CN113947007A - Energy load prediction method, device and equipment - Google Patents

Energy load prediction method, device and equipment Download PDF

Info

Publication number
CN113947007A
CN113947007A CN202110750161.2A CN202110750161A CN113947007A CN 113947007 A CN113947007 A CN 113947007A CN 202110750161 A CN202110750161 A CN 202110750161A CN 113947007 A CN113947007 A CN 113947007A
Authority
CN
China
Prior art keywords
load value
historical
value
day
load
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110750161.2A
Other languages
Chinese (zh)
Inventor
彭苗
董得志
李镇东
赵鸿飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Power Investment Group Science and Technology Research Institute Co Ltd
Original Assignee
State Power Investment Group Science and Technology Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Power Investment Group Science and Technology Research Institute Co Ltd filed Critical State Power Investment Group Science and Technology Research Institute Co Ltd
Priority to CN202110750161.2A priority Critical patent/CN113947007A/en
Publication of CN113947007A publication Critical patent/CN113947007A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • 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
    • G06N3/08—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)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Computer Hardware Design (AREA)
  • Game Theory and Decision Science (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application provides a method, a device and equipment for predicting load of energy, wherein the method comprises the following steps: acquiring an hourly historical load value in a first preset time period before a day to be predicted and hourly load value influence factors of the day to be predicted; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of the day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the load prediction precision can be improved.

Description

Energy load prediction method, device and equipment
Technical Field
The present application relates to the field of energy and data processing technologies, and in particular, to a method, an apparatus, and a device for predicting a load of an energy source.
Background
At present, due to the combination of the internet technology and the distributed energy station, the diversified energy utilization requirements of users can be fully met, the multi-energy complementation is realized, and the purpose of high-efficiency performance is achieved. To establish a comprehensive intelligent energy system of a distributed energy station, load prediction plays a crucial role.
In the related technology, ultra-short-term load prediction is carried out on an energy station by using a computer algorithm, and load prediction data is stored in a database to be used as next calculation data input. However, in the continuous operation process, if the data prediction is inaccurate in a part of time intervals, the accuracy of the next series of prediction is inaccurate.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
The application provides a method, a device and equipment for predicting energy load, which are used for solving the technical problem that in the prior art, if data prediction in a part of time intervals is inaccurate, the prediction precision of a series of subsequent data is inaccurate.
An embodiment of a first aspect of the present application provides a method for predicting a load of an energy source, including: acquiring an hourly historical load value in a first preset time period before a day to be predicted and hourly load value influence factors of the day to be predicted; wherein the load value influencing factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model.
According to the energy load prediction method, the historical load value of each hour in the first preset time period before the day to be predicted and the load value influence factors of each hour on the day to be predicted are obtained; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the load prediction precision can be improved.
In a second aspect of the present application, an apparatus for predicting a load of an energy source is provided, including: the system comprises a first obtaining module, a second obtaining module and a third obtaining module, wherein the first obtaining module is used for obtaining the historical load value of each hour in a first preset time period before a day to be predicted and the load value influence factors of each hour on the day to be predicted; wherein the load value influencing factors include: at least one of temperature, humidity, weather type, season type, and date type; and the prediction module is used for inputting the historical load value into a prediction model by combining the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model.
According to the load prediction device of the energy source, historical load values of each hour in a first preset time period before a day to be predicted and load value influence factors of each hour on the day to be predicted are obtained; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the load prediction precision can be improved.
An embodiment of the third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method for load prediction of an energy source as set forth in the embodiment of the first aspect of the present application is implemented.
An embodiment of a fourth aspect of the present application proposes a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the method for load prediction of an energy source as proposed in an embodiment of the first aspect of the present application.
An embodiment of a fifth aspect of the present application provides a computer program product, which when executed by an instruction processor performs the method for load prediction of an energy source as set forth in the embodiment of the first aspect of the present application.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a method for predicting a load of an energy source according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a method for predicting a load of an energy source according to a second embodiment of the present application;
fig. 3 is a schematic flowchart of a method for predicting a load of an energy source according to an embodiment of the present disclosure;
fig. 4 is a schematic flowchart of a method for predicting a load of an energy source according to a third embodiment of the present application;
fig. 5 is a schematic structural diagram of a load prediction apparatus for an energy source according to a fourth embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The energy load prediction method, device and equipment according to the embodiments of the present application are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a method for predicting a load of an energy source according to an embodiment of the present disclosure.
The embodiment of the present application exemplifies that the energy load prediction method is configured in an energy load prediction device, and the energy load prediction device can be applied to any computer equipment, so that the computer equipment can perform the energy load prediction function.
The Computer device may be a Personal Computer (PC), a cloud device, a mobile terminal, and the like, and the mobile terminal may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.
As shown in fig. 1, the load prediction method of the energy source may include the steps of:
step 101, acquiring a historical load value of each hour in a first preset time period before a day to be predicted and load value influence factors of each hour on the day to be predicted; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type.
For example, from the day to be predicted, the historical load value per hour of the day before the day to be predicted is selected from the energy station, and the historical load value may include at least one of the following historical load values: an electrical historical load value, a thermal historical load value, a cold historical load value, a hot water historical load value, and a photovoltaic historical load value.
In the embodiment of the present application, the load value influence factors of each hour of the day to be predicted may be obtained through a web crawler, and the load value influence factors may include: at least one of temperature, humidity, weather type, season type, and date type.
It should be noted that the weather types may include: sunny, cloudy, showering, thunderstorm with hail, sleet, light rain, medium rain, heavy rain, extra heavy rain, snow gust, small snow, medium snow, heavy snow, and heavy snow, the date types may include: weekdays and non-weekdays.
And 102, inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model.
In the embodiment of the application, the historical load value of each hour in the first preset time period before the day to be predicted is combined with the load value influence factor of each hour on the day to be predicted and input into the trained prediction model, and the output result of the prediction model is processed to obtain the load prediction value of the day to be predicted.
In conclusion, historical load values of each hour in a first preset time period before the day to be predicted and load value influence factors of each hour on the day to be predicted are obtained; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the prediction accuracy of the load is improved.
In order to improve the prediction accuracy of the load, as shown in fig. 2, fig. 2 is a schematic flowchart of a method for predicting the load of the energy source according to a second embodiment of the present application, and in the embodiment of the present application, before the historical load value is combined with the load value influence factor and input into the prediction model, an initial prediction model may be trained to obtain a trained prediction model. The embodiment shown in fig. 2 comprises the following steps:
step 201, acquiring a historical load value of each hour in a first preset time period before a day to be predicted and load value influence factors of each hour of the day to be predicted; wherein the load value influencing factors include: at least one of temperature, humidity, weather type, season type, and date type.
Step 202, obtaining an hourly sample historical load value in a second preset time period before the day to be predicted and hourly sample load value influence factors in the second preset time period and the day to be predicted.
For example, from the day to be predicted, an average historical load value of 100 days per hour of the seasonal history is selected forward, and the average historical load value is used as a sample historical load value. The sample historical load value may include at least one of the following average historical load values: a level average historical load value, a hot average historical load value, a cold average historical load value, a hot water average historical load value, and a photovoltaic average historical load value.
In this embodiment of the present application, sample load value influencing factors of each hour of a day to be predicted and within a second preset time period before the day to be predicted may be obtained by a web crawler, where the sample load value influencing factors may include: at least one of temperature, humidity, weather type, season type, and date type. For example, the influence factors of the sample load value of 100 days in the seasonal history before the day to be predicted and each hour of the day to be predicted are obtained.
And step 203, respectively carrying out normalization processing on the sample historical load value and the sample load value influence factor to obtain the normalized sample historical load value and the sample load value influence factor.
In order to facilitate normalization of the sample load value influence factors, the weather type, the season type and the date type in the sample load value influence factors can be quantized respectively, the result of quantization of the weather type is shown in table 1, and the result of quantization of the season type is: the winter value is-1, the transition season (e.g., spring and autumn) value is 0, the summer value is 1, and the date type quantization processing result is: the working day value is 1 and the non-working day value is 0. Meanwhile, the temperature and the humidity in the sample load value influence factors can be respectively processed to obtain at least one of the maximum temperature, the minimum temperature and the average temperature corresponding to the temperature and at least one of the maximum humidity, the minimum humidity and the average humidity corresponding to the humidity. For example, the temperature of each hour in the sample load value influence factor of a certain day is compared to obtain the maximum temperature and the minimum temperature corresponding to the temperature, and for example, the temperature of each hour in the sample load value influence factor of a certain day is compared with the corresponding hour number (for example, 24 hours) to obtain the average temperature corresponding to the temperature.
TABLE 1 weather type quantification
Figure BDA0003145856120000071
In order to improve the load prediction accuracy and the prediction speed, the historical load value of the sample and the influence factor of the load value of the sample can be respectively normalized.
As an example, whether the historical load value of the sample and the influence factor of the sample load value are in the corresponding preset ranges is judged, and when the historical load value of the sample and/or the influence factor of the sample load value are not in the corresponding preset ranges, the historical load value of the sample and/or the influence factor of the sample load value are/is set according to the upper limit value and/or the lower limit value of the corresponding preset ranges. For example, the upper limit value and the lower limit value of the preset range corresponding to the sample historical load value and the sample load value influence factor are shown in table 2, and if the sample historical load value is greater than the upper limit value of the preset range, the value of the sample historical load value is the upper limit value of the preset range; if the historical load value of the sample is smaller than the lower limit value of the preset range, the value of the historical load value of the sample is the lower limit value of the preset range, and similarly, the value of the influence factor of the sample load value can be obtained.
TABLE 2 Upper and lower limits of the preset range corresponding to the sample historical load value and sample load value influencing factor
Figure BDA0003145856120000072
And 204, generating a training data set according to the normalized sample historical load value and the sample load value influence factors.
In order to improve the load prediction accuracy, in the embodiment of the present application, the normalized historical load value of the sample and the influence factor of the load value of the sample may be divided into a plurality of groups of training data, and the plurality of groups of training data are used as a training data set.
For example, the average historical load value of 100 days per hour of the same-season history before the day to be predicted, the average historical load value of 100 days per season history before the day to be predicted, and the sample load value influence factors of each hour of the day to be predicted are normalized, the normalized average historical load value from the 1 st day to the 99 th day after the normalization processing is combined with the normalized date type, season type, weather type, maximum temperature, minimum temperature, average temperature, maximum humidity, minimum humidity, and average humidity from the 2 nd day to the 100 th day after the normalization processing as input values, and the normalized load value from the 2 nd day to the 100 th day after the normalization processing is used as a target value. For example, the average historical load value per hour on the first day after normalization processing is combined with the sample load value influence factors such as the date type, the season type, the weather type, the maximum temperature, the minimum temperature, the average temperature, the minimum humidity, the maximum humidity, and the average humidity per hour on the second day after normalization processing as input data, the average historical load value per hour on the second day within 100 days after normalization processing is output, the average historical load value per hour on the second day after normalization processing is combined with the sample load value influence factors such as the date type, the season type, the weather type, the maximum temperature, the minimum temperature, the average temperature, the minimum humidity, the maximum humidity, and the average humidity per hour on the third day after normalization processing as input data, the average historical load value per hour on the third day after normalization processing is output, and so on, the average historical load value per hour on the 99 th day after normalization processing is combined with the average historical load value per hour on the 100 th day after normalization processing The sample load value influence factors such as the date type, the season type, the weather type, the highest temperature, the lowest temperature, the average temperature, the lowest humidity, the highest humidity and the average humidity are used as input data, and the average historical load value of each hour on the 100 th day after normalization processing is used as output.
Step 205, training the initial prediction model according to the training data set.
Then, each set of training data in the training data set is used to train the initial prediction model, for example, the coefficients of the prediction model are adjusted to improve the prediction accuracy of the prediction model. Wherein the initial predictive model may be an untrained recurrent neural network.
And step 206, inputting the historical load value into the prediction model by combining with the load value influence factors, and obtaining a load prediction value of the day to be predicted according to the output result of the prediction model.
It should be noted that step 201 and step 206 may be implemented by any implementation manner of various embodiments in the present application, and the present application is not particularly limited.
In order to more clearly illustrate the above embodiments, the description will now be made by way of example.
For example, as shown in fig. 3, (1) selection of variables: acquiring the influence load factors of each hour on the day to be predicted;
(2) data acquisition and processing: selecting a historical load value of each hour of a day before a day to be predicted, and respectively carrying out normalization processing on the historical load value and the load influencing factors;
(3) off-line training: training the initial prediction model by using the hourly sample historical load value in a second preset time period (such as 100 days) before the day to be predicted and the hourly sample load value influence factors in the second preset time period and the day to be predicted to obtain a prediction model;
(4) online prediction: and inputting the normalized historical load value into a prediction model by combining with the influence load factors, performing inverse normalization processing on the model input result to obtain a load prediction value of a day to be predicted, and taking the predicted load prediction value as a next predicted historical load value.
In conclusion, the historical load value of each hour in a second preset time period before the day to be predicted and the influence factors of the load value of each hour in the second preset time period and the day to be predicted are obtained; respectively carrying out normalization processing on the historical load value of the sample and the influence factors of the sample load value to obtain the historical load value of the sample and the influence factors of the sample load value after the normalization processing; generating a training data set according to the normalized sample historical load value and the sample load value influence factors; the initial predictive model is trained based on the training data set. Therefore, the training data can be kept as the corresponding data in the second preset time period before the day to be predicted, the rolling prediction is realized, the prediction precision of the prediction model is improved, meanwhile, the prediction speed is improved, and the storage cost is saved.
In order to save storage cost and increase calculation speed, as shown in fig. 4, fig. 4 is a schematic flow chart of a method for predicting load of energy provided in a third embodiment of the present application, in the embodiment of the present application, before the historical load value is combined with the load value influence factor and input into a prediction model, normalization processing is performed on the historical load value and the load value influence factor, respectively, and the embodiment shown in fig. 4 includes the following steps:
step 401, acquiring a historical load value of each hour in a first preset time period before a day to be predicted and load value influence factors of each hour on the day to be predicted; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type.
And 402, respectively carrying out normalization processing on the historical load value and the load value influence factor to obtain the historical load value and the load value influence factor after the normalization processing.
In order to facilitate normalization of the load value influencing factors, the weather type, the season type and the date type in the load value influencing factors can be quantized respectively, the result of quantization of the weather type is shown in table 1 in the embodiment shown in fig. 2, and the result of quantization of the season type is: the value in winter is-1, the value in transition seasons (spring and autumn) is 0, the value in summer is 1, and the date type quantization processing result is as follows: the working day value is 1 and the non-working day value is 0. Meanwhile, the temperature and the humidity in the load value influence factors can be respectively processed to obtain at least one of the maximum temperature, the minimum temperature and the average temperature corresponding to the temperature and at least one of the maximum humidity, the minimum humidity and the average humidity corresponding to the humidity.
In order to improve the load prediction accuracy and the prediction speed, the historical load value and the load value influence factor can be respectively normalized.
As an example, whether the historical load value and the load value influence factor are in the corresponding preset range is judged, and when the historical load value and/or the load value influence factor are not in the corresponding preset range, the historical load value and/or the load value influence factor are set according to the upper limit value and/or the lower limit value of the corresponding preset range. For example, the upper limit value and the lower limit value of the preset range corresponding to the historical load value and the load value influence factor are as shown in table 2 in the embodiment shown in fig. 2, and if the historical load value is greater than the upper limit value of the corresponding preset range, the value of the historical load value is the upper limit value of the corresponding preset range; if the historical load value is smaller than the lower limit value of the corresponding preset range, the value of the historical load value is the lower limit value of the corresponding preset range, and similarly, the value of the load value influence factor can be taken.
And 403, inputting the historical load value into a prediction model in combination with the load value influence factors, and obtaining a load prediction value of the day to be predicted according to an output result of the prediction model.
In the embodiment of the application, the historical load value can be input into the prediction model by combining with the load value influence factor, the output result of the prediction model is subjected to inverse normalization processing, and the output result after the inverse normalization processing is used as the load prediction value.
It should be noted that, the step 401 may be implemented by any implementation manner of each embodiment in the present application, and the present application is not particularly limited.
In summary, the historical load value and the load value influence factor after the normalization processing are obtained by respectively performing the normalization processing on the historical load value and the load value influence factor, the historical load value after the normalization processing is input into the prediction model by combining the load value influence factor, and the load prediction value of the day to be predicted is obtained according to the output result of the prediction model. This can improve the load prediction accuracy and the prediction speed.
According to the energy load prediction method, the historical load value of each hour in the first preset time period before the day to be predicted and the load value influence factors of each hour on the day to be predicted are obtained; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the prediction accuracy of the load is improved.
In correspondence with the method for predicting the load of the energy source according to the embodiment of fig. 1 to 4, the present application also provides a device for predicting the load of the energy source, and since the device for predicting the load of the energy source according to the embodiment of the present application corresponds to the method for predicting the load of the energy source according to the embodiment of fig. 1 to 4, the embodiment of the method for predicting the load of the energy source according to the embodiment of the present application is also applicable to the device for predicting the load of the energy source according to the embodiment of the present application, and will not be described in detail in the embodiment of the present application.
Fig. 5 is a schematic structural diagram of a load prediction apparatus for an energy source according to a fourth embodiment of the present application.
As shown in fig. 5, the load prediction apparatus 500 of the energy source may include: a first acquisition module 510 and a prediction module 520.
The first obtaining module 510 is configured to obtain a historical load value of each hour in a first preset time period before a day to be predicted and a load value influence factor of each hour on the day to be predicted; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and the prediction module 520 is used for inputting the historical load value into the prediction model by combining with the load value influence factor, and obtaining a load prediction value of the day to be predicted according to the output result of the prediction model.
As a possible implementation manner of the embodiment of the present application, the apparatus 500 for predicting load of energy source further includes: the device comprises a second acquisition module, a first processing module, a generation module and a training module.
The second obtaining module is used for obtaining the sample historical load value of each hour in a second preset time period before the day to be predicted and the sample load value influence factors of each hour in the second preset time period and the day to be predicted; the first processing module is used for respectively carrying out normalization processing on the historical load value of the sample and the influence factors of the sample load value to obtain the historical load value of the sample and the influence factors of the sample load value after the normalization processing; the generating module is used for generating a training data set according to the normalized sample historical load value and the sample load value influence factors; and the training module is used for training the initial prediction model according to the training data set.
As a possible implementation manner of the embodiment of the present application, the apparatus 500 for predicting load of energy source further includes: and a second processing module.
The second processing module is used for respectively carrying out normalization processing on the historical load value and the load value influence factors so as to obtain the historical load value and the load value influence factors after the normalization processing.
As a possible implementation manner of the embodiment of the present application, the second processing module is specifically configured to: judging whether the historical load value and the load value influence factor are in a corresponding preset range; and when the historical load value and/or the load value influence factor are not in the corresponding preset range, setting the historical load value and/or the load value influence factor according to the upper limit value and/or the lower limit value of the corresponding preset range.
As a possible implementation manner of the embodiment of the present application, the second processing module is further configured to: when the historical load value and/or the load value influence factor are greater than or equal to the upper limit value of the corresponding preset range, setting the historical load value and/or the load value as the upper limit value of the corresponding preset range; and when the historical load value and/or the load value influence factor are smaller than the lower limit value of the corresponding preset range, setting the historical load value and/or the load value as the lower limit value of the corresponding preset range.
As a possible implementation manner of the embodiment of the present application, the second processing module is further configured to: respectively carrying out quantization processing on the weather type, the season type and the date type in the load value influence factors to obtain at least one of the weather type, the season type and the date type after the quantization processing; and respectively processing the temperature and the humidity in the load value influence factors to obtain at least one of the maximum temperature, the minimum temperature and the average temperature corresponding to the temperature and at least one of the maximum humidity, the minimum humidity and the average humidity corresponding to the humidity.
According to the load prediction device of the energy source, historical load values of each hour in a first preset time period before a day to be predicted and load value influence factors of each hour on the day to be predicted are obtained; wherein, the load value influence factors include: at least one of temperature, humidity, weather type, season type, and date type; and inputting the historical load value into a prediction model by combining with the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model. Therefore, the historical load value is combined with the load value influence factor and input into the trained prediction model, the load prediction value of the day to be predicted is obtained according to the output result of the prediction model, and the load prediction precision is improved.
In order to implement the foregoing embodiments, the present application also provides a computer device, including: the energy source load prediction method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the program, the energy source load prediction method is realized according to the embodiment of the application.
In order to achieve the above embodiments, the present application also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the load prediction method of an energy source as proposed in the previous embodiments of the present application.
In order to achieve the above embodiments, the present application further proposes a computer program product, which when executed by an instruction processor in the computer program product, executes the method for predicting the load of the energy source as proposed in the foregoing embodiments of the present application.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (14)

1. A method for predicting a load on an energy source, comprising:
acquiring an hourly historical load value in a first preset time period before a day to be predicted and hourly load value influence factors of the day to be predicted; wherein the load value influencing factors include: at least one of temperature, humidity, weather type, season type, and date type;
and inputting the historical load value into a prediction model by combining the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model.
2. The method of claim 1, wherein prior to inputting the historical load values in combination with the load value influencing factors into a predictive model, the method further comprises:
acquiring an hourly sample historical load value in a second preset time period before a day to be predicted and hourly sample load value influence factors in the second preset time period and the day to be predicted;
respectively carrying out normalization processing on the historical load value of the sample and the influence factors of the sample load value to obtain the historical load value of the sample and the influence factors of the sample load value after the normalization processing;
generating a training data set according to the normalized sample historical load value and the sample load value influence factors;
and training the initial prediction model according to the training data set.
3. The method of claim 1, wherein prior to inputting the historical load values in combination with the load value influencing factors into a predictive model, further comprising:
and respectively carrying out normalization processing on the historical load value and the load value influence factors to obtain the historical load value and the load value influence factors after the normalization processing.
4. The method according to claim 3, wherein the normalizing the historical load value and the load value influence factor to obtain a normalized historical load value and a normalized load value influence factor respectively comprises:
judging whether the historical load value and the load value influence factor are in a corresponding preset range;
and when the historical load value and/or the load value influence factor are not in the corresponding preset range, setting the historical load value and/or the load value influence factor according to the upper limit value and/or the lower limit value of the corresponding preset range.
5. The method according to claim 4, wherein when the historical load value and/or the load value influence factor are not in the corresponding preset range, setting the historical load value and/or the load value influence factor according to an upper limit value and/or a lower limit value of the preset range comprises:
when the historical load value and/or the load value influence factor are larger than or equal to the upper limit value of the corresponding preset range, setting the historical load value and/or the load value as the upper limit value of the corresponding preset range;
and when the historical load value and/or the load value influence factor are smaller than the lower limit value of the corresponding preset range, setting the historical load value and/or the load value as the lower limit value of the corresponding preset range.
6. The method according to claim 3 or 4, before normalizing the historical load value and the load value influence factor to obtain the processed historical load value and load value influence factor, further comprising:
respectively carrying out quantization processing on the weather type, the season type and the date type in the load value influence factors to obtain at least one of the weather type, the season type and the date type after the quantization processing;
and respectively processing the temperature and the humidity in the load value influence factors to obtain at least one of the maximum temperature, the minimum temperature and the average temperature corresponding to the temperature and at least one of the maximum humidity, the minimum humidity and the average humidity corresponding to the humidity.
7. An apparatus for predicting a load on an energy source, comprising:
the system comprises a first obtaining module, a second obtaining module and a third obtaining module, wherein the first obtaining module is used for obtaining the historical load value of each hour in a first preset time period before a day to be predicted and the load value influence factors of each hour on the day to be predicted; wherein the load value influencing factors include: at least one of temperature, humidity, weather type, season type, and date type;
and the prediction module is used for inputting the historical load value into a prediction model by combining the load value influence factors, and obtaining a load prediction value of a day to be predicted according to an output result of the prediction model.
8. The apparatus of claim 7, further comprising:
the second obtaining module is used for obtaining the hourly sample historical load value in a second preset time period before the day to be predicted and the hourly sample load value influence factors in the second preset time period and the day to be predicted;
the first processing module is used for respectively carrying out normalization processing on the historical sample load value and the sample load value influence factors to obtain the historical sample load value and the sample load value influence factors after the normalization processing;
the generating module is used for generating a training data set according to the normalized sample historical load value and the sample load value influence factors;
and the training module is used for training the initial prediction model according to the training data set.
9. The apparatus of claim 7, further comprising:
and the second processing module is used for respectively carrying out normalization processing on the historical load value and the load value influence factors so as to obtain the historical load value and the load value influence factors after the normalization processing.
10. The apparatus according to claim 9, wherein the second processing module is specifically configured to:
judging whether the historical load value and the load value influence factor are in a corresponding preset range;
and when the historical load value and/or the load value influence factor are not in the corresponding preset range, setting the historical load value and/or the load value influence factor according to the upper limit value and/or the lower limit value of the corresponding preset range.
11. The apparatus of claim 10, the second processing module further to:
when the historical load value and/or the load value influence factor are larger than or equal to the upper limit value of the corresponding preset range, setting the historical load value and/or the load value as the upper limit value of the corresponding preset range;
and when the historical load value and/or the load value influence factor are smaller than the lower limit value of the corresponding preset range, setting the historical load value and/or the load value as the lower limit value of the corresponding preset range.
12. The apparatus of claim 9 or 10, the second processing module to further:
respectively carrying out quantization processing on the weather type, the season type and the date type in the load value influence factors to obtain at least one of the weather type, the season type and the date type after the quantization processing;
and respectively processing the temperature and the humidity in the load value influence factors to obtain at least one of the maximum temperature, the minimum temperature and the average temperature corresponding to the temperature and at least one of the maximum humidity, the minimum humidity and the average humidity corresponding to the humidity.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, when executing the program, implementing the method of load prediction of an energy source according to any of claims 1-6.
14. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method for load prediction of an energy source according to any one of claims 1-6.
CN202110750161.2A 2021-07-02 2021-07-02 Energy load prediction method, device and equipment Pending CN113947007A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110750161.2A CN113947007A (en) 2021-07-02 2021-07-02 Energy load prediction method, device and equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110750161.2A CN113947007A (en) 2021-07-02 2021-07-02 Energy load prediction method, device and equipment

Publications (1)

Publication Number Publication Date
CN113947007A true CN113947007A (en) 2022-01-18

Family

ID=79327333

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110750161.2A Pending CN113947007A (en) 2021-07-02 2021-07-02 Energy load prediction method, device and equipment

Country Status (1)

Country Link
CN (1) CN113947007A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114565156A (en) * 2022-02-28 2022-05-31 广东电网有限责任公司 Power load prediction method, device, equipment and storage medium
CN114742263A (en) * 2022-03-02 2022-07-12 北京百度网讯科技有限公司 Load prediction method, load prediction device, electronic device, and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114565156A (en) * 2022-02-28 2022-05-31 广东电网有限责任公司 Power load prediction method, device, equipment and storage medium
CN114742263A (en) * 2022-03-02 2022-07-12 北京百度网讯科技有限公司 Load prediction method, load prediction device, electronic device, and storage medium
CN114742263B (en) * 2022-03-02 2024-03-01 北京百度网讯科技有限公司 Load prediction method, device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
Raza et al. An ensemble framework for day-ahead forecast of PV output power in smart grids
US20190265768A1 (en) Method, system and storage medium for predicting power load probability density based on deep learning
JP3984604B2 (en) Method, apparatus, and program for predicting power generation amount of solar power generation system
CN113947007A (en) Energy load prediction method, device and equipment
CN110009140B (en) Daily power load prediction method and prediction device
CN110380444B (en) Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula
CN104732296A (en) Modeling method for distributed photovoltaic output power short-term prediction model
CN104036328A (en) Self-adaptive wind power prediction system and prediction method
CN115271253B (en) Method and device for constructing water-wind-solar power generation power prediction model and storage medium
CN112365056A (en) Electrical load joint prediction method and device, terminal and storage medium
CN113962491A (en) Short-term combined prediction method and device for cooling, heating and power loads based on seasonal decomposition
CN116402203A (en) Method, system and medium for predicting short-time photovoltaic power generation capacity considering weather conditions
CN116599050A (en) Photovoltaic prediction method and related device based on self-attention mechanism
CN116663746A (en) Power load prediction method and device, computer equipment and storage medium
CN115189416A (en) Power generation system control method and system based on day-ahead electricity price grading prediction model
CN113657936A (en) Power load prediction method and terminal
CN117200223A (en) Day-ahead power load prediction method and device
CN117613883A (en) Method and device for predicting generated power, computer equipment and storage medium
CN117013580A (en) Prediction-based energy storage regulation and control method and system thereof
CN117252288A (en) Regional resource active support capacity prediction method and system
CN116484998A (en) Distributed photovoltaic power station power prediction method and system based on meteorological similar day
CN114493051A (en) Photovoltaic power prediction method and device for improving precision based on combined prediction
CN117077986B (en) Situation awareness method and related equipment for extreme operation risk scene of power system
US20240195174A1 (en) Energy prediction device, energy prediction method, and energy prediction program
CN117217822B (en) Method, device, terminal equipment and storage medium for predicting power transaction index

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