CN114049160A - Power consumption demand business index construction method based on electric power big data - Google Patents
Power consumption demand business index construction method based on electric power big data Download PDFInfo
- Publication number
- CN114049160A CN114049160A CN202111439911.0A CN202111439911A CN114049160A CN 114049160 A CN114049160 A CN 114049160A CN 202111439911 A CN202111439911 A CN 202111439911A CN 114049160 A CN114049160 A CN 114049160A
- Authority
- CN
- China
- Prior art keywords
- data
- monthly
- electric quantity
- index
- acceleration
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 25
- 230000001133 acceleration Effects 0.000 claims abstract description 72
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 42
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 42
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 7
- 230000008569 process Effects 0.000 claims abstract description 6
- 230000005611 electricity Effects 0.000 claims description 48
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000002194 synthesizing effect Effects 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 5
- 238000004088 simulation Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 241000251468 Actinopterygii Species 0.000 description 3
- 210000000988 bone and bone Anatomy 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000003723 Smelting Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000272778 Cygnus atratus Species 0.000 description 1
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000208125 Nicotiana Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 241000282806 Rhinoceros Species 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000003490 calendering Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 239000013064 chemical raw material Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000004753 textile 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a power consumption demand business index construction method based on electric power big data, which comprises the following steps: firstly, collecting monthly electric quantity data and monthly average air temperature data; secondly, screening monthly electric quantity data and eliminating noise data; thirdly, converting the monthly electric quantity data without the noise data into standard synthesis acceleration; selecting effective standard synthesis acceleration data by adopting a principal component analysis method, using the effective standard synthesis acceleration data as a prediction model independent variable, and inputting the prediction model into a pre-constructed prediction model, wherein the output of the prediction model is the optimal prediction electric quantity acceleration; fifthly, dynamic air temperature correction: establishing a monthly average air temperature data and standard synthesis acceleration nonlinear model, and correcting the optimal predicted electric quantity acceleration according to the average air temperature data of the future 3 period; sixthly, checking a predicted electric quantity acceleration result; seventhly, compiling a synthesis index; and eighthly, outputting the power consumption demand landscape index. The invention has stronger self-adaptive capability and low requirement on basic data, and does not need to judge and process abnormal values.
Description
Technical Field
The invention belongs to the technical field of electric power data analysis and prediction, and particularly relates to a power consumption demand prosperity index construction method based on electric power big data.
Background
At present, the social and economic environments at home and abroad are extremely complex, the 'black swan' and 'grey rhinoceros' events occur frequently, and a large number of uncertain factors exist in the power consumption demand. The severe external environment requires that the power department can respond to the change of power demand in time, study the power consumption law and grasp the prediction direction. By analyzing the power data with high timeliness and accuracy, the data value is deeply mined, and the possibility is provided for scientifically predicting the power demand.
At present, the prediction method of the power demand mostly focuses on learning the power data of the current period, and a single prediction model is constructed to realize the prediction of the development trend of the future power market. A single prediction model is effective for prediction in a normal electricity environment, but it cannot respond to a burst impact quickly. For external environmental impact, the existing prediction methods mainly take post analysis as a main method and cannot guide power development. In order to solve the problems, the invention constructs a 'prediction black box' of various prediction models, selects an optimal numerical value prediction model, sets a temperature correction module, ensures that the prediction model has the capabilities of timely responding to sudden impact events and temperature changes and automatically adjusting, adopts a 'pre-judging quarter and monthly correction' power demand scene index compilation mode, and timely reflects the power demand change situation and the development situation.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a power demand business index construction method based on electric power big data aiming at the defects in the prior art, wherein a prediction model is constructed, an optimal numerical value prediction model is selected, and an air temperature correction module is arranged, so that the timely response capability and the self-adaptive adjustment capability of a novel power demand business index are improved; meanwhile, the invention adopts a power demand prosperity index compiling mode of 'quarter pre-judgment and monthly correction' to predict the provincial power development trend in time, and can provide analysis support for the operation management and government macro decision of the power company.
In order to solve the technical problems, the invention adopts the technical scheme that: a power consumption prospect index construction method based on electric power big data is characterized by comprising the following steps:
collecting monthly electric quantity data and monthly average air temperature data;
step two, screening monthly electric quantity data and eliminating noise data;
thirdly, converting the monthly electric quantity data without the noise data into standard synthesis acceleration;
selecting effective standard synthesis acceleration data by adopting a principal component analysis method, using the effective standard synthesis acceleration data as a prediction model independent variable, inputting the prediction model independent variable into a pre-constructed prediction model, and outputting the prediction model as the optimal prediction electric quantity acceleration;
step five, dynamic air temperature correction: establishing a monthly average air temperature data and standard synthesis acceleration nonlinear model, and correcting the optimal predicted electric quantity acceleration according to the average air temperature data of the future 3 period;
step six, checking a predicted electric quantity acceleration result: when the prediction result is in the range of the addition of two standard deviations to the average value of the real same-ratio acceleration in the latest N period, selecting the electric quantity acceleration of the prediction model; otherwise, deleting the prediction model and selecting the prediction model again; when all the prediction models are deleted, selecting the most stable simulation walking model as the prediction model; wherein the value range of N is N not less than 12;
step seven, compiling a synthesis index: synthesizing index compilation is carried out by adopting a power demand landscape index compilation mode of 'prejudging quarters and correcting monthly', the total quantity of the electric quantity of the forecasted quarters is calculated according to the acceleration of the same ratio of the forecasted electric quantity, then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is compiled, and then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is linearized to synthesize the power demand landscape index;
and step eight, outputting the power consumption demand scene index.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: step eight is followed still include:
and ninthly, outputting monthly predicted electric quantity, and drawing a fishbone graph according to the power demand prosperity index and the output result of the monthly predicted electric quantity.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: and step two, filtering the monthly electric quantity data, and eliminating the monthly electric quantity data containing invalid electricity utilization information industries when eliminating the noise data, and eliminating the influence of spring festival effect on the monthly electric quantity data.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: the invalid electricity consumption information industry includes an industry in which monthly electricity data is less than 10 ten thousand kilowatt hours and data volume is less than 10% of total data volume.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: in the third step, the calculation formula for converting the monthly electric quantity data from which the noise data are removed into the standard synthesis acceleration rate is as follows:
wherein t is data period, positive integer, monthly electric quantitytMonthly electric quantity data and monthly electric quantity data representing the t periodt-12Monthly electricity data (i.e., monthly electricity data of the same year in the last year) representing the t-12 th periodt-24Monthly electricity data (i.e., monthly electricity data in the same period of the previous year) representing the t-24 th period, monthly electricityt-36The monthly electric quantity data (namely the monthly electric quantity data in the same period of the previous three years) representing the t-36 th period, and alpha is the monthly electric quantityt-12Beta is monthly electric quantityt-24λ is monthly electricity quantityt-36α, β, λ ∈ (0,1), α + β + λ ═ 1.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: in the fourth step, effective standard synthesis acceleration data are selected by adopting a principal component analysis method, and the specific process of taking the effective standard synthesis acceleration data as the independent variable of the prediction model is as follows:
step 401, eliminating standard synthesis acceleration data of invalid industry: eliminating the industries of the top 20% of the highest standard deviation of the latest 120-stage data in the local power database, eliminating the industries of which the standard synthesis speed increase of the current stage exceeds the average value of the latest 120 stage plus or minus two standard deviations, and eliminating the industries of which the latest 3 stage accounts for less than 1% of the power consumption of the whole society and the independent variable of which the correlation coefficient of the latest 120 stage and the dependent variable is less than 0.8;
step 402, mapping n-dimensional standard synthesis acceleration data to k-dimension by a principal component analysis method to obtain a prediction model independent variable; wherein, the values of n and k are both non-0 natural numbers and n is larger than k.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: and step five, establishing a nonlinear model for synthesizing monthly average air temperature data and the standard and increasing speed, wherein the expression of the nonlinear model is as follows:
correcting acceleration ratet-prediction of accelerationt＝k1X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2+k2X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]+k3X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]2+k4X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]+b
Wherein (temperature)tHigh temperature thresholdt) Not less than 0 (temperature)t-12High temperature thresholdt) Not less than 0 (temperature)tLow temperature thresholdt) Not less than 0 (temperature)t-12Low temperature thresholdt) Not less than 0, t is data period and is positive integer, and temperaturetMonthly average air temperature data and temperature representing the t periodt-12Monthly average air temperature data (i.e. monthly average air temperature data of the same year in the last year) representing the t-12 th period, and high temperature thresholdtHigh temperature threshold and low temperature threshold representing t periodtLow temperature threshold, k, for the t-th period1Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2Coefficient of (a), k2Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]Coefficient of (a), k3Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]2Coefficient of (a), k4Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]B is a constant.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: and step seven, the formula for calculating the total quantity of the predicted quarterly electric quantity according to the same-ratio acceleration of the predicted electric quantity is as follows:
wherein monthly electricity is predictedtPredicted monthly electric power representing the t-th period, predicted monthly electric powert+1Predicted monthly electric power representing the t +1 th period, predicted monthly electric powert+2Represents the predicted monthly electricity quantity of the t +2 th period, and t is a data period and is a positive integer.
The power consumption demand business index construction method based on the electric power big data is characterized by comprising the following steps of: in the seventh step, the calculation formula of the leading index weighted proportion is as follows:
the calculation formula of the consistent index weighted proportion in the step seven is as follows:
the time dimension of the index calculation is quarterly, once per quarterly, four quarters of a year, t denotes the current quarterly, t-1 denotes the last quarterly, t-2 denotes the last quarterly, t-4 denotes the same period of the last year, t-1-4 is the same period of the last quarterly last year, and t-2-4 is the same period of the last quarterly last year.
Aforementioned power consumption needs based on electric power big dataThe construction method for solving the prosperity index is characterized by comprising the following steps: in the seventh step, the formula for performing linearization on the weighted similarity of the leading indexes is as follows: leading indextA x look-ahead index weighted unity ratiot+ b, t is data period and is positive integer, a > 0, b > 0, antecedent indextA is equal to or more than 0, a is a weighted equal ratio of leading indexestB is a constant;
in the seventh step, the formula for performing linearization on the consistent exponential weighting similarity is as follows: index of conformitytC x unity index weighted unity ratiot+ d, t is data period and is positive integer, a > 0, b > 0, coincidence indextMore than or equal to 0, c is consistent exponential weighted homonymtD is a constant.
Compared with the prior art, the invention has the following advantages: the novel power consumption demand business index has stronger self-adaptive capacity and low requirement on basic data, and does not need to judge and process abnormal values. Compared with the traditional power market prediction, the method can realize timely response and automatic adjustment to the sudden impact event and the temperature change, improve the reliability of power demand prediction and widen the application occasions of power demand prediction.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a block flow diagram of the method of the present invention;
FIG. 2 is a diagram of the power demand prosperity index (Jiangsu) of the present invention;
FIG. 3 is a fish bone map of the power demand landscape index (first industry) of the present invention;
FIG. 4 is a fishbone diagram of the power demand landscape index (second industry) of the present invention;
FIG. 5 is a fish bone map of the power demand landscape index (third industry) of the present invention;
FIG. 6 is a fishbone diagram of the power demand prosperity index (urban and rural residents) of the present invention;
FIG. 7 is a chart of the power demand landscape index (industrial) fishbone of the present invention;
fig. 8 is a view of the fish bone with electricity demand landscape index (Nanjing) of the present invention.
Detailed Description
As shown in fig. 1, the method for constructing an electricity demand business index based on big power data of the present invention includes the following steps:
collecting monthly electric quantity data and monthly average air temperature data;
in specific implementation, the monthly electric quantity data is the electricity consumption data of all the industries of various cities and provinces, and the monthly air temperature data is the average air temperature data of various cities in the future 3 months;
step two, screening monthly electric quantity data and eliminating noise data;
in this embodiment, the monthly electric quantity data is screened in the second step, and when the noise data is removed, the monthly electric quantity data in the industry containing invalid electric information is removed, and the influence of the spring festival effect on the monthly electric quantity data is eliminated;
in specific implementation, the method for eliminating the influence of the spring festival effect on the monthly electric quantity data is to sum the monthly electric quantity data of january and february of the gregorian year to obtain combined electric quantity data;
in this embodiment, the invalid electricity consumption information industry includes an industry in which monthly electricity consumption data is less than 10 ten thousand kilowatt hours and a data volume is less than 10% of a total data volume. For example, in the catering industry of the third industry, the total data volume of monthly electricity data is 100 sets, wherein the data volume of monthly electricity data lower than 10 ten thousand kilowatt hours is 95 sets, and only 5 sets of monthly electricity data higher than 10 ten thousand kilowatts hours determine that the catering industry of the city a is the invalid electricity consumption information industry.
Thirdly, converting the monthly electric quantity data without the noise data into standard synthesis acceleration;
in this embodiment, the third step is to convert the monthly electric quantity data from which the noise data are removed into a standard synthetic acceleration rate by using a calculation formula:
wherein t is the data periodAnd is a positive integer, monthly electricitytMonthly electric quantity data and monthly electric quantity data representing the t periodt-12Monthly electricity data (i.e., monthly electricity data of the same year in the last year) representing the t-12 th periodt-24Monthly electricity data (i.e., monthly electricity data in the same period of the previous year) representing the t-24 th period, monthly electricityt-36The monthly electric quantity data (namely the monthly electric quantity data in the same period of the previous three years) representing the t-36 th period, and alpha is the monthly electric quantityt-12Beta is monthly electric quantityt-24λ is monthly electricity quantityt-36α, β, λ ∈ (0,1), α + β + λ ═ 1.
The monthly electric quantity data are processed by adopting a three-calendar history mean value method, the monthly electric quantity data with noise data removed are converted into standard synthesis acceleration, and a more accurate result can be obtained.
Selecting effective standard synthesis acceleration data by adopting a principal component analysis method, using the effective standard synthesis acceleration data as a prediction model independent variable, inputting the prediction model independent variable into a pre-constructed prediction model, and outputting the prediction model as the optimal prediction electric quantity acceleration;
in this embodiment, the effective standard synthesis acceleration data selected by the principal component analysis method in step four is specifically the following process as the prediction model independent variable:
step 401, eliminating standard synthesis acceleration data of invalid industry: eliminating the industries of the top 20% of the highest standard deviation of the latest 120-stage data in the local power database, eliminating the industries of which the standard synthesis speed increase of the current stage exceeds the average value of the latest 120 stage plus or minus two standard deviations, and eliminating the industries of which the latest 3 stage accounts for less than 1% of the power consumption of the whole society and the independent variable of which the correlation coefficient of the latest 120 stage and the dependent variable is less than 0.8;
step 402, mapping n-dimensional standard synthesis acceleration data to k-dimension by a principal component analysis method to obtain a prediction model independent variable; wherein, the values of n and k are both non-0 natural numbers and n is larger than k.
In particular, the k-dimensional principal component matrix may reflect more than eighty percent of the amount of information in the n-dimensional data matrix.
In specific implementation, the prediction model adopts a BP neural network model, a CNN convolutional neural network model, a support vector machine model, a VAR model, a simulated walking model, an ARIMAX model, a mechanical learning model or a time sequence model.
Step five, dynamic air temperature correction: establishing a monthly average air temperature data and standard synthesis acceleration nonlinear model, and correcting the optimal predicted electric quantity acceleration according to the average air temperature data of the future 3 period;
in this embodiment, in the fifth step, a nonlinear model for synthesizing the monthly average air temperature data with the standard acceleration rate is established, where the expression of the nonlinear model is:
correcting acceleration ratet-prediction of accelerationt＝k1X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2+k2X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]+k3X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]2+k4X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]+b
Wherein (temperature)tHigh temperature thresholdt) Not less than 0 (temperature)t-12High temperature thresholdt) Not less than 0 (temperature)tLow temperature thresholdt) Not less than 0 (temperature)t-12Low temperature thresholdt) Not less than 0, t is data period and is positive integer, and temperaturetMonthly average air temperature data and temperature representing the t periodt-12Monthly average air temperature data (i.e. monthly average air temperature data of the same year in the last year) representing the t-12 th period, and high temperature thresholdtHigh temperature threshold and low temperature threshold representing t periodtLow temperature threshold, k, for the t-th period1Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2Coefficient of (a), k2Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]Coefficient of (a), k3Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdValue oft)]2Coefficient of (a), k4Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]B is a constant.
In practice, high temperature thresholdtAnd low temperature thresholdtAnd (4) performing rolling adjustment in each period according to the temperature deviation sequence, wherein k1, k2, k3, k4 and b are obtained by performing regression fitting according to the temperature deviation sequence and the corrected speed-increasing deviation sequence, and the rolling adjustment in each period is performed.
Step six, checking a predicted electric quantity acceleration result: when the prediction result is in the range of the addition of two standard deviations to the average value of the real same-ratio acceleration in the latest N period, selecting the electric quantity acceleration of the prediction model; otherwise, deleting the prediction model and selecting the prediction model again; when all the prediction models are deleted, selecting the most stable simulation walking model as the prediction model; wherein the value range of N is N not less than 12; in the metrology economics, the simulated walk model is considered to be the most stable;
step seven, compiling a synthesis index: synthesizing index compilation is carried out by adopting a power demand landscape index compilation mode of 'prejudging quarters and correcting monthly', the total quantity of the electric quantity of the forecasted quarters is calculated according to the acceleration of the same ratio of the forecasted electric quantity, then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is compiled, and then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is linearized to synthesize the power demand landscape index;
in specific implementation, the 'prejudgment of quarter and monthly correction' means that only the electricity consumption of the quarter is predicted every quarter in the gregorian calendar year, and the predicted quarter electricity is corrected once every month;
in this embodiment, the formula for calculating the total predicted quarterly electric quantity according to the geometric acceleration of the predicted electric quantity in step seven is as follows:
wherein monthly electricity is predictedtPredicted monthly electric power representing the t-th period, predicted monthly electric powert+1Predicted monthly electricity representing the t +1 th phaseMeasuring, predicting monthly electricityt+2Represents the predicted monthly electricity quantity of the t +2 th period, and t is a data period and is a positive integer.
In this embodiment, the calculation formula of the leading index weighted proportion in the seventh step is:
the calculation formula of the consistent index weighted proportion in the step seven is as follows:
the time dimension of the index calculation is quarterly, once per quarterly, four quarters of a year, t denotes the current quarterly, t-1 denotes the last quarterly, t-2 denotes the last quarterly, t-4 denotes the same period of the last year, t-1-4 is the same period of the last quarterly last year, and t-2-4 is the same period of the last quarterly last year.
In this embodiment, the formula for performing linearization on the weighted average of the leading indices in step seven is as follows: leading indextA x look-ahead index weighted unity ratiot+ b, t is data period and is positive integer, a > 0, b > 0, antecedent indextA is equal to or more than 0, a is a weighted equal ratio of leading indexestB is a constant;
in the seventh step, the formula for performing linearization on the consistent exponential weighting similarity is as follows: index of conformitytC x unity index weighted unity ratiot+ d, t is data period and is positive integer, a > 0, b > 0, coincidence indextMore than or equal to 0, c is consistent exponential weighted homonymtD is a constant.
And step eight, outputting the power consumption demand scene index.
In this embodiment, after the step eight, the method further includes:
and ninthly, outputting monthly predicted electric quantity, and drawing a fishbone graph according to the power demand prosperity index and the output result of the monthly predicted electric quantity.
In specific implementation, the power consumption demand prosperity index is the power consumption demand prosperity index of all the industries of cities and provinces, and the monthly predicted power is the power predicted by all the industries of the cities and provinces in 3 months in the future.
The fishbone graph comprises a novel power demand consistency index, a novel power demand uncorrected leading index, a novel power demand primary corrected leading index, a novel power demand secondary corrected leading index and novel power demand landscape index interval information.
In order to verify the technical effect which can be generated by the method, the method provided by the invention is adopted to analyze the prospect index of the power demand of Jiangsu province and province.
In the first step, the data of the power utilization month of the whole industry of Jiangsu province and the thirteen districts and the prediction data of the average air temperature of the thirteen districts of Jiangsu province for 3 months in the future are input, as shown in tables 1 and 2:
TABLE 1 monthly data of electricity consumption of all industries of Jiangsu province and thirteen districts
TABLE 2 mean air temperature prediction data for the future 3 months in thirteen places of Jiangsu province
| City of land | Predicted value of average temperature in this month | Predicted value of average temperature of next month | Predicted value of average temperature in next two months |
| Nanjing | 29.5 | 27.5 | 20 |
| Xuzhou | 28.5 | 26 | 18.5 |
| Changzhou (Changzhou) | 30 | 28 | 20 |
| Tin-free | 29 | 27.5 | 20 |
| (Suzhou) | 30 | 28.5 | 20.5 |
| Nantong | 29 | 28 | 20 |
| Linyuankang | 28 | 25.5 | 18.5 |
| Huai' an medicine | 28.5 | 26 | 19 |
| Salt city | 29 | 27 | 20 |
| Yangzhou mountain | 30 | 28 | 20 |
| (Zhenjiang) | 29 | 27.5 | 20 |
| Taizhou province | 28.5 | 27.5 | 20.5 |
| Host migration | 29.5 | 26.5 | 19 |
The local power database comprises power consumption data of the whole industry in Jiangsu province from 2005 to 2017, wherein the power consumption data of the industry needs to be screened to extract effective data.
Screening monthly electric quantity data and eliminating noise data;
preferably, if the number of the industry electricity consumption data containing the null value and less than 10 is more than or equal to 15, the industry is rejected. And (4) aiming at the screened industries, if the data in 2018 and later have null values, carrying out equidistant processing on the data. In order to avoid the influence of spring festival on data quality, the data of 1 month and 2 months per year are merged. The industry of the primary screening of the obtained basic electric power data is shown in table 3:
TABLE 3 industry for Primary screening of basic Power data
In the third step, the monthly electric quantity data after the noise data are removed is converted into standard synthesis acceleration;
in order to reduce the influence of external sudden impact on power consumption prediction, a three-year exponential weighted average method is adopted to convert the power consumption prediction into a standard synthetic acceleration rate when the power consumption acceleration is predicted.
Selecting effective standard synthesis acceleration data by adopting a principal component analysis method, using the effective standard synthesis acceleration data as a prediction model independent variable, inputting the prediction model independent variable into a pre-constructed prediction model, and outputting the prediction model as the optimal prediction electric quantity acceleration; the industries for selecting and selecting the independent variable of the speed increase are shown in table 4:
TABLE 4 trade selection of acceleration independent variables
| Serial number | Name of trade | Serial number | Name of trade |
| 1 | Total electricity consumption of whole society | 17 | 11. Chemical fiber manufacturing |
| 2 | A. Total electricity consumption of whole industry | 18 | 12. Rubber and plastic products |
| 3 | First industry | 19 | 13. Non-metallic mineral product industry |
| 4 | |
20 | Wherein the cement is produced |
| 5 | B. Urban and rural resident living electricity consumption total | 21 | 14. Ferrous metal smelting and calendering |
| 6 | Urban residents | 22 | 15. Non-ferrous metal smelting and rolling processing industry |
| 7 | Village residents | 23 | 16. Metal product industry |
| 8 | Industry wide power classification | 24 | 17. General and special equipment manufacturing industry |
| 9 | Agriculture, forestry, animal husbandry and fishery | 25 | 18. Manufacturing industry of transportation, electric and electronic equipment |
| 10 | Second, industry | 26 | Wherein: manufacturing industry of transportation equipment |
| 11 | (II) manufacturing industry | 27 | 19. Handicraft and other manufacturing industries |
| 12 | 1. Food, beverage and tobacco manufacturing industries | 28 | Transportation, storage and postal service |
| 13 | 2. Textile industry | 29 | 1. Transportation industry |
| 14 | 3. Clothing, shoes and caps, leather and down and products thereof | 30 | 2. Land industry |
| 15 | 5. Paper and paper products industry | 31 | Eighth, utility and managementTissue of |
| 16 | 9. Chemical raw material and chemical product manufacturing industry | 32 | 3. Education, culture, sports and entertainment industry |
And step five, dynamic air temperature correction: establishing a monthly average air temperature data and standard synthesis acceleration nonlinear model, and correcting the optimal predicted electric quantity acceleration according to the average air temperature data of the future 3 period;
preferably, the low temperature threshold range is 8-15 degrees centigrade, and the high temperature threshold range is 16-31 degrees centigrade.
The high (low) temperature threshold is scanned. And generating a high (low) temperature threshold value two-dimensional array according to the high (low) temperature threshold value range, and sequentially scanning and calculating.
TABLE 5 high (low) temperature threshold array Table
And respectively calculating a temperature deviation sequence and a speed-increasing deviation sequence according to the high (low) temperature threshold, wherein data larger than the high temperature threshold enters the high temperature sequence, and data smaller than the low temperature threshold enters the low temperature sequence.
According to the two sequences, k in a nonlinear model for regressing the monthly average air temperature and power consumption acceleration1、k2、k3、k4And b are regressed by the least square method in this example.
In order to ensure that the prediction result does not have abnormal big or small, the prediction result is checked.
And sixthly, checking the predicted electric quantity acceleration result: when the prediction result is in the range of the addition of two standard deviations to the average value of the real same-ratio acceleration in the latest N period, selecting the electric quantity acceleration of the prediction model; otherwise, deleting the prediction model and selecting the prediction model again; when all the prediction models are deleted, selecting the most stable simulation walking model as the prediction model; wherein the value range of N is N not less than 12;
when the predicted speed increase is not more than the average value of the last 12 periods plus or minus two standard deviations, the speed increase is output. If not, the prediction model is removed from the 'prediction model', and the model is reselected.
Step seven, compiling a synthesis index: synthesizing index compilation is carried out by adopting a power demand landscape index compilation mode of 'prejudging quarters and correcting monthly', the total quantity of the electric quantity of the forecasted quarters is calculated according to the acceleration of the same ratio of the forecasted electric quantity, then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is compiled, and then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is linearized to synthesize the power demand landscape index;
and step eight, outputting the power consumption demand scene index.
And finally, outputting the power consumption demand prosperity indexes of Jiangsu province, thirteen districts, 8 departments and the predicted electric quantity in the future 3 months.
Table 6 output table of new power consumption requirement business index of Jiangsu
TABLE 7 predicted electric quantity output table for 3 months in the future of Jiangsu
Step eight is followed still include:
and ninthly, outputting monthly predicted electric quantity, and drawing a fishbone graph according to the power demand prosperity index and the output result of the monthly predicted electric quantity.
The drawn electricity demand landscape index (jiangsu) fishbone map is shown in fig. 2, the electricity demand landscape index (first industry) fishbone map is shown in fig. 3, the electricity demand landscape index (second industry) fishbone map is shown in fig. 4, the electricity demand landscape index (third industry) fishbone map is shown in fig. 5, the electricity demand landscape index (urban and rural residents) fishbone map is shown in fig. 6, the electricity demand landscape index (industry) fishbone map is shown in fig. 7, and the electricity demand landscape index (Nanjing) fishbone map is shown in fig. 8.
The power demand business index has stronger self-adaptive capacity, has the capacity of timely responding to sudden impact events and temperature changes and automatically adjusting, can reflect the power demand change situation and development situation in time, and provides scientific statistical analysis support for company operation management and government macro decision.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (10)
1. A power consumption prospect index construction method based on electric power big data is characterized by comprising the following steps:
collecting monthly electric quantity data and monthly average air temperature data;
step two, screening monthly electric quantity data and eliminating noise data;
thirdly, converting the monthly electric quantity data without the noise data into standard synthesis acceleration;
selecting effective standard synthesis acceleration data by adopting a principal component analysis method, using the effective standard synthesis acceleration data as a prediction model independent variable, inputting the prediction model independent variable into a pre-constructed prediction model, and outputting the prediction model as the optimal prediction electric quantity acceleration;
step five, dynamic air temperature correction: establishing a monthly average air temperature data and standard synthesis acceleration nonlinear model, and correcting the optimal predicted electric quantity acceleration according to the average air temperature data of the future 3 period;
step six, checking a predicted electric quantity acceleration result: when the prediction result is in the range of the addition of two standard deviations to the average value of the real same-ratio acceleration in the latest N period, selecting the electric quantity acceleration of the prediction model; otherwise, deleting the prediction model and selecting the prediction model again; when all the prediction models are deleted, selecting the most stable simulation walking model as the prediction model; wherein the value range of N is N not less than 12;
step seven, compiling a synthesis index: synthesizing index compilation is carried out by adopting a power demand landscape index compilation mode of 'prejudging quarters and correcting monthly', the total quantity of the electric quantity of the forecasted quarters is calculated according to the acceleration of the same ratio of the forecasted electric quantity, then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is compiled, and then the weighted same ratio of the leading indexes or the weighted same ratio of the consistent indexes is linearized to synthesize the power demand landscape index;
and step eight, outputting the power consumption demand scene index.
2. The power consumption demand landscape index construction method based on the electric power big data as claimed in claim 1, characterized in that: step eight is followed still include:
and ninthly, outputting monthly predicted electric quantity, and drawing a fishbone graph according to the power demand prosperity index and the output result of the monthly predicted electric quantity.
3. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: and step two, filtering the monthly electric quantity data, and eliminating the monthly electric quantity data containing invalid electricity utilization information industries when eliminating the noise data, and eliminating the influence of spring festival effect on the monthly electric quantity data.
4. The power consumption demand landscape index construction method based on the electric power big data as claimed in claim 3, characterized in that: the invalid electricity consumption information industry includes an industry in which monthly electricity data is less than 10 ten thousand kilowatt hours and data volume is less than 10% of total data volume.
5. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: in the third step, the calculation formula for converting the monthly electric quantity data from which the noise data are removed into the standard synthesis acceleration rate is as follows:
wherein t is data period, positive integer, monthly electric quantitytMonthly electric quantity data and monthly electric quantity data representing the t periodt-12Monthly electric quantity data and monthly electric quantity data representing t-12 th periodt-24Monthly electric quantity data and monthly electric quantity data representing t-24 th periodt-36Monthly electric quantity data representing t-36 th period, alpha is monthly electric quantityt-12Beta is monthly electric quantityt-24λ is monthly electricity quantityt-36α, β, λ ∈ (0,1), α + β + λ ═ 1.
6. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: in the fourth step, effective standard synthesis acceleration data are selected by adopting a principal component analysis method, and the specific process of taking the effective standard synthesis acceleration data as the independent variable of the prediction model is as follows:
step 401, eliminating standard synthesis acceleration data of invalid industry: eliminating the industries of the top 20% of the highest standard deviation of the latest 120-stage data in the local power database, eliminating the industries of which the standard synthesis speed increase of the current stage exceeds the average value of the latest 120 stage plus or minus two standard deviations, and eliminating the industries of which the latest 3 stage accounts for less than 1% of the power consumption of the whole society and the independent variable of which the correlation coefficient of the latest 120 stage and the dependent variable is less than 0.8;
step 402, mapping n-dimensional standard synthesis acceleration data to k-dimension by a principal component analysis method to obtain a prediction model independent variable; wherein, the values of n and k are both non-0 natural numbers and n is larger than k.
7. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: and step five, establishing a nonlinear model for synthesizing monthly average air temperature data and the standard and increasing speed, wherein the expression of the nonlinear model is as follows:
correcting acceleration ratet-prediction of accelerationt＝k1X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2+k2X [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]+k3X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]2+k4X [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]+b
Wherein (temperature)tHigh temperature thresholdt) Not less than 0 (temperature)t-12High temperature thresholdt) Not less than 0 (temperature)tLow temperature thresholdt) Not less than 0 (temperature)t-12Low temperature thresholdt) Not less than 0, t is data period and is positive integer, and temperaturetMonthly average air temperature data and temperature representing the t periodt-12Monthly average air temperature data representing the t-12 th period, and high temperature thresholdtHigh temperature threshold and low temperature threshold representing t periodtLow temperature threshold, k, for the t-th period1Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]2Coefficient of (a), k2Is [ (temperature)tHigh temperature thresholdt) - (temperature)t-12High temperature thresholdt)]Coefficient of (a), k3Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]2Coefficient of (a), k4Is [ (temperature)tLow temperature thresholdt) - (temperature)t-12Low temperature thresholdt)]B is a constant.
8. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: and step seven, the formula for calculating the total quantity of the predicted quarterly electric quantity according to the same-ratio acceleration of the predicted electric quantity is as follows:
wherein monthly electricity is predictedtPredicted monthly electric power representing the t-th period, predicted monthly electric powert+1Predicted monthly electric power representing the t +1 th period, predicted monthly electric powert+2Represents the predicted monthly electricity quantity of the t +2 th period, and t is a data period and is a positive integer.
9. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: in the seventh step, the calculation formula of the leading index weighted proportion is as follows:
the calculation formula of the consistent index weighted proportion in the step seven is as follows:
the time dimension of the index calculation is quarterly, once per quarterly, four quarters of a year, t denotes the current quarterly, t-1 denotes the last quarterly, t-2 denotes the last quarterly, t-4 denotes the same period of the last year, t-1-4 is the same period of the last quarterly last year, and t-2-4 is the same period of the last quarterly last year.
10. The power consumption prospect index construction method based on the electric power big data as claimed in claim 1 or 2, characterized in that: in the seventh step, the formula for performing linearization on the weighted similarity of the leading indexes is as follows: leading indextA x look-ahead index weighted unity ratiot+ b, t is data period and is positive integer, a > 0, b > 0, antecedent indextA is equal to or more than 0, a is a weighted equal ratio of leading indexestB is a constant;
in the seventh step, the formula for performing linearization on the consistent exponential weighting similarity is as follows: index of conformitytC x unity index weighted unity ratiot+ d, t is data period and is positive integer, a > 0, b > 0, coincidence indextMore than or equal to 0, c is consistent exponential weighted homonymtD is a constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111439911.0A CN114049160A (en) | 2021-11-30 | 2021-11-30 | Power consumption demand business index construction method based on electric power big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111439911.0A CN114049160A (en) | 2021-11-30 | 2021-11-30 | Power consumption demand business index construction method based on electric power big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114049160A true CN114049160A (en) | 2022-02-15 |
Family
ID=80211885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111439911.0A Pending CN114049160A (en) | 2021-11-30 | 2021-11-30 | Power consumption demand business index construction method based on electric power big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114049160A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112163A (en) * | 2014-04-24 | 2014-10-22 | 国家电网公司 | Construction method of electric power forecasting business index |
| CN109345021A (en) * | 2018-10-15 | 2019-02-15 | 易联众信息技术股份有限公司 | A method of using LSTM modeling and forecasting labour demand increment |
| CN110415140A (en) * | 2019-07-31 | 2019-11-05 | 国网河南省电力公司经济技术研究院 | A kind of annual power consumption prediction method based on industrial production person's producer price index |
-
2021
- 2021-11-30 CN CN202111439911.0A patent/CN114049160A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112163A (en) * | 2014-04-24 | 2014-10-22 | 国家电网公司 | Construction method of electric power forecasting business index |
| CN109345021A (en) * | 2018-10-15 | 2019-02-15 | 易联众信息技术股份有限公司 | A method of using LSTM modeling and forecasting labour demand increment |
| CN110415140A (en) * | 2019-07-31 | 2019-11-05 | 国网河南省电力公司经济技术研究院 | A kind of annual power consumption prediction method based on industrial production person's producer price index |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| Sun et al. | Coupling efficiency measurement and spatial correlation characteristic of water–energy–food nexus in China | |
| Le Bagousse-Pinguet et al. | Phylogenetic, functional, and taxonomic richness have both positive and negative effects on ecosystem multifunctionality | |
| Qu et al. | Understanding rural land use transition and regional consolidation implications in China | |
| Wu et al. | Optimal site selection for parabolic trough concentrating solar power plant using extended PROMETHEE method: A case in China | |
| Huang et al. | China’s income gap and inequality under clean energy transformation: A CGE model assessment | |
| Hou et al. | Coordinated relationship between urbanization and grain production in China: Degree measurement, spatial differentiation and its factors detection | |
| Shi et al. | Urbanization in China from the end of 1980s until 2010–spatial dynamics and patterns of growth using EO-data | |
| CN105512768A (en) | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data | |
| Liu et al. | Trade-offs analysis of land use functions in a hilly-mountainous city of northwest Hubei Province: The interactive effects of urbanization and ecological construction | |
| CN109214449A (en) | A kind of electric grid investment needing forecasting method | |
| CN110751416A (en) | Method, device and equipment for predicting water consumption | |
| Chen et al. | Spatiotemporal differentiation of urban-rural income disparity and its driving force in the Yangtze River Economic Belt during 2000-2017 | |
| Xu et al. | Building energy consumption optimization method based on convolutional neural network and BIM | |
| Yang et al. | Industrial water-use efficiency in China: Regional heterogeneity and incentives identification | |
| Tian et al. | A new quality management system of admittance indicators to improve industrial land use efficiency in the Beijing− Tianjin− Hebei region | |
| CN115099461A (en) | Solar radiation prediction method and system based on double-branch feature extraction | |
| Xu et al. | A classification approach for urban metabolism using the CART model and its application in China | |
| Bivand et al. | Exploring spatial data analysis techniques using R: The case of observations with no neighbors | |
| Gao et al. | Geospatial characteristics and the application of land use functions in the Yangtze River Economic Belt, China: Perspectives on provinces and urban agglomerations | |
| Guan et al. | Effect of Urban fringes green space fragmentation on ecosystem service value | |
| Li et al. | Evaluation of carbon emission efficiency and reduction potential of 336 cities in China | |
| Liu et al. | Temporal and spatial variations of ecological security on the northeastern Tibetan Plateau integrating ecosystem health-risk-services framework | |
| Wang et al. | Multi-scale analysis on sustainability and driving factors based on three-dimensional ecological footprint: A case study of the Yangtze River Delta region, China | |
| CN114049160A (en) | Power consumption demand business index construction method based on electric power big data |
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 |