CN112232559A - Short-term prediction method and device for load in power area - Google Patents
Short-term prediction method and device for load in power area Download PDFInfo
- Publication number
- CN112232559A CN112232559A CN202011083600.0A CN202011083600A CN112232559A CN 112232559 A CN112232559 A CN 112232559A CN 202011083600 A CN202011083600 A CN 202011083600A CN 112232559 A CN112232559 A CN 112232559A
- Authority
- CN
- China
- Prior art keywords
- load
- short
- power
- power load
- growth rate
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012417 linear regression Methods 0.000 claims abstract description 41
- 230000006870 function Effects 0.000 claims description 38
- 238000006243 chemical reaction Methods 0.000 claims description 19
- 238000006467 substitution reaction Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 abstract description 5
- 239000003102 growth factor Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a short-term prediction method and a short-term prediction device for a load in a power area. The method comprises the following steps: acquiring a historical power load demand value, and acquiring load characteristic information according to the historical power load demand value; establishing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model; and generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model. According to the invention, the factor data characteristics are highly consistent with the daily load data characteristics by constructing the increase rate factor, so that the increase rate factor does not change the original load data characteristics, the error rate of node load prediction can be greatly reduced when the multi-node load is predicted, and the prediction accuracy is improved.
Description
Technical Field
The invention relates to the technical field of computer software, in particular to a short-term prediction method and device for electric power regional loads.
Background
Generally, the power load refers to the total load borne by the power grid or the power plant at a certain moment, and also refers to the sum of all the instantaneous consumed power of the electric devices connected to the power grid. The power load prediction is to determine the power load value in a certain period or a certain moment in the future based on a mathematical method or a model under the requirement of certain prediction accuracy by considering the actual condition of local power operation and combining some real conditions and historical load change trends of the current region.
In recent years, intelligent technologies have started to rise and are widely used in load prediction, and more representative technologies include neural networks, fuzzy systems, genetic algorithms, support vector machines, and the like. The application of the intelligent technologies obviously improves the accuracy and reliability of long-term, medium-term, short-term and ultra-short-term load prediction, and the load prediction research and application reach a relatively high level, thereby providing powerful decision support for power grid planning and construction, scheduling and operation. However, due to actual load data, the load prediction accuracy in the prior art is low, and the actual load prediction requirement cannot be met, so a short-term prediction method and device for the load in the power region are urgently needed.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In view of the above, the present invention provides a short-term prediction method and apparatus for a load in a power domain, and aims to solve the technical problem that the accuracy of short-term actual load prediction cannot be improved by constructing a growth rate factor prediction model in the prior art.
The technical scheme of the invention is realized as follows:
in one aspect, the present invention provides a short-term prediction method for a load in a power domain, including:
s1, acquiring historical power load demand values, and acquiring load characteristic information according to the historical power load demand values;
s2, constructing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model;
and S3, generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model.
In addition to the above technical solution, preferably, before acquiring the historical power load demand value and acquiring the load characteristic information from the historical power load demand value in step S1, the method further includes setting a time interval, the time interval being 15 minutes, recording the power load demand values of each day from zero according to the time interval, summarizing and sorting the power load demand values according to the corresponding dates, and generating and storing the historical power load demand value date table.
Based on the above technical means, preferably, step S1 includes acquiring a historical power load demand value, and acquiring load characteristic information from the historical power load demand value, and further includes the steps of acquiring the historical power load demand value from a historical power load demand value date table, dividing the historical power load demand value into first, second, and third historical power load demand values, constructing a slope conversion formula from the first, second, and third historical power load demand values, and acquiring the load characteristic information from the slope conversion formula and the first, second, and third historical power load demand values.
Based on the above technical solution, preferably, the load characteristic information is obtained according to the slope conversion formula and the first, second and third historical power load demand values, and the method further includes the steps of calculating the third historical power load demand value to be compared through the first and second historical power load demand values according to the slope conversion formula, obtaining a historical power load error factor according to the third historical power load demand value and the third historical power load demand value to be compared, and establishing an original load prediction formula as the load characteristic information according to the slope conversion formula and the historical power load error factor.
On the basis of the above technical solution, preferably, in step S2, a power load growth rate factor data table is constructed according to the power load demand value, a linear regression model is established according to the power load growth rate factor data table, and a growth rate function is extracted from the linear regression model, and the method further includes the steps of constructing the power load growth rate factor data table according to the power load demand value, setting a linear regression standard expression, extracting the power load growth rate factor data from the power load growth rate factor data table and substituting the power load growth rate factor data into the linear regression standard expression, constructing the linear regression model according to the substitution result, extracting the growth rate function from the linear regression model, and obtaining the prediction factor according to the growth rate function.
On the basis of the above technical solution, preferably, the method further includes the following steps, and the growth rate function is:
wherein x isT+1(i) Represents the ith node load on day T +1, and T represents the date on which the power load demand value was recorded.
In addition to the above-described technical means, it is preferable that the step S3 is a step of generating a short-term load prediction model from the load characteristic information and the increase rate function, and predicting the short-term load from the short-term load prediction model, and a step of estimating a short-term load prediction formula as the short-term load prediction model from the load characteristic information, the increase rate function, and the prediction factor, and predicting the short-term load from the short-term load prediction model.
Still more preferably, the short-term prediction device of the power zone load includes:
the acquisition module is used for acquiring a historical power load demand value and acquiring load characteristic information according to the historical power load demand value;
the model building module is used for building a power load growth rate factor data table according to the power load demand value, building a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model;
and the prediction module is used for generating a load short-term prediction model according to the load characteristic information and the growth rate function and predicting the short-term load according to the load short-term prediction model.
In a second aspect, the method for short-term prediction of power domain loads further comprises a storage device comprising: a memory, a processor and a short term prediction method program of a power domain load stored on the memory and executable on the processor, the short term prediction method program of a power domain load being configured to implement the steps of the short term prediction method of a power domain load as described above.
In a third aspect, the short-term prediction method of the power area load further includes a medium, which is a computer medium having a short-term prediction method program of the power area load stored thereon, and when the short-term prediction method program of the power area load is executed by a processor, the method of the short-term prediction method of the power area load is implemented as described above.
Compared with the prior art, the short-term prediction method of the load in the power area has the following beneficial effects:
(1) by constructing the growth rate factor, the factor data characteristics are highly consistent with the daily load data characteristics, so that the growth rate factor does not change the original load data characteristics, and the stability and the accuracy of load prediction are improved.
(2) By optimizing the increase rate factor, namely the deviation factor of the probability distribution after the increase rate conversion, the error rate of node load prediction can be greatly reduced when the multi-node load is predicted at the same time, and the accuracy of the node load prediction is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an apparatus in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a short-term prediction method for load in a power domain according to a first embodiment of the present invention;
fig. 3 is a functional block diagram illustrating a short-term prediction method of a load in a power domain according to a first embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the storage device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the device, and that in actual implementations the device may include more or less components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005 as a medium may include an operating system, a network communication module, a user interface module, and a short-term prediction method program of a power region load.
In the device shown in fig. 1, the network interface 1004 is mainly used to establish a communication connection of the device with a server that stores all data required in the short-term prediction method system of power area load; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the short-term prediction method device of a power area load of the present invention may be provided in a short-term prediction method device of a power area load that calls a short-term prediction method program of a power area load stored in the memory 1005 by the processor 1001 and executes a short-term prediction method of a power area load provided by the present invention.
Referring to fig. 2, fig. 2 is a flowchart illustrating a short-term prediction method for a load in a power domain according to a first embodiment of the present invention.
In this embodiment, the short-term prediction method of the load in the power domain includes the following steps:
s10: and acquiring a historical power load demand value, and acquiring load characteristic information according to the historical power load demand value.
It should be understood that the present implementation predicts short term loads, which typically range from 24 hours daily to 168 hours weekly, requiring 1-7 days of load value. Generally, in short-term load prediction, changes in date, weather, and the like are often considered.
It should be understood that, the power system firstly sets a time interval, which is 15 minutes, records the power load demand values of each day from zero according to the time interval, and performs summary arrangement according to the corresponding dates to generate and store a historical power load demand value date table, in this embodiment, the load data (time, load) recorded by the system at 96 points of each day in the last four years 2014-2017 is set.
It should be understood that, the historical power load demand value is then obtained from the historical power load demand value date table, that is, load data at 96 points per day in the last four years 2014-2017 is collected, and in order to improve the accuracy of prediction, normalization processing is performed on the data, that is, normalization processing needs to be performed on numerical value variables (hysteresis historical characteristics and the like) in two data sets so as to meet the input requirement of the load prediction model. And normalizing the sample data to be between 0 and 1 by adopting a min-max normalization method, so that the historical load variables are in the same order of magnitude, wherein the min-max normalization method is a known normalization method.
It should be appreciated that after retrieving the historical power load demand values, a broad table of average loads per day is established as shown in table 1:
TABLE 1 average daily load Width Table
Then, a slope conversion formula is constructed according to the daily average load width table, namely the slope conversion formula is constructed according to the 15-minute slope characteristic of the 96-point load curve, and the constructed slope conversion formula is as follows:
converting 96-point load data in 2014-2017 according to a slope conversion formula to construct a wide table 2, wherein the table 2 is shown as the following table:
TABLE 2 node slope data
Firstly, according to the analysis of the association rule, a model for predicting 2017 year data by constructing 2014-charge 2017 year data is constructed, and the 2017 year data is predicted through 2014-charge 2016 year data in a certain range, so that an error factor function is established:
for vector (epsilon)i)n×1Performing simulation evaluation, and finding prediction error rate of [ -0.02,0.02 [)]The ratio of the two is only 96.21%, if the ratio is more than 98%, the ratio of the two to epsilon is also requirediAnd (6) correcting. Establishing a factor function offset function θ:
the deviation correcting amount is not fixed at 0.008 and changes along with the annual historical data change, so that an original load prediction formula can be deduced as load characteristic information.
g(xi+1)=xi×(1+θ(εi+1));
Wherein, g (x)i+1) For load prediction value, xiIs the ith node load.
It should be understood that the 96-point-per-day load forecasting method refers to forecasting the load demand value of every 15 minutes (96 time points in total) from zero time of the next day, and the 96-point load forecasting accuracy isWhereinIs the relative error of the ith time point in 96 examination points, wiIs the actual acquisition load at the moment i, w'iIs the predicted load at time i.
S20: and establishing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model.
It should be appreciated that the system will construct a power load growth factor data table based on the power load demand value, as shown in table 3:
year of year | Month and day | Week type | Legal holiday | Node point | Node growth rate |
2014 | 1-1 | 4 | 1 | 0 | - |
…… | …… | …… | …… | …… | …… |
2014 | 12-31 | 4 | 8 | 95 | -0.1378204 |
2015 | 1-1 | 5 | 1 | 0 | -0.0257365 |
2015 | 1-1 | 5 | 1 | 1 | -0.0338854 |
…… | …… | …… | …… | …… | …… |
2017 | 10-30 | 2 | 8 | 95 | 0.0473770 |
TABLE 3 growth factor data sheet
Then, a linear regression model is established according to the power load growth factor data table, and a growth rate function is extracted from the linear regression model, and the method further comprises the following steps of establishing the power load growth factor data table according to the power load demand value, setting a linear regression standard expression, extracting the power load growth factor data from the power load growth factor data table and substituting the power load growth factor data into the linear regression standard expression, establishing the linear regression model according to the substitution result, extracting the growth rate function from the linear regression model, and obtaining the prediction factor according to the growth rate function.
It should be understood that linear regression is a statistical analysis method that uses regression analysis in mathematical statistics to determine the quantitative relationship of interdependence between two or more variables, expressed as y ═ w' x + e, and e is a normal distribution with error following a mean of 0. In this embodiment, y is calculated using w' x + e.
wherein x isT+1(i) Represents the ith node load on day T +1, and T represents the date on which the power load demand value was recorded.
It should be understood that the resulting predictors are:
it should be appreciated that the cycle linear growth characteristic should also be considered for the load predictor on the same non-holiday date of the week.
S30: and generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model.
It should be understood that finally, a load short-term prediction formula is deduced as a load short-term prediction model according to the load characteristic information, the growth rate function and the prediction factor, and the short-term load is predicted according to the load short-term prediction model.
It should be understood that the load short term prediction formula is: g (x)T+1(i))=xT(95)×(1+ω(xT+1(i)))。
The above description is only for illustrative purposes and does not limit the technical solutions of the present application in any way.
As can be easily found from the above description, the present embodiment obtains the load characteristic information according to the historical power load demand value by obtaining the historical power load demand value; establishing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model; and generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model. According to the method and the device, the factor data characteristics of the growth rate factor are highly consistent with those of daily load data, so that the growth rate factor does not change the original load data characteristics, the error rate of node load prediction can be greatly reduced when the multi-node load is predicted, and the prediction accuracy is improved.
In addition, the embodiment of the invention also provides a short-term prediction device of the load of the power area. As shown in fig. 3, the short-term prediction device for a load in a power domain includes: the system comprises an acquisition module 10, a model building module 20 and a prediction module 30.
An obtaining module 10, configured to obtain a historical power load demand value, and obtain load characteristic information according to the historical power load demand value;
a model building module 20, configured to build a power load growth rate factor data table according to the power load demand value, build a linear regression model according to the power load growth rate factor data table, and extract a growth rate function from the linear regression model;
and the prediction module 30 is used for generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model.
In addition, it should be noted that the above-described embodiments of the apparatus are merely illustrative, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of the modules to implement the purpose of the embodiments according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not elaborated in the present embodiment may refer to the short-term prediction method of the power domain load provided in any embodiment of the present invention, and are not described herein again.
Furthermore, an embodiment of the present invention further provides a medium, which is a computer medium having a short-term prediction method program of a power area load stored thereon, where the short-term prediction method program of the power area load, when executed by a processor, implements the following operations:
s1, acquiring historical power load demand values, and acquiring load characteristic information according to the historical power load demand values;
s2, constructing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model;
and S3, generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
setting a time interval, wherein the time interval is 15 minutes, recording the power load demand values of each day from zero according to the time interval, performing summary arrangement according to corresponding dates, and generating and storing a historical power load demand value date table.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
the method comprises the steps of obtaining historical power load demand values from a historical power load demand value date table, dividing the historical power load demand values into first, second and third historical power load demand values, constructing a slope conversion formula according to the first, second and third historical power load demand values, and obtaining load characteristic information according to the slope conversion formula and the first, second and third historical power load demand values.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
and calculating a third history power load demand value to be compared according to the slope conversion formula and the first and second history power load demand values, acquiring a history power load error factor according to the third history power load demand value and the third history power load demand value to be compared, and establishing an original load prediction formula as load characteristic information according to the slope conversion formula and the history power load error factor.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
the method comprises the steps of constructing a power load growth rate factor data table according to a power load demand value, setting a linear regression standard expression, extracting power load growth rate factor data from the power load growth rate factor data table and substituting the power load growth rate factor data into the linear regression standard expression, constructing a linear regression model according to the substitution result, extracting a growth rate function from the linear regression model, and obtaining a prediction factor according to the growth rate function.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
the growth rate function is:
wherein x isT+1(i) Represents the ith node load on day T +1, and T represents the date on which the power load demand value was recorded.
Further, the short-term prediction method program of the power region load further realizes the following operations when being executed by a processor:
and a load short-term prediction formula is predicted according to the load characteristic information, the growth rate function and the prediction factor to serve as a load short-term prediction model, and the short-term load is predicted according to the load short-term prediction model.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A short-term prediction method of a load in a power area is characterized in that: comprises the following steps;
s1, acquiring historical power load demand values, and acquiring load characteristic information according to the historical power load demand values;
s2, constructing a power load growth rate factor data table according to the power load demand value, establishing a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model;
and S3, generating a load short-term prediction model according to the load characteristic information and the growth rate function, and predicting the short-term load according to the load short-term prediction model.
2. The method for short-term prediction of power domain loads according to claim 1, characterized by: in step S1, before the historical power load demand value is acquired and the load characteristic information is acquired based on the historical power load demand value, the method further includes setting a time interval, which is 15 minutes, recording the daily power load demand values from zero according to the time interval, performing summary arrangement according to the corresponding dates, and generating and storing a historical power load demand value date table.
3. The method for short-term prediction of power domain loads according to claim 2, characterized by: step S1 of obtaining a historical power load demand value and obtaining load characteristic information based on the historical power load demand value, further comprising the steps of obtaining the historical power load demand value from the historical power load demand value date table, dividing the historical power load demand value into a first, a second and a third historical power load demand values, constructing a slope conversion formula based on the first, the second and the third historical power load demand values, and obtaining the load characteristic information based on the slope conversion formula and the first, the second and the third historical power load demand values.
4. The method for short-term prediction of power domain loads according to claim 3, characterized by: and obtaining load characteristic information according to the slope conversion formula and the first, second and third historical power load demand values, and further comprising the following steps of calculating the third historical power load demand value to be compared through the first and second historical power load demand values according to the slope conversion formula, obtaining a historical power load error factor according to the third historical power load demand value and the third historical power load demand value to be compared, and establishing an original load prediction formula as the load characteristic information according to the slope conversion formula and the historical power load error factor.
5. The method for short-term prediction of power domain loads according to claim 4, characterized by: in step S2, a power load growth rate factor data table is constructed from the power load demand value, a linear regression model is established from the power load growth rate factor data table, and a growth rate function is extracted from the linear regression model, and the method further includes the steps of constructing the power load growth rate factor data table from the power load demand value, setting a linear regression standard expression, extracting the power load growth rate factor data from the power load growth rate factor data table and substituting the same into the linear regression standard expression, constructing the linear regression model from the substitution result, extracting the growth rate function from the linear regression model, and obtaining the prediction factor from the growth rate function.
7. The method for short-term prediction of power domain loads according to claim 6, characterized by: in step S3, a short-term load prediction model is generated based on the load characteristic information and the growth rate function, and the short-term load is predicted based on the short-term load prediction model, and the method further includes the step of estimating a short-term load prediction formula as a short-term load prediction model based on the load characteristic information, the growth rate function, and the prediction factor, and predicting the short-term load based on the short-term load prediction model.
8. A short-term prediction device for a power area load, comprising:
the acquisition module is used for acquiring a historical power load demand value and acquiring load characteristic information according to the historical power load demand value;
the model building module is used for building a power load growth rate factor data table according to the power load demand value, building a linear regression model according to the power load growth rate factor data table, and extracting a growth rate function from the linear regression model;
and the prediction module is used for generating a load short-term prediction model according to the load characteristic information and the growth rate function and predicting the short-term load according to the load short-term prediction model.
9. A storage device, the storage device comprising: a memory, a processor and a short term prediction method program of a power domain load stored on the memory and executable on the processor, the short term prediction method program of a power domain load being configured to implement the steps of the short term prediction method of a power domain load as claimed in any one of claims 1 to 7.
10. A medium, characterized in that the medium is a computer medium having stored thereon a short-term prediction method program of a power area load, which when executed by a processor, implements the steps of the short-term prediction method of a power area load according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011083600.0A CN112232559B (en) | 2020-10-12 | 2020-10-12 | Short-term prediction method and device for power regional load |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011083600.0A CN112232559B (en) | 2020-10-12 | 2020-10-12 | Short-term prediction method and device for power regional load |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112232559A true CN112232559A (en) | 2021-01-15 |
CN112232559B CN112232559B (en) | 2023-06-13 |
Family
ID=74112154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011083600.0A Active CN112232559B (en) | 2020-10-12 | 2020-10-12 | Short-term prediction method and device for power regional load |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112232559B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113298298A (en) * | 2021-05-10 | 2021-08-24 | 国核电力规划设计研究院有限公司 | Charging pile short-term load prediction method and system |
CN113675844A (en) * | 2021-08-05 | 2021-11-19 | 湘潭大学 | Multi-node power load prediction method |
CN116450995A (en) * | 2023-06-13 | 2023-07-18 | 中国林业科学研究院速生树木研究所 | Trunk liquid flow velocity prediction system based on big data analysis |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010034637A1 (en) * | 2000-02-04 | 2001-10-25 | Long-Ji Lin | Systems and methods for predicting traffic on internet sites |
US20020152305A1 (en) * | 2000-03-03 | 2002-10-17 | Jackson Gregory J. | Systems and methods for resource utilization analysis in information management environments |
CN103310284A (en) * | 2013-06-08 | 2013-09-18 | 深圳供电局有限公司 | Methods and device for determining economic loads and cooling loads |
CN105811402A (en) * | 2016-03-22 | 2016-07-27 | 广西电网有限责任公司电力科学研究院 | Electric power load forecasting system and forecasting method |
US9439081B1 (en) * | 2013-02-04 | 2016-09-06 | Further LLC | Systems and methods for network performance forecasting |
US20170102683A1 (en) * | 2015-10-12 | 2017-04-13 | International Business Machines Corporation | Automated energy load forecaster |
CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN110503471A (en) * | 2019-08-21 | 2019-11-26 | 广东电网有限责任公司 | A kind of user's maximum demand estimation method |
CN111461449A (en) * | 2020-04-09 | 2020-07-28 | 昆明能讯科技有限责任公司 | Power load prediction method and computer program product |
-
2020
- 2020-10-12 CN CN202011083600.0A patent/CN112232559B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20010034637A1 (en) * | 2000-02-04 | 2001-10-25 | Long-Ji Lin | Systems and methods for predicting traffic on internet sites |
US20020152305A1 (en) * | 2000-03-03 | 2002-10-17 | Jackson Gregory J. | Systems and methods for resource utilization analysis in information management environments |
US9439081B1 (en) * | 2013-02-04 | 2016-09-06 | Further LLC | Systems and methods for network performance forecasting |
CN103310284A (en) * | 2013-06-08 | 2013-09-18 | 深圳供电局有限公司 | Methods and device for determining economic loads and cooling loads |
US20170102683A1 (en) * | 2015-10-12 | 2017-04-13 | International Business Machines Corporation | Automated energy load forecaster |
CN105811402A (en) * | 2016-03-22 | 2016-07-27 | 广西电网有限责任公司电力科学研究院 | Electric power load forecasting system and forecasting method |
CN109034504A (en) * | 2018-09-14 | 2018-12-18 | 云南电网有限责任公司 | A kind of Short-term Load Forecasting Model method for building up and device |
CN109657844A (en) * | 2018-11-28 | 2019-04-19 | 国电南瑞科技股份有限公司 | Power Short-Term Load Forecasting method and apparatus |
CN110503471A (en) * | 2019-08-21 | 2019-11-26 | 广东电网有限责任公司 | A kind of user's maximum demand estimation method |
CN111461449A (en) * | 2020-04-09 | 2020-07-28 | 昆明能讯科技有限责任公司 | Power load prediction method and computer program product |
Non-Patent Citations (3)
Title |
---|
史文博;王健;沈添福;边瑞恩;: "基于改进倍比平滑法的节假日短期负荷预测方法", 电力建设 * |
李家璐: "应对海量数据的超短期负荷预测在实时电力市场的应用研究", 电力大数据 * |
谈韵 等: "计及光伏与风电资源的低压电网综合饱和负荷预测", 可再生能源 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113298298A (en) * | 2021-05-10 | 2021-08-24 | 国核电力规划设计研究院有限公司 | Charging pile short-term load prediction method and system |
CN113298298B (en) * | 2021-05-10 | 2023-12-29 | 国核电力规划设计研究院有限公司 | Short-term load prediction method and system for charging pile |
CN113675844A (en) * | 2021-08-05 | 2021-11-19 | 湘潭大学 | Multi-node power load prediction method |
CN113675844B (en) * | 2021-08-05 | 2022-09-27 | 湘潭大学 | Multi-node power load prediction method |
CN116450995A (en) * | 2023-06-13 | 2023-07-18 | 中国林业科学研究院速生树木研究所 | Trunk liquid flow velocity prediction system based on big data analysis |
CN116450995B (en) * | 2023-06-13 | 2023-09-22 | 中国林业科学研究院速生树木研究所 | Trunk liquid flow velocity prediction system based on big data analysis |
Also Published As
Publication number | Publication date |
---|---|
CN112232559B (en) | 2023-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110610280B (en) | Short-term prediction method, model, device and system for power load | |
CN112232559A (en) | Short-term prediction method and device for load in power area | |
CN109726872B (en) | Energy consumption prediction method and device, storage medium and electronic equipment | |
CN105225026A (en) | A kind of Research on Housing Vacancy Rate appraisal procedure based on electric energy service management platform | |
CN112330077B (en) | Power load prediction method, power load prediction device, computer equipment and storage medium | |
US10333307B2 (en) | Machine learning based demand charge | |
CN111612275A (en) | Method and device for predicting load of regional user | |
CN116227637A (en) | Active power distribution network oriented refined load prediction method and system | |
CN112907062A (en) | Power grid electric quantity prediction method, device, medium and terminal integrating temperature characteristics | |
Porteiro et al. | Short term load forecasting of industrial electricity using machine learning | |
CN113919655A (en) | Law enforcement personnel scheduling method, system, computer device and storage medium | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
Yu et al. | A model integrating ARIMA and ANN with seasonal and periodic characteristics for forecasting electricity load dynamics in a state | |
CN112801374B (en) | Model training method, power load prediction method, device and equipment | |
CN112508260B (en) | Medium-and-long-term load prediction method and device of distribution transformer based on comparative learning | |
CN117744916A (en) | Method and device for predicting energy storage capacity, computer equipment and readable storage medium | |
CN115577996B (en) | Risk assessment method, system, equipment and medium for power grid power failure plan | |
CN113837486B (en) | RNN-RBM-based distribution network feeder long-term load prediction method | |
CN113837467B (en) | Point-to-point energy project evaluation method and device, computer equipment and storage medium | |
CN114971736A (en) | Power metering material demand prediction method and device, electronic equipment and storage medium | |
CN114282952A (en) | Electricity price charging abnormity identification method and device, computer equipment and storage medium | |
WO2016077475A1 (en) | Behavioral demand response using substation meter data | |
Lee et al. | Peak Load Estimation with the Generalized Extreme Value Distribution | |
Zhang et al. | Medium and long-term load forecasting based on PCA and BP neural network method | |
CN113935536A (en) | Power utilization area first-aid repair planning 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |