CN114912679A - Load prediction method based on multi-industry historical typical load curve superposition - Google Patents
Load prediction method based on multi-industry historical typical load curve superposition Download PDFInfo
- Publication number
- CN114912679A CN114912679A CN202210508324.0A CN202210508324A CN114912679A CN 114912679 A CN114912679 A CN 114912679A CN 202210508324 A CN202210508324 A CN 202210508324A CN 114912679 A CN114912679 A CN 114912679A
- Authority
- CN
- China
- Prior art keywords
- load
- industry
- typical
- area
- hour
- 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 36
- 238000004590 computer program Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000013277 forecasting method Methods 0.000 claims abstract 2
- 230000005611 electricity Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 2
- 238000009851 ferrous metallurgy Methods 0.000 description 2
- 238000009856 non-ferrous metallurgy Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 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
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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)
- 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)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a load forecasting method based on superposition of multi-industry historical typical load curves, and relates to the technical field of power calculation and analysis methods. The invention provides a load prediction method based on multi-industry historical typical load curve superposition, which adopts a prediction method of multi-industry typical curve superposition to improve the accuracy of load prediction. According to the invention, the big data calculation is carried out based on the computer program, so that the errors caused by manual calculation can be reduced, the reliability of load prediction is improved, and the working efficiency of load prediction is improved.
Description
Technical Field
The invention belongs to the technical field of electric power calculation and analysis methods, and particularly relates to a load prediction method based on multi-industry historical typical load curve superposition.
Background
Load forecasting is an important component of the power market and is a precondition for scheduling and planning power resources. The accuracy of the load prediction will directly affect the rationality of the grid investment, the network layout and the grid scheduling operation. Along with the establishment of an electric power market, the requirement on the load prediction level increases day by day, the load prediction level is effectively improved by using big data of a computer to predict the load, the reduction of the energy consumption of a power grid is facilitated, the running mode of the power grid is reasonably arranged, a unit maintenance plan is established, and the improvement of the economic benefit and the social benefit of an electric power system is facilitated.
With the development of economy, more and more factors influencing the development of a power grid exist, the load prediction is carried out simply by manpower, the accuracy of the load prediction cannot be guaranteed, and the reliability of the dispatching operation and planning of the power grid is influenced.
Disclosure of Invention
The invention aims to provide a load prediction method based on multi-industry historical typical load curve superposition, thereby overcoming the defect that the accuracy of load prediction cannot be ensured by simply manually predicting the load in the prior art.
In order to achieve the purpose, the invention provides a load prediction method based on multi-industry historical typical load curve superposition, which comprises the following steps:
automatically acquiring historical 8760-hour load data of users in each industry, and simulating and calculating typical 8760-hour load curves of each industry;
processing the typical 8760-hour load curve of each industry to obtain a total 8760-hour load curve of a large industrial user;
calculating according to the historical 8760-hour load data of a certain area and the 8760-hour load data of the large industrial users of the area to obtain an area typical conventional 8760-hour load curve of the area;
obtaining a predicted annual conventional electric quantity and a predicted region 8760 hour load curve according to the predicted electric quantity of each industry, the typical 8760 hour load curve of each industry and the typical conventional 8760 hour load curve of the region in the predicted region;
and generating a load forecasting result according to the forecast annual conventional electric quantity and a forecast area 8760-hour load curve.
Preferably, the method automatically acquires historical 8760-hour load data of users in each industry, and simulates and calculates a typical 8760-hour load curve of each industry, and comprises the following steps:
acquiring a load metering value of a large reporting user in 8760 hours; and carrying out different industry classifications on the large users;
acquiring a historical 8760-hour load metering value of a large user in a certain industry, and carrying out weighted average on the historical 8760-hour load metering values of all the large users belonging to the same industry at the same moment to obtain a typical 8760-hour load curve of the industry;
repeat step S12 to obtain a typical 8760 hour load curve for each industry.
Preferably, the industry-typical 8760 hour load curve for a certain industry is calculated as:
X 1 ＝(A 1 +B 1 +C 1 +···+N 1 )/n
X 2 ＝(A 2 +B 2 +C 2 +···+N 2 )/n
X 3 ＝(A 3 +B 3 +C 3 +···+N 3 )/n
......
X n ＝(A n +B n +C n +···+N n )/n
P 1 ＝{X 1 ,X 2 ,X 3 ,···,X n }/X max
wherein, P 1 Represents the typical 8760 hour load curve, X, of a certain industry n Representing the load value, X, at each time in the typical 8760 hour load curve max Representation set P 1 Middle element X 1 -X n Maximum of (A), A, B, C, N represents a different large user in the same industry, A 1 、A 2 、A 3 、A n Representing the load values of the same user at different moments;
the typical 8760 hour load curve for each industry is:
P 2 ＝{Y 1 ,Y 2 ,Y 3 ,···,Y n }/Y max
......
P n ＝{Z 1 ,Z 2 ,Z 3 ,···,Z n }/Z max
wherein, P n Represents the industry typical 8760 hour load curve, Y, for the Nth industry max Representation set P 2 Middle Y 1 -Y n Maximum value among the elements. Z max Representation set P n Middle element Z 1 -Z n Maximum value of (2).
Preferably, the industry typical 8760 hour load curves are superimposed to obtain a total industry big user 8760 hour load curve.
Preferably, according to the historical 8760-hour load of a certain area and the 8760-hour load data of the industrial large users of the area, a typical conventional 8760-hour load curve of the area is obtained by calculation and simulation, and the method comprises the following steps:
acquiring the historical 8760-hour load data of a certain area;
the total industrial large user load of the area is obtained by overlapping a plurality of industries under the area;
calculating typical conventional 8760-hour load data of the area according to the historical 8760-hour load data of the area and the total industrial large user load of the area;
and simulating to obtain a typical conventional 8760-hour load curve of the area according to the typical conventional 8760-hour load data of the area.
Preferably, the step of generating the predicted area 8760 hour load curve according to the industry predicted electric quantity of the predicted area, the industry typical 8760 hour load curve and the area typical conventional 8760 hour load curve includes the steps of:
acquiring the predicted electric quantity of a large area user in a predicted area;
acquiring historical conventional electric quantity and historical conventional electric quantity increase rate of the prediction region, and calculating to obtain the predicted conventional electric quantity of the prediction region according to the historical conventional electric quantity and the historical conventional electric quantity increase rate of the region;
calculating the 8760-hour load of the prediction area according to the area large user prediction electric quantity of the prediction area and the prediction conventional electric quantity in the step S43;
and calculating a 8760-hour load curve and the maximum utilization hours of the prediction area according to the 8760-hour load of the prediction area.
Preferably, the step of generating the load prediction result according to the predicted annual conventional electric quantity and the predicted region 8760-hour load curve comprises the following steps:
acquiring the predicted electric quantity of each industry of the predicted area and the total predicted electric quantity of the calculated area, wherein the total predicted electric quantity of the area is represented by a curve to obtain a 8760-hour load curve based on the predicted area;
and generating a load prediction result according to the load curve of the prediction region 8760 hours.
A computer program product of a load prediction method based on multi-industry historical typical load curve overlay, the computer program product comprising a non-transitory readable storage medium and a computer program, the computer program being tangibly stored on the non-transitory readable storage medium, the computer program being executable by a processor in a computer to perform steps implementing the load prediction method as claimed in any one of claims 1 to 7.
Compared with the prior art, the invention has the following beneficial effects:
according to the load prediction method based on superposition of multi-industry historical typical load curves, historical 8760-hour load data of users in various industries are automatically obtained, a typical 8760-hour load curve of each industry is simulated and calculated, and the 8760-hour load curve is a year-lasting load curve; processing the typical 8760-hour load curve of each industry to obtain a total 8760-hour load curve of a large industrial user; calculating according to historical 8760 point load data of a certain area and load data of large industrial users 8760 hours of the area to obtain a typical conventional 8760 hour load curve of the area; obtaining a predicted annual conventional electric quantity and a predicted region 8760 hour load curve according to the predicted electric quantity of each industry, the typical 8760 hour load curve of each industry and the typical conventional 8760 hour load curve of the region in the predicted region; and generating a load prediction result according to the conventional predicted annual electric quantity and a predicted region 8760-hour load curve. According to the invention, load prediction and the like are carried out by an industry typical load curve superposition method, so that the accuracy of a load prediction result is improved, and a basis is provided for scientific power grid planning.
According to the invention, based on a large amount of user historical load data, a computer program is adopted to calculate a large amount of data, a typical load curve model of each industry is established, and a method of stacking typical load curves of the industry is adopted to predict the load, so that the accuracy of a load prediction result is improved, and a basis is provided for scientific power grid planning.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only one embodiment of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
FIG. 1 is a flow chart of a load prediction method based on multi-industry historical typical load curve stacking in accordance with the present invention;
FIG. 2 is a typical daily load graph for the ferrous metallurgy industry for one embodiment of the present invention;
FIG. 3 is a typical daily load graph for the nonferrous metallurgy industry according to one embodiment of the present invention.
Detailed Description
The technical solutions in the present invention are clearly and completely described below with reference to the drawings in 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 derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a load prediction method based on stacking of multi-industry historical typical load curves according to one embodiment of the present invention includes the following steps:
s1, automatically acquiring historical 8760-hour load data of users in each industry, and simulating and calculating a typical 8760-hour load curve of each industry, wherein the 8760-hour load curve is an annual continuous load curve;
s2, processing the typical 8760-hour load curve of each industry to obtain a total 8760-hour load curve of the large industrial user;
s3, calculating according to the historical 8760-hour load data of a certain area and the 8760-hour load data of the industrial large users of the area to obtain an area typical conventional 8760-hour load curve of the area;
and S4, obtaining the predicted annual conventional electric quantity and the predicted region 8760 hour load curve according to the predicted electric quantity of each industry, the typical 8760 hour load curve of each industry and the typical conventional 8760 hour load curve of the region in the predicted region.
And S5, generating a load prediction result according to the predicted annual conventional electric quantity and the predicted region 8760-hour load curve.
According to the load prediction method based on multi-industry historical typical load curve superposition, historical 8760-hour load data of users in each industry are automatically acquired, a typical 8760-hour load curve in each industry is simulated and calculated, and the 8760-hour load curve is an annual continuous load curve; processing the typical 8760-hour load curve of each industry to obtain a total 8760-hour load curve of a large industrial user; calculating according to historical 8760 point load data of a certain area and 8760-hour load data of large industrial users of the area to obtain a typical conventional 8760-hour load curve of the area; obtaining a predicted annual conventional electric quantity and a predicted region 8760 hour load curve according to the predicted electric quantity of each industry, the typical 8760 hour load curve of each industry and the typical conventional 8760 hour load curve of the region in the predicted region; and generating a load prediction result according to the conventional predicted annual electric quantity and a predicted region 8760-hour load curve. According to the invention, load prediction and the like are carried out by an industry typical load curve superposition method, so that the accuracy of a load prediction result is improved, and a basis is provided for scientific power grid planning.
In one embodiment, in step S1, historical 8760-hour load data of users in each industry is automatically obtained, and a typical 8760-hour load curve of each industry is simulated and calculated, including the following steps:
s11, acquiring a load metering value of a report large user in 8760 hours; and carrying out different industry classifications on the large users;
s12, obtaining the historical 8760-hour load metering value of a large user in a certain industry, and carrying out weighted average on the historical 8760-hour load metering values of all the large users belonging to the same industry at the same moment to obtain a typical 8760-hour load curve of the industry;
and S13, repeating the step S12 to obtain typical 8760-hour load curves of various industries.
In one embodiment, the industry typical 8760 hour load curve for a certain industry is calculated as:
X 1 ＝(A 1 +B 1 +C 1 +···+N 1 )/n
X 2 ＝(A 2 +B 2 +C 2 +···+N 2 )/n
X 3 ＝(A 3 +B 3 +C 3 +···+N 3 )/n
......
X n ＝(A n +B n +C n +···+N n )/n
P 1 ＝{X 1 ,X 2 ,X 3 ,···,X n }/X max
wherein, P 1 Represents the typical 8760 hour load curve, X, of a certain industry n Representing the load value, X, at each time in the typical 8760 hour load curve max Representation set P 1 Middle element X 1 -X n Maximum of (A), A, B, C, N represents a different large user in the same industry, A 1 、A 2 、A 3 、A n Representing the load values of the same user at different moments;
similarly, the typical 8760 hour load curve for each industry is:
P 2 ＝{Y 1 ,Y 2 ,Y 3 ,···,Y n }/Y max
......
P n ＝{Z 1 ,Z 2 ,Z 3 ,···,Z n }/Z max
wherein, P n Represents the industry typical 8760 hour load curve, Y, for the Nth industry max Representation set P 2 Middle Y 1 -Y n Maximum value among the elements. Z max Representation set P n Middle element Z 1 -Z n Maximum value of (2).
In one embodiment, in step S2, the industry typical 8760 hour load curves are added to obtain a total industry large user 8760 hour load curve.
Specifically, the formula for superimposing the typical 8760-hour load curve of each industry is as follows:
P user 8760 ＝P 1 *Q 1 +P 2 *Q 2 +···+P n *Q n
Wherein, P User 8760 Represents the total industry grand user 8760 hour load curve, Q, that each industry adds 1 Representing the electricity consumption, Q, corresponding to the first industry n And the corresponding electricity consumption of the nth industry is represented.
In one embodiment, in step S3, calculating and simulating an area typical conventional 8760-hour load curve of an area according to the historical 8760-hour load of the area and the area industrial macro users 8760-hour load data of the area, includes the following steps:
s31, obtaining the historical 8760 hour load data of a certain area from the historical 8760 hour load data of the industry users S11.
S32, calculating the total industrial large user load of the area obtained by overlapping a plurality of industries in the area;
classifying all industries of the large reporting users in the area, respectively calculating industry typical 8760 hour load curves of all industries in the area (the industry typical 8760 hour load curve and the industry typical 8760 hour load curve can be adopted for calculation), and finally overlapping the industry typical 8760 hour load curves of all industries in the area (the industry typical 8760 hour load curve overlapping formula can be adopted for calculation), so as to obtain the total industrial large user load overlapped by a plurality of industries in the area.
S33, calculating typical conventional 8760-hour load data of the area according to the historical 8760-hour load data of the area and the total industrial large user load of the area;
specifically, the formula for calculating typical conventional 8760 hour load data for the region is as follows:
P general procedure 8760 ＝P Region 8760 -P User 8760
Wherein, P Region 8760 8760 points of the set of loads, P, representing the region User 8760 Represents the total industrial large user load, P, of the area obtained by overlapping a plurality of industries under the area General procedure 8760 A typical conventional 8760 point load set representing the region。
S34, simulating and obtaining a typical conventional 8760-hour load curve of the area according to the typical conventional 8760-hour load data of the area;
specifically, a typical conventional 8760-hour load curve formula of the region is obtained by simulating the typical conventional 8760-hour load data of the region as follows:
P 8760 conventional curve ═ P General procedure 8760 /P Conventional 8760max
Wherein, P General procedure 8760 Is a typical conventional 8760 point load set, P, for the region Conventional 8760max Is represented by P General procedure 8760 Maximum value of middle element, P 8760 conventional curve Is represented by a curve representing a typical conventional 8760 hour load curve for the area in question.
In one embodiment, in step S4, generating a predicted area 8760-hour load curve according to the predicted electric quantity of each industry in the predicted area, the typical 8760-hour load curve of each industry, and the typical conventional 8760-hour load curve of the area, includes the following steps:
s41, acquiring the predicted electric quantity of the large regional user in the predicted region;
s42, acquiring historical conventional electric quantity and historical conventional electric quantity growth rate of the prediction region, calculating to obtain the predicted conventional electric quantity of the prediction region according to the historical conventional electric quantity and the historical conventional electric quantity growth rate of the region, and selecting the historical conventional electric quantity growth rate according to actual needs;
the calculation formula of the predicted conventional electric quantity is as follows:
wherein Q is (predictive routine) To predict annual conventional electricity quantity, Q (History convention) For the conventional electric quantity of the historical years, K1-Kn represents the conventional growth rate from the previous year to the previous N years, alpha, beta and lambda … … N are weighting factors, all the weighting factors are added to be 1, and the closer to the historical years of the predicted years, the more the weighting factor is takenIs large.
S43, calculating the 8760-hour load of the prediction area according to the area large user prediction electric quantity of the prediction area in the step S41 and the prediction conventional electric quantity in the step S43;
the formula for calculating the 8760 hour load for the predicted area is:
P (prediction region 8760) ＝P 1 *Q (1 prediction) +P 2 *Q (2 prediction) +P 3 *Q (3 prediction) +···+P n *Q (n prediction) +P General procedure 8760 *Q Predicting a convention
Wherein, P 1 Typical industry 8760 hour load curve, Q, for industry 1 (1 prediction) For the predicted annual regular power of industry 1, P n An industry typical 8760 hour load curve, Q, for industry n (n prediction) The predicted annual conventional electric quantity of the industry n.
And S44, calculating a load curve of the prediction area 8760 hours and the maximum utilization hours according to the 8760 hours of load of the prediction area.
Calculating a load curve of the prediction area 8760 hours and a maximum utilization hour number according to the load of the prediction area 8760 hours according to the following formula:
P prediction curve 8760 ＝{X 1 ,X 2 ,X 3 ,···,X n }/X max ＝{Y 1 ,Y 2 ,Y 3 ,···,Y n }
Y 1 ＝X 1 /X max ,
Y 2 ＝X 2 /X max ,
......
Y n ＝X n /X max
P Prediction curve 8760 ＝{Y 1 ,Y 2 ,Y 3 ,···,Y n }
Tmax＝Y 1 +Y 2 +Y 3 +···+Y n
Wherein, X max Representation set P Prediction curve 8760 Middle element X 1 -X n Maximum value of (1); typically, n is 8760, and,tmax is the maximum number of hours of utilization, Y 1 -Y n Representing a predicted region 8760 hour load value based on the set P Prediction curve 8760 The curve of the predicted area 8760 hours can be obtained through curve display.
In one embodiment, the step S5 of generating the load prediction result according to the predicted annual regular electricity quantity and the predicted region 8760-hour load curve includes the following steps:
s51, obtaining the predicted electric quantity of each industry of the predicted area and the predicted annual conventional electric quantity obtained in the step S42 to calculate the total predicted electric quantity of the area, wherein the total predicted electric quantity of the area is represented by a curve to obtain a 8760-hour load curve based on the predicted area;
specifically, the calculation formula of the total predicted electric quantity of the area is as follows:
Q (prediction) ＝Q (prediction industry 1) +Q (prediction industry 2) +···+Q (prediction industry n) +Q (predictive routine)
Wherein Q is (prediction) Predicting the amount of electricity, Q, for a region (predictive routine) To predict the conventional quantity of electricity, Q (prediction industry n) And predicting the electric quantity for the nth industry.
And S52, generating a load prediction result according to the load curve of the prediction region 8760 hours.
Specifically, the load prediction result is expressed as:
P＝Q (prediction) /Tmax
Where P is the predicted load and Tmax is the maximum number of hours of utilization.
In one embodiment, a computer program product of a load prediction method based on multi-industry historical typical load curve superposition includes a non-transitory readable storage medium and a computer program, the computer program being tangibly stored on the non-transitory readable storage medium, the computer program being executed by a processor in a computer to implement the steps of the load prediction method according to any of the above embodiments.
In one embodiment, step S1 automatically obtains 8760-hour load data of users in each industry, and divides large users into 9 types of industries with large electric quantity, including ferrous metallurgy; nonferrous metallurgy; mining industry; manufacturing a machine; chemical industry; the building materials industry; the paper industry; the food industry; other industries. A typical 8760 hour load curve for the nine major industries was calculated from the simulation. The typical daily load characteristic curve chart of part of industries is shown in the attached figures 2 and 3.
The prediction according to the present invention steps S1-S2 results in a load prediction as shown in Table 1,
table 1:
the above disclosure is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or modifications within the technical scope of the present invention, and shall be covered by the scope of the present invention.
Claims (8)
1. A load prediction method based on multi-industry historical typical load curve superposition is characterized by comprising the following steps:
automatically acquiring historical 8760-hour load data of users in each industry, and simulating and calculating typical 8760-hour load curves of each industry;
processing the typical 8760-hour load curve of each industry to obtain a total 8760-hour load curve of a large industrial user;
calculating according to historical 8760-hour load data of a certain area and 8760-hour load data of large industrial users of the area to obtain a typical conventional 8760-hour load curve of the area;
obtaining a predicted annual conventional electric quantity and a predicted region 8760 hour load curve according to the predicted electric quantity of each industry, the typical 8760 hour load curve of each industry and the typical conventional 8760 hour load curve of the region in the predicted region;
and generating a load prediction result according to the conventional predicted annual electric quantity and a predicted region 8760-hour load curve.
2. The load prediction method based on multi-industry historical typical load curve superposition as claimed in claim 1, wherein the historical 8760 hour load data of each industry user is automatically obtained, and the typical 8760 hour load curve of each industry is simulated and calculated, comprising the following steps:
acquiring a load metering value of a large reporting user in 8760 hours; and carrying out different industry classifications on the large users;
acquiring a historical 8760-hour load metering value of a large user in a certain industry, and carrying out weighted average on the historical 8760-hour load metering values of all the large users belonging to the same industry at the same moment to obtain a typical 8760-hour load curve of the industry;
repeat step S12 to obtain a typical 8760 hour load curve for each industry.
3. The method of claim 2, wherein the industry typical 8760 hour load curve for a certain industry is calculated as:
X 1 ＝(A 1 +B 1 +C 1 +···+N 1 )/n
X 2 ＝(A 2 +B 2 +C 2 +···+N 2 )/n
X 3 ＝(A 3 +B 3 +C 3 +···+N 3 )/n
......
X n ＝(A n +B n +C n +···+N n )/n
P 1 ＝{X 1 ,X 2 ,X 3, ···,X n }/X max
wherein, P 1 Represents the typical 8760 hour load curve, X, of a certain industry n Representing the load value, X, at each time in the typical 8760 hour load curve max Representation set P 1 Middle element X 1 -X n A, B, C, N representsDifferent big users in the same industry, A 1 、A 2 、A 3 、A n Representing the load values of the same user at different moments;
the typical 8760 hour load curve for each industry is:
P 2 ＝{Y 1 ,Y 2 ,Y 3 ,···,Y n }/Y max
......
P n ＝{Z 1 ,Z 2 ,Z 3 ,···,Z n }/Z max
wherein, P n Represents the industry typical 8760 hour load curve, Y, for the Nth industry max Representation set P 2 Middle Y 1 -Y n The maximum value among the elements. Z is a linear or branched member max Representation set P n Middle element Z 1 -Z n Of (2) is calculated.
4. The method for predicting the load based on the superposition of the multi-industry historical typical load curves according to claim 1, wherein the total 8760-hour load curve of the large industrial user is obtained by superposing the 8760-hour load curves of the various industries.
5. The method for predicting the load based on the superposition of the multi-industry historical typical load curves according to claim 1, wherein a typical conventional 8760-hour load curve of the area of a certain area is obtained through calculation and simulation according to the historical 8760-hour load of the area and the 8760-hour load data of the large industrial users of the area, and the method comprises the following steps:
acquiring the historical 8760-hour load data of a certain area;
the total industrial large user load of the area is obtained by overlapping a plurality of industries under the area;
calculating typical conventional 8760-hour load data of the area according to the historical 8760-hour load data of the area and the total industrial large user load of the area;
and simulating to obtain a typical conventional 8760-hour load curve of the area according to the typical conventional 8760-hour load data of the area.
6. The load prediction method based on superposition of multi-industry historical typical load curves according to claim 1, wherein a predicted area 8760-hour load curve is generated according to each industry predicted electric quantity of a predicted area, each industry typical 8760-hour load curve and the area typical conventional 8760-hour load curve, and the method comprises the following steps:
acquiring the predicted electric quantity of a large area user in a predicted area;
acquiring historical conventional electric quantity and historical conventional electric quantity increase rate of the prediction region, and calculating to obtain the predicted conventional electric quantity of the prediction region according to the historical conventional electric quantity and the historical conventional electric quantity increase rate of the region;
calculating the 8760-hour load of the prediction area according to the area large user prediction electric quantity of the prediction area and the prediction conventional electric quantity in the step S43;
and calculating a 8760-hour load curve and the maximum utilization hours of the prediction region according to the 8760-hour load of the prediction region.
7. The multi-industry historical typical load curve overlay-based load forecasting method of claim 1, wherein generating a load forecasting result according to the forecasted annual regular electricity quantity and forecasted area 8760 hour load curve comprises the steps of:
acquiring the predicted electric quantity of each industry of the predicted area and the total predicted electric quantity of the calculated area, wherein the total predicted electric quantity of the area is represented by a curve to obtain a 8760-hour load curve based on the predicted area;
and generating a load prediction result according to the load curve of the prediction region 8760 hours.
8. A computer program product of a load prediction method based on multi-industry historical typical load curve overlay, the computer program product comprising a non-transitory readable storage medium and a computer program, the computer program being tangibly stored on the non-transitory readable storage medium, the computer program being executable by a processor in a computer to perform steps implementing the load prediction method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508324.0A CN114912679A (en) | 2022-05-11 | 2022-05-11 | Load prediction method based on multi-industry historical typical load curve superposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508324.0A CN114912679A (en) | 2022-05-11 | 2022-05-11 | Load prediction method based on multi-industry historical typical load curve superposition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114912679A true CN114912679A (en) | 2022-08-16 |
Family
ID=82766644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210508324.0A Pending CN114912679A (en) | 2022-05-11 | 2022-05-11 | Load prediction method based on multi-industry historical typical load curve superposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114912679A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115313370A (en) * | 2022-08-19 | 2022-11-08 | 国网安徽省电力有限公司巢湖市供电公司 | Power distribution network load superposition analysis method |
-
2022
- 2022-05-11 CN CN202210508324.0A patent/CN114912679A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115313370A (en) * | 2022-08-19 | 2022-11-08 | 国网安徽省电力有限公司巢湖市供电公司 | Power distribution network load superposition analysis method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106447171B (en) | Power demand side schedulable resource potential modeling method and system | |
| Chang | Energy intensity, target level of energy intensity, and room for improvement in energy intensity: An application to the study of regions in the EU | |
| Olanrewaju et al. | Assessing the energy potential in the South African industry: A combined IDA-ANN-DEA (index decomposition analysis-artificial neural network-data envelopment analysis) model | |
| CN104992239B (en) | A kind of trade power consumption gauge rule Forecasting Methodology based on related coefficient | |
| WO2015081660A1 (en) | Method for forecasting residential quarter short-term load | |
| CN106779478A (en) | A kind of load scheduling Valuation Method | |
| CN104156786A (en) | Non-working day maximum daily load forecasting system considering meteorological multi-factor influences | |
| CN112950067B (en) | Power consumer electricity consumption efficiency evaluation method based on fuzzy comprehensive evaluation | |
| CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
| CN106529769A (en) | Power grid planning method based on comprehensive assessment | |
| CN109242169A (en) | A kind of short-term load forecasting method towards large power customers | |
| CN114912679A (en) | Load prediction method based on multi-industry historical typical load curve superposition | |
| CN109376911A (en) | A kind of micro-capacitance sensor short-term load forecasting method based on EMD-KELMs-SDPSO | |
| CN111680841A (en) | Short-term load prediction method and system based on principal component analysis and terminal equipment | |
| CN103679289B (en) | Methods of electric load forecasting based on multiple regression extrapolation | |
| CN104102840A (en) | Evaluation method for photovoltaic power receptivity of power distribution network | |
| CN110751327A (en) | Long-term load combination prediction method based on multiple linear regression and gray Verhulst model | |
| CN113344449A (en) | Method for predicting monthly-scale industrial water demand | |
| CN104299043A (en) | Ultra-short-term load prediction method of extreme learning machine | |
| CN110991768A (en) | Electric quantity prediction method and system | |
| CN117689160A (en) | Window visual method and system based on power scheduling day plan | |
| CN108321790A (en) | A kind of power grid regulation system and its working method | |
| CN111126716A (en) | Extreme gradient lifting algorithm-based system model for predicting electricity price | |
| Parreño | Analysis and forecasting of electricity demand in Davao del Sur, Philippines | |
| CN110322063B (en) | Power consumption simulation prediction method and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |