CN110991745B - Power load prediction method and device, readable medium and electronic equipment - Google Patents
Power load prediction method and device, readable medium and electronic equipment Download PDFInfo
- Publication number
- CN110991745B CN110991745B CN201911234527.XA CN201911234527A CN110991745B CN 110991745 B CN110991745 B CN 110991745B CN 201911234527 A CN201911234527 A CN 201911234527A CN 110991745 B CN110991745 B CN 110991745B
- Authority
- CN
- China
- Prior art keywords
- data
- load
- power load
- time
- sharing
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000005611 electricity Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 abstract description 2
- 230000000737 periodic effect Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000001816 cooling Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004378 air conditioning Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method, a device, a readable medium and an electronic device for predicting a power load, wherein the method comprises the following steps: acquiring historical load data, and determining a first power load curve corresponding to an execution day according to the historical load data; acquiring at least one type of overall load related data and at least one type of time-sharing load related data; determining an overall adjustment parameter by using a preset prediction model and the overall load related data; determining time-sharing adjustment parameters by using the prediction model and the time-sharing load related data; adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day; through the analysis of the historical load data, a first power load curve which accords with the historical periodic rule of an energy consumer is obtained as a reference, and the influence generated by various overall load related data and time-sharing load related data is calculated, so that the power load on the execution day is predicted more comprehensively and accurately.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for predicting a power load, a readable medium, and an electronic device.
Background
The prediction of the power load is an important link in the process of the electric power spot transaction. Before the execution date of each transaction, the two transaction parties need to predict the power load of the energy consumers on the execution date so as to realize accurate energy supply.
In fact, the electrical load of the consumers is affected by a number of factors. There is a great difficulty in making predictions accurately. The existing power load prediction is usually subjective estimation by combining historical data and experience. Various influencing factors cannot be effectively brought into prediction, so that the accuracy needs to be improved.
Disclosure of Invention
The invention provides a power load prediction method, a power load prediction device, a readable medium and electronic equipment.
In a first aspect, the present invention provides a method for predicting a power load, including:
acquiring historical load data, and determining a first power load curve corresponding to an execution day according to the historical load data;
acquiring at least one type of overall load related data and at least one type of time-sharing load related data;
determining an overall adjustment parameter by using a preset prediction model and the overall load related data;
determining time-sharing adjustment parameters by using the prediction model and the time-sharing load related data;
and adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day.
Preferably, before the determining the overall adjustment parameter and the time-sharing adjustment parameter by using the predictive model, the method further includes:
and training by using sample data to obtain the prediction model, wherein the prediction model comprises a weight coefficient corresponding to each piece of integral load related data and a weight coefficient corresponding to each piece of time-sharing load related data.
Preferably, the determining an overall adjustment parameter by using a preset prediction model and the overall load related data includes:
and determining an overall adjustment parameter according to the overall load related data and the weight coefficient corresponding to the overall load related data by using the prediction model.
Preferably, the determining time-sharing adjustment parameters by using the prediction model and the time-sharing load-related data includes:
and determining time-sharing adjustment parameters according to the time-sharing load related data and the weight coefficient corresponding to the time-sharing load related data by using the prediction model.
Preferably, the adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to an execution day includes:
adjusting the values of all data points in the first power load curve using the global adjustment parameter;
adjusting the value of the corresponding data point in the first power load curve using the time-sharing adjustment parameter;
and determining the adjusted first power load curve as a second power load curve.
Preferably, said adjusting the values of all data points in said first power load curve using said overall adjustment parameter comprises:
dividing the overall adjustment parameter by the number of data points in the first power load curve to obtain an adjustment difference value for each data point;
adjusting the values of all data points in the first power load curve according to the adjustment difference.
Preferably, the overall load related data comprises load trend data, energy price index data, historical weather data, weather data corresponding to execution days and/or exchange rate data determined according to the historical load data; the time-sharing load related data comprises historical weather data, weather data corresponding to execution days and/or historical electricity price transaction data.
In a second aspect, the present invention provides an apparatus for predicting a power load, including:
the first curve determining module is used for acquiring historical load data and determining a first power load curve corresponding to an execution day according to the historical load data;
the data acquisition module is used for acquiring at least one type of overall load related data and at least one type of time-sharing load related data;
the integral adjustment parameter determining module is used for determining an integral adjustment parameter by utilizing a preset prediction model and the integral load related data;
the time-sharing adjustment parameter determining module is used for determining a time-sharing adjustment parameter by utilizing the prediction model and the time-sharing load related data;
and the second curve determining module is used for adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter so as to obtain a second power load curve corresponding to the execution day.
In a third aspect, the invention provides a readable medium comprising executable instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the method of predicting a power load as defined in any one of the first aspect.
In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing execution instructions, wherein when the processor executes the execution instructions stored in the memory, the processor performs the method for predicting the power load according to any one of the first aspect.
The invention provides a power load prediction method, a device, a readable medium and electronic equipment.
Further effects of the above-mentioned unconventional preferred modes will be described below in conjunction with specific embodiments.
Drawings
In order to more clearly illustrate the embodiments or the prior art solutions of the present invention, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
Fig. 1 is a flowchart illustrating a method for predicting a power load according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating another method for predicting a power load according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a power load prediction apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail and completely with reference to the following embodiments and accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. 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.
The prediction of the power load is an important link in the process of the electric power spot transaction. Before the execution date of each transaction, the two transaction parties need to predict the power load of the energy consumers on the execution date so as to realize accurate energy supply. Generally, the power load prediction for the execution day needs to be accurate to the unit of hour, that is, the power load of each hour is predicted to be taken as a data point, and a power load curve is formed by 24 data points corresponding to the execution day.
The power load of the energy consumer has obvious regularity. However, on the basis of the overall rule, the influence of various factors is also caused, so that the change is caused to a certain degree. Environmental factors such as weather, recent climate, season, etc. on the day of execution, energy price factors such as recent electricity trading price, coal price index, natural gas price index, etc., and economic factors such as exchange rate, etc., all have a certain influence on the power load. Some of these factors affect the total daily electrical load, and some directly affect the electrical load within one or more hours of the day.
The existing power load prediction is generally subjective estimation by combining historical data and experience. Various influencing factors cannot be effectively brought into the prediction, so the accuracy needs to be improved. Therefore, the method and the device for predicting the power load provided by the invention can realize the prediction of the power load on the execution day by analyzing the historical load data and determining the second power load curve by combining the first power load curve and the load trend data.
The embodiment of the invention provides a power load prediction method, so as to realize more accurate prediction of the power load. As shown in fig. 1, the method in this embodiment includes the following steps:
The historical load data may be the actual daily power load data of the energy consumer over a period of time in the past. For example, the actual daily power load curve of the energy consumer within the last 4 weeks may be specific.
It is understood that the energy consumer is typically a production unit of industrial, commercial, or agricultural nature. The work and production of the device are generally cycled in a period of 'weeks' and generally have obvious regularity. From practical experience, the power consumers often have higher similarity of power load conditions on the same day in each week. For example, the actual power load curves of consumers on each Monday are typically quite similar in shape. The same applies to Tuesday-Sunday.
Therefore, the present embodiment selects, from the historical load data, the power load curve of the corresponding natural day in the last week of the execution day as the first power load curve. For example, a power load curve on a monday, i.e., the last monday, is executed as the first power load curve. The first power load curve will be the baseline for prediction in this embodiment.
In this embodiment, the whole load related data and the time-sharing load related data are further obtained. Both include various relevant data that affect the electrical load. The overall load related data refers to data which can be found through a historical rule and can affect the total daily load of the execution day, such as energy price index data, historical weather data, weather data corresponding to the execution day, and/or exchange rate data. The time-sharing load related data refers to data which can be found through a historical rule and can influence the load amount of a specific time period in the execution day, such as historical weather data, weather data corresponding to the execution day, historical electricity price trading data and the like.
That is, in the present embodiment, based on the first power load curve, the total daily load on the execution day and the load amount of the specific time period on the execution day are adjusted, so that various types of influences are taken into the first power load curve to predict the power load on the execution day.
And 103, determining an overall adjustment parameter by using a preset prediction model and the overall load related data.
In this step, the whole load related data needs to be substituted into a preset prediction model to predict the influence of the whole load related data on the first power load curve, that is, to determine the whole adjustment parameter. The global trim parameter will affect all data points on the first power load curve. And subsequently, on the basis of the first power load curve, adjusting all data points of the first power load curve according to the overall adjustment parameters, namely completing the prediction of the influence generated by the overall load related data.
It should be noted that, since the influence of multiple factors on the power load is considered in the prediction method in this embodiment, the general overall load related data is not only of one type, but also of multiple types. And under different specific conditions, the influence degrees of various types of overall load related data are also different. Therefore, in this embodiment, the prediction model needs to be obtained by training with various sample data generated historically, and the prediction model includes a weight coefficient corresponding to each piece of overall load related data. That is, the weight coefficient corresponding to each of the overall load related data represents the influence degree of each type of overall load related data in the current situation. For example, if the recent weather condition changes obviously, historical weather data and weather data corresponding to the execution day may become overall load-related data with a large weight coefficient; or if the recent energy price fluctuates greatly, the energy price index data can become the overall load related data with a large weight coefficient.
The prediction model can also be trained again periodically to re-determine the weight coefficient corresponding to each type of overall load related data, so that the prediction of the influence degree of the prediction model on each type of overall load related data is accurate enough.
Furthermore, in this embodiment, a weighting calculation may be performed according to each piece of overall load-related data and a weighting coefficient corresponding to each piece of overall load-related data by using the prediction model, so as to determine an overall adjustment parameter. In the overall adjustment parameter, the influence of each overall load-related data is distributed according to the weight coefficient. In the training method of the prediction model in this embodiment, the calculation method of the overall adjustment parameter included in the prediction model is not limited, and any technical means capable of achieving the same or similar effect may be combined in the overall technical solution of this embodiment.
And 104, determining time-sharing adjustment parameters by using the prediction model and the time-sharing load related data.
In this step, the time-sharing load related data is substituted into a preset prediction model to predict the influence of the time-sharing load related data on the first power load curve, that is, to determine the time-sharing adjustment parameter. The time-sharing adjustment parameter will affect the data points corresponding to the specific time period on the first power load curve. For example, assume that the weather data display 12 corresponding to the execution day: 00 start temperature rise, 20: and 00 is decreased. Then it is possible to change the state of the mobile station between 12: 00 begins, the consumer needs more power for air conditioning cooling, until 20: 00 cooling is finished. Then, 12: 00-20: the power load between 00 will increase and each data point in the period will be affected, while the values of other data points may not be affected. Therefore, the time-sharing adjustment parameters only aim at 12: 00-20: 00. And subsequently, on the basis of the first power load curve, adjusting part of data points of the first power load curve according to the time-sharing adjustment parameters, namely, completing the prediction of the influence generated by the time-sharing load related data.
Also, the time-sharing load related data in this embodiment is not limited to one type. Therefore, the weight coefficient corresponding to each time-sharing load related data is also included in the prediction model. That is, the weight coefficient corresponding to each time-sharing load related data represents the influence degree of each time-sharing load related data under the current condition.
When the prediction model is trained again at regular intervals, the weight coefficient corresponding to each time-sharing load related data is also determined again, so that the prediction of the influence degree of the prediction model on each time-sharing load related data is ensured to be accurate enough.
Furthermore, in this embodiment, a time-sharing adjustment parameter may be determined according to each time-sharing load-related data and a weight coefficient corresponding to each time-sharing load-related data by using the prediction model. In this embodiment, the calculation method of the time-sharing adjustment parameter included in the prediction model is not limited, and any technical means capable of achieving the same or similar effect may be combined in the overall technical solution of this embodiment.
And 105, adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day.
The overall adjustment parameter and the time-sharing adjustment parameter are both the influence on the first power load curve calculated based on various influence factors, that is, a "difference" that data points on the first power load curve need to be superimposed. Therefore, the prediction of the power load on the execution day is realized by overlapping the overall adjustment parameter and the time-sharing adjustment parameter on the basis of the first power load curve.
Specifically, for the overall adjustment parameter, it is necessary to adjust the values of all data points in the first power load curve by using the overall adjustment parameter. Since the overall adjustment parameter is for the daily total load, if the total load is reflected on the power load curve, the total load is further distributed to the data points corresponding to the respective hours. In this example, the average allocation will be made for each hour. Dividing the whole adjustment parameter by the number of data points in the first power load curve to obtain an adjustment difference value for each data point; and adjusting the numerical values of all data points in the first power load curve according to the adjustment difference value. From a visualization point of view, it is therefore possible to translate the first power load curve in the coordinate system up or down without changing its curve shape. Assuming that the overall tuning parameter is x, and 24 data points are included in the first power load curve in units of hours, the difference is adjusted to be x/24. The values of all 24 data points in the first power load curve will be added to the adjustment difference, respectively, thereby completing the adjustment.
For the time-sharing adjustment parameter, it is required to adjust the value of the corresponding data point in the first power load curve by using the time-sharing adjustment parameter. Aiming at 12: 00-20: for example, the time period 00 is a time period, the time-sharing adjustment parameter needs to include a value to be adjusted specifically for each data point in the time period, and the adjustment values are respectively superimposed with the data point values corresponding to the time period, thereby completing the adjustment. From the visualization point of view, that is, a part of data points in the first power load curve are translated up or down in the coordinate system, so as to change the curve shape.
In this embodiment, the adjusted first power load curve is determined as the second power load curve. The second power load curve is based on the first power load curve, and is superposed with the influence of various overall load related data and time-sharing load related data. The second power load curve may be a prediction of the power load for the current day of execution.
According to the technical scheme, the beneficial effects of the embodiment are as follows: through analysis of historical load data, a first power load curve which accords with the historical periodic rule of an energy consumer is obtained as a reference, and the influence generated by overlapping various overall load related data and time-sharing load related data is calculated, so that the power load on the execution day is predicted more comprehensively and accurately.
Fig. 1 shows only a basic embodiment of the method of the present invention, and based on this, certain optimization and expansion can be performed, and other preferred embodiments of the method can also be obtained.
Fig. 2 shows another embodiment of the method for predicting the power load according to the present invention. The present embodiment is described with reference to specific scenarios on the basis of the foregoing embodiments. In this embodiment, the overall load related data includes load trend data and energy price index data determined according to the historical load data; the time-sharing load related data comprises weather data corresponding to an execution day. The method specifically comprises the following steps:
In this embodiment, it is assumed that the data points in the first power load curve are in hours. That is, the first power load curve includes 24 data points from 0 hour to 23 hours of the day, and the numerical value of each data point is (a0, a2, a3 … … a 23).
In this embodiment, the overall load-related data includes load trend data and energy price index data determined according to the historical load data.
Wherein, the load trend data means that the electric load in the near future of the energy consumer will show a specific variation trend, which can be calculated by the historical load data. For example, when the recent air temperature gradually increases, the consumers need more power for air conditioning cooling, so the daily total amount of power load may show a tendency to gradually increase. The power load situation of the execution day can be predicted according to the change trend analyzed from the historical load data.
In this embodiment, at least one load trend data is calculated according to the historical load data. Where the historical load data includes the actual power load profile for each day over the past 4 weeks (i.e., 28 days), the load trend data may include first load trend data and second load trend data. Specifically, the daily average power load value on the last 7 days, the daily average power load value on the last 14 days, and the daily average power load value on the last 28 days may be calculated, respectively. Then, the daily average power load value on the next 7 days and the daily average power load value on the next 14 days (specifically, a difference value) are determined to determine the first load tendency data. The daily average power load value on the nearer day 14 and the daily average power load value on the nearer day 28 (specifically, a difference value) are used to determine the second load trend data.
The energy price index data may also affect the power load of the energy consumer. It is understood that electricity generation requires consumption of a specific energy source, and the price of the energy source is related to the cost of electricity production, i.e., the price of electricity is directly affected. The electricity price will affect the total daily load of the energy consumers. Similarly, in other cases, the exchange rate data may also be considered as overall load-related data. The exchange rate affects the import and export price of energy, thereby indirectly affecting the cost of power production. In addition, other weather data such as historical weather data and weather data corresponding to the execution day may also be used as the overall load data in some cases, and the influence principle thereof need not be described herein. In short, the total daily load which may affect the energy consumers can be analyzed and determined through historical experience, objective rules and economic rules, and all the daily load can be selected as the whole load data under the whole scheme of the invention.
The time-sharing load related data comprises weather data corresponding to an execution day. The weather data corresponding to the execution day will have an effect on the power load situation on the execution day. Specifically, in this embodiment, the weather data corresponding to the execution day is time-sharing weather data, that is, the weather condition of 24 hours on the execution day can be reflected. The weather change situation between 24 hours of the execution day can affect the power load of the execution day in a time sharing manner. That is, the weather for a particular time period will specifically affect the data point values on the power load curve for that time period. For example, it has been assumed in the embodiment shown in FIG. 1 that if the weather data display 12: 00 start temperature rise, 20: and 00 is decreased. Then it is possible to change the state of the mobile station between 12: 00 begins, the consumer needs more power for air conditioning cooling, until 20: and 00, cooling is finished. Then, 12: 00-20: the power load between 00 will increase and each data point in the period will be affected (causing an increase in value) while the values of other data points may not be affected.
And step 203, determining an overall adjustment parameter by using a preset prediction model and the overall load related data.
In this embodiment, the load trend data and the energy price index data are substituted into a prediction model to calculate an overall adjustment parameter. In the calculation process of the prediction model, the influence degree of the load trend data and the energy price index data on the power load on the execution day is determined through previous model training, and the weight coefficients are respectively configured for the load trend data and the energy price index data according to the influence degree. The influence of the prediction model and the daily load weight can be quantified through calculation of the prediction model, and a corresponding influence value is obtained. And then carrying out weighting calculation according to the influence numerical value and the weight coefficient to obtain the integral adjustment parameter. The following formula can be referred to:
x is w1x1+ w2x2, where x represents the overall tuning parameter, x1 represents the influence value of the load trend data, x2 represents the influence value of the energy price index data, w1 represents the weight coefficient of the load trend data, and w2 represents the weight coefficient of the energy price index data.
And step 204, determining time-sharing adjustment parameters by using the prediction model and the time-sharing load related data.
In this embodiment, the time-sharing load related data will affect 12: 00-20: 00. The time-sharing adjustment parameters calculated by the prediction model include the corresponding influence values for each data point in the time period, which are specifically represented as (y12, y13, y14 … … y 20).
It should be noted that, if a plurality of time-sharing load-related data are included, in the calculation process of the prediction model, the influence degree of each time-sharing load-related data is determined through previous model training, and the weight coefficients are respectively configured for the two according to the influence degrees. The influence of each time-sharing load related data on each data point can be quantified through calculation of the prediction model, and a corresponding influence value is obtained. And then, carrying out weighting calculation according to the influence numerical value and the weight coefficient to obtain the time-sharing adjustment parameter.
And step 205, adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day.
Since the overall adjustment parameter is for the daily total load, if the total load is reflected on the power load curve, the total load is further distributed to the data points corresponding to the respective hours. In this example, the average allocation will be made for each hour. Namely, dividing the integral adjustment parameter by the number of data points in the first power load curve to obtain an adjustment difference value for each data point. That is, the adjustment difference for each data point in the first power load curve is x/24. Meaning that (a0, a2, a3 … … a23) all need to be superimposed with x/24. The time-sharing adjustment parameters only affect 12: 00-20: a period of 00, i.e., where (a 12-a 20) needs to be superimposed with (y 12-y 20).
For example, for 00: and b, superposing x/24 on a data point a0 corresponding to 00 to obtain a data point a0+ x/24 as a data point in a second power load curve 00: 00 corresponding data point. For 12: and 00, if a data point a12 corresponding to the point 00 needs to be superposed with x/24 and y12, namely a12+ x/24+ y12 is obtained as 12 in the second power load curve: 00 corresponding data point. Therefore, all 24 data points in the second power load curve can be determined, namely, the complete second power load curve is obtained, and the prediction of the power load on the execution day is realized.
And step 206, determining a load confidence interval corresponding to the execution day according to the historical load data.
In addition, after the second power load curve is determined, the present embodiment may further perform statistical calculation in combination with the historical load data to determine confidence intervals, such as upper and lower limit values, expected values, and the like, of each data point corresponding to each hour on the execution day. The load confidence interval is compared with the second power load curve, so that the accuracy of the second power load curve, the ratio/ring ratio change and the like can be further evaluated.
According to the embodiment, the power load prediction is carried out by combining various related influence factors, and the prediction accuracy is further improved.
Fig. 3 shows an embodiment of the power load prediction apparatus according to the present invention. The apparatus of this embodiment is a physical apparatus for performing the method described in fig. 1-2. The technical solution is essentially the same as that in the above embodiment, and the corresponding description in the above embodiment is also applicable to this embodiment. The device in this embodiment includes:
the first curve determining module 301 obtains historical load data, and determines a first power load curve corresponding to an execution day according to the historical load data.
A data obtaining module 302, configured to obtain at least one type of overall load related data and at least one type of time-sharing load related data.
And an overall adjustment parameter determining module 303, configured to determine an overall adjustment parameter by using a preset prediction model and the overall load related data.
And a time-sharing adjustment parameter determining module 304, configured to determine a time-sharing adjustment parameter by using the prediction model and the time-sharing load related data.
The second curve determining module 305 adjusts the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. On the hardware level, the electronic device comprises a processor and optionally an internal bus, a network interface and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
And the memory is used for storing the execution instruction. In particular, a computer program that can be executed by executing instructions. The memory may include both memory and non-volatile storage and provides execution instructions and data to the processor.
In a possible implementation manner, the processor reads the corresponding execution instruction from the nonvolatile memory into the memory and then runs the corresponding execution instruction, and the corresponding execution instruction can also be obtained from other equipment so as to form the prediction device of the power load on a logic level. The processor executes the execution instructions stored in the memory, so that the power load prediction method provided by any embodiment of the invention is realized through the executed execution instructions.
The method executed by the power load prediction apparatus according to the embodiment of the present invention shown in fig. 4 may be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
Embodiments of the present invention further provide a readable storage medium, which stores an execution instruction, and when the stored execution instruction is executed by a processor of an electronic device, the electronic device can be caused to execute the method for predicting a power load provided in any embodiment of the present invention, and is specifically configured to execute the method shown in fig. 1 to 3.
The electronic device described in the foregoing embodiments may be a computer.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present invention, and is not intended to limit the present invention. Various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims (8)
1. A method for predicting a power load, comprising:
acquiring historical load data, and determining a first power load curve corresponding to an execution day according to the historical load data;
acquiring at least one type of overall load related data and at least one type of time-sharing load related data;
determining an overall adjustment parameter by using a preset prediction model and the overall load related data;
determining time-sharing adjustment parameters by using the prediction model and the time-sharing load related data;
adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day;
the adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day includes:
adjusting the values of all data points in the first power load curve using the overall adjustment parameter;
adjusting the value of the corresponding data point in the first power load curve using the time-sharing adjustment parameter;
determining the adjusted first power load curve as a second power load curve;
said adjusting the values of all data points in said first power load curve using said overall adjustment parameter comprises:
dividing the overall adjustment parameter by the number of data points in the first power load curve to obtain an adjustment difference value for each data point;
adjusting the values of all data points in the first power load curve according to the adjustment difference.
2. The method of claim 1, wherein prior to determining the global adjustment parameter and the time-share adjustment parameter using the predictive model, further comprising:
and training by using sample data to obtain the prediction model, wherein the prediction model comprises a weight coefficient corresponding to each piece of integral load related data and a weight coefficient corresponding to each piece of time-sharing load related data.
3. The method of claim 2, wherein determining the global tuning parameters using the predetermined predictive model and the global load related data comprises:
and determining an overall adjustment parameter according to the overall load related data and the weight coefficient corresponding to the overall load related data by using the prediction model.
4. The method of claim 2, wherein determining a time-share adjustment parameter using the predictive model and time-share load-related data comprises:
and determining time-sharing adjustment parameters according to the time-sharing load related data and the weight coefficient corresponding to the time-sharing load related data by using the prediction model.
5. The method according to any one of claims 1 to 4, wherein:
the overall load related data comprises load trend data, energy price index data, historical weather data, weather data corresponding to execution days and/or exchange rate data which are determined according to the historical load data;
the time-sharing load related data comprises historical weather data, weather data corresponding to execution days and/or historical electricity price transaction data.
6. An apparatus for predicting an electric load, comprising:
the first curve determining module is used for acquiring historical load data and determining a first power load curve corresponding to an execution day according to the historical load data;
the data acquisition module is used for acquiring at least one type of overall load related data and at least one type of time-sharing load related data;
the integral adjustment parameter determining module is used for determining an integral adjustment parameter by utilizing a preset prediction model and the integral load related data;
the time-sharing adjustment parameter determining module is used for determining a time-sharing adjustment parameter by utilizing the prediction model and the time-sharing load related data;
the second curve determining module is used for adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter so as to obtain a second power load curve corresponding to the execution day;
the second curve determining module is specifically configured to:
the adjusting the first power load curve by using the overall adjustment parameter and the time-sharing adjustment parameter to obtain a second power load curve corresponding to the execution day includes:
adjusting the values of all data points in the first power load curve using the overall adjustment parameter; the method comprises the following steps: dividing the overall adjustment parameter by the number of data points in the first power load curve to obtain an adjustment difference value for each data point; adjusting the values of all data points in the first power load curve according to the adjustment difference;
adjusting the value of the corresponding data point in the first power load curve using the time-sharing adjustment parameter;
and determining the adjusted first power load curve as a second power load curve.
7. A readable medium comprising executable instructions which, when executed by a processor of an electronic device, cause the electronic device to perform the method of predicting a power load as claimed in any one of claims 1 to 5.
8. An electronic device comprising a processor and a memory storing execution instructions, the processor performing the method of predicting the power load according to any one of claims 1 to 5 when the processor executes the execution instructions stored in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911234527.XA CN110991745B (en) | 2019-12-05 | 2019-12-05 | Power load prediction method and device, readable medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911234527.XA CN110991745B (en) | 2019-12-05 | 2019-12-05 | Power load prediction method and device, readable medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110991745A CN110991745A (en) | 2020-04-10 |
| CN110991745B true CN110991745B (en) | 2022-06-03 |
Family
ID=70090374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911234527.XA Active CN110991745B (en) | 2019-12-05 | 2019-12-05 | Power load prediction method and device, readable medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110991745B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117333219B (en) * | 2023-12-01 | 2024-03-08 | 国网浙江省电力有限公司 | Transaction electric quantity prediction method, device, equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3014613B1 (en) * | 2013-12-11 | 2016-01-15 | Electricite De France | PREDICTING ERASED FLUID CONSUMPTION |
-
2019
- 2019-12-05 CN CN201911234527.XA patent/CN110991745B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103036231A (en) * | 2012-12-07 | 2013-04-10 | 温州电力局 | Forecasting method, device, and upper computer of power load |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110991745A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112529301B (en) | Power consumption prediction method, device and storage medium | |
| CN109711440B (en) | Data anomaly detection method and device | |
| CN109945420B (en) | Air conditioner control method and device based on load prediction and computer storage medium | |
| JP6142781B2 (en) | Power demand forecasting device, power demand forecasting method, and power demand forecasting program | |
| US20140128997A1 (en) | Identifying models of dynamic systems | |
| CN109726909B (en) | Energy efficiency evaluation method and device, readable medium and electronic equipment | |
| CN107730097B (en) | Bus load prediction method and device and computing equipment | |
| CN111680841B (en) | Short-term load prediction method, system and terminal equipment based on principal component analysis | |
| CN113168656B (en) | Transaction price prediction device and transaction price prediction method | |
| US11455544B2 (en) | Prediction model generation device, prediction model generation method, and recording medium | |
| JP6094369B2 (en) | Power demand forecasting device, power demand forecasting method, and power demand forecasting program | |
| CN112148557B (en) | Method for predicting performance index in real time, computer equipment and storage medium | |
| JP6782606B2 (en) | Trend predictor and load predictor | |
| CN110991745B (en) | Power load prediction method and device, readable medium and electronic equipment | |
| CN111125931B (en) | Automatic optimization type searching method and device for cooling tower | |
| CN108736474B (en) | Power load prediction method and device | |
| JP7010674B2 (en) | Power Demand Forecasting Device, Power Demand Forecasting Method and Program | |
| CN111553529A (en) | Load prediction method and device, computer readable storage medium and electronic equipment | |
| CN110991762A (en) | Prediction method, prediction device, computer-readable storage medium and electronic equipment | |
| JP2018113817A (en) | Information processing system and information processing program | |
| CN117710008A (en) | Ecological product sales information management system suitable for karst region | |
| CN110826196B (en) | Industrial equipment operation data processing method and device | |
| JP2021131627A (en) | DR activation prediction system | |
| CN112700043B (en) | Load prediction method, load prediction device, computer readable storage medium and electronic equipment | |
| CN109858119B (en) | Dynamic energy efficiency modeling method and device, readable medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |