of the electricity consumption of the average person;
and establishing a mapping relation model of the average human power consumption and the related characteristics from the preprocessed data through a machine learning method.
Optionally, the preprocessing is performed on the historical annual data and the relevant characteristic data of the average electricity consumption of people, and specifically includes:
judging whether the historical annual data is a stable time sequence;
if not, the historical annual data is subjected to stabilization processing;
and carrying out regularization processing on the relevant characteristic data to ensure that the processed relevant characteristic data are distributed in a regularization range.
Optionally, the establishing, by using a machine learning method, a mapping relationship model between the average human power consumption and the relevant features from the preprocessed data specifically includes:
judging whether the preprocessed data is in a format required by a LibSVM;
if not, converting the preprocessed data into a format required by the LibSVM;
and constructing an SVM model of the average human power consumption and related characteristics by using a LibSVM library function.
Optionally, before the pre-processing of the historical annual data and the relevant characteristic data of the average electricity consumption of the people, the method further includes:
performing single-feature fitting error analysis on the relevant feature data to obtain a fitting error between each relevant feature and the electricity consumption of the person;
and screening the relevant characteristics according to the fitting error.
Optionally, the prediction method further includes:
when discrete data is included in the related characteristic information, the discrete data needs to be encoded.
Optionally, the prediction method further includes:
judging whether the prediction result of the average electricity consumption of people meets the prediction precision or not;
and if the prediction result of the average human power consumption does not meet the prediction accuracy, adjusting the kernel function and the optimal parameters, reestablishing a mapping relation model of the average human power consumption and the relevant characteristics, and redetermining the prediction result of the average human power consumption in the period to be predicted according to the reestablished mapping relation model of the average human power consumption and the relevant characteristics so as to enable the redetermined prediction result of the average human power consumption to meet the prediction accuracy.
The invention also provides a power grid load prediction device, which comprises:
the data acquisition module is used for acquiring historical annual data and relevant characteristic information of the per-person electricity consumption;
the model establishing module is used for establishing a mapping relation model of the average human power consumption and the relevant characteristics according to the historical annual data and the relevant characteristic information of the average human power consumption;
the system comprises a per-person electricity consumption prediction module, a per-person electricity consumption prediction module and a prediction module, wherein the per-person electricity consumption prediction module is used for determining a per-person electricity consumption prediction result of a to-be-predicted period according to a mapping relation model of per-person electricity consumption and relevant characteristics;
and the calculation module is used for calculating the predicted power consumption of the period to be predicted according to the average human power consumption prediction result and the population number of the period to be predicted.
In addition, the present invention also provides an electric power system comprising: the grid load prediction device as described above.
By adopting the technical scheme, the power grid load prediction method comprises the following steps: acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person; establishing a mapping relation model of the average human power consumption and relevant characteristics according to historical annual data and relevant characteristic information of the average human power consumption; determining a prediction result of the average human power consumption in the period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics; and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted. The power grid load prediction method fully considers the per-capita electricity consumption and the characteristic factors and the correlation among the characteristic factors, can realize the prediction of the medium and long term power grid load, and can achieve better prediction effect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a power grid load prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a power grid load prediction method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the annual characteristic variation relationship between the electricity consumption of 2008-2017 and the related characteristics;
fig. 4 is a schematic structural diagram provided by an embodiment of a power grid load prediction apparatus of the present invention.
In the figure: 1. a data acquisition module; 2. a model building module; 3. the average human power consumption prediction module; 4. and a calculation module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
Fig. 1 is a schematic flow chart of a power grid load prediction method according to an embodiment of the present invention.
As shown in fig. 1, the method for predicting the load of the power grid according to this embodiment includes:
s101: acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person;
further, the related feature information includes one or more of the following items:
GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, import and export total, and per-capita import and export total.
S102: establishing a mapping relation model of the average human power consumption and relevant characteristics according to historical annual data and relevant characteristic information of the average human power consumption;
s103: determining a prediction result of the average human power consumption in the period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics;
s104: and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted.
The power grid load prediction method is a medium-long term load prediction method, and is suitable for predicting the power consumption of the whole society. The data used in the method are all from publicly released national economic and social development statistical publications.
Electricity consumption is the average electricity consumption of people
Load is the average population load
The prediction of total electricity usage (load) can be translated into a prediction of population and a prediction of average electricity usage for a person. In general, population growth is relatively stable, and high prediction accuracy can be achieved, so that the key of the method is to predict the average human electricity consumption. Compared with the total amount, the correlation between the human-average electricity consumption and the influence factors is higher, and the prediction is more accurate.
The per-capita electricity consumption is influenced by various factors, and the more concerned factors comprise GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, total import and export of per-capita and the like. Wherein GDP, fixed asset investment, industry added value are gross characteristics. GDP is shared by all people, investment of capital is fixed by all people, value is increased by industry, and total import and export of all people is characterized by being shared by all people.
Further, before performing step S12, the method further includes:
performing single-feature fitting error analysis on the relevant feature data to obtain a fitting error between each relevant feature and the electricity consumption of the person; and screening the relevant characteristics according to the fitting error.
For example, single feature fitting error analysis is carried out on eight features including GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, total import and export, and total import and export of per-capita respectively to obtain a fitting error of each single feature and per-capita electricity consumption; and if the fitting error between the import and export total amount and the average import and export total amount of the people and the average electricity consumption of the people is the maximum, abandoning the two characteristics, and determining the relevant characteristics as GDP, GDP for the people, fixed asset investment for the people, industry added value and industry added value for the people.
The prediction method further comprises the following steps:
judging whether the prediction result of the average electricity consumption of people meets the prediction precision or not;
and if the prediction result of the average human power consumption does not meet the prediction accuracy, adjusting the kernel function and the optimal parameters, reestablishing a mapping relation model of the average human power consumption and the relevant characteristics, and redetermining the prediction result of the average human power consumption in the period to be predicted according to the reestablished mapping relation model of the average human power consumption and the relevant characteristics so as to enable the redetermined prediction result of the average human power consumption to meet the prediction accuracy.
The power grid load prediction method fully considers the correlation between the per-capita electricity consumption and the characteristic factors and among the characteristic factors, can realize prediction of medium and long term power grid loads, has small prediction error, and has a good prediction effect.
Fig. 2 is a schematic flow chart of a power grid load prediction method according to a second embodiment of the present invention.
As shown in fig. 2, the method for predicting the load of the power grid according to the embodiment includes:
s201: acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person;
further, the related feature information includes one or more of the following items:
GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, import and export total, and per-capita import and export total.
S202: judging whether the historical annual data is a stable time sequence;
s203: if not, the historical annual data is subjected to stabilization processing;
s204: carrying out regularization processing on the relevant characteristic data to enable the processed relevant characteristic data to be distributed in a regularization range;
s205: judging whether the preprocessed data is in a format required by a LibSVM;
s206: if not, converting the preprocessed data into a format required by the LibSVM;
s207: constructing an SVM model of the average human power consumption and related characteristics by using a LibSVM library function;
s208: determining a prediction result of the average power consumption of the people in the period to be predicted according to the SVM model;
s209: judging whether the prediction result of the average electricity consumption of people meets the prediction precision or not;
s210: if the prediction result of the average electricity consumption does not meet the prediction precision, adjusting the kernel function and the optimal parameters, and executing S207-S210 again;
s211: and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted.
FIG. 3 shows the relationship between 2008 + 2017 decade annual characteristic changes of per-capita electricity consumption and six characteristics (GDP, GDP per capita, fixed asset investment, GDP per capita, industry added value, and industry added value per capita). The change trend also shows that the average power consumption of people has strong correlation with the characteristics.
In actual execution, in order to establish a functional relationship between the average human power consumption and the characteristics, a generalized linear model considering multiple factors is often adopted in the conventional method, but in some years, the average human power consumption and the characteristics do not have a good linear relationship, the characteristic factors are not mutually independent, and the establishment of the generalized linear model ignores the correlation between the characteristics, so that a larger error is caused. In the embodiment, the SVM algorithm is used for modeling, great advantages can be achieved without the advantage of manually setting a specific fitting curve pattern, relevant characteristic factors are used as samples to be input into the SVM, and the best prediction effect can be achieved by optimizing parameters.
Population indexes and economic indexes influencing per-capita electricity consumption have stable change rate in a certain period, so that the economic indexes can be predicted by adopting a growth speed method. Because the magnitude of each relevant characteristic value is different, if the relevant characteristic values are not processed and input into the SVM model, the value with higher magnitude is dominant. Therefore, before inputting, the data is first preprocessed to make each eigenvalue distributed in the same range, the regularization range may be [ -1, 1], or [0, 1], and the [0, 1] interval is selected in the current prediction. In addition, since the annual data of the electricity consumption per capita is stationary time series data, no additional processing is required, and only regularization processing is required. If discrete data such as season, wind speed, etc. are included in the related characteristic information, it is necessary to encode the discrete data, and the encoding may be a one-hot encoding.
The power grid load prediction method fully considers the per-capita electricity consumption and the characteristic factors and the correlation among the characteristic factors, can realize prediction of medium and long term power grid loads, has small prediction error and good prediction effect, and can provide effective technical support for power grid planning and power design.
Fig. 4 is a schematic structural diagram provided by an embodiment of a power grid load prediction apparatus of the present invention.
As shown in fig. 4, the grid load prediction apparatus according to this embodiment includes:
the data acquisition module 1 is used for acquiring historical annual data and relevant characteristic information of the per-person electricity consumption;
the model establishing module 2 is used for establishing a mapping relation model of the average human power consumption and the relevant characteristics according to the historical annual data and the relevant characteristic information of the average human power consumption;
the average human power consumption prediction module 3 is used for determining an average human power consumption prediction result of a period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics;
and the calculating module 4 is used for calculating the predicted power consumption of the period to be predicted according to the average power consumption prediction result of people and the population number of the period to be predicted.
The working principle of the power grid load prediction device in this embodiment is the same as that of the power grid load prediction method in any of the above embodiments, and details are not repeated here.
The power grid load prediction device fully considers the correlation between the per-capita electricity consumption and the characteristic factors and among the characteristic factors, can predict the medium-term and long-term power grid loads, has small prediction error, and has a better prediction effect.
In addition, the present invention also provides an embodiment of a power system, comprising: the grid load prediction device as described in fig. 4.
The power system can accurately predict the medium and long-term power grid loads through the power grid load prediction device, and is favorable for providing effective technical support for power grid planning and power design.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A power grid load prediction method is characterized by comprising the following steps:
acquiring historical annual data and relevant characteristic information of the electricity consumption of the average person;
establishing a mapping relation model of the average human power consumption and relevant characteristics according to historical annual data and relevant characteristic information of the average human power consumption;
determining a prediction result of the average human power consumption in the period to be predicted according to a mapping relation model of the average human power consumption and the relevant characteristics;
and calculating the predicted power consumption of the period to be predicted according to the prediction result of the average power consumption of people and the population number of the period to be predicted.
2. The method of claim 1, wherein the relevant feature information comprises one or more of:
GDP, per-capita GDP, fixed asset investment, per-capita fixed asset investment, industry added value, per-capita industry added value, import and export total, and per-capita import and export total.
3. The method according to claim 1, wherein the establishing of the mapping relationship model between the average human power consumption and the relevant characteristics according to the historical annual data of the average human power consumption and the relevant characteristic information specifically comprises:
preprocessing historical annual data and relevant characteristic data of the electricity consumption of the average person;
and establishing a mapping relation model of the average human power consumption and the related characteristics from the preprocessed data through a machine learning method.
4. The method according to claim 3, wherein the preprocessing of the historical annual data and the relevant characteristic data of the average human power consumption specifically comprises:
judging whether the historical annual data is a stable time sequence;
if not, the historical annual data is subjected to stabilization processing;
and carrying out regularization processing on the relevant characteristic data to ensure that the processed relevant characteristic data are distributed in a regularization range.
5. The method according to claim 3, wherein the establishing a mapping relation model of the average human power consumption and the related features from the preprocessed data through a machine learning method specifically comprises:
judging whether the preprocessed data is in a format required by a LibSVM;
if not, converting the preprocessed data into a format required by the LibSVM;
and constructing an SVM model of the average human power consumption and related characteristics by using a LibSVM library function.
6. The method of claim 3, further comprising, prior to preprocessing the historical annual data and associated characteristic data for average human power usage:
performing single-feature fitting error analysis on the relevant feature data to obtain a fitting error between each relevant feature and the electricity consumption of the person;
and screening the relevant characteristics according to the fitting error.
7. The method of any of claims 1 to 6, further comprising:
when discrete data is included in the related characteristic information, the discrete data needs to be encoded.
8. The method of any of claims 1 to 6, further comprising:
judging whether the prediction result of the average electricity consumption of people meets the prediction precision or not;
and if the prediction result of the average human power consumption does not meet the prediction accuracy, adjusting the kernel function and the optimal parameters, reestablishing a mapping relation model of the average human power consumption and the relevant characteristics, and redetermining the prediction result of the average human power consumption in the period to be predicted according to the reestablished mapping relation model of the average human power consumption and the relevant characteristics so as to enable the redetermined prediction result of the average human power consumption to meet the prediction accuracy.
9. A grid load prediction device, comprising:
the data acquisition module is used for acquiring historical annual data and relevant characteristic information of the per-person electricity consumption;
the model establishing module is used for establishing a mapping relation model of the average human power consumption and the relevant characteristics according to the historical annual data and the relevant characteristic information of the average human power consumption;
the system comprises a per-person electricity consumption prediction module, a per-person electricity consumption prediction module and a prediction module, wherein the per-person electricity consumption prediction module is used for determining a per-person electricity consumption prediction result of a to-be-predicted period according to a mapping relation model of per-person electricity consumption and relevant characteristics;
and the calculation module is used for calculating the predicted power consumption of the period to be predicted according to the average human power consumption prediction result and the population number of the period to be predicted.
10. An electrical power system, comprising: a grid load prediction device as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564615.9A CN112561206A (en) | 2020-12-25 | 2020-12-25 | Power grid load prediction method and device and power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011564615.9A CN112561206A (en) | 2020-12-25 | 2020-12-25 | Power grid load prediction method and device and power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561206A true CN112561206A (en) | 2021-03-26 |
Family
ID=75032518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011564615.9A Pending CN112561206A (en) | 2020-12-25 | 2020-12-25 | Power grid load prediction method and device and power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561206A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678403A (en) * | 2015-12-30 | 2016-06-15 | 国网浙江省电力公司经济技术研究院 | Region saturation load prediction method based on model family decomposition and integration technology |
| CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
| CN109685277A (en) * | 2018-12-28 | 2019-04-26 | 国网冀北电力有限公司经济技术研究院 | Electricity demand forecasting method and device |
| CN110135635A (en) * | 2019-04-29 | 2019-08-16 | 国网山东省电力公司经济技术研究院 | A kind of region electric power saturation load forecasting method and system |
-
2020
- 2020-12-25 CN CN202011564615.9A patent/CN112561206A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105678403A (en) * | 2015-12-30 | 2016-06-15 | 国网浙江省电力公司经济技术研究院 | Region saturation load prediction method based on model family decomposition and integration technology |
| CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
| CN109685277A (en) * | 2018-12-28 | 2019-04-26 | 国网冀北电力有限公司经济技术研究院 | Electricity demand forecasting method and device |
| CN110135635A (en) * | 2019-04-29 | 2019-08-16 | 国网山东省电力公司经济技术研究院 | A kind of region electric power saturation load forecasting method and system |
Non-Patent Citations (3)
| Title |
|---|
| 柯尚军;蔡国田;张云涛;: "广州市用电量预测模型比较研究", 生态经济, no. 08, pages 63 - 67 * |
| 焦杰: "基于经济发展阶段的用电特征及中长期电量预测研究", 《华北电力大学(北京)硕士论文》 * |
| 韦亦龙: "电力需求预测及负荷特性分析系统的设计与实现", 《湖南大学硕士论文》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112734128B (en) | 7-day power load peak prediction method based on optimized RBF | |
| CN108921358B (en) | Prediction method, prediction system and related device of power load characteristics | |
| CN111027872A (en) | Method and system for determining power utilization maturity of regional users | |
| CN112085256B (en) | Full-period load prediction method considering load jump | |
| CN113126019A (en) | Intelligent ammeter error remote estimation method, system, terminal and storage medium | |
| CN102509173A (en) | Markov chain based method for accurately forecasting power system loads | |
| CN106992525A (en) | Management of power load method and apparatus | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| JP2013253805A (en) | Information processing device, and control method and program for the same | |
| CN114237884A (en) | Cloud computing data center energy consumption optimization method based on gray Markov chain | |
| CN112561206A (en) | Power grid load prediction method and device and power system | |
| CN112200596B (en) | Method, system, device and medium for determining regional marginal electricity price of power system | |
| CN111080037A (en) | Short-term power load prediction method and device based on deep neural network | |
| CN110705750A (en) | Method and system for predicting electric quantity of columnar power users in region | |
| CN116128117A (en) | Distribution line loss prediction method and device based on digital twinning | |
| CN113052630B (en) | Method for configuring electric power equipment by using model and electric power equipment configuration method | |
| CN114595591A (en) | Load decomposition method and device for industrial facility based on mixed integer programming | |
| CN108988340B (en) | Method and device for reducing line loss and server | |
| CN105447598A (en) | Error correction model based load prediction apparatus and method in power system | |
| CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
| CN111368257A (en) | Method and device for analyzing and predicting coal-to-electricity load characteristics | |
| CN112747413A (en) | Air conditioning system load prediction method and device | |
| CN117878927B (en) | Power system load trend analysis method based on time sequence analysis | |
| CN110674986B (en) | Peak regulation influence evaluation method for outsourcing electricity sale annual decomposition scheme and related equipment | |
| CN117613874A (en) | Industrial flexible load day-ahead scheduling potential equivalent method, system, equipment and medium |
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 |