CN115034519A - Method and device for predicting power load, electronic equipment and storage medium - Google Patents
Method and device for predicting power load, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115034519A CN115034519A CN202210906096.2A CN202210906096A CN115034519A CN 115034519 A CN115034519 A CN 115034519A CN 202210906096 A CN202210906096 A CN 202210906096A CN 115034519 A CN115034519 A CN 115034519A
- Authority
- CN
- China
- Prior art keywords
- load
- historical
- data
- electricity
- target type
- 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 56
- 230000005611 electricity Effects 0.000 claims abstract description 74
- 230000001932 seasonal effect Effects 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 29
- 238000012360 testing method Methods 0.000 claims description 17
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 3
- 230000004931 aggregating effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process 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
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Power Engineering (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicting an electrical load, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical power load data of a target type; wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values; respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, and acquiring a combined prediction value matched with each target type and output by each combined prediction model; and summarizing the combined predicted values matched with the target types to obtain a predicted electric load value. By using the technical scheme of the invention, the power load can be predicted based on different industries, and the accuracy of the prediction result is improved.
Description
Technical Field
The invention relates to the technical field of smart power grids, in particular to a method and a device for predicting power load, electronic equipment and a storage medium.
Background
With the development of smart power grids and the increasing demand of the power industry, the importance of power load prediction is increasingly shown, and the requirement on the power load prediction precision is higher and higher.
In the prior art, the prediction mode of the power load is to comprehensively predict all power utilization conditions of a transformer substation by taking the transformer substation as a unit. However, because some industries have relatively high growth rates and some industries have relatively low growth rates, the electric loads are predicted uniformly, and the prediction result of the electric loads has large errors.
Disclosure of Invention
The invention provides a method and a device for predicting an electrical load, electronic equipment and a storage medium, which are used for realizing the prediction of the electrical load based on different industries and improving the accuracy of a prediction result.
In a first aspect, an embodiment of the present invention provides a method for predicting an electrical load, where the method includes:
acquiring historical electricity load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, and acquiring a combined prediction value matched with each target type and output by each combined prediction model;
and summarizing the combined predicted values matched with the target types to obtain a predicted electric load value.
In a second aspect, an embodiment of the present invention further provides an apparatus for predicting an electrical load, where the apparatus includes:
the historical power consumption load data acquisition module is used for acquiring historical power consumption load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
the target type combined predicted value acquisition module is used for respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type and acquiring a combined predicted value which is output by each combined prediction model and matched with each target type;
and the predicted electric load value acquisition module is used for summarizing the combined predicted values matched with the target types to obtain the predicted electric load value.
In a third aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for predicting the electrical load according to any one of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a storage medium storing computer-executable instructions, which when executed by a computer processor, are used for executing the method for predicting the electrical load according to any one of the embodiments of the present invention.
According to the technical scheme of the embodiment of the invention, the electric load data are divided into the industrial electric load type, the commercial electric load type and the residential electric load type, different combined prediction models are respectively adopted for predicting the electric load of different types of electric load data, and predicted values of all types are summarized to obtain a total predicted electric load value. The method solves the problem that the prediction result has larger error in the mode of predicting the power load by taking a transformer substation as a unit in the prior art, realizes the power load prediction based on different industries, and improves the accuracy of the power load prediction result.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for predicting an electrical load according to an embodiment of the present invention;
fig. 2 is a flowchart of a method for predicting an electrical load according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electrical load prediction apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a method for predicting an electrical load according to an embodiment of the present invention, where the present embodiment is applicable to a case where electrical load prediction is performed based on different industries, and the method may be performed by an electrical load prediction apparatus, where the electrical load prediction apparatus may be implemented in a form of hardware and/or software, and the electrical load prediction apparatus may be configured in a computer device.
As shown in fig. 1, the method includes:
and S110, acquiring historical electric load data of the target type.
Wherein the target types include industrial power, commercial power, and residential power, and the historical power load data includes a historical power load value, and seasonal data and date data that match the historical power load value.
The historical electric load data is divided into historical electric load data of industrial electricity, historical electric load data of commercial electricity and historical electric load data of residential electricity according to the type of the electric load. The historical electricity load value is a numerical value of the electricity load corresponding to the historical time point, the season data may be a season where the historical time point is located, the date data may be a date where the historical time point is located, and whether the date is a weekend or a working day, whether the date is a month, end, or whether the date is a holiday, and the like. Meanwhile, in this embodiment, the content included in the historical electrical load data is also not limited, and the historical electrical load data may also include a temperature matching the historical electrical load value, or a policy on whether there is a power privilege at the historical time point, or the like.
In the embodiment of the invention, because the different types of loads have different properties, the different types of electric loads are respectively predicted, and the error of the prediction result can be reduced.
In the embodiment of the invention, according to the data analysis of the historical electric load value, the electric load presents seasonal periodicity, relatively speaking, the electric load is higher in summer, meanwhile, the date also has certain influence on the electric load, and the difference between the electric load in the working day period and the electric load on the weekend is larger. Therefore, when the electric load is predicted, factors such as the season and date of the historical electric load value are considered in addition to the historical electric load value, and the accuracy of the electric load prediction can be improved.
And S120, respectively inputting the historical load electricity consumption data of each target type into the combined prediction model matched with each target type, and acquiring the combined prediction value matched with each target type and output by each combined prediction model.
For the prediction of different types of power loads, a combined prediction model is trained in advance according to historical load power consumption data of the type, and the combined prediction models used for the prediction of the different types of power loads are different.
In the embodiment of the invention, the combined prediction model is adopted to predict the electric load, and compared with other prediction modes such as an S-shaped curve prediction method or a gray system envelope model, the combined prediction model has higher accuracy and more stable accuracy.
Optionally, the combined prediction model matched with the target type is obtained by training a preset combined prediction model according to historical power load sample data of the target type; the preset combined prediction model is obtained by combining at least two single prediction models.
Optionally, the combined prediction value is a single prediction value output by each single prediction model in the combined prediction model, and is obtained by combining according to a combined algorithm.
In the embodiment of the invention, a plurality of single prediction models are integrated in the combined prediction model, and after the single prediction models respectively predict the electric load, the prediction results of the single prediction models are combined to determine the final electric load prediction result. By combining the prediction results of a plurality of single prediction models, a more stable and more accurate prediction result can be obtained.
Optionally, the single prediction model may include a ridge regression model, a catboost model, and a light gradient elevator model; the combination algorithm is an equal-weight combination algorithm.
The ridge regression model is a multivariate regression prediction model for analyzing multiple collinearity, the catboost model is a GBDT (Gradient Boosting Decision Tree) model which has few parameters and supports type variables and high accuracy and is based on a symmetric Decision Tree algorithm, and the Light Gradient booster model is also a LightGBM (Light Gradient Boosting Machine) model and is a distributed Gradient Boosting model based on the Decision Tree algorithm. The equal weight combination algorithm, namely the EW (equal weight) combination algorithm, performs Weighted calculation on the prediction results of the plurality of single prediction models to obtain the final prediction result. The present embodiment does not limit the specific type of each single prediction model and the specific type of the combination algorithm employed.
And S130, summarizing the combined predicted values matched with the target types to obtain a predicted electric load value.
And after the electric loads of the target types are respectively predicted, combining the combined predicted values of the target types to obtain a predicted electric load value.
Optionally, summarizing the combined predicted values matched with the target types to obtain the predicted electric load value may include: and taking the sum of the products of the combined predicted value matched with each target type and the weight matched with each target type as a predicted electric load value.
Wherein the weights matched with the target types can be the same or different. Meanwhile, the sum of the weights matched with the respective target types needs to be the same as the number of the target types. For example, when the target types are industrial electricity, commercial electricity, and residential electricity, the sum of the weights matched with the target types should be 3.
Specifically, when the weights of the target types are the same, the weight of each target type is 1, that is, the combined predicted values matched with the target types are directly added to obtain the predicted electrical load value. Different target types can be given different weights, and for example, if the current summer period is determined according to the season data and date data of the historical electricity load data, and the factory is in the electricity limit period, the industrial electricity can be given a weight of 0.9, and the residential electricity can be given a weight of 1.1. The present embodiment does not limit the weight of each object type and the manner of determining the weight of each object type.
According to the technical scheme of the embodiment of the invention, the electric load data are divided into the industrial electric load type, the commercial electric load type and the residential electric load type, different combined prediction models are respectively adopted for predicting the electric load of different types of electric load data, and predicted values of all types are summarized to obtain a total predicted electric load value. The method and the device solve the problem that the prediction result has larger error in the mode of predicting the power load by taking a transformer substation as a unit in the prior art, realize power load prediction based on different industries and improve the accuracy of the power load prediction result.
Example two
Fig. 2 is a flowchart of a method for predicting an electrical load according to a second embodiment of the present invention, and the embodiment of the present invention further embodies a training process of a combined prediction model on the basis of the above embodiments.
As shown in fig. 2, the method includes:
s210, obtaining historical power load sample data of the target type.
The historical electric load sample data comprises a historical electric load sample value, and seasonal data and date data matched with the historical electric load sample value.
Training of the combined prediction model of the target type can be performed according to the historical power load sample data of the target type in the historical time period.
And S220, missing value filling processing is carried out on the historical power load sample data.
Since the historical power load sample data is time-series data, if a missing value exists in the historical power load sample data, the missing value can be filled according to historical power load sample values before and after the missing value, and the filling manner of the missing value is not limited in this embodiment.
And S230, performing data standardization processing on the historical power consumption load sample data after the missing value is filled.
The data standardization processing of the historical power load sample data has the effects of eliminating the influence of abnormal data on the prediction result and improving the accuracy of power load prediction.
Specifically, the data normalization processing may be performed by using a method such as an extreme value method, a standard deviation method, or a three-fold line method, and the specific method used for the data normalization is not limited in this embodiment.
And S240, dividing the historical power load sample data into a training set, a test set and a verification set.
For example, the training set, the test set and the verification set may be in a ratio of 7:2:1, but the present embodiment does not limit the ratio of the training set, the test set and the verification set.
And S250, training a preset combined prediction model according to the historical electric load sample data of the first time period and the historical electric load sample data of the second time period in the training set.
Wherein the first time period is earlier than the second time period.
And training a combined prediction model by taking the historical electric load sample data of the first time period as an independent variable and the historical electric load sample value of the second time period as a dependent variable. For example, the first time period may be the first seven days, and the second time period may be the eighth day, that is, the power load of the eighth day is predicted by using the power load of the previous week, but the specific sizes of the first time period and the second time period are not limited in this embodiment.
In the embodiment of the invention, the training set is input into each single prediction model in the combined prediction model for model training.
And S260, testing the combined prediction model according to the test set, and verifying the combined prediction model according to the verification set until the test result and the verification result both meet the training success condition.
In the embodiment of the invention, the combined prediction model in the training process is tested through the test set, the combined prediction model in the training process is verified and evaluated through the verification set, and the parameters of each single prediction model in the combined prediction model are continuously adjusted until the test result and the verification result both meet the training success condition. The test result and the verification result both meet the successful training condition, the precision of the model can reach a preset precision threshold, and the obtained combined prediction model is the combined prediction model matched with the target type and used for predicting the power load of the subsequent target type.
And S270, acquiring historical electric load data of the target type.
And S280, respectively inputting the historical load electricity consumption data of each target type into the combined prediction model matched with each target type, and acquiring the combined prediction value matched with each target type and output by each combined prediction model.
In the embodiment of the invention, the historical load electricity utilization data of the target type is input into the combined prediction model of the target type, each single prediction model in the combined prediction model of the target type predicts to obtain a single prediction value according to the historical load electricity utilization data of the target type, and the combined prediction model of the target type combines each single prediction value according to a combined algorithm to obtain a combined prediction value. And repeating the process for the historical load electricity consumption data of each type to obtain the combined predicted value corresponding to each target type.
And S290, taking the sum of products of the combined predicted value matched with each target type and the weight matched with each target type as a predicted electric load value.
Wherein the weights matched with the target types are the same or different.
And summarizing the combined predicted value of the industrial power utilization, the combined predicted value of the commercial power utilization and the combined predicted value of the residential power utilization to obtain a total predicted power utilization load value. In the embodiment, the method for predicting the power load based on different industry types has higher accuracy of the prediction result compared with the method for predicting the load based on the transformer substation in the prior art.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a device for predicting an electrical load according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: a historical electrical load data obtaining module 310, a target type combination predicted value obtaining module 320 and a predicted electrical load value obtaining module 330. Wherein:
a historical electrical load data acquisition module 310, configured to acquire historical electrical load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
a target type combined predicted value obtaining module 320, configured to input the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, respectively, and obtain a combined predicted value matched with each target type and output by each combined prediction model;
and the predicted electrical load value acquisition module 330 is configured to summarize the combined predicted values matched with the target types to obtain a predicted electrical load value.
According to the technical scheme of the embodiment of the invention, the electric load data are divided into the industrial electric load type, the commercial electric load type and the residential electric load type, different combined prediction models are respectively adopted for predicting the electric load of different types of electric load data, and the predicted values of all types are summarized to obtain the total predicted electric load value. The method solves the problem that the prediction result has larger error in the mode of predicting the power load by taking a transformer substation as a unit in the prior art, realizes the power load prediction based on different industries, and improves the accuracy of the power load prediction result.
On the basis of the embodiment, the combined prediction model matched with the target type is obtained by training a preset combined prediction model according to historical power load sample data of the target type;
the preset combined prediction model is obtained by combining at least two single prediction models.
On the basis of the above embodiment, the combined predicted value is a single predicted value output to each single prediction model in the combined prediction model, and is obtained by combining according to a combination algorithm.
On the basis of the above embodiment, the single prediction model includes a ridge regression model, a catboost model and a light gradient elevator model;
the combination algorithm is an equal-weight combination algorithm.
On the basis of the above embodiment, the apparatus includes:
the historical power load sample data acquisition module is used for acquiring historical power load sample data of a target type, wherein the historical power load sample data comprises a historical power load sample value, and seasonal data and date data matched with the historical power load sample value;
the historical power load sample data dividing module is used for dividing the historical power load sample data into a training set, a test set and a verification set;
the combined prediction model training module is used for training a preset combined prediction model according to the historical power load sample data of the first time period and the historical power load sample value of the second time period in the training set;
wherein the first time period is earlier than the second time period;
and the training success condition judgment module is used for testing the combined prediction model according to the test set and verifying the combined prediction model according to the verification set until the test result and the verification result both meet the training success condition.
On the basis of the above embodiment, the apparatus further includes:
the missing value filling module is used for filling missing values of historical power load sample data;
and the data standardization processing module is used for carrying out data standardization processing on the historical power consumption load sample data after the missing value is filled.
On the basis of the foregoing embodiment, the module 330 for obtaining a predicted electrical load value includes:
a predicted electrical load value determination unit for determining the sum of products of the combined predicted value matched with each target type and the weight matched with each target type as a predicted electrical load value;
wherein the weights matched with the target types are the same or different.
The device for predicting the electrical load provided by the embodiment of the invention can execute the method for predicting the electrical load provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer apparatus according to a fourth embodiment of the present invention, as shown in fig. 4, the computer apparatus includes a processor 70, a memory 71, an input device 72, and an output device 73; the number of processors 70 in the computer device may be one or more, and one processor 70 is taken as an example in fig. 4; the processor 70, the memory 71, the input device 72 and the output device 73 in the computer apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 4.
The memory 71 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as modules corresponding to the method for predicting the electrical load in the embodiment of the present invention (for example, a historical electrical load data obtaining module 310, a target type combination prediction value obtaining module 320, and a predicted electrical load value obtaining module 330 in the device for predicting the electrical load). The processor 70 executes various functional applications and data processing of the computer device by executing software programs, instructions and modules stored in the memory 71, that is, the above-mentioned method for predicting the power load is implemented. The method comprises the following steps:
acquiring historical power load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, and acquiring a combined prediction value matched with each target type and output by each combined prediction model;
and summarizing the combined predicted values matched with the target types to obtain a predicted electric load value.
The memory 71 may mainly include a storage program area and a storage data area, wherein the storage program 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 the use of the terminal, and the like. Further, the memory 71 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 71 may further include memory located remotely from the processor 70, which may be connected to a computer device over 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 input device 72 may be used to receive input numeric or character information and generate key signal inputs relating to user settings and function controls of the computer apparatus. The output device 73 may include a display device such as a display screen.
EXAMPLE five
An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method for predicting a power consumption load, the method including:
acquiring historical power load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, and acquiring a combined prediction value matched with each target type and output by each combined prediction model;
and summarizing the combined predicted values matched with the target types to obtain a predicted electric load value.
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 method for predicting the electrical load provided by any embodiment of the present invention.
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 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 may be embodied in the form of a software product, which can 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 personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above prediction apparatus for electrical load, the included units and modules are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. Those skilled in the art will appreciate that the present invention is not limited to the particular embodiments described herein, and that various obvious changes, rearrangements and substitutions will now be 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 an electrical load, comprising:
acquiring historical power load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
respectively inputting the historical load electricity consumption data of each target type into a combined prediction model matched with each target type, and acquiring a combined prediction value matched with each target type and output by each combined prediction model;
and summarizing the combined predicted values matched with the target types to obtain a predicted electric load value.
2. The method according to claim 1, wherein the combined prediction model matched with the target type is obtained by training a preset combined prediction model according to historical power load sample data of the target type;
the preset combined prediction model is obtained by combining at least two single prediction models.
3. The method of claim 2, wherein the combined predicted value is a single predicted value output to each single prediction model in the combined prediction model, and is obtained by combining according to a combination algorithm.
4. The method of claim 3, wherein the single predictive model comprises a ridge regression model, a catboost model, and a light gradient elevator model;
the combination algorithm is an equal-weight combination algorithm.
5. The method of claim 2, wherein the training process of the combined predictive model matched with the target type comprises:
acquiring historical power load sample data of a target type, wherein the historical power load sample data comprises a historical power load sample value, seasonal data and date data matched with the historical power load sample value;
dividing historical power load sample data into a training set, a test set and a verification set;
training a preset combined prediction model according to the historical power load sample data of the first time period and the historical power load sample data of the second time period in the training set;
wherein the first time period is earlier than the second time period;
and testing the combined prediction model according to the test set, and verifying the combined prediction model according to the verification set until the test result and the verification result both meet the training success condition.
6. The method of claim 5, further comprising, after obtaining historical power load sample data for a target type:
missing value filling processing is carried out on historical power load sample data;
and carrying out data standardization processing on the historical power load sample data after the missing value is filled.
7. The method of claim 1, wherein aggregating the combined forecasted values matching each target type to obtain a forecasted electrical load value comprises:
taking the sum of products of the combined predicted value matched with each target type and the weight matched with each target type as a predicted electric load value;
wherein the weights matched with the target types are the same or different.
8. An apparatus for predicting an electrical load, comprising:
the historical power consumption load data acquisition module is used for acquiring historical power consumption load data of a target type;
wherein the target types comprise industrial electricity, commercial electricity and residential electricity, and the historical electricity load data comprises historical electricity load values and seasonal data and date data matched with the historical electricity load values;
the target type combined predicted value acquisition module is used for respectively inputting the historical load electricity consumption data of each target type into combined prediction models matched with each target type and acquiring combined predicted values matched with each target type and output by each combined prediction model;
and the predicted electric load value acquisition module is used for summarizing the combined predicted values matched with the target types to obtain the predicted electric load value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of predicting electrical load according to any one of claims 1 to 7 when executing said program.
10. A storage medium storing computer-executable instructions for performing the method of predicting electrical load according to any one of claims 1 to 7 when executed by a computer processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210906096.2A CN115034519A (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting power load, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210906096.2A CN115034519A (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting power load, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115034519A true CN115034519A (en) | 2022-09-09 |
Family
ID=83130489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210906096.2A Pending CN115034519A (en) | 2022-07-29 | 2022-07-29 | Method and device for predicting power load, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115034519A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115186944A (en) * | 2022-09-15 | 2022-10-14 | 合肥优晟电力科技有限公司 | Urban power distribution network planning method and system |
| CN115758255A (en) * | 2023-01-10 | 2023-03-07 | 佰聆数据股份有限公司 | Electricity consumption abnormal behavior analysis method and device under fusion model |
| CN117353300A (en) * | 2023-12-04 | 2024-01-05 | 拓锐科技有限公司 | Rural power consumption demand analysis method based on big data |
| CN117436935A (en) * | 2023-11-30 | 2024-01-23 | 湖北华中电力科技开发有限责任公司 | Regional power consumption prediction method, regional power consumption prediction system, computer equipment and storage medium |
-
2022
- 2022-07-29 CN CN202210906096.2A patent/CN115034519A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115186944A (en) * | 2022-09-15 | 2022-10-14 | 合肥优晟电力科技有限公司 | Urban power distribution network planning method and system |
| CN115758255A (en) * | 2023-01-10 | 2023-03-07 | 佰聆数据股份有限公司 | Electricity consumption abnormal behavior analysis method and device under fusion model |
| CN115758255B (en) * | 2023-01-10 | 2023-05-05 | 佰聆数据股份有限公司 | Power consumption abnormal behavior analysis method and device under fusion model |
| CN117436935A (en) * | 2023-11-30 | 2024-01-23 | 湖北华中电力科技开发有限责任公司 | Regional power consumption prediction method, regional power consumption prediction system, computer equipment and storage medium |
| CN117353300A (en) * | 2023-12-04 | 2024-01-05 | 拓锐科技有限公司 | Rural power consumption demand analysis method based on big data |
| CN117353300B (en) * | 2023-12-04 | 2024-02-23 | 拓锐科技有限公司 | Rural power consumption demand analysis method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| CN111198799A (en) | Machine room power consumption early warning method, system, terminal and storage medium based on LSTM | |
| CN110391840B (en) | Method and system for judging abnormality of telemetry parameters of sun synchronous orbit satellite | |
| CN112418921A (en) | Power demand prediction method, device, system and computer storage medium | |
| US20240037677A1 (en) | Method for power consumption analysis and troubleshooting of production line based on industrial internet of things, system and storage medium thereof | |
| CN112907062A (en) | Power grid electric quantity prediction method, device, medium and terminal integrating temperature characteristics | |
| CN111709548A (en) | Power consumer load prediction method, device, equipment and storage medium based on support vector machine | |
| CN112819258A (en) | Bank branch to store customer quantity prediction method and device | |
| CN114548756A (en) | Comprehensive benefit evaluation method and device for comprehensive energy project based on principal component analysis | |
| CN113743661A (en) | Method, system, equipment and storage medium for predicting online capacity of lithium ion battery | |
| CN112506619A (en) | Job processing method, apparatus, electronic device, storage medium, and program product | |
| CN103646670A (en) | Method and device for evaluating performances of storage system | |
| CN112801374B (en) | Model training method, power load prediction method, device and equipment | |
| CN116757650B (en) | Project management and resource scheduling method based on machine learning | |
| CN116706884A (en) | Photovoltaic power generation amount prediction method, device, terminal and storage medium | |
| CN116073340A (en) | Relay protection constant value list generation method and device under source-load interaction scene | |
| CN113434690B (en) | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium | |
| CN115907391A (en) | Scheduling method and system for electric energy meter verification task | |
| CN113973339B (en) | Load coordination method and device for 4G cell and 5G cell and computer storage medium | |
| Peralta et al. | Unit commitment with load uncertainty by joint chance-constrained programming | |
| CN113742187A (en) | Capacity prediction method, device, equipment and storage medium of application system | |
| CN112330009A (en) | Power grid load prediction method | |
| CN110781540A (en) | Design scheme analysis method and device, storage medium and computer equipment | |
| CN112418509A (en) | Task data prediction method and device, storage medium and electronic device | |
| CN110942195A (en) | Power load prediction method and device |
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 |