CN114565156A - Power load prediction method, device, equipment and storage medium - Google Patents
Power load prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114565156A CN114565156A CN202210186722.5A CN202210186722A CN114565156A CN 114565156 A CN114565156 A CN 114565156A CN 202210186722 A CN202210186722 A CN 202210186722A CN 114565156 A CN114565156 A CN 114565156A
- Authority
- CN
- China
- Prior art keywords
- sub
- data
- prediction
- prediction model
- power load
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 29
- 239000013604 expression vector Substances 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013506 data mapping Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Power Engineering (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 power load prediction method, a power load prediction device, power load equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining factor data affecting the load of the power system on at least one historical day before a to-be-predicted day, mapping and converting the factor data into to-be-input data, selecting a first sub-prediction model with the highest relevance with the to-be-input data from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms, and inputting the to-be-input data into the first sub-prediction model to obtain a load prediction result output by the power load prediction model. The power load prediction model comprises a plurality of sub-prediction models which are built based on a plurality of prediction algorithms, and a first sub-prediction model with the highest relevance degree with data to be input is selected from the plurality of sub-prediction models of the pre-trained power load prediction model according to the data to be input, so that the prediction accuracy of the model is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of power load prediction, in particular to a power load prediction method, a power load prediction device, power load prediction equipment and a storage medium.
Background
Under the background of continuous deepening of electric power system innovation, the requirements of the whole society on safe, energy-saving and efficient operation of a power grid and the whole electric power industry are increasingly improved. When a scheduling department researches a planned operation mode in a future time period, demand analysis is firstly carried out, the condition of future electric loads is analyzed, not only total amount information is needed, but also the distribution condition of the electric loads is analyzed, and load prediction is carried out. The load prediction provides refined demand analysis data and analysis results for power production, and lays a foundation for realizing lean management of a scheduling plan flow.
There are many factors affecting the power load (e.g., social factors, policy factors, weather factors, holiday and festival factors, etc.). The power load prediction is extremely complex, and the accuracy of the conventional prediction result is not high.
Disclosure of Invention
The invention provides a power load prediction method, a power load prediction device, power load equipment and a storage medium, which are used for improving the prediction accuracy of a model.
In a first aspect, the present invention provides a power load prediction method, including:
acquiring factor data influencing the load of the power system on at least one historical day before the day to be predicted;
mapping and converting the factor data into data to be input;
selecting a first sub-prediction model with the highest degree of association with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
Optionally, the data to be input includes expression vectors of each factor in the factor data, and a first sub-prediction model with a highest degree of association with the expression vectors is selected from a plurality of sub-prediction models of a pre-trained power load prediction model, including:
carrying out weighting calculation on the expression vectors of all factors in the factor data to obtain a comprehensive weight value;
and selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model based on the comprehensive weight value.
Optionally, each of the sub-prediction models is associated with a weight range, the weight ranges of the plurality of sub-prediction models form a weight space, and a first sub-prediction model with the highest association degree with the data to be input is selected from the plurality of sub-prediction models of the pre-trained power load prediction model based on the comprehensive weight value, including:
mapping the integrated weight values to the weight space;
and taking the sub-prediction model corresponding to the weight range in which the comprehensive weight value falls as a first sub-prediction model with the highest association degree with the data to be input.
Optionally, the factor data includes temperature data, humidity data, rainfall data and date data.
Optionally, the training process of the power load prediction model includes:
acquiring a historical load sample of a power system and factor data corresponding to the historical load sample;
mapping and converting factor data corresponding to the historical load sample into a data sample to be input;
selecting a second sub-prediction model with the highest relevance degree with the data sample to be input from a plurality of sub-prediction models of a power load prediction model;
and training the second sub-prediction model by taking the historical load samples and the data samples to be input as training samples.
Optionally, training the second sub-prediction model by using the historical load sample and the to-be-input data sample as training samples, including:
inputting the data sample to be input into the second sub-prediction model to obtain a load prediction result output by the power load prediction model;
calculating loss values of the load prediction result and the historical load sample;
when the loss values of the load prediction result and the historical load sample are larger than a preset value, updating model parameters of the second sub-prediction model, and returning to the step of acquiring the historical load sample of the power system and factor data corresponding to the historical load sample;
and when the loss values of the load prediction result and the historical load sample are less than or equal to a preset value, determining that the second sub-prediction model is trained completely.
Optionally, the updating the model parameters of the second sub-prediction model includes:
and updating the model parameters of the second sub-prediction model by adopting a point-to-point multiple ratio method, wherein the selection range of the point-to-point smoothing coefficient of the point-to-point multiple ratio method is 0.1-0.99.
In a second aspect, the present invention further provides an electrical load prediction apparatus, including:
the system comprises a first data acquisition module, a second data acquisition module and a data processing module, wherein the first data acquisition module is used for acquiring factor data influencing the load of the power system on at least one historical day before a day to be predicted;
the first data conversion module is used for mapping and converting the factor data into data to be input;
the first sub-prediction model determining module is used for selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and the prediction result determining module is used for inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
Optionally, the first sub-prediction model determining module includes:
the weighting submodule is used for carrying out weighting calculation on the expression vectors of all factors in the factor data to obtain a comprehensive weight value;
and the first sub-prediction model determining sub-module is used for selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of the pre-trained power load prediction model based on the comprehensive weight value.
Optionally, each of the sub-prediction models is associated with a weight range, the weight ranges of a plurality of the sub-prediction models form a weight space, and the first sub-prediction model determining sub-module includes:
a weight value mapping unit for mapping the integrated weight value to the weight space;
and the first sub-prediction model determining unit is used for taking the sub-prediction model corresponding to the weight range in which the comprehensive weight value falls as the first sub-prediction model with the highest relevance with the data to be input.
Optionally, the factor data includes temperature data, humidity data, rainfall data and date data.
Optionally, the power load prediction apparatus further includes a power load prediction model training module, configured to train the power load prediction model, where the power load prediction model training module includes:
the second data acquisition module is used for acquiring historical load samples of the power system and factor data corresponding to the historical load samples;
the second data conversion module is used for mapping and converting factor data corresponding to the historical load sample into a data sample to be input;
the second sub-prediction model determining module is used for selecting a second sub-prediction model with the highest relevance degree with the data sample to be input from a plurality of sub-prediction models of the power load prediction model;
and the model training submodule is used for training the second sub-prediction model by taking the historical load sample and the data sample to be input as training samples.
Optionally, the model training sub-module includes:
the prediction result determining unit is used for inputting the data sample to be input into the second sub-prediction model to obtain a load prediction result output by the power load prediction model;
a loss value calculation unit for calculating the load prediction result and the loss value of the historical load sample;
the model updating unit is used for updating the model parameters of the second sub-prediction model when the loss values of the load prediction result and the historical load sample are larger than a preset value, and returning to the step of acquiring the historical load sample of the power system and the factor data corresponding to the historical load sample;
and the model determining unit is used for determining that the second sub-prediction model is trained completely when the loss values of the load prediction result and the historical load sample are less than or equal to a preset value.
Optionally, the model updating unit updates the model parameter of the second sub-prediction model by using a point-to-point multiple ratio method, where a selection range of a point-to-point smoothing coefficient of the point-to-point multiple ratio method is 0.1 to 0.99.
In a third aspect, the present invention also provides a computer device, comprising:
one or more processors;
storage means for storing one or more programs;
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the power load prediction method as provided by the first aspect of the invention.
In a fourth aspect, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the power load prediction method as provided in the first aspect of the present invention.
The invention provides a power load prediction method, which comprises the following steps: the method comprises the steps of obtaining factor data affecting the load of the power system on at least one historical day before a to-be-predicted day, mapping and converting the factor data into to-be-input data, selecting a first sub-prediction model with the highest relevance with the to-be-input data from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms, and inputting the to-be-input data into the first sub-prediction model to obtain a load prediction result output by the power load prediction model. In the embodiment of the invention, the power load prediction model comprises a plurality of sub-prediction models which are built based on a plurality of prediction algorithms, and the first sub-prediction model with the highest relevance degree with the data to be input is selected from the plurality of sub-prediction models of the pre-trained power load prediction model according to the data to be input, so that the prediction accuracy of the model is improved.
Drawings
Fig. 1 is a flowchart of a power load prediction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a power load prediction apparatus according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
Example one
Fig. 1 is a flowchart of a power load prediction method according to an embodiment of the present invention, where this embodiment is applicable to a case of predicting a power load, and the method may be executed by a power load prediction apparatus according to an embodiment of the present invention, where the apparatus may be implemented by software and/or hardware, and is generally configured in a computer device, as shown in fig. 1, where the method specifically includes the following steps:
s101, factor data influencing the load of the power system on at least one historical day before the day to be predicted is obtained.
In the embodiment of the present invention, the day to be predicted may be one or more days after the current date, and the historical day may be one or more days before the current date.
There are various kinds of factor data affecting the load of the power system, and in the embodiment of the present invention, the factor data affecting the load of the power system includes temperature data, humidity data, rainfall data, and date data. In the power load prediction, many factors affect the predicted value of the power load to different extents. Some factors vary from one another, such as weather. Some of them are different according to the regional conditions, such as the development speed of industry and agriculture. Some factors are important events which cannot be estimated, such as serious disasters, etc., and the influence of each factor on the load may be different, and the influence of different levels of the same factor on the load is also different.
Meteorological factors including temperature, humidity, rainfall and the like directly influence load fluctuation, and particularly in areas with higher proportion of resident load, the influence is larger.
Compared with the normal working day, the load of the ordinary holiday is obviously reduced, taking the spring festival as an example, the load curve during the spring festival generally has great reduction and deformation, and the change period of the load curve is approximately consistent with the holiday period.
The influence of the large-scale industrial user emergency is larger for the area where the large-scale industrial user is connected with the capacity and occupies a higher electric load, and the influence of the large-scale industrial user in the load prediction deviation is also larger.
It should be noted that the factor data affecting the load of the power system is an exemplary description of the present invention, and in other embodiments of the present invention, the factor data affecting the load of the power system may further include other factors, and the embodiments of the present invention are not limited herein.
And S102, mapping and converting the factor data into data to be input.
In the embodiment of the present invention, feature extraction (for example, word vector embedding, data mapping, and other operations) may be performed on factor data, and the factor data is mapped and converted into data to be input, where the data to be input includes expression vectors of each factor in the factor data. In practical applications, because the dimensions of each factor data (feature quantity) are different, it is necessary to map the values of different dimensions to a specific interval through non-dimensionalization processing, so that the quantities can have numerical comparability, thereby facilitating the quantitative calculation of similarity and difference.
S103, selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of the pre-trained power load prediction model.
In the embodiment of the invention, the power load prediction model comprises a plurality of sub-prediction models which are built based on a plurality of prediction algorithms so as to adapt to different types of input data. In the embodiment of the invention, after the factor data are mapped and converted into the data to be input, the sub-model with the highest relevance degree with the data to be input is selected from a plurality of sub-prediction models of the pre-trained power load prediction model as the first sub-prediction model. The sub-prediction model with the highest relevance is the sub-prediction model which is most suitable for processing the data to be input. For example, a certain sub-prediction model is most suitable for processing the data to be input with the highest temperature data proportion, and if the data to be input has the highest temperature data proportion, the sub-prediction model can be selected as the sub-model with the highest relevance with the data to be input as the first sub-prediction model.
Illustratively, in some embodiments of the invention, selecting the first sub-prediction model with the highest degree of association with the expression vector from the plurality of sub-prediction models of the pre-trained power load prediction model comprises:
1. and carrying out weighting calculation on the expression vectors of all factors in the factor data to obtain a comprehensive weight value.
Specifically, the corresponding weight is set according to the degree of influence of each factor on the power load, for example, if the temperature influence is large, the weight corresponding to the temperature is large. And multiplying the expression vectors of the factors in the factor data by the corresponding weights, and adding the products to obtain a comprehensive weight value.
2. And selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of the pre-trained power load prediction model based on the comprehensive weight value.
Illustratively, after the comprehensive weight value is obtained, a sub-prediction model corresponding to the factor is determined according to the magnitude of the comprehensive weight value, that is, the sub-prediction model is the first sub-prediction model with the highest relevance to the data to be input.
Illustratively, each sub-prediction model is associated with a weight range, the weight ranges of the sub-prediction models form a weight space, and a first sub-prediction model with the highest association degree with the data to be input is selected from the sub-prediction models of the pre-trained power load prediction model based on the comprehensive weight value, and the method comprises the following steps:
and mapping the comprehensive weight value to a weight space, and taking a sub-prediction model corresponding to the weight range in which the comprehensive weight value falls as a first sub-prediction model with the highest association degree with the data to be input.
And S104, inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
After the first sub-prediction model with the highest relevance degree with the data to be input is determined, the data to be input is input into the first sub-prediction model, the load prediction result output by the power load prediction model is obtained, and therefore the load curve formed by the power loads on days after the current date is obtained in a prediction mode.
The power load prediction method provided by the embodiment of the invention comprises the following steps: the method comprises the steps of obtaining factor data affecting the load of the power system on at least one historical day before a to-be-predicted day, mapping and converting the factor data into to-be-input data, selecting a first sub-prediction model with the highest relevance with the to-be-input data from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms, and inputting the to-be-input data into the first sub-prediction model to obtain a load prediction result output by the power load prediction model. In the embodiment of the invention, the power load prediction model comprises a plurality of sub-prediction models which are built based on a plurality of prediction algorithms, and the first sub-prediction model with the highest relevance degree with the data to be input is selected from the plurality of sub-prediction models of the pre-trained power load prediction model according to the data to be input, so that the prediction accuracy of the model is improved.
In some embodiments of the invention, the training process of the power load prediction model comprises:
1. historical load samples of the power system and factor data corresponding to the historical load samples are obtained.
Specifically, the historical load sample is the power load of the historical day, and the factor data corresponding to the historical load sample is the factor data affecting the historical load sample. As described above, there are various factor data affecting the load of the power system, and in the embodiment of the present invention, the factor data affecting the load of the power system includes temperature data, humidity data, rainfall data, and date data, which are not described herein again.
2. And mapping and converting the factor data corresponding to the historical load sample into a to-be-input data sample.
Illustratively, feature extraction (for example, word vector embedding, data mapping, and the like) is performed on factor data corresponding to the historical load sample, and the factor data mapping corresponding to the historical load sample is converted into a data sample to be input, where the data sample to be input includes an expression vector of each factor in the factor data. In practical applications, because the dimensions of each factor data (feature quantity) are different, it is necessary to map the values of different dimensions to a specific interval through non-dimensionalization processing, so that the quantities can have numerical comparability, thereby facilitating the quantitative calculation of similarity and difference.
3. And selecting a second sub-prediction model with the highest relevance with the data sample to be input from a plurality of sub-prediction models of the power load prediction model.
In an embodiment of the invention, the power load prediction model comprises a plurality of sub-prediction models based on different prediction algorithms to accommodate different types of input data. In the embodiment of the invention, after factor data corresponding to the historical load sample is mapped and converted into the data sample to be input, the sub-model with the highest relevance degree with the data to be input is selected from a plurality of sub-prediction models of the pre-trained power load prediction model to serve as the second sub-prediction model. Specifically, the process of selecting the sub-model with the highest degree of association with the data to be input from the plurality of sub-prediction models of the pre-trained power load prediction model as the second sub-prediction model is similar to the process of selecting the sub-model with the highest degree of association with the data to be input from the plurality of sub-prediction models of the pre-trained power load prediction model as the first sub-prediction model, and the details of the embodiment of the present invention are not repeated here.
4. And training a second sub-prediction model by taking the historical load samples and the data samples to be input as training samples.
And arranging the historical load samples and the data samples to be input into training samples, and training a second sub-prediction model.
Illustratively, the training process is as follows:
and 4.1, inputting the data sample to be input into the second sub-prediction model to obtain a load prediction result output by the power load prediction model.
And 4.2, calculating loss values of the load prediction result and the historical load sample.
In the embodiment of the present invention, the square loss and the absolute loss of the load prediction result and the historical load sample may be calculated, which is not limited herein.
And 4.3, when the loss values of the load prediction result and the historical load sample are larger than a preset value, updating the model parameters of the second sub-prediction model, and returning to the step of acquiring the historical load sample of the power system and the factor data corresponding to the historical load sample.
Specifically, a point-to-point multiple ratio method is adopted to update the model parameters of the second sub-prediction model, and the selection range of the point-to-point smoothing coefficient of the point-to-point multiple ratio method is 0.1-0.99.
And 4.4, when the loss values of the load prediction result and the historical load sample are less than or equal to a preset value, determining that the second sub-prediction model is trained completely.
In the process of short-term prediction, in order to obtain a prediction result accurately, various information and related data must be collected carefully, and the accuracy is improved by means of an accurate mathematical physical model, so that a better result is obtained by calculation each time.
However, with the rapid development of economy and the tension of power supply situation in recent years, the randomness of the bus load is high, and the difficulty of bus load prediction is high. The result of identifying the regularity and the stability of the historical load of the bus shows that the load sequence of the bus has different regularity in different regions, different seasons and different moments.
The traditional prediction mode usually depends on experience, and a prediction result is obtained after a mathematical model is selected and model parameters are fixed. The model with fixed parameters obviously reflects the historical load regularity of the bus in different regions and at different times. How to select the parameters of the model in different regions and different seasons is the key to the accuracy of the bus load prediction.
The embodiment of the invention continuously updates the model parameters in the model training process, and finally takes the parameters with the best prediction effect as the final model parameters for load prediction in the future. Therefore, the prediction accuracy of the model is greatly improved.
Example two
Fig. 2 is a schematic structural diagram of an electrical load prediction apparatus according to a second embodiment of the present invention, as shown in fig. 2, the apparatus includes:
a first data obtaining module 201, configured to obtain factor data affecting a load of the power system on at least one historical day before a day to be predicted;
a first data conversion module 202, configured to map and convert the factor data into data to be input;
the first sub-prediction model determining module 203 is configured to select a first sub-prediction model with the highest degree of association with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, where the power load prediction model includes a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and the prediction result determining module 204 is configured to input the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
Optionally, the first sub-prediction model determining module 203 includes:
the weighting submodule is used for carrying out weighting calculation on the expression vectors of all factors in the factor data to obtain a comprehensive weight value;
and the first sub-prediction model determining sub-module is used for selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of the pre-trained power load prediction model based on the comprehensive weight value.
Optionally, each of the sub-prediction models is associated with a weight range, the weight ranges of a plurality of the sub-prediction models form a weight space, and the first sub-prediction model determining sub-module includes:
a weight value mapping unit for mapping the integrated weight value to the weight space;
and the first sub-prediction model determining unit is used for taking the sub-prediction model corresponding to the weight range in which the comprehensive weight value falls as the first sub-prediction model with the highest relevance with the data to be input.
Optionally, the factor data includes temperature data, humidity data, rainfall data and date data.
Optionally, the power load prediction apparatus further includes a power load prediction model training module, configured to train the power load prediction model, where the power load prediction model training module includes:
the second data acquisition module is used for acquiring historical load samples of the power system and factor data corresponding to the historical load samples;
the second data conversion module is used for mapping and converting factor data corresponding to the historical load sample into a data sample to be input;
the second sub-prediction model determining module is used for selecting a second sub-prediction model with the highest relevance degree with the data sample to be input from a plurality of sub-prediction models of the power load prediction model;
and the model training submodule is used for training the second sub-prediction model by taking the historical load sample and the data sample to be input as training samples.
Optionally, the model training sub-module includes:
the prediction result determining unit is used for inputting the data sample to be input into the second sub-prediction model to obtain a load prediction result output by the power load prediction model;
a loss value calculation unit for calculating the load prediction result and the loss value of the historical load sample;
the model updating unit is used for updating the model parameters of the second sub-prediction model when the loss values of the load prediction result and the historical load sample are larger than a preset value, and returning to the step of acquiring the historical load sample of the power system and the factor data corresponding to the historical load sample;
and the model determining unit is used for determining that the second sub-prediction model is trained completely when the loss values of the load prediction result and the historical load sample are less than or equal to a preset value.
Optionally, the model updating unit updates the model parameter of the second sub-prediction model by using a point-to-point multiple ratio method, where a selection range of a point-to-point smoothing coefficient of the point-to-point multiple ratio method is 0.1 to 0.99.
The power load prediction device can execute the power load prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the power load prediction method.
EXAMPLE III
A third embodiment of the present invention provides a computer device, and fig. 3 is a schematic structural diagram of a computer device provided in the third embodiment of the present invention, as shown in fig. 3, the computer device includes a processor 301, a memory 302, a communication module 303, an input device 304, and an output device 305; the number of the processors 301 in the computer device may be one or more, and one processor 301 is taken as an example in fig. 3; the processor 301, the memory 302, the communication module 303, the input means 304 and the output means 305 in the computer apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 3. The processor 301, the memory 302, the communication module 303, the input device 304 and the output device 305 may be integrated on a control board of the computer apparatus.
The memory 302 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as the modules corresponding to the power load prediction method in the present embodiment. The processor 301 executes various functional applications and data processing of the computer device by executing the software programs, instructions and modules stored in the memory 302, that is, implements the power load prediction method provided by the above-described embodiment.
The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the computer device, and the like. Further, the memory 302 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 302 may further include memory located remotely from the processor 301, which may be connected to a computer device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The communication module 303 is configured to establish a connection with an external device (e.g., an intelligent terminal), and implement data interaction with the external device. The input means 304 may be used to receive input numeric or character information and to generate key signal inputs relating to user settings and function controls of the computer device.
The computer device provided by this embodiment may perform the power load prediction method provided by any of the above embodiments of the present invention, and its corresponding functions and advantages are described in detail.
Example four
An embodiment of the present invention provides a storage medium containing computer-executable instructions, where a computer program is stored, and when the computer program is executed by a processor, the method for predicting the power load provided by any of the above embodiments of the present invention is implemented, where the method includes:
acquiring factor data influencing the load of the power system on at least one historical day before the day to be predicted;
mapping and converting the factor data into data to be input;
selecting a first sub-prediction model with the highest degree of association with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the power load prediction method provided by the embodiments of the present invention.
It should be noted that, as for the apparatus, the device and the storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and in relevant places, reference may be made to the partial description of the method embodiments.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention or portions thereof contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a robot, a personal computer, a server, or a network device, etc.) to execute the power load prediction method according to any embodiment of the present invention.
It should be noted that, in the above apparatus, each module, sub-module, and unit included in the apparatus is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope 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 a memory and executed by a suitable instruction execution device. 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.
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.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for predicting a power load, comprising:
acquiring factor data influencing the load of the power system on at least one historical day before the day to be predicted;
mapping and converting the factor data into data to be input;
selecting a first sub-prediction model with the highest degree of association with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
2. The power load prediction method according to claim 1, wherein the data to be input includes an expression vector of each factor in the factor data, and the selecting a first sub-prediction model having a highest degree of association with the expression vector from a plurality of sub-prediction models of a pre-trained power load prediction model includes:
carrying out weighting calculation on the expression vectors of all factors in the factor data to obtain a comprehensive weight value;
and selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model based on the comprehensive weight value.
3. The power load prediction method according to claim 2, wherein each of the sub-prediction models is associated with a weight range, the weight ranges of the plurality of sub-prediction models form a weight space, and the selecting a first sub-prediction model with the highest association with the data to be input from the plurality of sub-prediction models of the pre-trained power load prediction model based on the integrated weight value comprises:
mapping the integrated weight values to the weight space;
and taking the sub-prediction model corresponding to the weight range in which the comprehensive weight value falls as a first sub-prediction model with the highest association degree with the data to be input.
4. The power load prediction method of claim 1, wherein the factor data comprises temperature data, humidity data, rainfall data, and date data.
5. A power load prediction method according to any one of claims 1 to 4, wherein the training process of the power load prediction model comprises:
acquiring a historical load sample of a power system and factor data corresponding to the historical load sample;
mapping and converting factor data corresponding to the historical load sample into a data sample to be input;
selecting a second sub-prediction model with the highest relevance degree with the data sample to be input from a plurality of sub-prediction models of a power load prediction model;
and training the second sub-prediction model by taking the historical load samples and the data samples to be input as training samples.
6. The power load prediction method according to claim 5, wherein training the second sub-prediction model with the historical load samples and the data samples to be input as training samples comprises:
inputting the data sample to be input into the second sub-prediction model to obtain a load prediction result output by the power load prediction model;
calculating loss values of the load prediction result and the historical load sample;
when the loss values of the load prediction result and the historical load sample are larger than a preset value, updating model parameters of the second sub-prediction model, and returning to the step of acquiring the historical load sample of the power system and factor data corresponding to the historical load sample;
and when the loss values of the load prediction result and the historical load sample are less than or equal to a preset value, determining that the second sub-prediction model is trained completely.
7. The power load prediction method of claim 6, wherein updating the model parameters of the second sub-prediction model comprises:
and updating the model parameters of the second sub-prediction model by adopting a point-to-point multiple ratio method, wherein the selection range of the point-to-point smoothing coefficient of the point-to-point multiple ratio method is 0.1-0.99.
8. An electric load prediction apparatus, comprising:
the system comprises a first data acquisition module, a second data acquisition module and a data processing module, wherein the first data acquisition module is used for acquiring factor data influencing the load of the power system on at least one historical day before a day to be predicted;
the first data conversion module is used for mapping and converting the factor data into data to be input;
the first sub-prediction model determining module is used for selecting a first sub-prediction model with the highest relevance degree with the data to be input from a plurality of sub-prediction models of a pre-trained power load prediction model, wherein the power load prediction model comprises a plurality of sub-prediction models built based on a plurality of prediction algorithms;
and the prediction result determining module is used for inputting the data to be input into the first sub-prediction model to obtain a load prediction result output by the power load prediction model.
9. A computer device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the power load prediction method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the power load prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210186722.5A CN114565156A (en) | 2022-02-28 | 2022-02-28 | Power load prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210186722.5A CN114565156A (en) | 2022-02-28 | 2022-02-28 | Power load prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114565156A true CN114565156A (en) | 2022-05-31 |
Family
ID=81715267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210186722.5A Pending CN114565156A (en) | 2022-02-28 | 2022-02-28 | Power load prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114565156A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053066A (en) * | 2017-12-12 | 2018-05-18 | 中国西电电气股份有限公司 | The Forecasting Methodology of adjustable electric load in industrial production user's energy management system |
| WO2020252784A1 (en) * | 2019-06-21 | 2020-12-24 | 西门子股份公司 | Power load data prediction method and device, and storage medium |
| CN113256016A (en) * | 2021-06-04 | 2021-08-13 | 广东电网有限责任公司珠海供电局 | Load prediction method and system based on virtual power plant operation |
| CN113516291A (en) * | 2021-05-24 | 2021-10-19 | 国网河北省电力有限公司经济技术研究院 | Power load prediction method, device and equipment |
| CN113657936A (en) * | 2021-08-17 | 2021-11-16 | 国网河北省电力有限公司邢台供电分公司 | Power load prediction method and terminal |
| CN113947007A (en) * | 2021-07-02 | 2022-01-18 | 国家电投集团科学技术研究院有限公司 | Energy load prediction method, device and equipment |
-
2022
- 2022-02-28 CN CN202210186722.5A patent/CN114565156A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108053066A (en) * | 2017-12-12 | 2018-05-18 | 中国西电电气股份有限公司 | The Forecasting Methodology of adjustable electric load in industrial production user's energy management system |
| WO2020252784A1 (en) * | 2019-06-21 | 2020-12-24 | 西门子股份公司 | Power load data prediction method and device, and storage medium |
| CN113516291A (en) * | 2021-05-24 | 2021-10-19 | 国网河北省电力有限公司经济技术研究院 | Power load prediction method, device and equipment |
| CN113256016A (en) * | 2021-06-04 | 2021-08-13 | 广东电网有限责任公司珠海供电局 | Load prediction method and system based on virtual power plant operation |
| CN113947007A (en) * | 2021-07-02 | 2022-01-18 | 国家电投集团科学技术研究院有限公司 | Energy load prediction method, device and equipment |
| CN113657936A (en) * | 2021-08-17 | 2021-11-16 | 国网河北省电力有限公司邢台供电分公司 | Power load prediction method and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111563610B (en) | Building electric load comprehensive prediction method and system based on LSTM neural network | |
| CN112348292B (en) | Short-term wind power prediction method and system based on deep learning network | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN111832809B (en) | Building energy consumption load prediction method and system based on Holt-Winters and extreme learning machine | |
| CN111539841A (en) | Electric quantity prediction method, device, equipment and readable storage medium | |
| CN110232476A (en) | A kind of micro-grid load prediction technique based on deep learning | |
| CN110751416A (en) | Method, device and equipment for predicting water consumption | |
| CN113112099A (en) | Power grid daily electric quantity prediction model training method and power grid daily electric quantity prediction method | |
| CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
| CN112990587A (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| CN107239850A (en) | A kind of long-medium term power load forecasting method based on system dynamics model | |
| CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
| CN111179108A (en) | Method and device for predicting power consumption | |
| CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
| CN113807593B (en) | Data quantity and data quality prediction method and system based on power scheduling | |
| Ruxue et al. | Load forecasting based on weighted grey relational degree and improved ABC-SVM | |
| Yuan et al. | A SAFSA-and metabolism-based nonlinear grey Bernoulli model for annual water consumption prediction | |
| CN115238854A (en) | Short-term load prediction method based on TCN-LSTM-AM | |
| CN111178641A (en) | Short-term power load prediction method based on feature extraction and multi-core RSVR combined model | |
| CN117791618A (en) | Power scheduling method, device, computer equipment and storage medium | |
| CN113139698A (en) | Load prediction method, device and equipment | |
| CN111177278A (en) | Grid user short-term load prediction real-time processing tool | |
| CN114565156A (en) | Power load prediction method, device, equipment and storage medium | |
| CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
| CN110298476A (en) | Energy consumption prediction technique, device, computer equipment and storage 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 |