CN112614006A - Load prediction method, device, computer readable storage medium and processor - Google Patents
Load prediction method, device, computer readable storage medium and processor Download PDFInfo
- Publication number
- CN112614006A CN112614006A CN202011376905.0A CN202011376905A CN112614006A CN 112614006 A CN112614006 A CN 112614006A CN 202011376905 A CN202011376905 A CN 202011376905A CN 112614006 A CN112614006 A CN 112614006A
- Authority
- CN
- China
- Prior art keywords
- load
- variable
- data
- day
- derivative
- 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 40
- 230000008859 change Effects 0.000 claims abstract description 20
- 238000010801 machine learning Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 27
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 13
- 230000000875 corresponding effect Effects 0.000 description 49
- 238000004422 calculation algorithm Methods 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 11
- 230000005611 electricity Effects 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000002203 pretreatment Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000003245 coal Substances 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000015654 memory Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005485 electric heating Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- 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"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Human Resources & Organizations (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a load prediction method, a load prediction device, a computer readable storage medium and a processor. Wherein, the method comprises the following steps: determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve; inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: variables and the load to which the variables correspond. The invention solves the technical problem of low load prediction precision in the prior art by adopting the traditional load prediction method.
Description
Technical Field
The present invention relates to the field of load prediction technologies, and in particular, to a load prediction method, an apparatus, a computer-readable storage medium, and a processor.
Background
In recent years, with the gradual expansion of the scale of the users of 'coal to electricity', the supply of power load plays an increasingly important role in 'coal to electricity' engineering, which also puts higher demands on the power grid. The stable and uninterrupted high-quality electric energy provides guarantee for industrial and even social stable operation, so that a reasonable scheduling scheme needs to be formulated, the power load prediction plays an important role in the process, the correct prediction of the power load prediction plays an important role in the normal operation of a power system, a machine learning load prediction technology represented by a Long Short-Term Memory (LSTM) algorithm is widely applied to the power industry, the load prediction requirement is accurate, and a certain scale is formed.
The load prediction technology determines load data at a certain future moment according to a plurality of factors such as the operating characteristics, capacity increasing decision, natural conditions, social influence and the like of a system under the condition of meeting a certain precision requirement, namely, the future value of the power load is estimated according to the past and the present of the power load. However, the load data has the characteristics of time sequence, nonlinearity, uncertainty and the like, the traditional load prediction technology cannot well represent the rule and the requirement of the load data, and the high-precision load prediction can be realized only by adopting the artificial intelligence load prediction technology.
Although, with the continuous maturity and popularization and application of the machine learning prediction technology, many industries such as real estate, finance, internet and the like adopt a machine learning algorithm to perform business modeling, and deal with practical problems. But have been applied to a somewhat lesser extent to the problems associated with coal-to-electricity conversion. The traditional load prediction method generally adopts time series or regression analysis to predict the load, does not consider the characteristics of nonlinearity and uncertainty of load data, is influenced by complex internal and external environments, and cannot well represent the rule of the load data, so that the accuracy of power load prediction is low. For the problem of low load prediction accuracy, the load data is modified by adopting the load mean value of adjacent moments in combination with the historical load data to predict the load again, but the effect is very little.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a load prediction method, a load prediction device, a computer readable storage medium and a processor, which are used for at least solving the technical problem of low predicted load precision of a traditional load prediction method in the related art.
According to an aspect of an embodiment of the present invention, there is provided a load prediction method, including: determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve; inputting the target variable into the load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: a variable and a load corresponding to the variable.
Optionally, before determining the target variable affecting the predicted daily load based on the correlation coefficient and the load trend curve, the method further comprises: acquiring power load data; preprocessing the power load data to obtain preprocessed power load data; and determining an original variable and a derivative variable corresponding to the original variable based on the preprocessed power load data.
Optionally, the pre-treatment comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
Optionally, determining the original variable and the derivative variable corresponding to the original variable includes: under the condition that the original variable is the temperature, the derivative variable corresponding to the temperature is the load value at t-1, t and t +1 moments before the prediction day of one week; under the condition that the original variable is humidity, the derivative variable corresponding to the humidity is the load value of the moment t-1, t and t +1 before the forecast day; under the condition that the original variable is the number of users, the derivative variable corresponding to the number of users is the load value at t-1, t and t +1 days before the forecast day; under the condition that the original variable is the day type, the derivative variable corresponding to the day type is the load values at t-1, t and t +1 moments three days before the forecast day; under the condition that the original variable is the row identifier, the derivative variables corresponding to the row identifier are predicted before one quarter of a day t, two quarters of a day and three quarters of a day; and if the original variable is the week category, the derivative variable corresponding to the week category is null.
According to another aspect of the embodiments of the present invention, there is also provided a load prediction apparatus, including: the first determination module is used for determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve; a processing module, configured to input the target variable into the load prediction model to obtain a predicted daily load corresponding to the target variable, where the load prediction model is obtained by using multiple sets of data through machine learning training, and each set of data in the multiple sets of data includes: a variable and a load corresponding to the variable.
Optionally, the apparatus further comprises: the acquisition module is used for acquiring the electric load data before determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve; the preprocessing module is used for preprocessing the power load data to obtain preprocessed power load data; and the second determination module is used for determining an original variable and a derivative variable corresponding to the original variable based on the preprocessed power load data.
Optionally, the pre-treatment comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
Optionally, the second determining module includes: the first processing subunit is used for, under the condition that the original variable is the temperature, obtaining the load values of t-1, t and t +1 moments before the prediction day and a week by the derivative variable corresponding to the temperature; the second processing subunit is used for, under the condition that the original variable is humidity, obtaining the load values of t-1, t and t +1 moments before the prediction day by using the derivative variables corresponding to the humidity; the third processing subunit is configured to, when the original variable is the number of users, determine that the derivative variable corresponding to the number of users is a load value at a time t-1, t +1 two days before the prediction day; the fourth processing subunit is used for, under the condition that the original variable is the day type, determining the derived variable corresponding to the day type to be the load values at t-1, t and t +1 three days before the forecast day; a fifth processing subunit, configured to, if the original variable is a row identifier, determine that the derived variables corresponding to the row identifier are one quarter hour before, two quarter hours before, and three quarter hours before the predicted time t; and the sixth processing subunit is configured to, if the original variable is the week category, leave the derived variable corresponding to the week category.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the load prediction method described in any one of the above.
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program executes to perform the load prediction method described in any one of the above.
In the embodiment of the invention, a target variable influencing the predicted daily load is determined based on the correlation coefficient and the load trend change curve; inputting the target variable into the load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: the variable and the load corresponding to the variable are used for identifying the predicted daily load corresponding to the target variable through the load prediction model, so that the purpose of rapidly predicting the load value of the future time period is achieved, the technical effect of improving the load prediction accuracy is achieved, and the technical problem that the load prediction precision is low in the conventional load prediction method in the related technology is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a method of load prediction according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a load prediction apparatus according to an 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 sequences other 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 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a load prediction method, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a load prediction method according to an embodiment of the present invention, as shown in fig. 1, the load prediction method includes the steps of:
step S102, determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve;
the target variables include, but are not limited to, humidity, temperature, number of users, day type, etc.
As an alternative embodiment, the variation trend between different variables and the load can be identified according to the load trend variation curve. For example, observing the data characteristics of the data source A, the user load variation trend has a relatively obvious periodicity. The early 8 o 'clock to the late 8 o' clock is a flat section, and the late 8 o 'clock to the early 8 o' clock is a valley section. During the flat section, electric heating power load descends gradually, and during the valley section, because valley section coal changes the user into electricity and has the price of electricity subsidy, when the price of electricity was 0.1 yuan/kilowatt after the subsidy, the power load can be higher, and the power load of electric heating equipment can rise gradually, and the fluctuation trend of power load daily is similar, has certain deviation on the peak value. And observing the data characteristics of the data source B, wherein the user load presents an obvious reverse relation with the variable A and presents a forward relation with the variable B, and the data characteristics conform to the actual change rule.
As an alternative embodiment, the important factors influencing the load prediction can be known according to the correlation coefficient. And determining factors influencing the load by means of correlation analysis and combination of related service conditions. The correlation analysis is used for checking whether the variables are correlated or not, researching the quantity of linear correlation degree between the variables and accurately displaying the correlation between the two variables. And calculating the correlation coefficient of each variable by using the Pearson correlation coefficient.
For a given two continuous variablesxAndythe pearson correlation coefficient ρ is defined as:
generally, if the correlation coefficient is greater than 0.5, a strong correlation exists between the variables, but the correlation is not the only criterion, and the influence of the actual business situation and the actual influence situation of the variables on the screening of the key variables is also one of the selected criteria.
Through correlation analysis, the outdoor temperature, the humidity, the number of users, the day type, the load values of the moments t-1, t and t +1 before the predicted day one week, the load values of the moments t-1, t and t +1 before the predicted day one day, the load values of the moments t-1, t and t +1 before the predicted day two days, the load values of the moments t-1, t and t +1 before the predicted day three days, the correlation coefficients of the indexes and the loads before the predicted day t moment, two quarter minutes and three quarter minutes are higher, and the correlation coefficients show that the indexes influence the accuracy of load prediction.
Step S104, inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: variables and the load to which the variables correspond.
The load prediction model is based on an LSTM algorithm model, and can be combined with selected factors influencing load prediction and historical load data to construct a prediction model based on the LSTM algorithm to predict short-term and medium-term loads.
As an alternative embodiment, the LSTM algorithm model can be established by the following steps:
(1) and acquiring characteristic data influencing the load, preprocessing the data, and dividing the data into a training set and a test set.
(2) And selecting a final model input variable based on the correlation coefficient analysis and the load trend change curve analysis.
(3) Setting initial values of parameters of an input layer, a hidden layer and an output layer of the prediction model of the LSTM algorithm, and an objective function and an optimizer of the prediction model.
(4) And (3) performing short-term and medium-term load prediction on the user load by using a short-term and medium-term load prediction model based on an LSTM algorithm prediction model, and calculating a prediction error by adopting an average absolute percentage error.
(5) And adjusting and optimizing the load prediction accuracy and applying the load prediction accuracy.
In addition, based on the LSTM algorithm, a better model can be trained by using a large amount of user load data. And obtaining a model which can be deployed and applied by a large amount of data iterative optimization model. The data processing is carried out in the early stage of data input, dirty data and data with small information amount are deleted, and the data calculation quality is guaranteed. Based on the trained model, the load value of the future time period can be predicted quickly. Compared with the traditional method, the load value of the future time period is manually deduced, and a big data technology and a machine learning algorithm are adopted, so that the load result is more accurate, and meanwhile, the method also supports other researches.
It should be noted that the dirty data includes data that is not within the specified range or has no meaning to the service, or the data format is illegal, and there is irregular coding and ambiguous service logic in the source system.
As an optional embodiment, the load data can be deeply mined by combining a big data technology on the basis of realizing the service requirement, the reasons of abnormality and loss of the load data are mined, and the change rule of the load data is found. And determining main factors influencing the load prediction precision by adopting correlation analysis and combining with the load data change rule. A short-term and medium-term load prediction model is determined through a mainstream machine learning algorithm, such as an LSTM algorithm, and the load prediction precision is effectively improved. And (3) proposing constructive opinions on the problem of low load prediction precision, effectively improving a load prediction model and improving the load prediction accuracy.
In addition, an LSTM algorithm is adopted, and based on mass historical data, the data is derived from marketing system data, coal-to-electricity intelligent service platforms, external data of the power industry and the like. Through data integration and data mining, effective implementation and application of improving the load prediction accuracy are achieved, the cost waste of companies is avoided, and a guarantee is made for a subsequent prediction model. Through data processing, the accuracy, uniqueness and value of the load data are guaranteed. And the LSTM algorithm is combined, so that the result is more accurate when the model algorithm analysis is carried out.
Through the steps, the target variable influencing the predicted daily load can be determined based on the correlation coefficient and the load trend change curve; inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: the variable and the load corresponding to the variable are identified through the load forecasting model to forecast the daily load corresponding to the target variable, so that the aim of quickly forecasting the load value of the future time period is fulfilled, the technical effect of improving the load forecasting accuracy is achieved, and the technical problem that the forecasting load precision is low in the conventional load forecasting method in the related technology is solved.
Optionally, before determining the target variable affecting the predicted daily load based on the correlation coefficient and the load trend curve, the method further includes: acquiring power load data; preprocessing the power load data to obtain preprocessed power load data; and determining an original variable and a derivative variable corresponding to the original variable based on the preprocessed power load data.
As an alternative embodiment, the electric load data is derived from marketing system data, coal-to-electricity intelligent service platforms, electric power industry external data and the like. Due to the fact that the data volume is large, the attributes are multiple, needed variables are found out through data preprocessing and data integration and in combination with an actual business model, and derivative variables are built.
As an alternative embodiment, the user data is accessed in Python and excel. And correcting the valuable abnormal value by using the attribute characteristics of the user data, and deleting the useless abnormal data and the meaningless variable. And filling the missing data by adopting an averaging method and combining the change rule of the load data, and deleting the information data of the user if the missing value is large.
As an alternative embodiment, the characteristics of load prediction can be combined to construct derivative variables corresponding to the original variables: predicting load values at t-1, t and t +1 moments before one week of the day; predicting load values at t-1, t and t +1 moments before one day; predicting load values at t-1, t and t +1 moments two days before the day; predicting load values at t-1, t and t +1 moments three days before the day; and predicting the time t of the day before one quarter, two quarter and three quarter.
It should be noted that, in the variable construction process, related variables can be created according to the existing data, for example, the median of each group can be calculated by knowing two groups of data, and this variable can be regarded as a new variable constructed by the attribute.
Optionally, the pre-treatment comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
Optionally, determining the original variable and the derivative variable corresponding to the original variable includes: under the condition that the original variable is the temperature, the derivative variable corresponding to the temperature is the load values at t-1, t and t +1 moments before the prediction day in one week; under the condition that the original variable is humidity, the derivative variable corresponding to the humidity is the load values at t-1, t and t +1 moments before the forecast day; under the condition that the original variable is the number of users, the derivative variable corresponding to the number of users is the load value at t-1, t and t +1 days before the forecast day; under the condition that the original variable is the day type, the derivative variable corresponding to the day type is the load values at t-1, t and t +1 moments three days before the forecast day; under the condition that the original variable is the row identifier, the derivative variables corresponding to the row identifier are predicted before one quarter, two quarter and three quarter of the day t; and when the original variable is the week category, the derivative variable corresponding to the week category is null.
Example 2
According to another aspect of the embodiments of the present invention, there is also provided a load prediction apparatus, and fig. 2 is a schematic diagram of the load prediction apparatus according to the embodiments of the present invention, as shown in fig. 2, the load prediction apparatus includes: a first determination module 22 and a processing module 24. The load prediction apparatus will be described in detail below.
The first determination module 22 is used for determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve; a processing module 24, connected to the first determining module 22, configured to input the target variable into a load prediction model, so as to obtain a predicted daily load corresponding to the target variable, where the load prediction model is obtained by using multiple sets of data through machine learning training, and each set of data in the multiple sets of data includes: variables and the load to which the variables correspond.
In the embodiment of the invention, the load prediction device can identify the predicted daily load corresponding to the target variable through the load prediction model, so as to achieve the purpose of rapidly predicting the load value of the future time period, thereby achieving the technical effect of improving the load prediction accuracy, and further solving the technical problem of low predicted load precision of the traditional load prediction method in the related art.
It should be noted that the above modules may be implemented by software or hardware, for example, for the latter, the following may be implemented: the modules can be located in the same processor; alternatively, the modules may be located in different processors in any combination.
It should be noted here that the first determining module 22 and the processing module 24 correspond to steps S102 to S104 in embodiment 1, and the modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the disclosure of embodiment 1. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.
Optionally, the apparatus further comprises: the acquisition module is used for acquiring the electric load data before determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve; the preprocessing module is used for preprocessing the power load data to obtain preprocessed power load data; and the second determination module is used for determining the original variable and the derivative variable corresponding to the original variable based on the preprocessed power load data.
Optionally, the pre-treatment comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
Optionally, the second determining module includes: the first processing subunit is used for, under the condition that the original variable is the temperature, obtaining the load values of t-1, t and t +1 moments before the prediction day and a week corresponding to the derived variable corresponding to the temperature; the second processing subunit is used for, under the condition that the original variable is humidity, obtaining the load values of t-1, t and t +1 moments before the prediction day by using the derivative variables corresponding to the humidity; the third processing subunit is used for, under the condition that the original variable is the number of users, setting the derivative variable corresponding to the number of users as the load values at t-1, t and t +1 days before the forecast day; the fourth processing subunit is used for determining that the derived variables corresponding to the day type are load values at t-1, t and t +1 days before the forecast day if the original variable is the day type; the fifth processing subunit is configured to, when the original variable is the row identifier, determine that the derived variables corresponding to the row identifier are one quarter hour before, two quarter hours before, and three quarter hours before the predicted time t; and the sixth processing subunit is configured to, if the original variable is the week category, leave the derived variable corresponding to the week category empty.
Example 3
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which includes a stored program, wherein when the program runs, the apparatus in which the computer-readable storage medium is located is controlled to execute the load prediction method of any one of the above.
Optionally, in this embodiment, the computer-readable storage medium may be located in any one of a group of computer terminals in a computer network or in any one of a group of mobile terminals, and the computer-readable storage medium includes a stored program.
Optionally, the program when executed controls an apparatus in which the computer-readable storage medium is located to perform the following functions: determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve; inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: variables and the load to which the variables correspond.
Example 4
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program executes a load prediction method of any one of the above.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein the processor executes the program and realizes the following steps: determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve; inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: variables and the load to which the variables correspond.
The invention also provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve; inputting the target variable into a load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using a plurality of groups of data through machine learning training, and each group of data in the plurality of groups of data comprises: variables and the load to which the variables correspond.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method of load prediction, comprising:
determining target variables influencing the predicted daily load based on the correlation coefficient and the load trend change curve;
inputting the target variable into the load prediction model to obtain a predicted daily load corresponding to the target variable, wherein the load prediction model is obtained by using multiple groups of data through machine learning training, and each group of data in the multiple groups of data comprises: a variable and a load corresponding to the variable.
2. The method of claim 1, wherein prior to determining the target variable affecting the predicted daily load based on the correlation coefficient and the load trend curve, the method further comprises:
acquiring power load data;
preprocessing the power load data to obtain preprocessed power load data;
and determining an original variable and a derivative variable corresponding to the original variable based on the preprocessed power load data.
3. The method of claim 2, wherein the pre-processing comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
4. The method of claim 2, wherein determining a primary variable and a derivative variable corresponding to the primary variable comprises:
under the condition that the original variable is the temperature, the derivative variable corresponding to the temperature is the load value at t-1, t and t +1 moments before the prediction day of one week;
under the condition that the original variable is humidity, the derivative variable corresponding to the humidity is the load value of the moment t-1, t and t +1 before the forecast day;
under the condition that the original variable is the number of users, the derivative variable corresponding to the number of users is the load value at t-1, t and t +1 days before the forecast day;
under the condition that the original variable is the day type, the derivative variable corresponding to the day type is the load values at t-1, t and t +1 moments three days before the forecast day;
under the condition that the original variable is the row identifier, the derivative variables corresponding to the row identifier are predicted before one quarter of a day t, two quarters of a day and three quarters of a day;
and if the original variable is the week category, the derivative variable corresponding to the week category is null.
5. A load prediction apparatus, comprising:
the first determination module is used for determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve;
a processing module, configured to input the target variable into the load prediction model to obtain a predicted daily load corresponding to the target variable, where the load prediction model is obtained by using multiple sets of data through machine learning training, and each set of data in the multiple sets of data includes: a variable and a load corresponding to the variable.
6. The apparatus of claim 5, further comprising:
the acquisition module is used for acquiring the electric load data before determining a target variable influencing the predicted daily load based on the correlation coefficient and the load trend change curve;
the preprocessing module is used for preprocessing the power load data to obtain preprocessed power load data;
and the second determination module is used for determining an original variable and a derivative variable corresponding to the original variable based on the preprocessed power load data.
7. The apparatus of claim 6, wherein the pre-processing comprises at least one of: correcting valuable abnormal data, deleting useless abnormal data and meaningless variables.
8. The apparatus of claim 6, wherein the second determining module comprises:
the first processing subunit is used for, under the condition that the original variable is the temperature, obtaining the load values of t-1, t and t +1 moments before the prediction day and a week by the derivative variable corresponding to the temperature;
the second processing subunit is used for, under the condition that the original variable is humidity, obtaining the load values of t-1, t and t +1 moments before the prediction day by using the derivative variables corresponding to the humidity;
the third processing subunit is configured to, when the original variable is the number of users, determine that the derivative variable corresponding to the number of users is a load value at a time t-1, t +1 two days before the prediction day;
the fourth processing subunit is used for, under the condition that the original variable is the day type, determining the derived variable corresponding to the day type to be the load values at t-1, t and t +1 three days before the forecast day;
a fifth processing subunit, configured to, if the original variable is a row identifier, determine that the derived variables corresponding to the row identifier are one quarter hour before, two quarter hours before, and three quarter hours before the predicted time t;
and the sixth processing subunit is configured to, if the original variable is the week category, leave the derived variable corresponding to the week category.
9. A computer-readable storage medium, comprising a stored program, wherein the program, when executed, controls an apparatus in which the computer-readable storage medium is located to perform the load prediction method of any one of claims 1 to 4.
10. A processor configured to execute a program, wherein the program executes to perform the load prediction method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011376905.0A CN112614006A (en) | 2020-11-30 | 2020-11-30 | Load prediction method, device, computer readable storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011376905.0A CN112614006A (en) | 2020-11-30 | 2020-11-30 | Load prediction method, device, computer readable storage medium and processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112614006A true CN112614006A (en) | 2021-04-06 |
Family
ID=75228235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011376905.0A Pending CN112614006A (en) | 2020-11-30 | 2020-11-30 | Load prediction method, device, computer readable storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614006A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672666A (en) * | 2021-08-23 | 2021-11-19 | 成都佳华物链云科技有限公司 | Machine load prediction method and device, electronic equipment and readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009673A (en) * | 2017-11-24 | 2018-05-08 | 国网北京市电力公司 | Novel load Forecasting Methodology and device based on deep learning |
| CN108335014A (en) * | 2017-12-29 | 2018-07-27 | 国网北京市电力公司 | Load Analytic Method, device, storage medium and processor |
| CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
| CN110135635A (en) * | 2019-04-29 | 2019-08-16 | 国网山东省电力公司经济技术研究院 | A kind of region electric power saturation load forecasting method and system |
| CN110781947A (en) * | 2019-10-22 | 2020-02-11 | 北京交通大学 | Power load prediction model training and power load prediction method and device |
| CN110969285A (en) * | 2019-10-29 | 2020-04-07 | 京东方科技集团股份有限公司 | Prediction model training method, prediction device, prediction equipment and medium |
| CN111784019A (en) * | 2019-12-26 | 2020-10-16 | 国网北京市电力公司 | Power load processing method and device |
| CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
-
2020
- 2020-11-30 CN CN202011376905.0A patent/CN112614006A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009673A (en) * | 2017-11-24 | 2018-05-08 | 国网北京市电力公司 | Novel load Forecasting Methodology and device based on deep learning |
| CN108335014A (en) * | 2017-12-29 | 2018-07-27 | 国网北京市电力公司 | Load Analytic Method, device, storage medium and processor |
| CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
| CN110135635A (en) * | 2019-04-29 | 2019-08-16 | 国网山东省电力公司经济技术研究院 | A kind of region electric power saturation load forecasting method and system |
| CN110781947A (en) * | 2019-10-22 | 2020-02-11 | 北京交通大学 | Power load prediction model training and power load prediction method and device |
| CN110969285A (en) * | 2019-10-29 | 2020-04-07 | 京东方科技集团股份有限公司 | Prediction model training method, prediction device, prediction equipment and medium |
| CN111784019A (en) * | 2019-12-26 | 2020-10-16 | 国网北京市电力公司 | Power load processing method and device |
| CN112001439A (en) * | 2020-08-19 | 2020-11-27 | 西安建筑科技大学 | GBDT-based shopping mall building air conditioner cold load prediction method, storage medium and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 彭显刚;潘可达;张丹;刘艺;林志坚;: "基于季节性负荷自适应划分及重要点分割的多分段短期负荷预测", 电网技术, no. 02, 5 February 2020 (2020-02-05), pages 237 - 247 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113672666A (en) * | 2021-08-23 | 2021-11-19 | 成都佳华物链云科技有限公司 | Machine load prediction method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| CN111210093B (en) | Daily water consumption prediction method based on big data | |
| Kuosmanen et al. | What is the best practice for benchmark regulation of electricity distribution? Comparison of DEA, SFA and StoNED methods | |
| CN102063550A (en) | Intelligent design system of cold extrusion piece with machine intelligence involved design decision | |
| CN111178957B (en) | Method for early warning sudden increase of electric quantity of electricity consumption customer | |
| CN105678414A (en) | Data processing method of predicting resource consumption | |
| CN111178585A (en) | Fault reporting amount prediction method based on multi-algorithm model fusion | |
| CN114399021A (en) | Probability wind speed prediction method and system based on multi-scale information | |
| CN111680841A (en) | Short-term load prediction method and system based on principal component analysis and terminal equipment | |
| CN103853939A (en) | Combined forecasting method for monthly load of power system based on social economic factor influence | |
| CN114943565A (en) | Electric power spot price prediction method and device based on intelligent algorithm | |
| CN116091118A (en) | Electricity price prediction method, device, equipment, medium and product | |
| CN112633556A (en) | Short-term power load prediction method based on hybrid model | |
| Flammini et al. | Reducing fossil fuel-based generation: Impact on wholesale electricity market prices in the North-Italy bidding zone | |
| CN114154716B (en) | Enterprise energy consumption prediction method and device based on graph neural network | |
| CN110837952A (en) | Game theory-based power grid new technology equipment selection method and system | |
| CN117494906B (en) | Natural gas daily load prediction method based on multivariate time series | |
| CN114581141A (en) | Short-term load prediction method based on feature selection and LSSVR | |
| CN112614006A (en) | Load prediction method, device, computer readable storage medium and processor | |
| Şişman | A comparison of ARIMA and grey models for electricity consumption demand forecasting: The case of Turkey | |
| CN112614010A (en) | Load prediction method and device, storage medium and electronic device | |
| CN109829115B (en) | Search engine keyword optimization method | |
| CN107704723A (en) | A kind of notable Variable Selection based on Slope correlation | |
| CN112330017A (en) | Power load prediction method, power load prediction device, electronic device, and storage medium | |
| CN116011698B (en) | Method, device, computer equipment and storage medium for determining unit combination |
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 |