CN111598296A - Power load prediction method, power load prediction device, computer equipment and storage medium - Google Patents
Power load prediction method, power load prediction device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111598296A CN111598296A CN202010289333.6A CN202010289333A CN111598296A CN 111598296 A CN111598296 A CN 111598296A CN 202010289333 A CN202010289333 A CN 202010289333A CN 111598296 A CN111598296 A CN 111598296A
- Authority
- CN
- China
- Prior art keywords
- data
- power load
- historical
- source information
- grid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013507 mapping Methods 0.000 claims abstract description 73
- 238000005316 response function Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 10
- 238000009825 accumulation Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000005538 encapsulation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012731 temporal analysis Methods 0.000 description 2
- 238000000700 time series analysis Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- 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)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to an electric load prediction method, an electric load prediction device, a computer device and a storage medium. The method comprises the following steps: acquiring a storage medium and a storage format of grid data, and acquiring a mapping relation of the grid data; acquiring source information of the grid data based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data; acquiring historical power load data according to the source information of the grid data; and predicting the power load according to the historical power load data to obtain a power load prediction result. By adopting the method, the power load condition of the power grid can be accurately predicted.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for predicting an electrical load, a computer device, and a storage medium.
Background
With the continuous improvement of living standard of people, household appliances are continuously increased, so that the demand on electric quantity is sharply increased. The scale of the power grid is continuously enlarged, the whole power system accelerates the intelligentized pace, and the data volume of the power grid information is sharply increased. At present, most power systems are structured by physical equipment grid data detection and collection and storage in a relational database.
However, early grid management systems were independent of each other, corresponding to different power systems, with different storage systems having their own storage means, resulting in multiple types of configuration data. In order to achieve reasonable power dispatching, the power load condition of each power grid needs to be predicted, but the power load condition of each power grid cannot be predicted accurately due to different formats of data.
Disclosure of Invention
In view of the above, it is necessary to provide an electrical load prediction method, an electrical load prediction apparatus, a computer device, and a storage medium, which can accurately predict an electrical load situation, in view of the above technical problems.
A method of electrical load prediction, the method comprising:
acquiring a storage medium and a storage format of grid data, and acquiring a mapping relation of the grid data;
acquiring source information of the grid data based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
acquiring historical power load data according to the source information of the grid data;
and predicting the power load according to the historical power load data to obtain a power load prediction result.
An electrical load prediction apparatus, the apparatus comprising:
the mapping relation acquisition module is used for acquiring a storage medium and a storage format of the grid data and acquiring the mapping relation of the grid data;
a source information obtaining module, configured to obtain source information of the mesh data based on the mapping relationship, where the source information includes a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
the historical data acquisition module is used for acquiring historical power load data according to the source information of the grid data;
and the load determining module is used for predicting the power load according to the historical power load data to obtain a power load prediction result.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a storage medium and a storage format of grid data, and acquiring a mapping relation of the grid data;
acquiring source information of the grid data based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
acquiring historical power load data according to the source information of the grid data;
and predicting the power load according to the historical power load data to obtain a power load prediction result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring a storage medium and a storage format of grid data, and acquiring a mapping relation of the grid data;
acquiring source information of the grid data based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
acquiring historical power load data according to the source information of the grid data;
and predicting the power load according to the historical power load data to obtain a power load prediction result.
According to the power load prediction method, the power load prediction device, the computer equipment and the storage medium, the storage medium and the storage format of the grid data are obtained, the mapping relation of the grid data is obtained, and the source information of the grid data is obtained based on the mapping relation, wherein the source information comprises the type of a database and an information field; the mapping relation is the association relation among the storage media, the storage formats and the source information of the grid data, so that historical data of different storage media and different storage formats can be obtained and associated. Historical power load data are obtained according to source information of the grid data, power load prediction is carried out according to the historical power load data, a power load prediction result is obtained, and the future power load condition can be predicted based on combination of historical data of different storage media and different storage formats, so that prediction is more accurate.
Drawings
FIG. 1 is a diagram of an exemplary embodiment of a power load prediction method;
FIG. 2 is a flow diagram illustrating a method for predicting an electrical load according to one embodiment;
FIG. 3 is a schematic diagram of grid data stored by rows and columns in one embodiment;
FIG. 4 is a flowchart illustrating the steps of mapping relationships in one embodiment;
FIG. 5 is a flow diagram illustrating a process for power load prediction based on historical load data according to one embodiment;
FIG. 6 is a schematic diagram illustrating a process for power load prediction based on historical load data according to another embodiment;
FIG. 7 is a schematic flow chart of the power load prediction using the gray prediction method in another embodiment;
FIG. 8 is a schematic flow chart illustrating a power load prediction method using time-series prediction according to another embodiment;
FIG. 9 is a block diagram showing the structure of an electric load predicting apparatus according to an embodiment;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The power load prediction method provided by the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 104 may be implemented by an independent server or a server cluster formed by a plurality of servers. In this embodiment, the terminal 102 initiates a power load prediction request to the grid to the server 104. When the server 104 receives the request, the server 104 obtains the storage medium and the storage format of the grid data in the power grid, and obtains the mapping relationship of the grid data. Then, the server 104 obtains the source information of the grid data based on the mapping relationship, wherein the source information includes the database type and the information field; the mapping relationship is an association relationship between a storage medium of the mesh data, a storage format, and the source information. Next, the server 104 acquires historical power load data according to the source information of the grid data; next, the server 104 performs power load prediction based on the historical power load data to obtain a power load prediction result. Next, the server 104 returns the power load prediction result to the terminal 102. The historical data based on different storage media and different storage formats are combined to predict the future electric load condition, so that the prediction is more accurate.
In one embodiment, as shown in fig. 2, there is provided an electrical load prediction method, which is described by taking the application of the method to the server in fig. 1 as an example, and includes the following steps:
The storage medium refers to a carrier for data storage, and includes, but is not limited to, a hard disk, a floppy disk, a flash memory, a usb disk, and an optical disk. Storage formats include, but are not limited to, text, sound, and images. The grid data is a process of gridding data, that is, data which is not distributed uniformly in space is reduced to a representative value (trend value) in a regular grid according to a certain method (such as a moving average method, a kriging method, or another suitable numerical estimation method).
Specifically, when an electric power enterprise needs to predict the electric load condition of the power grid in the jurisdiction in a future period of time, an electric load prediction request can be initiated to the server through the terminal. When the server receives the power load prediction request sent by the terminal, the server can acquire the storage medium and the storage format of the grid data corresponding to the power grid. Next, the server may obtain a mapping relationship for the grid data.
The mapping relationship is a structure stored in columns, and as shown in fig. 3, a schematic diagram of storing grid data in rows and columns is shown. It can be seen from fig. 3 that the column-wise storage mode only reads selected columns when querying data, and any column can be used as an index without constructing a specific index. And the data types of each column are the same, so that the data are convenient to compress. Storing queries without indices by rows requires a large amount of input/output, and establishing indices consumes resources.
The source information refers to the source information of the database, and comprises a database type and an information field. The information field refers to fields to be used for accessing the database, such as an account number and a password. The information field may also include an address of the database. The source information may also include database access information, which refers to which data in the database the user needs to access.
Specifically, the server obtains a mapping relationship of the mesh data, which represents an association relationship between a storage medium, a storage format, and source information of the mesh data. The server can obtain the corresponding database type from the mapping relation and the information field required for accessing the database corresponding to the database type through the storage medium and the storage format of the grid data.
And step 206, acquiring historical power load data according to the source information of the grid data.
The historical power load data refers to power load condition statistical data of a power grid within a historical preset time period.
Specifically, after the server determines the source information of the grid data, the server may use the account password to access the address of the database corresponding to the database type in the server. The server then retrieves historical power load data from the database.
In this embodiment, the terminal may acquire historical power load data for a preset time period from the database.
And step 208, performing power load prediction according to the historical power load data to obtain a power load prediction result.
Specifically, the historical power load data acquired by the server may be acquired from different types of databases, and thus the data types of the historical power load data for the respective periods may not be the same. The server may convert the historical power load data of the different data types to data of the same format. Then, the server predicts the power load in the future preset time period based on the historical power load data in the same format to obtain a power load prediction result in the future preset time period.
In this embodiment, the server may process the historical power load data in the same format based on a grayscale prediction manner, so as to obtain a power load prediction result in a future preset time period.
In this embodiment, the server may process the historical power load data in the same format based on a time series prediction manner, so as to obtain a power load prediction result in a future preset time period.
In the power load prediction method, a storage medium and a storage format of grid data are obtained, a mapping relation of the grid data is obtained, and source information of the grid data is obtained based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the association relation among the storage media, the storage formats and the source information of the grid data, so that historical data of different storage media and different storage formats can be obtained and associated. Historical power load data are obtained according to source information of the grid data, power load prediction is carried out according to the historical power load data, a power load prediction result is obtained, and therefore the future power load condition can be predicted based on combination of historical power load data of different storage media and different storage formats, and prediction is more accurate.
In one embodiment, as shown in fig. 4, the mapping relationship is constructed in a manner including:
Specifically, the data storage media and the power data storage formats used by the power grids put into use at different periods are different. In order to ensure that the grid data of different storage formats of different storage media can be used in combination, the server can store the grid data of different storage formats of different storage media into a distributed storage database. The server may obtain storage media for storing grid data for the power grid at different times, and obtain grid data of each storage format from each storage medium.
And step 404, storing the grid data into a corresponding database according to the data type.
The data types include, but are not limited to, MySQL data and Java data. The corresponding database refers to a database of the same data type as the mesh data.
Specifically, the server may classify the acquired mesh data according to data types, and separately store each type of mesh data in a corresponding database. For example, grid data with a data type of MySQL is stored in a MySQL database. And obtaining different databases after the grid data are divided according to the types of the grid data. Then, the server can store the different types of databases into a database system of distributed storage, so that the fusion of multi-source heterogeneous data is realized. For example Hbase database systems. The HBase database is a distributed and column-oriented open source database and is suitable for storing unstructured data. The HBase database is a column based rather than row based storage schema. The HBase database system can contain a plurality of databases. The server may column an association between data stored in each type of database.
The type of the database includes, but is not limited to, MySQL database, Java database.
Specifically, the server may determine the addresses of each type of database and determine the information fields that need to be used to access each type of database. For example, the storage locations of a plurality of different types of databases included in the HBase database system are different, that is, the addresses are different, and the account numbers and passwords used for accessing the different types of databases may be different. Next, the server takes the database type and the information field as source information of the mesh data. The server may then build a mapping between the storage media, storage formats, and source information in columns.
In this embodiment, the storage medium of the mesh data is acquired, the mesh data of each storage format is acquired from the storage medium, the mesh data is stored in the database of the corresponding type according to the data type, the information field used for accessing the databases of different types is determined, the database type and the information field are used as the source information of the mesh data, the mapping relationship between the storage medium, the storage format and the source information of the mesh data is constructed, the data of different sources, different structures and different types can be associated, and the acquisition and the use of the data are facilitated.
In one embodiment, obtaining source information of the mesh data based on the mapping relationship includes: determining a database type corresponding to the grid data according to the mapping relation; and determining the information field used for accessing the database corresponding to the database type according to the database type.
Specifically, the server may obtain the mapping relationship, and determine the database type corresponding to the mesh data according to the mapping relationship among the storage medium, the storage format, and the source information of the mesh data. Different database types correspond to different information fields, and the server can acquire the corresponding information fields according to the database types.
In this embodiment, different storage media, different storage formats, and different data types are associated based on the mapping association, so that information fields required to be used for accessing various types of databases can be quickly and accurately obtained based on the association relationship.
In one embodiment, obtaining historical electrical load data from source information of grid data includes: and accessing a database corresponding to the database type according to the database type and the information field, and acquiring historical power load data from the database.
Specifically, the server can determine the address of the database corresponding to the database type, and use the information field to access the database corresponding to the database type, so that the historical power load information can be acquired from the database. Different types of databases are accessed through different information fields to obtain various historical electrical load information stored in the different types of databases.
In one embodiment, after obtaining the historical electrical load data according to the source information of the grid data, the method further comprises: converting source information of the grid data and historical power load data into an extensible markup language format file;
should carry out the power load prediction according to historical load data, obtain the power load prediction result, include: and predicting the power load according to the extensible markup language format file to obtain a power load prediction result.
Specifically, if the storage media and the storage format of the grid data are different, the corresponding historical power load data may also be different. The server predicts the future power load of the power grid based on historical power data of different storage media and different storage formats of the same power grid, and the future power load may be abnormal or inaccurate in prediction. The server may obtain the source information of the grid data, and may convert the historical power data of different storage media and different storage formats, and the source information of different storage media and different storage formats into the same format after obtaining the historical power load data of the power grid based on the source information. Further, the server may convert the source information of the grid data and the historical power load data into an extended markup language format file, such as an XML format file.
Then, the server can integrate and analyze the XML file through the PHP script to obtain identifiable historical power load data, and store the data in the cache. Php (HyperText markup language) is a language in which HTML (HyperText markup language) is embedded, and is a script language that is executed on a server side to embed an HTML document.
And then, the server records the data set in the cache through a load prediction algorithm for prediction to obtain a power load prediction result. Finally, the server may integrate the load prediction results into a graph.
In this embodiment, by converting the source information of the grid data and the historical power load data into the xml format file, different types of data in different formats can be converted into the same format file, so as to perform power prediction processing. The electric load prediction is carried out according to the extensible markup language format file, the electric load prediction result can be accurately obtained, and the problem that the electric load cannot be predicted by using different formats and different types of data is solved.
In one embodiment, as shown in fig. 5, the performing the electrical load prediction according to the historical load data to obtain the electrical load prediction result includes:
Specifically, the server can perform first-order accumulation generation on the historical data, so that the historical data is disorderly and irregular
The original data are added successively to generate a new accumulated data sequence, and after the new accumulated data sequence is generated by accumulation, the historical load data are changed into an increasing number sequence with an exponential growth rule. The increasing sequence with exponential growth law is a first-order load sequence.
And step 504, fitting the change rule of the first-order load sequence by using a first-order equation to obtain a time response function.
Specifically, the server fits the change law of the first order load sequence by using a first order equation. And then, the server solves the undetermined parameters of the first-order load sequence by using a least square method, and brings the solved undetermined parameters into the first-order equation to obtain a time response function.
Specifically, the server performs first order subtraction reduction on the time response function model, so that the increasing number sequence is reduced to a normal number sequence. The normal sequence is the grey prediction result of the historical load data.
And step 508, carrying out mean value processing on the grey prediction results to obtain the power load prediction value.
Specifically, the server performs averaging processing on the gray prediction results of the historical load data. And calculating the average value of the normal sequence, wherein the obtained average value is the predicted value of the power load of the historical load data.
In this embodiment, a first-order load sequence is obtained by performing first-order accumulation generation on the historical load data, so that the historical load data is changed into an increasing number sequence with an exponential growth rule. The method comprises the steps of fitting a change rule of a first-order load sequence by using a first-order equation to obtain a time response function, carrying out first-order subtraction reduction on the time response function to obtain a grey prediction result of historical load data, and carrying out mean value processing on the grey prediction result, so that an electric power load prediction value is accurately calculated, and electric power scheduling is reasonably planned.
In one embodiment, as shown in fig. 6, the performing the electrical load prediction according to the historical load data to obtain the electrical load prediction result includes:
Specifically, the server acquires historical load information and acquires the time for collecting the historical load information. Then, the server can generate a time sequence according to the acquisition time corresponding to the load information. The time sequence refers to a sequence formed by arranging the time for acquiring the historical load information according to the acquisition sequence. The main purpose of time series analysis is to predict the future based on existing historical data. The time series analysis is to further estimate the future development trend by statistical analysis by using the past historical data according to the continuous regularity of the development of the objective objects.
And 606, predicting historical power load data based on the time sequence to obtain a power load prediction result.
Specifically, the server predicts the power load information of the power grid at a preset moment according to the time sequence. The electric load information of the power grid at the preset moment can be predicted according to the following formula:
wherein, XtIs a prediction result of predicting the power load information of the power grid at a preset time t, c is a constant representing the prediction stability,tRepresenting a preset error at a preset time t. Both p and q represent the number of acquisition times participating in the calculation determined from the time series, which are consecutive in time.
Time series related parameter, theta, representing the ith acquisition timejA preset error related parameter representing the jth acquisition time. Xt-iIs a prediction result of predicting the power load information of the power grid at a preset time t-i,t-jRepresenting a preset error at a preset time t-j.
In the embodiment, the time corresponding to the historical power load data is obtained, the time sequence is generated according to the time corresponding to the historical power load data, the historical power load data is predicted based on the time sequence, the power load prediction result is obtained, and the power load of the power grid can be accurately predicted.
In one embodiment, the method further comprises: and displaying the power prediction result at each moment through a graph.
Specifically, the server calculates the power prediction results at each time, and generates a graph of the power prediction results at each time. And then, the server sends the curve graph to a smart power grid platform for displaying, and a user can click the curve to check the corresponding load predicted value, so that the power load predicted result of the power grid at each moment is visually displayed.
As shown in fig. 7, a graph of power load prediction in each future time period is obtained by processing historical power load data by the server in a gray prediction manner. As shown in fig. 8, the server processes the historical power load data by using a rate smoothing (i.e., time-series) prediction method to obtain a power load prediction graph in each future time period. The user can display the corresponding time and the predicted power load value at any position on the curve by clicking the position.
In one embodiment, there is provided an electrical load prediction method, the method comprising:
the server acquires a storage medium of the mesh data, and acquires the mesh data of each storage format from the storage medium.
And then, the server stores the grid data into a corresponding database according to the data type.
Further, the server determines information fields used to access different types of databases, with the database types and information fields as source information for the grid data.
Next, the server constructs a mapping relationship of the storage medium, the storage format, and the source information of the mesh data.
Then, the server acquires the storage medium and the storage format of the mesh data, and acquires the mapping relationship of the mesh data.
Further, the server determines the database type corresponding to the grid data according to the mapping relation.
And then, the server determines the information field used for accessing the database corresponding to the database type according to the database type.
Further, the server accesses a database corresponding to the database type according to the database type and the information field, and obtains historical power load data from the database.
And then, the server performs first-order accumulation generation on the historical load data to obtain a first-order load sequence.
And then, the server fits the change rule of the first-order load sequence by using a first-order equation to obtain a time response function.
And then, the server performs first-order subtraction reduction on the time response function to obtain a grey prediction result of the historical load data.
Further, the server performs mean processing on the grey prediction result to obtain a power load prediction value.
In this embodiment, by mapping relationships among storage media, storage formats, and source information of different constructed mesh data, data of different sources, different structures, and different types can be associated, which is beneficial to acquisition and use of data. Historical power load data are obtained based on source information of the grid data, power load prediction is carried out according to the historical power load data, a power load prediction result is obtained, historical power load data based on different storage media and different storage formats can be combined, future power load conditions can be predicted, and prediction is more accurate.
In one embodiment, the server constructs different types of databases according to the data types of the grid data, and stores the grid data into the corresponding databases respectively. For example, grid data of data type a for the grid is stored in database substtation 01. The database substtation 01 includes a data table Info01, and the data table Info01 records basic information of the store Substation. The database substition 01 further includes a data table EnergyConsumer01, and the data table EnergyConsumer01 records Substation load information.
The grid data of the power grid with the data type B is stored in a database substtation 02, no data table exists in the database, and basic information of the Substation is stored in the database substtation 02.
Grid data of the power grid with the data type C is stored in a database substtation 03, the database substtation 03 is provided with a data table name of Info03, and the data table Info03 is used for storing basic information of the Substation.
The substation information includes shop substation information and other information (other data), and the shop substation and the substation are distinguished by the presence or absence of other data, as shown in the following table one and table two:
meter-store substation basic information
Basic information of transformer substation with meter two
After the server stores the grid data into different databases according to data types, a data column can be constructed based on the information structure in each database and the information structure of each data table in each database, so that the information structures of the databases are associated and stored in an Hbase database system, and the construction of the mapping relation is completed.
After the mapping structure is established, when the application program requests the grid data, the coordinator obtains the source information of the grid data, including the database type, the database access information and the required information fields, by querying the mapping structure.
For example, to obtain the basic information subsystem and global ID03 of the grid and the power load information at time T0, the network location addr03 of the database may be queried through a mapping table, obtaining the username and password link usr03/psw03 used to access the database.
The grid basic information subsystem Info03 is stored in a data table with historical power load information in the data table energy consumer03 for the energy consummer pfixed03 area and the Time03 area.
Data access operations continue after work takeover of the encapsulation. Unlike the coordinator, part of the wrapper actually interacts with the grid with the data source, the encapsulation involving direct access to the data source. The different sources of grid data correspond to different packages, and are also a reflection of the source and heterogeneity of the grid data. The wrapper may be a platform independent JAR (Java archive), here using the Java language that enables querying and accessing of different data sources across platforms.
In the power load forecasting scenario, if the data cube subsystem in the storage grid used by the platform is a MySQL database, i.e. the C database is a MySQL database. The upper power application may access the data source of the site. The wrapper packages are as follows:
1) the server connects and stores a database of grid data, namely a connected database substtation 03.
Getconnection (usr03 addr03 psw 03);
2) the basic information table and the third grid subsystem, i.e. the query Info03 table, are accessed for all the information contained therein.
Statement stmt＝Connect.createStatement()；
ResultSet rs＝stmt.executeQuery(“select*from Info03”)；
3) The time-of-day load actual value of T0 is accessed from the load information data table.
Statement stmt2＝connect.createStatement()；
ResultSetrs2＝stmt2.executeQuery(“select EnergyConsumerPfixed03fromEnergyConsumer03 Where Time03＝T0")；
After the required grid data is obtained, the JDOM toolkit is used for organizing the grid data source information and the historical power load information into an XML format file which conforms to the CIM model and submits the subsequent grid data of a coordinator through a uniform programming interface. At the moment, the whole multi-source heterogeneous network data fusion process is completely simulated.
After multi-source heterogeneous data integration is realized, the load prediction can be realized only by loading data stored in an XML file on a B/S mode smart grid application platform. After the prediction algorithm is executed, the final result can be displayed by visualization.
And when the user submits the requested grid data of the load prediction transformer substation, the server for analyzing the request sends an access request to the coordinator. The coordinator obtains the corresponding load data. The coordinator processes the request and sends a request. The basic information of the transformer substation and the data loaded by the XML data file are returned to the server; and the XML file received by the server is integrated and analyzed through the PHP script to obtain historical power load data, and the historical power load data is stored in a cache. Then, the load prediction algorithm realizes loading of the data set in the relevant cache and obtains a prediction result. Finally, the load prediction results are integrated into a user visualization chart.
It should be understood that although the various steps in the flowcharts of fig. 2-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, as shown in fig. 9, there is provided an electrical load prediction apparatus including: a mapping relation obtaining module 902, a source information obtaining module 904, a historical data obtaining module 906, and a load determining module 908, wherein:
a mapping relation obtaining module 902, configured to obtain a storage medium and a storage format of the mesh data, and obtain a mapping relation of the mesh data.
A source information obtaining module 904, configured to obtain source information of the mesh data based on the mapping relationship, where the source information includes a database type and an information field; the mapping relationship is an association relationship between a storage medium of the mesh data, a storage format, and the source information.
A historical data obtaining module 906, configured to obtain historical power load data according to the source information of the grid data.
And a load determination module 908, configured to perform power load prediction according to the historical power load data to obtain a power load prediction result.
In the power load prediction device, a storage medium and a storage format of grid data are obtained, a mapping relation of the grid data is obtained, and source information of the grid data is obtained based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the association relation among the storage media, the storage formats and the source information of the grid data, so that historical data of different storage media and different storage formats can be obtained and associated. Historical power load data are obtained according to source information of the grid data, power load prediction is carried out according to the historical power load data, a power load prediction result is obtained, and the future power load condition can be predicted based on combination of historical data of different storage media and different storage formats, so that prediction is more accurate.
In one embodiment, the electrical load prediction apparatus further comprises: and constructing a module. The building block is configured to: acquiring a storage medium of the grid data, and acquiring the grid data of each storage format from the storage medium; storing the grid data to a corresponding database according to the data type; determining information fields used for accessing different types of databases, and taking the types of the databases and the information fields as source information of the grid data; and constructing a mapping relation among a storage medium, a storage format and source information of the grid data.
In this embodiment, the storage medium of the mesh data is acquired, the mesh data of each storage format is acquired from the storage medium, the mesh data is stored in the database of the corresponding type according to the data type, the information field used for accessing the databases of different types is determined, the database type and the information field are used as the source information of the mesh data, the mapping relationship between the storage medium, the storage format and the source information of the mesh data is constructed, the data of different sources, different structures and different types can be associated, and the acquisition and the use of the data are facilitated.
In one embodiment, the source information obtaining module 904 is further configured to: determining a database type corresponding to the grid data according to the mapping relation; and determining the information field used for accessing the database corresponding to the database type according to the database type.
In this embodiment, different storage media, different storage formats, and different data types are associated based on the mapping association, so that information fields required to be used for accessing various types of databases can be quickly and accurately obtained based on the association relationship.
In one embodiment, the historical data acquisition module 906 is further configured to: and accessing a database corresponding to the database type according to the database type and the information field, and acquiring historical power load data from the database. Different types of databases are accessed through different information fields to obtain various historical electrical load information stored in the different types of databases.
In one embodiment, the load determination module 908 is further configured to: converting source information of the grid data and historical power load data into an extensible markup language format file; and predicting the power load according to the extensible markup language format file to obtain a power load prediction result.
In this embodiment, by converting the source information of the grid data and the historical power load data into the xml format file, different types of data in different formats can be converted into the same format file, so as to perform power prediction processing. The electric load prediction is carried out according to the extensible markup language format file, the electric load prediction result can be accurately obtained, and the problem that the electric load cannot be predicted by using different formats and different types of data is solved.
In one embodiment, the load determination module 908 is further configured to: performing first-order accumulation generation on historical load data to obtain a first-order load sequence; fitting a change rule of a first-order load sequence by using a first-order equation to obtain a time response function; performing first-order subtraction reduction on the time response function to obtain a grey prediction result of historical load data; and carrying out average processing on the grey prediction results to obtain the power load prediction value.
In this embodiment, a first-order load sequence is obtained by performing first-order accumulation generation on the historical load data, so that the historical load data is changed into an increasing number sequence with an exponential growth rule. The method comprises the steps of fitting a change rule of a first-order load sequence by using a first-order equation to obtain a time response function, carrying out first-order subtraction reduction on the time response function to obtain a grey prediction result of historical load data, and carrying out mean value processing on the grey prediction result, so that an electric power load prediction value is accurately calculated, and electric power scheduling is reasonably planned.
In one embodiment, the load determination module 908 is further configured to: acquiring time corresponding to historical power load data; generating a time sequence according to time corresponding to historical power load data; and predicting historical power load data based on the time series to obtain a power load prediction result.
In the embodiment, the time corresponding to the historical power load data is obtained, the time sequence is generated according to the time corresponding to the historical power load data, the historical power load data is predicted based on the time sequence, the power load prediction result is obtained, and the power load of the power grid can be accurately predicted.
For specific limitations of the power load prediction device, reference may be made to the above limitations of the power load prediction method, which are not described herein again. The modules in the electrical load prediction device may be implemented in whole or in part by software, hardware, and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store electrical load forecast data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a power load prediction method.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that implements the steps of the various embodiments when the processor executes the computer program.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the respective embodiment.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of electrical load prediction, the method comprising:
acquiring a storage medium and a storage format of grid data, and acquiring a mapping relation of the grid data;
acquiring source information of the grid data based on the mapping relation, wherein the source information comprises a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
acquiring historical power load data according to the source information of the grid data;
and predicting the power load according to the historical power load data to obtain a power load prediction result.
2. The method according to claim 1, wherein the mapping relationship is constructed in a manner that includes:
acquiring a storage medium of grid data, and acquiring the grid data of each storage format from the storage medium;
storing the grid data to a corresponding database according to data types;
determining information fields used for accessing different types of databases, and taking the types of the databases and the information fields as source information of the grid data;
and constructing a mapping relation among the storage medium, the storage format and the source information of the grid data.
3. The method of claim 2, wherein the obtaining source information of the mesh data based on the mapping relationship comprises:
determining a database type corresponding to the grid data according to the mapping relation;
and determining an information field used for accessing the database corresponding to the database type according to the database type.
4. The method of claim 3, wherein the obtaining historical electrical load data from the source information of the grid data comprises:
and accessing a database corresponding to the database type according to the database type and the information field, and acquiring historical power load data from the database.
5. The method of claim 1, further comprising, after the obtaining historical electrical load data from the source information of the grid data:
converting source information of the grid data and the historical power load data into an extensible markup language format file;
the predicting the power load according to the historical load data to obtain a power load prediction result comprises the following steps:
and predicting the power load according to the extended markup language format file to obtain a power load prediction result.
6. The method of claim 1, wherein the performing the power load prediction according to the historical load data to obtain a power load prediction result comprises:
performing first-order accumulation generation on the historical load data to obtain a first-order load sequence;
fitting the change rule of the first-order load sequence by using a first-order equation to obtain a time response function;
performing first-order subtraction reduction on the time response function to obtain a gray prediction result of the historical load data;
and carrying out mean value processing on the grey prediction result to obtain a power load prediction value.
7. The method of claim 1, wherein the performing the power load prediction according to the historical load data to obtain a power load prediction result comprises:
acquiring time corresponding to the historical power load data;
generating a time sequence according to the time corresponding to the historical power load data;
and predicting the historical power load data based on the time sequence to obtain a power load prediction result.
8. An electrical load prediction apparatus, the apparatus comprising:
the mapping relation acquisition module is used for acquiring a storage medium and a storage format of the grid data and acquiring the mapping relation of the grid data;
a source information obtaining module, configured to obtain source information of the mesh data based on the mapping relationship, where the source information includes a database type and an information field; the mapping relation is the incidence relation among the storage medium, the storage format and the source information of the grid data;
the historical data acquisition module is used for acquiring historical power load data according to the source information of the grid data;
and the load determining module is used for predicting the power load according to the historical power load data to obtain a power load prediction result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910981671 | 2019-10-16 | ||
| CN2019109816713 | 2019-10-16 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111598296A true CN111598296A (en) | 2020-08-28 |
Family
ID=72192164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010289333.6A Pending CN111598296A (en) | 2019-10-16 | 2020-04-14 | Power load prediction method, power load prediction device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598296A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628066A (en) * | 2021-06-28 | 2021-11-09 | 南京南瑞继保电气有限公司 | Method for extracting multidimensional feature vector data of wind generating set in loose coupling mode |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108632082A (en) * | 2018-03-27 | 2018-10-09 | 北京国电通网络技术有限公司 | A kind of prediction technique and device of the load information of server |
| CN110222882A (en) * | 2019-05-21 | 2019-09-10 | 国家电网公司西南分部 | A kind of prediction technique and device of electric system Mid-long Term Load |
-
2020
- 2020-04-14 CN CN202010289333.6A patent/CN111598296A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108632082A (en) * | 2018-03-27 | 2018-10-09 | 北京国电通网络技术有限公司 | A kind of prediction technique and device of the load information of server |
| CN110222882A (en) * | 2019-05-21 | 2019-09-10 | 国家电网公司西南分部 | A kind of prediction technique and device of electric system Mid-long Term Load |
Non-Patent Citations (1)
| Title |
|---|
| HUAHUI LYU 等: "Mass Data Storage Platform for Smart Grid", pages 530 - 535 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113628066A (en) * | 2021-06-28 | 2021-11-09 | 南京南瑞继保电气有限公司 | Method for extracting multidimensional feature vector data of wind generating set in loose coupling mode |
| CN113628066B (en) * | 2021-06-28 | 2024-03-19 | 南京南瑞继保电气有限公司 | Multi-dimensional feature vector data loose coupling extraction method for wind generating set |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20170132263A1 (en) | Space-time-node engine signal structure | |
| US20190057284A1 (en) | Data processing apparatus for accessing shared memory in processing structured data for modifying a parameter vector data structure | |
| CN101442561A (en) | Method for monitoring grid based on vector machine support | |
| CN110704445B (en) | Industrial data lake system | |
| CN107015900A (en) | A kind of service performance Forecasting Methodology of video website | |
| CN114462722B (en) | New energy power generation light-weight high-precision cloud prediction system, method and device | |
| CN115564152A (en) | Carbon emission prediction method and device based on STIRPAT model | |
| CN115641019A (en) | Index anomaly analysis method and device, computer equipment and storage medium | |
| CN112907064A (en) | Electric quantity prediction method and device based on self-adaptive window, storage medium and terminal | |
| CN112365070A (en) | Power load prediction method, device, equipment and readable storage medium | |
| CN116316617A (en) | Multi-station intelligent fusion new energy generation power region prediction method and system | |
| CN113553341A (en) | Multidimensional data analysis method, multidimensional data analysis device, multidimensional data analysis equipment and computer readable storage medium | |
| CN113793681B (en) | Hospital multi-stage medical index quality control method and system | |
| CN116827950A (en) | Cloud resource processing method, device, equipment and storage medium | |
| Zhang et al. | A novel hybrid model for docker container workload prediction | |
| CN111598296A (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
| CN111475526B (en) | Sequential data conversion method based on oracle data and related equipment thereof | |
| Karmitsa et al. | Adaptive limited memory bundle method for bound constrained large-scale nonsmooth optimization | |
| CN115186855A (en) | Logistics network cargo quantity prediction method, device, equipment and computer storage medium | |
| CN113837467B (en) | Point-to-point energy project evaluation method and device, computer equipment and storage medium | |
| CN113642669B (en) | Feature analysis-based fraud prevention detection method, device, equipment and storage medium | |
| CN115509877A (en) | Method for evaluating performance efficiency of information system | |
| CN114925919A (en) | Service resource processing method and device, computer equipment and storage medium | |
| CN107562695A (en) | A kind of load data processing method and processing device of distribution transformer | |
| CN115545248A (en) | Target object prediction method, device, equipment and 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 |