CN112614010A - Load prediction method and device, storage medium and electronic device - Google Patents
Load prediction method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN112614010A CN112614010A CN202011419010.0A CN202011419010A CN112614010A CN 112614010 A CN112614010 A CN 112614010A CN 202011419010 A CN202011419010 A CN 202011419010A CN 112614010 A CN112614010 A CN 112614010A
- Authority
- CN
- China
- Prior art keywords
- load
- parameters
- prediction
- data
- load prediction
- 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 54
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000010219 correlation analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 239000003245 coal Substances 0.000 description 2
- 238000005485 electric heating Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011985 exploratory data analysis Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 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
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06N20/00—Machine learning
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Water Supply & Treatment (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a load prediction method and device, a storage medium and an electronic device, wherein the method comprises the following steps: determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold; extracting a target parameter from prediction data of a target object to be subjected to load prediction, and inputting the target parameter into a load prediction model to predict a load of the prediction data, wherein the load prediction model is trained by machine learning by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter. By adopting the technical scheme, the problems of low prediction precision and prediction accuracy and the like in load prediction of the traditional load prediction technology are solved.
Description
Technical Field
The present invention relates to the field of communications, and in particular, to a load prediction method and apparatus, a storage medium, and an electronic apparatus.
Background
In recent years, with the gradual expansion of the scale of the user of 'coal to electricity', the load condition of the transformer area where the user is located is more complex, the workload is increased for the marketing, operation and maintenance and safety operation of the power grid, and higher requirements are provided for the power grid. The stable and uninterrupted high-quality electric energy provides guarantee for the stable operation of industry and even society, so that a reasonable scheduling scheme needs to be formulated, the power load prediction plays an important role in the process, and the correct prediction of the power load plays an important role in the normal operation of a power system.
However, the load data has the characteristics of time sequence, nonlinearity, uncertainty and the like, and the traditional load prediction technology cannot well represent the load data rule and meet the requirement.
Aiming at the problems of low prediction precision and prediction accuracy and the like in the load prediction of the traditional load prediction technology in the related technology, no effective solution is provided at present.
Disclosure of Invention
The embodiment of the invention provides a load prediction method and device, a storage medium and an electronic device, which at least solve the problems of low prediction precision and prediction accuracy and the like when the traditional load prediction technology is used for load prediction.
According to an aspect of an embodiment of the present invention, there is provided a load prediction method, including: determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold; extracting a target parameter from prediction data of a target object to be subjected to load prediction, and inputting the target parameter into a load prediction model to predict a load of the prediction data, wherein the load prediction model is trained by machine learning by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
In one exemplary embodiment, determining a plurality of parameters for which the correlation coefficient with the load parameter exceeds a preset threshold includes: acquiring all parameters allowing analysis; respectively determining correlation coefficients of all the parameters and the load parameters; a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined.
In an exemplary embodiment, determining the correlation coefficients of all the parameters and the load parameter respectively comprises: and respectively determining the correlation coefficients of all the parameters and the load parameters according to the Pearson correlation coefficients.
In one exemplary embodiment, the plurality of parameters includes at least one of: outdoor temperature, humidity, the number of users in the area where the target object is located, a day type, load values at different times before the predicted day one week, load values at different times before the predicted day one day, load values at different times before the predicted day two days, load values at different times before the predicted day three days, load values at the predicted day t time, load values at one quarter, two quarter and three quarter, and t is a positive integer.
In an exemplary embodiment, before extracting a target parameter from prediction data of a target object to be subjected to load prediction and inputting the target parameter into a load prediction model to predict a load of the prediction data, the method further includes: setting an initial value of the load prediction model; and predicting the load of the prediction data based on the initial value.
In an exemplary embodiment, the predicted day includes at least one of: the time difference from the current time is a first value, the time difference from the current time is a second value, and the time difference from the current time is a third value, wherein the first value is greater than the second value, and the second value is greater than the third value.
According to another aspect of the embodiment of the present invention, there is also provided a load prediction apparatus, including a determining module, configured to determine a plurality of parameters whose correlation coefficients with load parameters exceed a preset threshold; the prediction module is used for extracting a target parameter from prediction data of a target object to be subjected to load prediction and inputting the target parameter into a load prediction model so as to predict the load of the prediction data, wherein the load prediction model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
In an exemplary embodiment, the determining module is configured to obtain all parameters that allow analysis; respectively determining correlation coefficients of all the parameters and the load parameters; a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above load prediction method when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the load prediction method through the computer program.
According to the load prediction method and device, a load prediction model is introduced when load prediction is carried out, a plurality of parameters are determined through a preset threshold, correlation coefficients of the parameters and the load parameters exceed the preset threshold, then target parameters are extracted from prediction data of a target object to be subjected to load prediction, the target parameters are input into the load prediction model, and the load of the prediction data is predicted through the load prediction model. By adopting the technical scheme, the problems of low prediction precision and prediction accuracy and the like in load prediction of the traditional load prediction technology are solved. And then target parameters are input into the load prediction model through the introduction of the load prediction model, and the prediction data of the electric load is obtained through the load prediction model, so that the prediction precision and the prediction accuracy rate in the load prediction are greatly improved.
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 block diagram of a hardware configuration of a computer terminal of a load prediction method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of load prediction according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method of load prediction according to an embodiment of the present invention (two);
fig. 4 is a block 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.
The method provided by the embodiment of the application can be executed in a computer terminal or a similar operation device. Taking the example of the method running on a computer terminal, fig. 1 is a hardware structure block diagram of a computer terminal of a load prediction method according to an embodiment of the present invention. As shown in fig. 1, the computer terminal may include one or more (only one shown in fig. 1) processors 102 (the processors 102 may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and in an exemplary embodiment, may also include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration and is not intended to limit the structure of the computer terminal. For example, the computer terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration with equivalent functionality to that shown in FIG. 1 or with more functionality than that shown in FIG. 1.
The memory 104 may be used to store a computer program, for example, a software program and a module of an application software, such as a computer program corresponding to the load prediction method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, so as to implement the method described above. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to a computer terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the computer terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In the related technology, the traditional load prediction method generally adopts a trend extrapolation method, a time sequence and regression analysis to predict the load, does not consider the characteristics of nonlinearity and uncertainty of load data, is influenced by a plurality of internal and external environmental factors, and cannot well represent the change rule of the load data, so that the accuracy of power load prediction is low and does not meet the actual requirement; the traditional load prediction method can be used for correcting abnormal load data by adopting the average value of loads at the same time on different days in a week and combining historical load data to predict the load again for the problem of low load prediction accuracy, but the effect is very little.
In order to solve the above technical problem, in this embodiment, a load prediction method is provided, and fig. 2 is a flowchart (a) of the load prediction method according to the embodiment of the present invention, where the flowchart includes the following steps:
step S202, determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold;
step S204, extracting target parameters from the prediction data of a target object to be subjected to load prediction, and inputting the target parameters into a load prediction model to predict the load of the prediction data, wherein the load prediction model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
Through the steps, a load prediction model is introduced when load prediction is carried out, a plurality of parameters are determined through a preset threshold value, correlation coefficients of the parameters and the load parameters exceed the preset threshold value, then target parameters are extracted from prediction data of a target object to be subjected to load prediction, the target parameters are input into the load prediction model, and the load of the prediction data is predicted through the load prediction model. By adopting the technical scheme, the problems of low prediction precision and prediction accuracy and the like in load prediction of the traditional load prediction technology are solved. And then target parameters are input into the load prediction model through the introduction of the load prediction model, and the prediction data of the electric load is obtained through the load prediction model, so that the prediction precision and the prediction accuracy rate in the load prediction are greatly improved.
It can be understood that, the load prediction model is trained by machine learning using multiple sets of data, multiple parameters are determined by a preset threshold, correlation coefficients of the multiple parameters and the load parameters exceed the preset threshold, and then a target parameter is extracted from prediction data of a target object to be subjected to load prediction, the target parameter is input into the load prediction model, and the load of the prediction data is predicted by the load prediction model to obtain prediction data, where each set of data in the multiple sets of data includes: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter. For example, the data to be predicted includes parameters such as a, B, C, D, E, and F, assuming that the preset threshold is M, first, a plurality of parameters are determined from the parameters such as a, B, C, D, E, and F, the correlation coefficients of the plurality of parameters and the load parameter exceed the preset threshold M, it should be noted that different parameters are different or the same for the preset threshold M, assuming that the correlation coefficients of the three parameters a, B, and C and the load parameter exceed the preset threshold M, and the predicted data X, Y, and Z of the target object to be subjected to load prediction are extracted from the three predicted data X, Y, and Z, the values of the target parameters a, B, and C are extracted, the target parameters are input into a load prediction model to predict the load of the predicted data, the prediction result is N, the load prediction model is trained by a machine learning algorithm XGBoost using a plurality of sets of data, each of the sets of data includes three parameters a, B, C and a predicted daily load N after the current time.
In an alternative embodiment, determining a plurality of parameters for which the correlation coefficient with the load parameter exceeds a preset threshold comprises: acquiring all parameters allowing analysis; respectively determining correlation coefficients of all the parameters and the load parameters; a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined. For example, all parameters that are allowed to be analyzed in the data to be predicted are a, B, C, D, E, F, G, assuming that a correlation coefficient between the parameter a and the load parameter is a, a correlation coefficient between the parameter B and the load parameter is C, a correlation coefficient between the parameter C and the load parameter is C, a correlation coefficient between the parameter D and the load parameter is D, a correlation coefficient between the parameter E and the load parameter is E, and a correlation coefficient between the parameter F and the load parameter is F, assuming that a, B, C exceed a preset threshold M in all the correlation coefficients a, B, C, D, E, F, the determined parameters are a, B, C.
When the correlation coefficients of all the parameters and the load parameters are actually determined, a plurality of correlation coefficient determination methods exist, and optionally, the correlation coefficients of all the parameters and the load parameters are respectively determined according to pearson correlation coefficients. In the present embodiment, for the target parameter x and the load parameter y, the correlation coefficient is calculated from the pearson correlation coefficientρSpecific expressions are as follows.
The plurality of parameters a, B, C, D, E, F, etc. include at least one of the following: outdoor temperature, humidity, the number of users in the area where the target object is located, a day type, load values at different times before the predicted day one week, load values at different times before the predicted day one day, load values at different times before the predicted day two days, load values at different times before the predicted day three days, load values at the predicted day t time, load values at one quarter, two quarter and three quarter, and t is a positive integer.
In an optional implementation, before extracting a target parameter from prediction data of a target object to be subjected to load prediction and inputting the target parameter into a load prediction model to predict a load of the prediction data, the method further includes: setting an initial value of the load prediction model; and predicting the load of the prediction data based on the initial value. In this embodiment, a target parameter is extracted from prediction data of a target object to be subjected to load prediction, and the target parameter is set as an initial value of a load prediction model, which predicts a load of the prediction data based on the initial value, and is input to the load prediction model. For example, target parameters a, B, and C are determined from parameters a, B, C, D, E, and F, and initial values of a load prediction model are set as a, B, and C, and the load prediction model predicts the prediction data X, Y, and Z based on the three initial values a, B, and C.
In an alternative embodiment, the predicted day includes at least one of: the time difference from the current time is a first value, the time difference from the current time is a second value, and the time difference from the current time is a third value, wherein the first value is greater than the second value, and the second value is greater than the third value. In this embodiment, in order to perform short, medium and long term load prediction, three different time points from the current time are selected as prediction days. For example, when the current time is 12 months and 1 day, 12 months and 3 days are selected as short-term prediction days, 12 months and 13 days are selected as medium-term prediction periods, and 12 months and 30 days are selected as long-term prediction days.
In order to better understand the above load prediction method, the following describes the above process with reference to an alternative embodiment, but is not intended to limit the technical solution of the embodiment of the present invention, specifically:
in order to obtain massive historical load data, a big data technology is adopted, and the data are derived from marketing system data, a coal-to-electricity intelligent service platform, external data of the power industry and the like. Because the data volume is large and the variables are more, the required variables are found out by data preprocessing and data integration and combining with an actual business model, and the derived variables are associated, wherein the specific original variables and the derived variables are shown in the table.
| Variables of | Derived variable |
| Temperature of | Predicting load values at t-1, t and t +1 times before one week |
| Humidity | Predicting load values at t-1, t +1 times one day before day |
| Number of users | Predicting load values at t-1, t and t +1 moments two days before day |
| Type of day | Predicting load values at t-1, t and t +1 moments three days before day |
| Line identification | Predicting the time t of the day before one quarter, two quarter and three quarter |
| Week classification |
Fig. 3 is a flowchart (two) of a load prediction method according to an embodiment of the present invention, and as shown in fig. 3, in an alternative embodiment, a specific process may be composed of the following steps:
the method comprises the following steps: data access and data processing, wherein user data are accessed into Python and excel, attribute characteristics of the user data are observed through exploratory analysis, valuable abnormal values are corrected, useless abnormal data and meaningless variables are deleted, an averaging method is adopted, a change rule of load data is combined, missing data are filled, and if the missing value is large in quantity, information data of the user are deleted.
Step two: and (3) attribute construction, namely constructing derivative variables according to the exploration target and the characteristics of load prediction: 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.
Step three: influence factor analysis, firstly, a load curve change rule is explored, data characteristics of a data source A are observed, and the fact that the load change trend of a user has obvious periodicity can be found, wherein the average section is from 8 points earlier to 8 points later, and the valley section is from 8 points later to 8 points earlier. During the leveling period, the electric load of the electric heating device gradually decreases, during the valley period, because a user who changes coal into electricity has a subsidy of electricity price, when the electricity price is 0.1 yuan/kilowatt after the subsidy, the electric load is higher, the electric load of the electric heating device gradually increases, the fluctuation trend of the daily electric load is similar, and a certain deviation exists 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.
And then, searching important factors influencing load prediction, determining the factors influencing the load by combining relevant service conditions through correlation analysis according to a load curve change rule, wherein the correlation analysis is used for detecting 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. Calculating correlation coefficients for variables using Pearson's correlation coefficient (Person), e.g. given two consecutive variables x and y, Pearson's correlation coefficientρIs 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 t-1, t and t +1 moments before the predicted day one week, the load values of t-1, t and t +1 moments before the predicted day one day, the load values of t-1, t and t +1 moments before the predicted day two days, the load values of t-1, t and t +1 moments 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, so that the correlation coefficients can be used as the input of a load prediction model.
Step four: establishing a model, and constructing a short-term and medium-term load prediction method based on an XGboost machine learning algorithm prediction model by combining selected variables influencing load prediction based on the XGboost machine learning algorithm model, wherein the establishing steps are as follows: 1) acquiring characteristic data influencing load, preprocessing the data, and dividing the data into a training set and a test set; 2) selecting required model input variables based on correlation analysis and load trend change curve analysis; 3) setting initial values of parameters of a prediction model of an XGboost machine learning algorithm; 4) respectively predicting the load of the user in the short and medium periods by using a short and medium period load prediction model based on an XGboost machine learning 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, according to the technical scheme of the embodiment of the invention, based on a model algorithm, a better model is trained by using a large amount of user load data, and based on the trained model, the load value of a future time period can be predicted quickly; meanwhile, an applicable model is obtained through a large amount of data iterative optimization model, wherein data processing is carried out in the early stage of data input, dirty data and data with small information amount are deleted, the data calculation quality is guaranteed, the traditional load value in the future time period is deduced based on manual work, and a large data technology and a machine learning algorithm are adopted, so that the load result is more accurate, and meanwhile, support is also provided for other researches.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a load prediction apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description of the apparatus is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated, and FIG. 4 is a block diagram of a load prediction apparatus according to an embodiment of the present invention, the apparatus including:
a determining module 40, configured to determine a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold;
a prediction module 42, configured to extract a target parameter from prediction data of a target object to be subjected to load prediction, and input the target parameter into a load prediction model to predict a load of the prediction data, where the load prediction model is trained through machine learning by using multiple sets of data, and each set of data in the multiple sets of data includes: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
According to the load prediction method and device, a load prediction model is introduced when load prediction is carried out, a plurality of parameters are determined through a preset threshold, correlation coefficients of the parameters and the load parameters exceed the preset threshold, then target parameters are extracted from prediction data of a target object to be subjected to load prediction, the target parameters are input into the load prediction model, and the load of the prediction data is predicted through the load prediction model. By adopting the technical scheme, the problems of low prediction precision and prediction accuracy and the like in load prediction of the traditional load prediction technology are solved. And then target parameters are input into the load prediction model through the introduction of the load prediction model, and the prediction data of the electric load is obtained through the load prediction model, so that the prediction precision and the prediction accuracy rate in the load prediction are greatly improved.
It can be understood that, the load prediction model is trained through machine learning by using multiple sets of data, in the determination module 42, multiple parameters are determined through a preset threshold, and correlation coefficients of the multiple parameters and the load parameters exceed the preset threshold, so as to extract a target parameter from prediction data of a target object to be subjected to load prediction, input the target parameter into the load prediction model, and predict a load of the prediction data through the load prediction model to obtain prediction data, where each set of data in the multiple sets of data includes: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter. For example, the data to be predicted includes parameters such as a, B, C, D, E, and F, assuming that the preset threshold is M, first, a plurality of parameters are determined from the parameters such as a, B, C, D, E, and F, the correlation coefficients of the plurality of parameters and the load parameter exceed the preset threshold M, it should be noted that different parameters are different or the same for the preset threshold M, assuming that the correlation coefficients of the three parameters a, B, and C and the load parameter exceed the preset threshold M, and the predicted data X, Y, and Z of the target object to be subjected to load prediction are extracted from the three predicted data X, Y, and Z, the values of the target parameters a, B, and C are extracted, the target parameters are input into a load prediction model to predict the load of the predicted data, the load prediction model is trained by a machine learning algorithm XGBoost using a plurality of sets of data, each of the sets of data includes three parameters a, B, C and a predicted daily load after the current time.
In an alternative embodiment, determining a plurality of parameters for which the correlation coefficient with the load parameter exceeds a preset threshold comprises: acquiring all parameters allowing analysis; respectively determining correlation coefficients of all the parameters and the load parameters; a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined. For example, all parameters that are allowed to be analyzed in the data to be predicted are a, B, C, D, E, F, G, assuming that a correlation coefficient between the parameter a and the load parameter is a, a correlation coefficient between the parameter B and the load parameter is C, a correlation coefficient between the parameter C and the load parameter is C, a correlation coefficient between the parameter D and the load parameter is D, a correlation coefficient between the parameter E and the load parameter is E, and a correlation coefficient between the parameter F and the load parameter is F, assuming that a, B, C exceed a preset threshold M in all the correlation coefficients a, B, C, D, E, F, the determined parameters are a, B, C.
When actually determining the correlation coefficients of all the parameters and the load parameters, there are a plurality of correlation coefficient determination methods, and optionally, the correlation coefficients are determined respectively according to the pearson correlation coefficientsAnd the correlation coefficient of all the parameters and the load parameter. In the present embodiment, for the target parameter x and the load parameter y, the correlation coefficient is calculated from the pearson correlation coefficientρSpecific expressions are as follows.
The plurality of parameters a, B, C, D, E, F, etc. include at least one of the following: outdoor temperature, humidity, the number of users in the area where the target object is located, a day type, load values at different times before the predicted day one week, load values at different times before the predicted day one day, load values at different times before the predicted day two days, load values at different times before the predicted day three days, load values at the predicted day t time, load values at one quarter, two quarter and three quarter, and t is a positive integer.
Optionally, the prediction module 44 is further configured to extract a target parameter from prediction data of a target object to be subjected to load prediction, and input the target parameter into a load prediction model, so that before the load of the prediction data is predicted, the method further includes: setting an initial value of the load prediction model; and predicting the load of the prediction data based on the initial value. In this embodiment, a target parameter is extracted from prediction data of a target object to be subjected to load prediction, and the target parameter is set as an initial value of a load prediction model, which predicts a load of the prediction data based on the initial value, and is input to the load prediction model. For example, target parameters a, B, and C are determined from parameters a, B, C, D, E, and F, and initial values of a load prediction model are set as a, B, and C, and the load prediction model predicts the prediction data X, Y, and Z based on the three initial values a, B, and C.
In an alternative embodiment, the predicted day includes at least one of: the time difference from the current time is a first value, the time difference from the current time is a second value, and the time difference from the current time is a third value, wherein the first value is greater than the second value, and the second value is greater than the third value. In this embodiment, in order to perform short, medium and long term load prediction, three different time points from the current time are selected as prediction days. For example, when the current time is 12 months and 1 day, 12 months and 3 days are selected as short-term prediction days, 12 months and 13 days are selected as medium-term prediction periods, and 12 months and 30 days are selected as long-term prediction days.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold;
s2, extracting a target parameter from the prediction data of a target object to be subjected to load prediction, and inputting the target parameter into a load prediction model to predict a load of the prediction data, wherein the load prediction model is trained by machine learning using a plurality of sets of data, and each set of data in the plurality of sets of data includes: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold;
s2, extracting a target parameter from the prediction data of a target object to be subjected to load prediction, and inputting the target parameter into a load prediction model to predict a load of the prediction data, wherein the load prediction model is trained by machine learning using a plurality of sets of data, and each set of data in the plurality of sets of data includes: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and they may be implemented using program code executable by the computing devices, such that they may be stored in a memory device and executed by the computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into various integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of load prediction, comprising:
determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold;
extracting a target parameter from prediction data of a target object to be subjected to load prediction, and inputting the target parameter into a load prediction model to predict a load of the prediction data, wherein the load prediction model is trained by machine learning by using a plurality of groups of data, and each group of data in the plurality of groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
2. The method of claim 1, wherein determining a plurality of parameters for which the correlation coefficient with the load parameter exceeds a preset threshold comprises:
acquiring all parameters allowing analysis;
respectively determining correlation coefficients of all the parameters and the load parameters;
a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined.
3. The method of claim 2, wherein determining the correlation coefficients of all the parameters with the load parameter respectively comprises:
and respectively determining the correlation coefficients of all the parameters and the load parameters according to the Pearson correlation coefficients.
4. The method of claim 1, wherein the plurality of parameters includes at least one of: outdoor temperature, humidity, the number of users in the area where the target object is located, a day type, load values at different times before the predicted day one week, load values at different times before the predicted day one day, load values at different times before the predicted day two days, load values at different times before the predicted day three days, load values at the predicted day t time, load values at one quarter, two quarter and three quarter, and t is a positive integer.
5. The method according to claim 1, wherein before extracting target parameters from prediction data of a target object to be load predicted and inputting the target parameters into a load prediction model to predict a load of the prediction data, the method further comprises:
setting an initial value of the load prediction model;
and predicting the load of the prediction data based on the initial value.
6. The method of any one of claims 1 to 5, wherein the predicted day includes at least one of: the time difference from the current time is a first value, the time difference from the current time is a second value, and the time difference from the current time is a third value, wherein the first value is greater than the second value, and the second value is greater than the third value.
7. A load prediction apparatus, comprising:
the determining module is used for determining a plurality of parameters of which the correlation coefficients with the load parameters exceed a preset threshold;
the prediction module is used for extracting a target parameter from prediction data of a target object to be subjected to load prediction and inputting the target parameter into a load prediction model so as to predict the load of the prediction data, wherein the load prediction model is trained by machine learning by using multiple groups of data, and each group of data in the multiple groups of data comprises: a plurality of parameters and a load on a predicted day after a current time, the plurality of parameters including: a target parameter.
8. The apparatus of claim 7, wherein the determining module is configured to obtain all parameters that allow analysis; respectively determining correlation coefficients of all the parameters and the load parameters; a plurality of parameters whose correlation coefficients with the load parameters exceed a preset threshold are determined.
9. A computer-readable storage medium, comprising a stored program, wherein the program is operable to perform the method of any one of claims 1 to 6.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 6 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419010.0A CN112614010A (en) | 2020-12-07 | 2020-12-07 | Load prediction method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011419010.0A CN112614010A (en) | 2020-12-07 | 2020-12-07 | Load prediction method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112614010A true CN112614010A (en) | 2021-04-06 |
Family
ID=75229110
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011419010.0A Pending CN112614010A (en) | 2020-12-07 | 2020-12-07 | Load prediction method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112614010A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610174A (en) * | 2021-08-13 | 2021-11-05 | 中南大学 | Power grid host load prediction method, equipment and medium based on Phik feature selection |
| CN115409292A (en) * | 2022-10-31 | 2022-11-29 | 广东电网有限责任公司佛山供电局 | Short-term load prediction method for power system and related device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109376971A (en) * | 2018-12-29 | 2019-02-22 | 北京中电普华信息技术有限公司 | A kind of load curve forecasting method and system towards power consumer |
| CN109727066A (en) * | 2018-12-27 | 2019-05-07 | 浙江华云信息科技有限公司 | A kind of big industrial electricity consumers load forecasting method based on XGBoost algorithm |
| CN109858674A (en) * | 2018-12-27 | 2019-06-07 | 国网浙江省电力有限公司 | Monthly load forecasting method based on XGBoost algorithm |
| CN110070209A (en) * | 2019-03-18 | 2019-07-30 | 天津理工大学 | A kind of space-heating system short-term load forecasting method based on SD-DNNs |
| CN110472778A (en) * | 2019-07-29 | 2019-11-19 | 上海电力大学 | A kind of short-term load forecasting method based on Blending integrated study |
| CN111340273A (en) * | 2020-02-17 | 2020-06-26 | 南京邮电大学 | Short-term load prediction method for power system based on GEP parameter optimization XGboost |
| CN111967655A (en) * | 2020-07-28 | 2020-11-20 | 中国南方电网有限责任公司 | Short-term load prediction method and system |
| 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
- 2020-12-07 CN CN202011419010.0A patent/CN112614010A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727066A (en) * | 2018-12-27 | 2019-05-07 | 浙江华云信息科技有限公司 | A kind of big industrial electricity consumers load forecasting method based on XGBoost algorithm |
| CN109858674A (en) * | 2018-12-27 | 2019-06-07 | 国网浙江省电力有限公司 | Monthly load forecasting method based on XGBoost algorithm |
| CN109376971A (en) * | 2018-12-29 | 2019-02-22 | 北京中电普华信息技术有限公司 | A kind of load curve forecasting method and system towards power consumer |
| CN110070209A (en) * | 2019-03-18 | 2019-07-30 | 天津理工大学 | A kind of space-heating system short-term load forecasting method based on SD-DNNs |
| CN110472778A (en) * | 2019-07-29 | 2019-11-19 | 上海电力大学 | A kind of short-term load forecasting method based on Blending integrated study |
| CN111340273A (en) * | 2020-02-17 | 2020-06-26 | 南京邮电大学 | Short-term load prediction method for power system based on GEP parameter optimization XGboost |
| CN111967655A (en) * | 2020-07-28 | 2020-11-20 | 中国南方电网有限责任公司 | Short-term load prediction method and system |
| 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 |
|---|
| 彭慧敏, 赵菁, 袁旭峰, 张家亮, 谢维廉: "电力系统短期负荷组合预测", 贵州工业大学学报(自然科学版), no. 01 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610174A (en) * | 2021-08-13 | 2021-11-05 | 中南大学 | Power grid host load prediction method, equipment and medium based on Phik feature selection |
| CN115409292A (en) * | 2022-10-31 | 2022-11-29 | 广东电网有限责任公司佛山供电局 | Short-term load prediction method for power system and related device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dvorkin et al. | Assessing flexibility requirements in power systems | |
| US20210133536A1 (en) | Load prediction method and apparatus based on neural network | |
| CN111210093B (en) | Daily water consumption prediction method based on big data | |
| CN103413188B (en) | A kind of monthly industrial power predicating method based on industry Business Process System | |
| CN111612275B (en) | Method and device for predicting load of regional user | |
| CN110246037B (en) | Transaction characteristic prediction method, device, server and readable storage medium | |
| CN112614010A (en) | Load prediction method and device, storage medium and electronic device | |
| CN112712203B (en) | Day-highest load prediction method and system for power distribution network | |
| CN115034519A (en) | Method and device for predicting power load, electronic equipment and storage medium | |
| US20220245096A1 (en) | Method and device for facilitating storage of data from an industrial automation control system or power system | |
| CN113724101B (en) | Table relation identification method and system, equipment and storage medium | |
| CN110728395A (en) | Main transformer short-term power load calculation method and device, computer and storage medium | |
| CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN108154259B (en) | Load prediction method and device for heat pump, storage medium, and processor | |
| CN111160614B (en) | Training method and device of resource transfer prediction model and computing equipment | |
| CN112465266A (en) | Bus load prediction accuracy analysis method and device and computer equipment | |
| CN110837889A (en) | Neural network training method and device, storage medium and electronic device | |
| CN110826829A (en) | Intelligent scoring and scheduling method based on big data | |
| CN112614006A (en) | Load prediction method, device, computer readable storage medium and processor | |
| CN112669091B (en) | Data processing method, device and storage medium | |
| CN109981327B (en) | Method and system for predicting traffic | |
| Kanellou et al. | A game theory approach towards real-time pricing in future electricity markets | |
| CN111026863A (en) | Customer behavior prediction method, apparatus, device and medium | |
| Liu et al. | Distributed assimilation of grid conditions and load integration via social learning | |
| Jie et al. | A customer baseline load prediction and optimization method based on non-demand-response factors |
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 |