CN111047108A - Optimal combination model-based electric energy ratio prediction method in terminal energy consumption - Google Patents

Optimal combination model-based electric energy ratio prediction method in terminal energy consumption Download PDF

Info

Publication number
CN111047108A
CN111047108A CN201911344861.0A CN201911344861A CN111047108A CN 111047108 A CN111047108 A CN 111047108A CN 201911344861 A CN201911344861 A CN 201911344861A CN 111047108 A CN111047108 A CN 111047108A
Authority
CN
China
Prior art keywords
energy consumption
model
electric energy
prediction
total
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201911344861.0A
Other languages
Chinese (zh)
Other versions
CN111047108B (en
Inventor
周建华
姜维伊
朱倩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201911344861.0A priority Critical patent/CN111047108B/en
Publication of CN111047108A publication Critical patent/CN111047108A/en
Application granted granted Critical
Publication of CN111047108B publication Critical patent/CN111047108B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • 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)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses an optimal combination model-based method for predicting electric energy ratio in terminal energy consumption, which comprises the steps of obtaining an energy-electric energy consumption predicted value by taking a trend extrapolation model as a single prediction model; the energy-electric energy consumption predicted value is obtained by taking the gray prediction model as a single prediction model; solving the prediction errors of the trend extrapolation model and the gray prediction model; determining the weight of each single model in the combined model according to the reciprocal of the sum of squares of the model prediction errors, thereby determining the combined prediction model; determining the optimal prediction point number according to the principle of minimum model error; on the basis of the electric energy consumption and the energy consumption, the electric energy and the energy consumption in the future year are respectively predicted by utilizing a combined prediction model, and the predicted value of the electric energy ratio PETEC in the terminal energy consumption is indirectly obtained through proportional operation. The method has a good prediction effect on the data sequence which presents a stable evolution rule as a whole along with the change of time, and can effectively predict the energy consumption trend.

Description

Optimal combination model-based electric energy ratio prediction method in terminal energy consumption
Technical Field
The invention belongs to the field of electric new energy research, and particularly relates to an optimal combination model-based electric energy ratio prediction method in terminal energy consumption.
Background
In recent years, urban energy revolution promotes improvement of regional energy consumption structure and development of electric energy substitution process, and the improvement further promotes remarkable increase of electricity consumption in future regions and continuous increase of electric energy ratio in terminal energy consumption; meanwhile, as the policies and measures of energy change are staged, the electric energy ratio acceleration rate in the terminal energy consumption of the region presents a randomly fluctuating time change trend to a certain extent, higher requirements are put forward for the power demand prediction work of the power grid company, PETEC presents an increasing trend on the whole in the city energy change process, but as the energy change comprises different development stages, the energy policies, propulsion measures and transformation progress of each stage are different, so that the growth rate of PETEC in different years is greatly changed, the difficulty of accurately predicting the PETEC is increased, in the electrified energy consumption level prediction work, the direct or indirect prediction of PETEC prediction is carried out by utilizing a single prediction model by the energy statistics department of China and the traditional prediction mode of the power grid company, the prediction process is simplified to a certain extent, but the electrified level growth rule is difficult to be comprehensively grasped by only using one prediction model, the accuracy of energy and power consumption prediction is limited.
The modern prediction method mainly comprises a grey prediction method, a bionics algorithm, a wavelet analysis method, a combined prediction method, a fuzzy mathematical method, a support vector machine, a chaos prediction method and the like, the grey GM (1, 1) prediction model of energy consumption is established according to total energy consumption data and coal, petroleum, natural gas and electric power consumption data in an energy consumption structure, a radial basis kernel function parameter is optimized through particle swarm optimization, a resident life energy consumption prediction model based on the support vector machine technology is established, and the models have the following defects:
1. the prediction model is single. The single prediction model simplifies the prediction process, is difficult to comprehensively master the increase rule of the electrification level, limits the accuracy of energy and power consumption prediction, and solves the problem well due to the occurrence of the combined prediction method.
2. In order to consider the electric energy proportion in the terminal energy consumption to PETEC. The ratio of electric energy in terminal energy consumption is an important index for measuring the structure of terminal energy consumption and an important mark for measuring the energy change and development level of a country or a region, and the index is indispensable for researching the energy and electric power consumption change trend under the urban energy change background.
In summary, it is necessary to consider the electric energy ratio index in the terminal energy consumption, and perform a suitable combination of prediction models to predict the electric energy ratio in the terminal energy consumption, so as to provide a construction basis for the development of the energy and power consumption conditions.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problems and provide a construction basis for the development of energy and power consumption conditions, the invention provides an optimal combination model-based electric energy ratio prediction method in terminal energy consumption.
The technical scheme is as follows: in order to realize the purpose, the invention adopts the following technical scheme:
a method for predicting the electric energy ratio in terminal energy consumption based on an optimal combination model comprises the following steps:
s1, acquiring the total energy consumption data and the total energy consumption data of the years before the year to be predicted, establishing a trend extrapolation prediction model, and calculating an energy-electric energy consumption prediction value by taking the trend extrapolation model as a single prediction model;
step S2, calculating an energy-electric energy consumption predicted value by taking the gray prediction model as a single prediction model;
step S3, respectively solving the prediction errors of the trend extrapolation model and the gray prediction model;
step S4, determining the weight of each single model in the combined model according to the reciprocal of the sum of squares of the model prediction errors, thereby determining the combined prediction model;
step S5, determining the optimal prediction point number according to the principle of minimum model error;
and step S6, on the basis of the electric energy consumption and the energy consumption, respectively predicting the electric energy and the energy consumption in the future year by using the combined prediction model, and indirectly obtaining the predicted value of the electric energy ratio PETEC in the terminal energy consumption through proportional operation.
Further, the trend extrapolation model in step S1 is:
pn+1＝a1(n+1)2+a2(n+1)+a3(1)；
qn+1＝b1(n+1)2+b2(n+1)+b3(2)；
wherein, a1、a2、a3Values of the first three items of a coefficient matrix a to be solved for the total amount of electric energy consumption, in the form of a trend extrapolated prediction model matrix, pn+1Total amount of electric energy consumed in the n +1 th year, b1、b2、b3Values of the first three terms of a coefficient matrix b to be solved for the total amount of energy consumption, in the form of a trend extrapolated prediction model matrix, qn+1The total electric energy consumption of the (n + 1) th year;
the solving mode of a and b is as follows:
a＝(xTx)-1xtP (3)；
b＝(xTx)-1xTQ (4)；
wherein the content of the first and second substances,
Figure BDA0002333059150000031
obtaining a predicted value pre of the electric energy ratio in the terminal energy consumption in the (n + 1) th year based on the trend extrapolation model according to the relation between the total electric energy consumption and the total energy consumption and the electric energy ratio in the terminal energy consumption1The formula is as follows:
Figure BDA0002333059150000032
wherein R isLAnd ReLIs energy, electric energy loss rate, RequAnd converting the coefficient into the standard coal of the electric energy.
Further, in step S2, the energy-electric energy consumption prediction value obtained by using the gray prediction model as the single prediction model is respectively accumulated with the total electric energy consumption data P and the total energy consumption data Q of the past year n years before the year to be predicted to generate new data sequences P _ sum and Q _ sum, and then a first-order differential equation of the gray prediction model is constructed for the new data sequences P _ sum and Q _ sum:
Figure BDA0002333059150000033
Figure BDA0002333059150000034
wherein, c1、c2Respectively, the solving coefficient of the total amount of electric energy consumption, d1、d2Respectively solving coefficients of the total electric energy consumption;
the solution of this first order differential equation is in exponential form, i.e.:
Figure BDA0002333059150000035
Figure BDA0002333059150000036
wherein p _ sumn+1Q _ sum being the sum of the first n +1 variables of the total amount of power consumptionn+1For the sum of n +1 variables before the total energy consumption, n of the formulas (8) and (9) is changed into n-1 to respectively obtain the sum of n variables before the total energy consumptionnAnd the sum of the first n variables of the total energy consumption q _ sumnA prediction value p 'of the total amount of electric energy consumption of n +1 year based on the gray prediction model'n+1And predicted value q 'of total energy consumption'n+1The calculation formula is shown in formulas (10) to (11):
p′n+1＝p_sumn+1-p_sumn(10)；
q′n+1＝q_sumn+1-q_sumn(11)。
further, the prediction errors of the trend extrapolation model and the gray prediction model found in step S3 are:
Figure BDA0002333059150000041
wherein, △11％、△12% is the predicted value error of the total amount of electric energy consumed in the n +1 year based on the trend extrapolation model and based on the gray prediction model, △21％、△22% is the predicted value error of the total energy consumption of the n +1 year based on the trend extrapolation model and the gray prediction model respectively, act1、act2The total electric energy consumption and the total energy consumption of the corresponding year are respectively.
Further, in step S4, the weight of each single model in the combined model is determined according to the inverse of the sum of squares of the model prediction errors, and the combined prediction model is determined as follows:
Figure BDA0002333059150000042
therein, pre1Prediction of total power consumption, pre, determined for a combined model1A predicted value, omega, of the total amount of energy consumption determined for the combined model1、ω2Representing the weight, omega, of the predicted value of the total amount of energy consumption in a combined model based on a trend extrapolation model and a grey prediction model, respectively3、ω4Respectively representing the weight of the total electric energy consumption predicted value in a combined model based on a trend extrapolation model and a grey prediction model.
Further, in step S5, the optimal prediction points J of the total amount of power consumption and the total amount of energy consumption are determined respectively according to the principle of minimum error of the combined model1、J2(ii) a The formula is as follows:
Figure BDA0002333059150000051
therein, pre1(i) For the predicted value of the ith year of the total consumption of electric energy, pre2(i) For the predicted value of the ith year of the total energy consumption, under each to-be-selected prediction point k, performing error sum of squares accumulation on all historical data capable of performing prediction error detection, and finally when the average value of each group of error sum of squares is minimum, the corresponding prediction point is the optimal prediction point,n is the number of years covered by the historical data.
Further, step S6 is to consume the electric energy EeTAnd energy consumption ETBased on the prediction model, the combined prediction model is used for respectively predicting the electric energy consumption pre of the future year1And energy consumption pre2Indirectly obtaining the predicted value of the electric energy ratio PETEC in the terminal energy consumption through proportional operation
Figure BDA0002333059150000052
Figure BDA0002333059150000053
Wherein R isequConversion factor, R, for standard coal of electric energyeLFor rate of loss of electric energy, RLFor energy loss rate, PETEC is the ratio of electric energy in the original terminal energy consumption, △E% and △e% is relative prediction error of electric energy consumption and energy consumption.
Has the advantages that: compared with the prior art, the method provided by the invention provides a PETEC combined prediction model aiming at the change characteristics of PETEC under the background of urban energy revolution, and the advantages of a trend extrapolation prediction model and a gray prediction model are compatible. The prediction error of the combined prediction model is reduced by selecting the number of prediction points and the weight of different single models in the combination; the total electric energy consumption and the total energy consumption are predicted and calculated through the combined prediction model, the electric energy ratio in the terminal energy consumption is indirectly predicted through the mathematical relation between the total electric energy consumption and the total energy consumption and the electric energy ratio in the terminal energy consumption, and the prediction error of the predicted values of the total electric energy consumption and the total energy consumption is considered in the indirect prediction process, so that the prediction model has practical significance.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The technical solution of the present invention will be further explained with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a method for predicting the electric energy ratio in terminal energy consumption based on an optimal combination model includes the following steps:
step S1, acquiring the total power consumption data of the years before the year to be predicted
Figure BDA0002333059150000061
And total energy consumption data
Figure BDA0002333059150000062
Establishing a trend extrapolation prediction model, wherein the matrix form of a formula is as follows:
pn+1＝a1(n+1)2+a2(n+1)+a3(1)；
qn+1＝b1(n+1)2+b2(n+1)+b3(2)；
wherein, a1、a2、a3Values of the first three items of a coefficient matrix a to be solved for the total amount of electric energy consumption, in the form of a trend extrapolated prediction model matrix, pn+1Total amount of electric energy consumed in the n +1 th year, b1、b2、b3Values of the first three terms of a coefficient matrix b to be solved for the total amount of energy consumption, in the form of a trend extrapolated prediction model matrix, qn+1The total amount of electric energy consumption in the (n + 1) th year.
The solving mode of a and b is as follows:
a＝(xTx)-1xtP (3)；
b＝(xTx)-1xTQ (4)；
wherein the content of the first and second substances,
Figure BDA0002333059150000063
a calculated by the equations (3) and (4)1、a2、a3、b1、b2、b3After the value of (a), the sum of the total power consumption in the (n + 1) th year based on the trend extrapolation model is obtained by substituting the values of (a) and (b) into the formula (1) and (2), respectivelyTotal energy consumption.
Step S2, accumulating the total electric energy consumption data P and the total energy consumption data Q of the previous year n years of the year to be predicted respectively to generate new data sequences P _ sum and Q _ sum, and then constructing a gray prediction model first-order differential equation for the new data sequences P _ sum and Q _ sum respectively:
Figure BDA0002333059150000071
Figure BDA0002333059150000072
wherein, c1、c2Respectively, the solving coefficient of the total amount of electric energy consumption, d1、d2Respectively, the solving coefficients of the total electric energy consumption.
The solution of this first order differential equation is in exponential form, i.e.:
Figure BDA0002333059150000073
Figure BDA0002333059150000074
wherein p _ sumn+1Q _ sum being the sum of the first n +1 variables of the total amount of power consumptionn+1For the sum of n +1 variables before the total energy consumption, n of the formulas (7) and (8) is changed into n-1 to respectively obtain the sum of n variables before the total energy consumptionnAnd the sum of the first n variables of the total energy consumption q _ sumnA prediction value p 'of the total amount of electric energy consumption of n +1 year based on the gray prediction model'n+1And predicted value q 'of total energy consumption'n+1The calculation formula is shown in formulas (9) to (10):
p′n+1＝p_sumn+1-p_sumn(9)；
q′n+1＝q_sumn+1-q_sumn(10)；
step S3, respectively solving the prediction errors of the trend extrapolation model and the gray prediction model, wherein the formula is as follows:
Figure BDA0002333059150000081
wherein, △11％、△12% is the predicted value error of the total amount of electric energy consumed in the n +1 year based on the trend extrapolation model and based on the gray prediction model, △21％、△22% is the predicted value error of the total energy consumption of the n +1 year based on the trend extrapolation model and the gray prediction model respectively, act1、act2Respectively the total electric energy consumption and the total energy consumption of the corresponding year;
step S4, determining the weight of each single model in the combined model according to the reciprocal of the sum of squares of the model prediction errors, and determining the combined model, wherein the formula is as follows:
Figure BDA0002333059150000082
therein, pre1For combined model based prediction of total power consumption, pre1For the combined model-based prediction of total energy consumption, ω1、ω2Representing the weight, omega, of the predicted value of the total amount of energy consumption in a combined model based on a trend extrapolation model and a grey prediction model, respectively3、ω4Respectively representing the weight of the total electric energy consumption predicted value in a combined model based on a trend extrapolation model and a gray prediction model, and the calculation method is as follows:
Figure BDA0002333059150000083
wherein D is1、D2The sum of squares of total errors of the total electric energy consumption based on a trend extrapolation model and a grey prediction model respectively has the following calculation formula:
Figure BDA0002333059150000091
wherein act1(i) Is the actual value of the total amount of power consumption in the ith year2(i) Is an actual value of the total energy consumption in the ith year, pi、qiRespectively predicting the energy-electric energy consumption values of the ith year of the trend extrapolation model and the gray prediction model, wherein p is the year of prediction accuracy test;
step S5, determining the optimal prediction points J of the total electric energy consumption and the total energy consumption respectively according to the principle of minimum combined model error1、J2. The formula is as follows:
Figure BDA0002333059150000092
therein, pre1(i) Prediction of the i-th year, pre, based on a combined model for the total amount of electric energy consumption2(i) For the total energy consumption prediction value based on the ith year of the combined model, carrying out error square sum accumulation on all historical data capable of carrying out prediction error detection under each to-be-selected prediction point k, and finally when the average value of each group of error square sums is minimum, the corresponding prediction point is the optimal prediction point, and N is the number of all years covered by the historical data;
step S6, consumption E of electric energyeTAnd energy consumption ETBased on the prediction model, the combined prediction model is used for respectively predicting the electric energy consumption pre of the future year1And energy consumption pre2Indirectly obtaining the predicted value of the electric energy ratio PETEC in the terminal energy consumption through proportional operation
Figure BDA0002333059150000093
Figure BDA0002333059150000101
Wherein R isequConversion factor, R, for standard coal of electric energyeLFor rate of loss of electric energy, RLFor energy loss rate, PETEC is the ratio of electric energy in the original terminal energy consumption, △E% and △e% ofThe calculation method of the relative prediction error of the electric energy consumption and the energy consumption is as follows:
Figure BDA0002333059150000102
the above-mentioned embodiments describe the present invention in further detail, and some parameters and functions are instantiated, so that equivalent substitutions can be made in practical applications, and suitable parameters can be selected according to specific situations.
The invention discloses an electric energy proportion prediction method in terminal energy consumption based on an optimal combination model, which is based on the data of the total electric energy consumption and the total energy consumption in the past year, respectively selects a trend extrapolation model and a gray prediction model as single prediction models according to sequence characteristics and prediction requirements, calculates the weight according to single model errors so as to determine the combination prediction model, determines the optimal prediction points according to the principle of minimum model errors, respectively predicts the electric energy and the energy consumption in the future year by using the combination prediction model on the basis of the electric energy consumption and the energy consumption, indirectly calculates the PETEC prediction value through proportional operation, and determines the terminal electric energy consumption proportion prediction recommendation value.

Claims (7)

1. A method for predicting the electric energy ratio in terminal energy consumption based on an optimal combination model is characterized by comprising the following steps:
s1, acquiring the total energy consumption data and the total energy consumption data of the years before the year to be predicted, establishing a trend extrapolation prediction model, and calculating an energy-electric energy consumption prediction value by taking the trend extrapolation model as a single prediction model;
step S2, calculating an energy-electric energy consumption predicted value by taking the gray prediction model as a single prediction model;
step S3, respectively solving the prediction errors of the trend extrapolation model and the gray prediction model;
step S4, determining the weight of each single model in the combined model according to the reciprocal of the sum of squares of the model prediction errors, thereby determining the combined prediction model;
step S5, determining the optimal prediction point number according to the principle of minimum model error;
and step S6, on the basis of the electric energy consumption and the energy consumption, respectively predicting the electric energy and the energy consumption in the future year by using the combined prediction model, and indirectly obtaining the predicted value of the electric energy ratio PETEC in the terminal energy consumption through proportional operation.
2. The method for predicting the electric energy ratio in the terminal energy consumption based on the optimal combination model as claimed in claim 1, wherein the trend extrapolation model in step S1 is:
pn+1＝a1(n+1)2+a2(n+1)+a3(1)；
qn+1＝b1(n+1)2+b2(n+1)+b3(2)；
wherein, a1、a2、a3Values of the first three items of a coefficient matrix a to be solved for the total amount of electric energy consumption, in the form of a trend extrapolated prediction model matrix, pn+1Total amount of electric energy consumed in the n +1 th year, b1、b2、b3Values of the first three terms of a coefficient matrix b to be solved for the total amount of energy consumption, in the form of a trend extrapolated prediction model matrix, qn+1The total electric energy consumption of the (n + 1) th year;
the solving mode of a and b is as follows:
a＝(xTx)-1xtP (3)；
b＝(xTx)-1xTQ (4)；
wherein the content of the first and second substances,
Figure FDA0002333059140000011
obtaining a predicted value pre of the electric energy ratio in the terminal energy consumption in the (n + 1) th year based on the trend extrapolation model according to the relation between the total electric energy consumption and the total energy consumption and the electric energy ratio in the terminal energy consumption1The formula is as follows:
Figure FDA0002333059140000021
wherein R isLAnd ReLIs energy, electric energy loss rate, RequAnd converting the coefficient into the standard coal of the electric energy.
3. The method according to claim 1, wherein the energy-to-electric energy consumption prediction value obtained in step S2 by using the gray prediction model as the single prediction model is accumulated with total energy consumption data P and total energy consumption data Q of the past year n years before the year to be predicted to generate new data sequences P _ sum and Q _ sum, and then a gray prediction model first order differential equation is constructed for the new data sequences P _ sum and Q _ sum, respectively:
Figure FDA0002333059140000022
Figure FDA0002333059140000023
wherein, c1、c2Respectively, the solving coefficient of the total amount of electric energy consumption, d1、d2Respectively solving coefficients of the total electric energy consumption;
the solution of this first order differential equation is in exponential form, i.e.:
Figure FDA0002333059140000024
Figure FDA0002333059140000025
wherein p _ sumn+1Q _ sum being the sum of the first n +1 variables of the total amount of power consumptionn+1For the sum of the first n +1 variables of the total energy consumption, the equations (8) and (9)N is changed into n-1 to respectively obtain the sum p _ sum of the first n variables of the total electric energy consumptionnAnd the sum of the first n variables of the total energy consumption q _ sumnA prediction value p 'of the total amount of electric energy consumption of n +1 year based on the gray prediction model'n+1And predicted value q 'of total energy consumption'n+1The calculation formula is shown in formulas (10) to (11):
p′n+1＝p_sumn+1-p_sumn(10)；
q′n+1＝q_sumn+1-q_sumn(11)。
4. the method for predicting the electric energy ratio in the terminal energy consumption based on the optimal combination model as claimed in claim 1, wherein the prediction errors of the trend extrapolation model and the gray prediction model obtained in the step S3 are as follows:
Figure FDA0002333059140000031
wherein, △11％、△12% is the predicted value error of the total amount of electric energy consumed in the n +1 year based on the trend extrapolation model and based on the gray prediction model, △21％、△22% is the predicted value error of the total energy consumption of the n +1 year based on the trend extrapolation model and the gray prediction model respectively, act1、act2The total electric energy consumption and the total energy consumption of the corresponding year are respectively.
5. The method according to claim 1, wherein the weight of each single model in the combined model is determined according to the inverse of the sum of squares of the model prediction errors in step S4, and the combined prediction model is determined as follows:
Figure FDA0002333059140000032
therein, pre1Determined for a combined modelPrediction of total power consumption, pre1A predicted value, omega, of the total amount of energy consumption determined for the combined model1、ω2Representing the weight, omega, of the predicted value of the total amount of energy consumption in a combined model based on a trend extrapolation model and a grey prediction model, respectively3、ω4Respectively representing the weight of the total electric energy consumption predicted value in a combined model based on a trend extrapolation model and a grey prediction model.
6. The method for predicting the electric energy ratio in the terminal energy consumption based on the optimal combination model as claimed in claim 1, wherein the optimal prediction points J of the total electric energy consumption and the total energy consumption are respectively determined in step S5 based on the principle of minimum error of the combination model1、J2(ii) a The formula is as follows:
Figure FDA0002333059140000041
therein, pre1(i) For the predicted value of the ith year of the total consumption of electric energy, pre2(i) And (3) accumulating the error sum of squares of all historical data capable of carrying out prediction error detection for the predicted value of the ith year of the energy consumption under each to-be-selected prediction point k, and finally, when the average value of each group of error sum of squares is minimum, the corresponding prediction point is the optimal prediction point, and N is the number of all year covered by the historical data.
7. The method for predicting the electric energy ratio in the terminal energy consumption based on the optimal combination model as claimed in claim 1, wherein the step S6 is performed according to the electric energy consumption EeTAnd energy consumption ETBased on the prediction model, the combined prediction model is used for respectively predicting the electric energy consumption pre of the future year1And energy consumption pre2Indirectly obtaining the predicted value of the electric energy ratio PETEC in the terminal energy consumption through proportional operation
Figure FDA0002333059140000042
Figure FDA0002333059140000043
Wherein R isequConversion factor, R, for standard coal of electric energyeLFor rate of loss of electric energy, RLFor energy loss rate, PETEC is the ratio of electric energy in the original terminal energy consumption, △E% and △e% is relative prediction error of electric energy consumption and energy consumption.
CN201911344861.0A 2019-12-24 2019-12-24 Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model Active CN111047108B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911344861.0A CN111047108B (en) 2019-12-24 2019-12-24 Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911344861.0A CN111047108B (en) 2019-12-24 2019-12-24 Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model

Publications (2)

Publication Number Publication Date
CN111047108A true CN111047108A (en) 2020-04-21
CN111047108B CN111047108B (en) 2023-12-12

Family

ID=70238758

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911344861.0A Active CN111047108B (en) 2019-12-24 2019-12-24 Electric energy duty ratio prediction method in terminal energy consumption based on optimal combination model

Country Status (1)

Country Link
CN (1) CN111047108B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112669983A (en) * 2020-12-30 2021-04-16 华南师范大学 Infectious disease collaborative prediction method based on incomplete data deep learning and robot

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107748972A (en) * 2017-11-29 2018-03-02 国家电网公司 A kind of method based on Dual-energy source index prediction Analyzing Total Electricity Consumption
CN109033013A (en) * 2018-07-04 2018-12-18 国家电网公司 A kind of calculation method for household energy consumption structure in the countryside structure
CN109492818A (en) * 2018-11-16 2019-03-19 上海交通大学 Based on energy development and the entitled electricity demand forecasting method of Shapley value

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107748972A (en) * 2017-11-29 2018-03-02 国家电网公司 A kind of method based on Dual-energy source index prediction Analyzing Total Electricity Consumption
CN109033013A (en) * 2018-07-04 2018-12-18 国家电网公司 A kind of calculation method for household energy consumption structure in the countryside structure
CN109492818A (en) * 2018-11-16 2019-03-19 上海交通大学 Based on energy development and the entitled electricity demand forecasting method of Shapley value

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
刘孝萍等: "基于组合预测模型的我国能源需求预测分析", 《财经理论研究》 *
史王民: "中国人均能源消费水平的灰色预测与建议", 《价值工程》 *
姜维伊: "城市能源变革背景下终端能源消费中电能占比研究", 《中国优秀硕士学位论文全文库 工程科技Ⅱ辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112669983A (en) * 2020-12-30 2021-04-16 华南师范大学 Infectious disease collaborative prediction method based on incomplete data deep learning and robot
CN112669983B (en) * 2020-12-30 2023-08-04 华南师范大学 Infectious disease collaborative prediction method based on incomplete data deep learning and robot

Also Published As

Publication number Publication date
CN111047108B (en) 2023-12-12

Similar Documents

Publication Publication Date Title
Li et al. Regional environmental efficiency evaluation in China: Analysis based on the Super-SBM model with undesirable outputs
CN103177395A (en) Smart distribution grid energy conservation and emission reduction comprehensive evaluating method based on social expectation
WO2015081660A1 (en) Method for forecasting residential quarter short-term load
CN112819225A (en) Carbon market price prediction method based on BP neural network and ARIMA model
CN106327028A (en) Terminal energy consumption prediction method and device
CN104699959A (en) Similar line-loss division method based on K-MEANS algorithm
CN104573857A (en) Power grid load rate prediction method based on intelligent algorithm optimization and combination
CN108197764A (en) Predict the method and its equipment of electric power enterprise comprehensive energy consumption
CN101916335A (en) Prediction method of city water-requirement time series-exponent smoothing model
CN113554466A (en) Short-term power consumption prediction model construction method, prediction method and device
CN110909958A (en) Short-term load prediction method considering photovoltaic grid-connected power
CN116845889B (en) Hierarchical hypergraph neural network-based power load prediction method
CN103530700B (en) Urban distribution network saturation loading Comprehensive Prediction Method
CN115600722A (en) Long-term prediction method for electric carbon factor of enterprise
CN116796403A (en) Building energy saving method based on comprehensive energy consumption prediction of commercial building
CN110212592B (en) Thermal power generating unit load regulation maximum rate estimation method and system based on piecewise linear expression
CN113344449B (en) Method for predicting monthly industrial water demand
CN111047108A (en) Optimal combination model-based electric energy ratio prediction method in terminal energy consumption
CN110991747A (en) Short-term load prediction method considering wind power plant power
CN108108837B (en) Regional new energy power supply structure optimization prediction method and system
CN112330089B (en) Comprehensive energy efficiency monitoring method and monitoring system for equipment manufacturing enterprises
CN117422165A (en) Urban water delivery system water quantity prediction method and system based on low carbon emission
CN110414776B (en) Quick response analysis system for power utilization characteristics of different industries
CN115660234B (en) Double-carbon prediction optimization model based on hybrid measurement and calculation method
CN110991748A (en) Short-term load prediction method for urban power grid

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant