CN114841458B - Power load prediction method and system, electronic device, and storage medium - Google Patents
Power load prediction method and system, electronic device, and storage medium Download PDFInfo
- Publication number
- CN114841458B CN114841458B CN202210552011.5A CN202210552011A CN114841458B CN 114841458 B CN114841458 B CN 114841458B CN 202210552011 A CN202210552011 A CN 202210552011A CN 114841458 B CN114841458 B CN 114841458B
- Authority
- CN
- China
- Prior art keywords
- power load
- load data
- moment
- standard score
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 claims description 2
- 230000000737 periodic effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
Abstract
The invention discloses a power load prediction method and system, electronic equipment and a storage medium. The power load prediction method comprises the following steps: acquiring power load data at the current moment; searching a characteristic value corresponding to the current moment from a database, and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment; predicting the standard score of the next moment according to a prediction model constructed based on the standard score of the current moment; and searching the characteristic value corresponding to the next moment from the database, and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment. The power load prediction method provided by the invention combines the distribution situation of historical power load data, so that the prediction result of the power load data is more accurate.
Description
Technical Field
The present invention relates to the field of power load prediction, and in particular, to a power load prediction method and system, an electronic device, and a storage medium.
Background
The load prediction is to determine load data at a certain future moment according to various factors such as the operating characteristics, capacity increasing decision, natural conditions, social influence and the like of a system under the condition of meeting certain precision requirements. Here, the load means a power demand (power) or a power consumption. Load prediction is an important content in economic dispatch of a power system and is an important module of an energy management system. Since the load prediction is to estimate its future value from the past and present of the power load, the object of the load prediction work is an affirmative event. Only if the events are not certain events and random events, people need to adopt proper prediction technology to deduce the development trend and the possible conditions of the load.
For actual load prediction under most conditions, a periodic time naive prediction method is usually used, that is, an observed value of a corresponding position in a previous time period is used as a predicted value. For example, the load of the last week is shifted to the next week as a basis for load prediction of the next week. The method has certain applicability to scenes with regular loads, but in some scenes with low load regularity or large load fluctuation, a translation scheme is used, which will certainly cause small errors.
Disclosure of Invention
The invention aims to solve the technical problem that a periodic time naive prediction method in the prior art is not suitable for scenes with low load regularity or large load fluctuation, and provides a power load prediction method and system, electronic equipment and a storage medium.
The invention solves the technical problems through the following technical scheme:
a first aspect of the present invention provides a power load prediction method, including the steps of:
acquiring power load data at the current moment;
searching a characteristic value corresponding to the current moment from a database, and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment; the database stores characteristic values at different moments, and the characteristic values are obtained by extraction according to distribution characteristics of historical power load data in a preset period;
predicting the standard score of the next moment according to a prediction model constructed based on the standard score of the current moment;
searching a characteristic value corresponding to the next moment from the database, and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment;
and parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the predicted sample power load data and the corresponding real power load data.
Optionally, the prediction model is constructed based on the norm score for the current time instant and at least a first derivative of the norm score for the current time instant.
Optionally, the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, and specifically comprising the following steps:
MASE _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and MASE _2 is an average absolute error between the historical power load data of the previous cycle and the real power load data of the current cycle at the same time.
Optionally, the historical power load data in the preset period satisfies a gaussian distribution, and the characteristic value includes a mean value and a standard deviation.
A second aspect of the present invention provides a power load prediction system, including:
the load acquisition module is used for acquiring the power load data at the current moment;
the standard score calculation module is used for searching a characteristic value corresponding to the current moment from a database and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment; the database stores characteristic values at different moments, and the characteristic values are obtained by extraction according to distribution characteristics of historical power load data in a preset period;
the standard score prediction module is used for predicting the standard score of the next moment according to a prediction model constructed based on the standard score of the current moment;
the load prediction module is used for searching a characteristic value corresponding to the next moment from the database and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment;
and parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the sample power load data obtained by prediction and the corresponding real power load data.
Optionally, the prediction model is constructed based on the norm score for the current time instant and at least a first derivative of the norm score for the current time instant.
Optionally, the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, and specifically comprising the following steps:
MASE _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and MASE _2 is an average absolute error between the historical power load data of the previous cycle and the real power load data of the current cycle at the same time.
Optionally, the historical power load data in the preset period satisfies a gaussian distribution, and the characteristic value includes a mean value and a standard deviation.
A third aspect of the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the power load prediction method according to the first aspect when executing the computer program.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the power load prediction method according to the first aspect.
On the basis of the common knowledge in the field, the above preferred conditions can be combined randomly to obtain the preferred embodiments of the invention.
The positive progress effects of the invention are as follows: the distribution characteristics of historical power load data in a preset period are extracted to obtain characteristic values at different moments, a database is built according to moment information and the characteristic values, and the power load data at the current moment, the characteristic values at different moments stored in the database and a prediction model can be used for predicting the power load data at the next moment.
Drawings
Fig. 1 is a flowchart of a power load prediction method according to embodiment 1 of the present invention.
Fig. 2 is a schematic diagram illustrating a comparison between an actual power load and a predicted power load according to embodiment 1 of the present invention.
Fig. 3 is a block diagram of a power load prediction system according to embodiment 1 of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to embodiment 2 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
Fig. 1 is a flowchart illustrating a power load prediction method provided in this embodiment, where the power load prediction method may be performed by a power load prediction system, the power load prediction system may be implemented by software and/or hardware, and the power load prediction system may be part or all of an electronic device. The electronic device in this embodiment may be a Personal Computer (PC), such as a desktop, an all-in-one machine, a notebook Computer, a tablet Computer, and the like, and may also be a terminal device such as a mobile phone, a wearable device, and a Personal Digital Assistant (PDA). The following describes the power load prediction method provided in this embodiment with an electronic device as an execution subject.
As shown in fig. 1, the power load prediction method provided by the present embodiment may include the following steps S1 to S4:
and S1, acquiring power load data at the current moment. The power load data may also be referred to as a power load, and the power load data at the current moment refers to the sum of electric power consumed by various electric devices borne at the current moment, and the standard unit is KW.
S2, searching a characteristic value corresponding to the current moment from a database, and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment.
The database stores characteristic values at different moments, and the characteristic values are extracted according to distribution characteristics of historical power load data in a preset period.
In specific implementation, the database stores time information and a feature value by a key value pair, wherein the time information is used as a key, and the feature value is used as a value. In some examples, the database may also be referred to as a probability distribution dictionary.
The preset period may be set according to actual conditions, and may be set to 15 minutes, for example. The historical power load data of one week may be divided into 7 × 24 × 4=672 sets of data at intervals of 15 minutes, and then 672 pieces of time information and characteristic values may be stored in the database. And the characteristic value of each moment is obtained by extracting the distribution characteristic corresponding to the historical power load data within 15 minutes.
The historical power load data may be updated according to actual conditions, and the database may need to be updated appropriately even after the historical power load data is updated.
In an optional embodiment, the historical power load data in the preset period satisfies a gaussian distribution, and the characteristic value includes a mean value and a standard deviation. In a specific example, the mean and standard deviation of the historical power load data every 15 minutes are counted to form a database with the following structure:
wherein "mu" represents a mean value and "sigma" represents a standard deviation.
In other examples of implementations, the characteristic values may include skewness and kurtosis.
And S3, predicting the standard score of the next moment according to a prediction model constructed based on the standard score of the current moment.
And S4, searching a characteristic value corresponding to the next moment from the database, and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment.
And parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the sample power load data obtained by prediction and the corresponding real power load data.
In an alternative embodiment, the prediction model is constructed based on the norm score of the current time and at least a first derivative of the norm score of the current time. In a specific example, the predictive model is constructed based on the norm and its first derivative at the current time. In another specific example, the prediction model is constructed based on the standard deviation of the current time and the first and second derivatives thereof. It should be noted that, by constructing the prediction model using more order derivatives of the standard components at the current time, the finally predicted power load data is more accurate.
In an alternative embodiment, the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, and specifically comprising the following steps:
the mask _1 is an average absolute error of the predicted sample power load data and the corresponding real power load data, and the mask _2 is obtained according to a periodic naive prediction method, specifically, an average absolute error of historical power load data of a previous period and real power load data of a current period at the same time.
In specific implementation, different parameter values can be selected through grid search or heuristic algorithm and the like to enable the loss function f loss The value of (d) is minimized, and thus the optimal parameters of the optimal prediction model are obtained by fitting.
The following describes the power load prediction method provided in the present embodiment with reference to a specific example.
Acquiring power load P at time k k Searching the mean value mu corresponding to the k moment from the database k Sum standard deviation σ k According to the following formula, the power load P at the time k k Performing standardization to obtain standard score S at time k k ：
Predicting the standard score at time k +1 according to the following prediction model
Wherein the standard score of k time is S k The first derivative of (d) is: s k ′＝S k -S k-1 Standard score of time k S k The second derivative of (d) is: s k ″＝S k ′-S k ′ -1 In one embodiment, the score S is based on the criterion at time k-1 k-1 And a standard score S at time k-2 k-2 Calculating S k ′ -1 ：S k ′ -1 ＝S k-1 -S k-2 And the standard score S at the time k-1 k-1 According to the electric load P at the moment of k-1 k-1 And the mean value mu of the k-1 time instant looked up from the database k-1 And standard deviation σ k-1 Get, the standard score S at time k-2 k-2 According to the electric load P at the moment of k-2 k-2 And the mean value mu at the time k-2 searched from the database k-2 And standard deviation σ k-2 The specific calculation formula is obtained as follows:
wherein the parameters α, β, γ of the prediction model may be based on a pair loss function f loss The fitting is performed to obtain, specifically,
MASE _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and MASE _2 is an average absolute error between the historical power load data of the previous week and the real power load data of the current week at the same time.
Finally, the mean value mu corresponding to the k +1 moment is searched from the database k+1 And standard deviation σ k+1 And according to the mean value mu k+1 Standard deviation σ k+1 And the standard score of the k +1 time
Predicting power load P at time k +1 k+1 ：
Comparing the power load predicted by the power load prediction method provided by the present example with the real power load, the comparison effect of the day of 10 months and 1 days can be seen in fig. 2, and it can be seen that the error between the two is small. Compared with the method of using a periodic time naive prediction method, namely directly translating historical power load data of a previous period to a current period, the loss value calculated according to the loss function is 0.80457 which is smaller than the loss value 1 obtained by using the periodic time naive prediction method, so that the prediction result of the power load prediction method provided by the example is more accurate.
In the power load prediction method provided by this embodiment, the distribution characteristics of the historical power load data in the preset period are extracted to obtain the characteristic values at different times, a database is built according to the time information and the characteristic values, and the power load data at the current time, the characteristic values at different times stored in the database and a prediction model are used to realize prediction of the power load data at the next time.
The present embodiment further provides an electrical load prediction system 30, as shown in fig. 3, including a load obtaining module 31, a standard score calculating module 32, a standard score prediction module 33, and a load prediction module 34.
The load obtaining module 31 is configured to obtain power load data at a current moment. The standard score calculation module 32 is configured to search a database for a feature value corresponding to the current time, and perform standardization processing on the power load data according to the feature value corresponding to the current time to obtain a standard score of the current time. The database stores characteristic values at different moments, and the characteristic values are extracted according to distribution characteristics of historical power load data in a preset period. The standard score prediction module 33 is configured to predict a standard score of a next time according to a prediction model constructed based on the standard score of the current time. The load prediction module 34 is configured to search the database for a feature value corresponding to the next time, and predict the power load data of the next time according to the feature value corresponding to the next time and the standard score of the next time. And parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the sample power load data obtained by prediction and the corresponding real power load data.
In an alternative embodiment, the prediction model is constructed based on the norm score of the current time and at least a first derivative of the norm score of the current time.
In an alternative embodiment, the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, and specifically comprising the following steps:
MASE _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and MASE _2 is an average absolute error between the historical power load data of the previous cycle and the real power load data of the current cycle at the same time.
In an optional embodiment, the historical power load data in the preset period satisfies a gaussian distribution, and the characteristic value includes a mean value and a standard deviation.
It should be noted that, the power load prediction system in this embodiment may be a separate chip, a chip module, or an electronic device, or may be a chip or a chip module integrated in an electronic device.
The power load prediction system described in this embodiment may include various modules/units, which may be software modules/units, or hardware modules/units, or may be partly software modules/units and partly hardware modules/units.
Example 2
Fig. 4 is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device includes at least one processor and a memory communicatively coupled to the at least one processor. Wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the power load prediction method of embodiment 1. The electronic device provided by this embodiment may be a personal computer, such as a desktop, an all-in-one machine, a notebook computer, a tablet computer, and the like, and may also be a mobile phone, a wearable device, a palmtop computer, and other terminal devices. The electronic device 3 shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
The components of the electronic device 3 may include, but are not limited to: the at least one processor 4, the at least one memory 5, and a bus 6 connecting various system components including the memory 5 and the processor 4.
The bus 6 includes a data bus, an address bus, and a control bus.
The memory 5 may include volatile memory, such as Random Access Memory (RAM) 51 and/or cache memory 52, and may further include Read Only Memory (ROM) 53.
The memory 5 may also include a program/utility 55 having a set (at least one) of program modules 54, such program modules 54 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The processor 4 executes various functional applications and data processing, such as the above-described power load prediction method, by executing the computer program stored in the memory 5.
The electronic device 3 may also communicate with one or more external devices 7, such as a keyboard, pointing device, etc. Such communication may be via an input/output (I/O) interface 8. Also, the electronic device 3 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 9. As shown in fig. 4, the network adapter 9 communicates with other modules of the electronic device 3 via the bus 6. It should be appreciated that although not shown in FIG. 4, other hardware and/or software modules may be used in conjunction with the electronic device 3, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, to name a few.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 3
The present embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the power load prediction method of embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the invention may also be implemented in the form of a program product comprising program code for causing an electronic device to perform the power load prediction method implementing embodiment 1 when the program product is run on the electronic device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the electronic device, partly on the electronic device, as a stand-alone software package, partly on the electronic device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (8)
1. A method for predicting a power load, comprising the steps of:
acquiring power load data at the current moment;
searching a characteristic value corresponding to the current moment from a database, and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment; the characteristic values at different moments are stored in the database and are extracted according to the distribution characteristics of historical power load data in a preset period;
predicting the standard score of the next moment according to a prediction model constructed based on the standard score of the current moment and at least one first-order derivative of the standard score of the current moment;
searching a characteristic value corresponding to the next moment from the database, and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment;
the parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the sample power load data obtained by prediction and corresponding real power load data;
specifically, the standard score S at time k is determined according to the following formula k ：
Wherein, P k The characteristic value corresponding to the moment k comprises the mean value mu of historical power load data in a preset period k And standard deviation σ k ；
Predicting the power load P at the time k +1 according to the following formula k+1 ：
Wherein, the characteristic value corresponding to the k +1 moment comprises a mean value mu k+1 And standard deviation σ k+1 ，
Is the standard score of the k +1 time predicted by the prediction model.
2. The power load prediction method of claim 1, wherein the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, specifically comprising:
MASE _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and MASE _2 is an average absolute error between the historical power load data of the previous cycle and the real power load data of the current cycle at the same time.
3. The power load prediction method according to any one of claims 1-2, wherein the historical power load data in the preset period satisfies a gaussian distribution, and the characteristic values include a mean value and a standard deviation.
4. An electrical load prediction system, comprising:
the load acquisition module is used for acquiring the power load data at the current moment;
the standard score calculation module is used for searching a characteristic value corresponding to the current moment from a database and carrying out standardization processing on the power load data according to the characteristic value corresponding to the current moment to obtain a standard score of the current moment; the database stores characteristic values at different moments, and the characteristic values are obtained by extraction according to distribution characteristics of historical power load data in a preset period;
the standard score prediction module is used for predicting the standard score of the next moment according to a prediction model constructed on the basis of the standard score of the current moment and at least one first-order derivative of the standard score of the current moment;
the load prediction module is used for searching a characteristic value corresponding to the next moment from the database and predicting the power load data of the next moment according to the characteristic value corresponding to the next moment and the standard score of the next moment;
the parameters of the prediction model are obtained by fitting a loss function, and the loss function is established according to the sample power load data obtained by prediction and corresponding real power load data;
specifically, the standard score is calculatedThe module is specifically configured to determine a criterion score S for time k according to the following formula k ：
Wherein, P k The characteristic value corresponding to the k moment comprises a mean value mu of historical power load data in a preset period k And standard deviation σ k ；
The load prediction module is specifically used for predicting the power load P at the moment k +1 according to the following formula k+1 ：
Wherein, the characteristic value corresponding to the k +1 moment comprises a mean value mu k+1 And standard deviation σ k+1 ，
Is the standard score of the k +1 time predicted by the prediction model.
5. The power load prediction system of claim 4, wherein the loss function f loss Establishing according to the predicted sample power load data and the corresponding real power load data, and specifically comprising the following steps:
mask _1 is an average absolute error between the predicted sample power load data and the corresponding real power load data, and mask _2 is an average absolute error between the historical power load data of the previous cycle and the real power load data of the current cycle at the same time.
6. A power load prediction system according to any of claims 4-5, characterized in that the historical power load data over the preset period satisfies a Gaussian distribution, and the characteristic values include a mean and a standard deviation.
7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the power load prediction method of any one of claims 1-3 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the power load prediction method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210552011.5A CN114841458B (en) | 2022-05-18 | 2022-05-18 | Power load prediction method and system, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210552011.5A CN114841458B (en) | 2022-05-18 | 2022-05-18 | Power load prediction method and system, electronic device, and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114841458A CN114841458A (en) | 2022-08-02 |
| CN114841458B true CN114841458B (en) | 2023-03-24 |
Family
ID=82569010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210552011.5A Active CN114841458B (en) | 2022-05-18 | 2022-05-18 | Power load prediction method and system, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114841458B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002937A (en) * | 2018-09-07 | 2018-12-14 | 深圳供电局有限公司 | Power grid load prediction method and device, computer equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101425158A (en) * | 2008-12-04 | 2009-05-06 | 清华大学 | Short term load prediction method based on information |
| CN104424294A (en) * | 2013-09-02 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Information processing method and information processing device |
| CN109815084B (en) * | 2018-12-29 | 2020-12-29 | 北京城市网邻信息技术有限公司 | Abnormity identification method and device, electronic equipment and storage medium |
| EP3968247A4 (en) * | 2019-06-21 | 2022-12-21 | Siemens Aktiengesellschaft | Power load data prediction method and device, and storage medium |
-
2022
- 2022-05-18 CN CN202210552011.5A patent/CN114841458B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002937A (en) * | 2018-09-07 | 2018-12-14 | 深圳供电局有限公司 | Power grid load prediction method and device, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于组合模型的电力系统短期负荷预测研究;邓仁等;《第40届中国控制会议论文集》;20210731;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114841458A (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109753356A (en) | A kind of container resource regulating method, device and computer readable storage medium | |
| CN112508118B (en) | Target object behavior prediction method aiming at data offset and related equipment thereof | |
| CN112990583B (en) | Method and equipment for determining model entering characteristics of data prediction model | |
| Hsu et al. | A Robust Two‐Machine Flow‐Shop Scheduling Model with Scenario‐Dependent Processing Times | |
| CN116992274B (en) | Short-term wind speed prediction method and system based on improved principal component regression model | |
| CN114784882A (en) | Unit combination optimization processing method and device | |
| CN114841458B (en) | Power load prediction method and system, electronic device, and storage medium | |
| CN113505595A (en) | Text phrase extraction method and device, computer equipment and storage medium | |
| CN116502771B (en) | Power distribution method and system based on electric power material prediction | |
| CN112434872A (en) | Hotel yield prediction method, system, equipment and storage medium | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN114841457B (en) | Power load estimation method and system, electronic device, and storage medium | |
| CN115952878A (en) | Power load prediction method and device, electronic equipment and storage medium | |
| CN113094602B (en) | Hotel recommendation method, system, equipment and medium | |
| CN111967806B (en) | User risk updating method and device based on periodic retrace and electronic equipment | |
| CN115099875A (en) | Data classification method based on decision tree model and related equipment | |
| CN111339063B (en) | Method and device for intelligent management of assumed data and computer readable storage medium | |
| CN114513578A (en) | Outbound method, device, computer equipment and storage medium | |
| CN113095963A (en) | Real estate cost data processing method, real estate cost data processing device, computer equipment and storage medium | |
| CN115858324B (en) | AI-based IT equipment fault processing method, apparatus, equipment and medium | |
| CN113157896B (en) | Voice dialogue generation method and device, computer equipment and storage medium | |
| CN116541766B (en) | Training method of electroencephalogram data restoration model, electroencephalogram data restoration method and device | |
| JP7026279B1 (en) | Devices, methods, and programs that generate power generation calculation models | |
| CN117200206A (en) | Power consumer side load processing method and device based on high-performance heterogeneous computation | |
| CN116644854A (en) | Regional distributed power supply energy permeability prediction method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |