CN115438832A - Gas load prediction method and system during holidays - Google Patents
Gas load prediction method and system during holidays Download PDFInfo
- Publication number
- CN115438832A CN115438832A CN202210859315.6A CN202210859315A CN115438832A CN 115438832 A CN115438832 A CN 115438832A CN 202210859315 A CN202210859315 A CN 202210859315A CN 115438832 A CN115438832 A CN 115438832A
- Authority
- CN
- China
- Prior art keywords
- load
- air temperature
- holiday
- data
- gas
- 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 37
- 238000012549 training Methods 0.000 claims abstract description 38
- 230000000694 effects Effects 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 23
- 238000010586 diagram Methods 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 8
- 239000007789 gas Substances 0.000 description 80
- 230000006870 function Effects 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 239000002737 fuel gas Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a gas load prediction method and a gas load prediction system during holidays, which belong to the technical field of energy load prediction and comprise the following steps: acquiring air temperature data of a target holiday period of a region to be predicted; and processing the acquired air temperature data of the target holiday period of the region to be predicted by using a pre-trained load prediction model to obtain a gas load result of the target holiday period of the region to be predicted. According to the method, the relationship among the gas temperature, the holiday and the load is obtained by calculating the load difference between the holiday period and the non-holiday period according to the change conditions of the gas temperature and the gas load and training by using a machine learning algorithm under the condition that specific quantitative parameters of the holiday effect are not needed, so that the prediction error caused by the slippage of the lunar calendar holiday on the Gregorian calendar date is effectively reduced, the regional limitation is avoided, the corresponding result can be obtained only by inputting data of different regions, the universality is high, the precision of the prediction result is high, and the precision requirement of load prediction can be well met.
Description
Technical Field
The invention relates to the technical field of energy load prediction, in particular to a gas load prediction method and system during holidays.
Background
The gas load prediction is made for policies, gas supply guarantee is achieved, economic benefits are improved, and reasonable management of a gas pipe network is achieved. The gas has wide application in people's life, especially in winter in cold areas, the gas consumption for heat supply is relatively large, and is closely related to the change of air temperature. The production organization of industrial enterprises and the living and going-out habits of social groups are changed in holidays, the consumption and supply requirements of the fuel gas are changed, and the requirement for accurate prediction is provided for the response of a fuel gas supply side. During the legal public holiday period of the lunar calendar, the influence of holidays and living customs exists, the production, management and personnel flow change of enterprises is large, and the short-term gas load is uncertain due to the superposed temperature change in northern cold regions.
The gas load is a time sequence array, the slippage of the traditional holiday on a historical date causes the expected slippage of the whole gas consumption during the holiday, the gas consumption during the same holiday in adjacent years is different along with the change of the solar terms and the air temperature, and the current prediction mostly takes the historical date as a time sequence reference and depends on the experience of the same period of the historical years to predict, thus causing the deviation of the prediction result. On the other hand, holidays have a great influence on actual gas use, and the effect is next to the air temperature. However, the attribute of the holiday is a qualitative parameter, and the influence of the lunar calendar holiday on the gas load is difficult to analyze due to the lack of a sufficient quantification method.
Disclosure of Invention
The present invention is directed to a method and a system for predicting gas load during holidays based on lunar calendar dates, so as to solve at least one of the technical problems in the background art.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides a gas load prediction method during holidays, which comprises the following steps:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the region to be predicted during the historical holidays and labels marking the gas loads corresponding to the air temperature data during the historical holidays.
Preferably, training the load prediction model comprises:
selecting historical gas load and gas temperature data of an area to be predicted, and dividing the historical gas load and gas temperature data into a data set with all holidays removed and a target holiday data set;
drawing a scatter diagram of the air temperature data and the gas load in the data set by using the data set with all the holidays removed to obtain a functional relation between the air temperature and the gas load;
establishing a regression equation of the gas load and the air temperature by using the data set with all holidays removed, and determining coefficients of all parts in the equation;
inputting the air temperature data of the target holiday into a regression equation, calculating to obtain a group of load data, and calculating a residual error between the group of load data and actual gas load data;
and establishing a prediction model by adopting a BP neural network algorithm in machine learning, taking the air temperature data and residual error data of a target holiday as model input, taking an actual gas load as network output, training a network, and adjusting network parameters to obtain the load prediction model.
Preferably, a data set excluding all holidays is used, and a scatter diagram is drawn on the air temperature data and the gas load in the data set so as to analyze the functional relation between the air temperature and the load; and establishing a model according to the functional relation between the air temperature and the load.
Preferably, the load data and the temperature data of the historical target holiday are input into the model established according to the functional relationship between the temperature and the load, the calculation result is the load at the temperature during the holiday, and the difference value is calculated from the actual load, and the difference value is the influence of the holiday effect on the gas load.
Preferably, a prediction model is established by adopting a BP neural network in machine learning, the load difference and air temperature data are input into the BP neural network prediction model by utilizing the excellent processing capacity of the BP neural network on complex nonlinear mapping, and the actual gas load is used as an output set to train the network.
Preferably, the data of the last year corresponding to the target holiday is used as a test set, the air temperature data and the residual value are input into the trained network model to obtain a prediction result, the prediction result is compared with an actual value, and the network parameters are adjusted according to errors.
In a second aspect, the present invention provides a gas load prediction system during holidays, comprising:
the acquisition module is used for acquiring air temperature data of a target holiday period of a region to be predicted;
the prediction module is used for processing the acquired air temperature data of the region to be predicted during the target holiday period by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday period; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the region to be predicted during the historical holidays and labels marking the gas loads corresponding to the air temperature data during the historical holidays.
In a third aspect, the invention provides a non-transitory computer readable storage medium for storing computer instructions which, when executed by a processor, implement a method of gas load prediction during holidays as described above.
In a fourth aspect, the invention provides a computer program product comprising a computer program for implementing a gas load prediction method during holidays as described above, when the computer program is run on one or more processors.
In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected to the memory, the computer program being stored in the memory, the processor executing the computer program stored in the memory when the electronic device is running, to cause the electronic device to execute instructions implementing the gas load prediction method during holidays as described above.
The invention has the beneficial effects that: the method has a good effect on the system analysis of the influence of the lunar calendar holidays on the load, is deeply explored from the perspective of basic data, obtains the relation among the air temperature, the holidays and the load through a large amount of data training by calculating the load difference between the holidays and the non-holidays according to the change conditions of the air temperature and the gas load and utilizing a machine learning algorithm under the condition of not needing specific quantitative parameters of the holiday effect, avoids errors caused by the fact that empirical quantitative values are adopted for the holiday effect in the traditional prediction, effectively reduces the prediction errors caused by the slippage of the lunar calendar holidays on the holidays, has no region limitation, can obtain corresponding results only by inputting data of different regions, is high in universality and high in prediction result precision, and can better meet the precision requirement of load prediction.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a holiday gas load prediction method based on a lunar calendar according to an embodiment of the present invention.
Fig. 2 is a scatter plot of gas load data and air temperature data according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by way of the drawings are illustrative only and are not to be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the description of the specification, reference to the description of "one embodiment," "some embodiments," "an example," "a specific example," or "some examples" or the like means 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. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the purpose of facilitating an understanding of the present invention, the present invention will be further explained by way of specific embodiments with reference to the accompanying drawings, which are not intended to limit the present invention.
It will be appreciated by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements in the drawings are not necessarily required to practice the present invention.
Example 1
The present embodiment 1 provides a gas load prediction system during holidays, including:
the acquisition module is used for acquiring air temperature data of a target holiday period of a region to be predicted;
the prediction module is used for processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the region to be predicted during the historical holidays and labels marking the gas loads corresponding to the air temperature data during the historical holidays.
In embodiment 1, the above system is used to implement a method for predicting gas load during holidays, which includes:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the region to be predicted during the historical holidays and labels marking the gas loads corresponding to the air temperature data during the historical holidays.
Training the load prediction model, comprising:
selecting historical gas load and gas temperature data of a region to be predicted, and dividing the historical gas load and gas temperature data into a data set excluding all holidays and a target holiday data set;
drawing a scatter diagram of air temperature data and gas load in a data set by using the data set without all holidays to obtain a functional relation between the air temperature and the gas load;
establishing a regression equation of the gas load and the air temperature by using the data set with all holidays removed, and determining coefficients of all parts in the equation;
inputting the air temperature data of the target holiday into a regression equation, calculating to obtain a group of load data, and calculating a residual error between the group of load data and actual gas load data;
and establishing a prediction model by adopting a BP neural network algorithm in machine learning, taking temperature data and residual error data of a target holiday as model input, taking an actual gas load as network output, training the network, and adjusting network parameters to obtain the load prediction model.
Using a data set with all holidays removed, drawing a scatter diagram of the air temperature data and the gas load in the data set to analyze the functional relation between the air temperature and the load; and establishing a model according to the functional relation between the air temperature and the load.
The load data and the air temperature data of the historical target holiday are input into the model established according to the functional relation between the air temperature and the load, the calculated result is the load under the air temperature during the holiday, and the difference value is calculated with the actual load, and the difference value is the influence of the holiday effect on the gas load. A prediction model is established by adopting a BP neural network in machine learning, the load difference value and air temperature data are input into the BP neural network prediction model by utilizing the excellent processing capacity of the BP neural network on complex nonlinear mapping, and the actual gas load is used as an output set to train a network. And taking the data of the last year corresponding to the target holiday as a test set, inputting the air temperature data and the residual error value into the trained network model to obtain a prediction result, comparing the prediction result with an actual value, and adjusting the network parameters according to errors.
Example 2
The embodiment 2 provides a holiday load prediction method based on a lunar calendar date, which comprises the following steps:
step 1: selecting gas load and gas temperature data of a prediction region (n-1) year as historical data, and dividing the historical data into a data set with all holidays removed and a data set during a spring festival;
step 2: drawing a scatter diagram of the air temperature and the gas load of the data by using the data after the elimination of the holiday days to obtain a functional relation between the air temperature and the gas load;
and step 3: establishing a regression equation of the gas load and the air temperature according to the data of the removed holiday part of the (n-1) year, determining coefficients of all parts in the equation, and verifying the fitting effect of the equation;
and 4, step 4: inputting the air temperature data in the spring festival of (n-1) year into an equation, calculating to obtain a group of load data, and calculating the residual error between the load data and the actual gas load;
and 5: establishing a prediction model by adopting a BP neural network algorithm in machine learning, taking temperature data and residual error data in the spring festival of (n-1) as model input, taking actual gas load as network output, and training a network;
step 6: and taking data in the spring festival of the nth year as a test set, inputting the air temperature data and the residual error value into the trained network model to obtain a prediction result, comparing the prediction result with an actual value, and adjusting network parameters according to errors.
In this embodiment 2, the step 1 includes:
the reason for selecting the gas load data and the air temperature data of (n-1) year as historical data is that the data of the nth year is used for verifying and predicting results of the test set, and the larger the value of n is, the more the establishment of the subsequent equation and the accuracy of the prediction results are improved;
the data is divided according to the principle that the elimination of all holiday data is to remove the load data of all holidays in the whole year, remove holiday influence effects from the data and highlight the influence of air temperature and gas load;
the data of the spring festival period selected in the step 1 is influenced by the properties of the air temperature and the holiday and the air consumption peak of the heating period at the time, so that the prediction significance is great. The spring festival period referred to here is from thirty-thirty lunar calendar to six beginner of the lunar calendar, and the spring festival holiday is determined by the national law, and the festival holiday effect is the most obvious in the period.
The step 2 comprises the following steps:
the data of the removed holidays most influencing the gas load is the temperature factor, in order to explain the relationship between the temperature and the load, a scatter diagram is drawn by the temperature factor and the load factor to analyze the functional relationship between the temperature and the load, and the function is marked as y = f (x), wherein: z is the load data of the removed holidays, and x is the temperature data corresponding to the load date.
A scatter diagram is drawn on the gas load data and the gas temperature data which are selected by the embodiment and are removed from all holidays, and an exponential function relational expression is obtained as shown in fig. 2 y ＝a×ex p (bx) according to the formula
Calculating the fitting effect of the data under the exponential function relationship, and calculating to obtain R 2 Is 0.85, which shows that the fitting effect of the current data under the exponential function relation is better.
The step 3 comprises the following steps:
a regression equation with the air temperature as an independent variable is established, and a variable coefficient is trained by adopting historical data, wherein the more data, the more accurate the coefficient is.
The step 4 comprises the following steps:
inputting the air temperature data of the spring festival period divided in the step 1 into an equation, and calculating the result as the load y under the air temperature during the holiday ij (i = thirty wintery, early first one in true moon.,. First six in true moon,. J =1, 2.. N-1), which shows that the load result is calculated according to the air temperature during the spring festival without the influence of the holidays, the actual load value includes the holiday influence effect, and the difference value is calculated from the actual load, and the calculation formula is as follows: Δ y ij ＝Y ij -y ij The difference includes the influence of the holiday and festival effect on the gas load.
The step 5 comprises the following steps:
as the attribute of the holiday and the festival is a qualitative parameter and cannot be input in a numerical form, the empirical quantitative value of the holiday and the festival is inaccurate, and the functional relationship between the holiday and the load is unknown, a model is established by adopting a BP neural network with excellent performance for processing complex nonlinear mapping, and the air temperature data t during the spring festival of (n-1) year is subjected to the model establishment by adopting a machine learning algorithm ij And Δ y ij As input set, actual gas load Y ij As an output set, the network is trained.
Because the holidays are qualitative parameters, an effective quantification method for the holidays is lacked at present, most of the traditional predictions select an empirical quantification value for holiday effects, the influence of the holidays on loads is difficult to analyze, and prediction errors are easily caused. By calculating the load changes of different date attributes at a uniform temperature, the holiday effect is embodied in the form of a load change difference. In order to better analyze the relationship among the holidays, the air temperature and the load, a machine learning algorithm BP neural network with excellent performance for processing nonlinear mapping is adopted as a prediction model, under the condition that holiday parameters are not required to be quantized, the load difference value is used as the embodiment of the holiday effect, and the optimal prediction model is obtained through training of a large amount of historical data.
The step 6 comprises the following steps:
inputting the temperature data and the load difference value of the nth year into the trained BP neural network model to obtain a load predicted value during the spring festival of the nth year, calculating the error between the predicted value and the actual value, and adjusting the parameters of the neural network according to the error condition to enable the predicted result to be more accurate.
Compared with the prior art, the lunar calendar date-based holiday period load prediction method has a good effect on the system analysis of the influence of the lunar calendar holiday on the load, is deeply explored from the perspective of basic data, calculates the load difference between the holiday and the non-holiday period according to the change condition of the air temperature and the gas load, and obtains the relation among the air temperature, the holiday and the load through mass data training by utilizing a machine learning algorithm under the condition that specific quantitative parameters of the holiday effect are not needed, so that the error caused by the fact that an empirical quantitative value is adopted for the holiday effect in the traditional prediction is avoided, the prediction error caused by the slippage of the lunar calendar holiday on the holiday in the lunar calendar date is effectively reduced, the method is free of regional limitation, corresponding results can be obtained only by inputting data of different regions, the universality is high, the prediction effect is improved in precision compared with other prediction methods, and the requirement on the precision of load prediction can be better met.
Example 3
Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium for storing computer instructions, which when executed by a processor, implement a gas load prediction method during holidays, the method including:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the area to be predicted during a historical holiday and a label marking a gas load corresponding to the air temperature data during the historical holiday.
Example 4
An embodiment 4 of the present invention provides a computer program (product) comprising a computer program for implementing, when running on one or more processors, a method of gas load prediction during holidays, the method comprising:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the area to be predicted during a historical holiday and a label marking a gas load corresponding to the air temperature data during the historical holiday.
Example 5
An embodiment 5 of the present invention provides an electronic device, including: a processor, a memory, and a computer program; wherein a processor is coupled to the memory, a computer program is stored in the memory, and the processor executes the computer program stored in the memory when the electronic device is running to cause the electronic device to execute instructions to implement a method of gas load prediction during holidays, the method comprising:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the area to be predicted during a historical holiday and a label marking a gas load corresponding to the air temperature data during the historical holiday.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts based on the technical solutions disclosed in the present invention.
Claims (10)
1. A gas load prediction method during holidays is characterized by comprising the following steps:
acquiring air temperature data of a target holiday period of a region to be predicted;
processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the area to be predicted during a historical holiday and a label marking a gas load corresponding to the air temperature data during the historical holiday.
2. The method of gas load prediction during holidays of claim 1 wherein training the load prediction model comprises:
selecting historical gas load and gas temperature data of a region to be predicted, and dividing the historical gas load and gas temperature data into a data set excluding all holidays and a target holiday data set;
drawing a scatter diagram of the air temperature data and the gas load in the data set by using the data set with all the holidays removed to obtain a functional relation between the air temperature and the gas load;
establishing a regression equation of the gas load and the air temperature by using the data set without all holidays, and determining coefficients of all parts in the equation;
inputting the air temperature data of the target holiday into a regression equation, calculating to obtain a group of load data, and calculating a residual error between the group of load data and actual gas load data;
and establishing a prediction model by adopting a BP neural network algorithm in machine learning, taking the air temperature data and residual error data of a target holiday as model input, taking an actual gas load as network output, training a network, and adjusting network parameters to obtain the load prediction model.
3. The method of claim 2, wherein a data set excluding all holidays is used, and the temperature data and the gas load in the data set are plotted as a scatter plot to analyze the functional relationship between temperature and load; and establishing a model according to the functional relation between the air temperature and the load.
4. The method for predicting a gas load during a holiday according to claim 2, wherein the load data and the air temperature data of a historical target holiday are inputted to the model created from the functional relationship between the air temperature and the load, the load at the air temperature during the holiday is calculated as a result of the calculation, and a difference is calculated from the actual load, and the difference is an influence of the holiday effect on the gas load.
5. The method of claim 4, wherein a BP neural network in machine learning is used to build a prediction model, and the load difference and air temperature data are input into the BP neural network prediction model using its excellent processing ability for complex nonlinear mapping, and the actual gas load is used as an output set to train the network.
6. The method of claim 4, wherein the data of the previous year corresponding to the target holiday is used as a test set, the temperature data and the residual error value are input into the trained network model to obtain a prediction result, the prediction result is compared with an actual value, and the network parameters are adjusted according to errors.
7. A gas load prediction system during holidays, comprising:
the acquisition module is used for acquiring air temperature data of a target holiday period of a region to be predicted;
the prediction module is used for processing the acquired air temperature data of the region to be predicted during the target holiday by using a pre-trained load prediction model to obtain a gas load result of the region to be predicted during the target holiday; the pre-trained load prediction model is obtained by training by using a training set, wherein the training set comprises air temperature data of the region to be predicted during the historical holidays and labels marking the gas loads corresponding to the air temperature data during the historical holidays.
8. A non-transitory computer-readable storage medium for storing computer instructions which, when executed by a processor, implement the method of gas load prediction during holidays as recited in any of claims 1-6.
9. A computer program product, comprising a computer program for implementing a method of gas load prediction during holidays as claimed in any one of claims 1-6 when run on one or more processors.
10. An electronic device, comprising: a processor, a memory, and a computer program; wherein a processor is connected to the memory, a computer program is stored in the memory, and the processor executes the computer program stored in the memory when the electronic device is running, to cause the electronic device to execute instructions implementing the gas load prediction method during holidays as claimed in any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859315.6A CN115438832A (en) | 2022-07-21 | 2022-07-21 | Gas load prediction method and system during holidays |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859315.6A CN115438832A (en) | 2022-07-21 | 2022-07-21 | Gas load prediction method and system during holidays |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115438832A true CN115438832A (en) | 2022-12-06 |
Family
ID=84240847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210859315.6A Pending CN115438832A (en) | 2022-07-21 | 2022-07-21 | Gas load prediction method and system during holidays |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115438832A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742263A (en) * | 2022-03-02 | 2022-07-12 | 北京百度网讯科技有限公司 | Load prediction method, load prediction device, electronic device, and storage medium |
-
2022
- 2022-07-21 CN CN202210859315.6A patent/CN115438832A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114742263A (en) * | 2022-03-02 | 2022-07-12 | 北京百度网讯科技有限公司 | Load prediction method, load prediction device, electronic device, and storage medium |
| CN114742263B (en) * | 2022-03-02 | 2024-03-01 | 北京百度网讯科技有限公司 | Load prediction method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111144286A (en) | Urban PM2.5 concentration prediction method fusing EMD and LSTM | |
| CN111079989B (en) | DWT-PCA-LSTM-based water supply amount prediction device for water supply company | |
| CN112001439A (en) | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment | |
| CN110210993B (en) | Urban short-term gas load prediction method based on cyclic neural network model | |
| CN111563610A (en) | LSTM neural network-based building electrical load comprehensive prediction method and system | |
| CN111639783A (en) | Line loss prediction method and system based on LSTM neural network | |
| CN112990587B (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| CN111476677A (en) | Big data-based electricity consumption type electricity sales quantity analysis and prediction method and system | |
| Li et al. | A k-nearest neighbor locally weighted regression method for short-term traffic flow forecasting | |
| CN107085371A (en) | Crude(oil)unit economic model forecast control method based on data-driven | |
| CN103699947A (en) | Meta learning-based combined prediction method for time-varying nonlinear load of electrical power system | |
| CN115438832A (en) | Gas load prediction method and system during holidays | |
| CN114862032B (en) | XGBoost-LSTM-based power grid load prediction method and device | |
| Sanyal et al. | Simulation and big data challenges in tuning building energy models | |
| CN112801388B (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN114581141A (en) | Short-term load prediction method based on feature selection and LSSVR | |
| CN114091776A (en) | K-means-based multi-branch AGCNN short-term power load prediction method | |
| CN116826745A (en) | Layered and partitioned short-term load prediction method and system in power system background | |
| CN117277312A (en) | Gray correlation analysis-based power load influence factor method and equipment | |
| CN116048023B (en) | Fine energy management and control method, system, internet of things cloud management and control server and storage medium thereof | |
| CN110276478B (en) | Short-term wind power prediction method based on segmented ant colony algorithm optimization SVM | |
| Wang et al. | Cloud computing and extreme learning machine for a distributed energy consumption forecasting in equipment-manufacturing enterprises | |
| CN115759469A (en) | Method and device for predicting peak load and occurrence time thereof | |
| CN110909492A (en) | Sewage treatment process soft measurement method based on extreme gradient lifting algorithm | |
| CN115619447A (en) | Monthly electricity sales combined prediction method, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |