CN111461449A - Power load prediction method and computer program product - Google Patents
Power load prediction method and computer program product Download PDFInfo
- Publication number
- CN111461449A CN111461449A CN202010275049.3A CN202010275049A CN111461449A CN 111461449 A CN111461449 A CN 111461449A CN 202010275049 A CN202010275049 A CN 202010275049A CN 111461449 A CN111461449 A CN 111461449A
- Authority
- CN
- China
- Prior art keywords
- load
- year
- historical
- predicted
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004590 computer program Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 47
- 230000005611 electricity Effects 0.000 claims description 22
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 6
- 230000007774 longterm Effects 0.000 claims description 4
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 2
- 238000013277 forecasting method Methods 0.000 claims 1
- 238000011161 development Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (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 relates to a power load prediction method and a computer program product, which are used for automatically calculating a load prediction result in power grid planning work. The method for automatically generating the load prediction result comprises the following steps: acquiring historical load characteristic data and historical load prediction condition data; establishing a load prediction calculation model; automatically configuring high, medium and low scheme parameter configuration combined with expert experience; intelligent load prediction calculation and automatic generation of load prediction results. The invention provides a plurality of load prediction methods, which consider a plurality of load prediction influence factors and improve the accuracy of load prediction. The invention can reduce the error caused by manual calculation, improve the reliability of load prediction and improve the working efficiency of load prediction.
Description
Technical Field
The invention relates to an electric load prediction method and a computer program product, and belongs to the technical field of electric power calculation analysis methods.
Background
The power load prediction refers to a mathematical method for researching and utilizing a set of energy system to process past and future loads under the condition of fully considering some important operating characteristics, capacity increasing decisions, natural conditions and social influences. Load prediction is an indispensable important link for planning and operating an electric power system, and the accuracy of the load prediction directly influences the rationality of investment, network layout and operation. The power load prediction is a precondition and an important basis for implementing control, operation plan and development planning, and the power quantity prediction is particularly important in medium-long term load prediction.
The accuracy of electric quantity prediction directly influences the rationality of power grid planning. At present, medium-and-long-term electric quantity prediction is mainly carried out manually by workers, and a medium-and-long-term electric quantity prediction result is obtained through statistical analysis and manual experience of a large amount of data.
With the development of social economy, factors influencing economic growth are more and more, and the accuracy of electric quantity prediction cannot be guaranteed by simply relying on manual work, so that the reliability of power grid planning is influenced.
Disclosure of Invention
In view of the above, the present invention mainly provides a method for predicting an electrical load and a computer product, and provides a load prediction method including multiple influence factors, and establishes a multi-method mathematical model in a computer, and adopts high-speed calculation of the computer to replace the conventional manual statistical analysis, and uses prediction parameters calculated by the computer to replace prediction parameters formed by manual experience, so as to improve the accuracy of medium and long term load prediction and improve the reliability of power grid planning.
The invention comprises the following steps:
A. automatically acquiring historical load characteristic data and historical load prediction condition data;
B. establishing a load prediction data calculation model;
C. constructing a high, medium and low scheme parameter configuration module which automatically generates and combines with expert experience;
D. and intelligently predicting and calculating the load to generate a load prediction result.
Further, the process of automatically acquiring the historical load characteristic data and the historical load prediction condition data in the step a is as follows:
a1, acquiring historical power load data, and acquiring historical condition data required by load calculation and prediction;
a2, checking the correctness of the historical power load data and the historical condition data;
a3, data with possible exception at the mark.
Further, the step of establishing the data calculation model in the step B is as follows:
b1, establishing a relevant load prediction model according to the acquired historical condition data and historical load data;
and B2, establishing a large user and natural growth rate model, an elasticity coefficient model, a man-power-average method model, a time series model and an industrial unit consumption model.
Further: the specific modeling conditions of the established data calculation model are as follows:
1) the method comprises the following steps of adding a natural growth rate model to a large user, and calculating the predicted electricity utilization data, historical conventional electricity utilization data and the conventional electricity quantity growth rate of the large user, wherein:
P＝P(dyh)+P(cg)
P(dyh)＝(P1+P2+…+Pn)*C
wherein P is the predicted annual total load, P(dyh)To predict annual user load, P(cg)To predict annual routine load, P(s)In order to predict the conventional load of the previous year, K1-Kn identifies the growth rate from the previous year to the previous N years, α, β and lambda … … N are weighting factors, all the weighting factors are added to be 1, the closer to the historical year of the predicted year, the larger the value of the weighting factor is, the more 5 years are taken in the historical year, p1 … … Pn is the predicted annual power consumption of each large user, C is the coincidence rate, and the coincidence rate is generally 0.92 according to the power utilization law.
2) And establishing an elastic coefficient calculation model, wherein the elastic coefficient is the ratio of the average load increase rate to the total domestic production value increase rate, and the total electrical load at the end of the planning period is obtained according to the increase speed of the total domestic production value and the elastic coefficient. Calculating the planned annual elastic coefficient by using an exponential smoothing method:
wherein T isnFor the elasticity coefficient of the predicted year, α, β and lambda … … n are weighting factors, the historical year is taken as 5 years, and the weighting factors are higher closer to the predicted year;
after the elastic coefficient is calculated, the predicted annual load average growth rate can be calculated:
F(p)＝T(n)*GDP％
wherein GDP% is the predicted national production total value growth rate of the predicted year, and the predicted year load is as follows:
P＝P(n-1)*(1+F(p))
3) establishing a unit consumption model, calculating the predicted annual load, and calculating the required power load according to the product yield (or output value) and the unit power consumption in the prediction period, namely
In the formula, Ah represents the demand load of a certain industry prediction period, Ui represents the unit consumption of electricity of various products (calculated according to the output value), and Qi represents the output (or the output value) of various products;
firstly, calculating the unit consumption growth rate of a planning year:
wherein F (d)n) For the unit consumption increase rate of the forecast year, α, β and lambda … … n are weighting factors, the historical year is 5 years, the weighting factor is higher closer to the forecast year, and the unit consumption of the forecast year is as follows:
dn＝d(n-1)*F(dn)
calculating unit consumption of different industries by different industries, and finally calculating predicted annual load:
predicted annual load is the unit consumption of the first industry GDP × in the predicted year, the unit consumption of the second industry GDP × in the predicted year, the unit consumption of the third industry GDP × in the predicted year
4) And establishing a man-average load calculation model, and calculating the planned annual load by utilizing the planned annual population and the planned annual man-average load. The planning year per capita power can be divided into a near-term value and a far-term value, the near-term value is calculated by using a regression analysis method, and the far-term value obtains a national macro planning long-term related target value.
Calculating the recent per-capita load, firstly calculating the per-capita load increase rate:
wherein F (t)n) In order to predict the annual average load growth rate, α, β and lambda … … n are weighting factors, all the weighting factors are added to be 1, the historical year is taken as 5 years, and the weighting factor is higher when the year is closer to the prediction year;
the planned annual average load is as follows:
T(rn)＝T(rn-1)*F(tn)
T＝T(rn)*R
wherein R is the planned annual population.
Further: constructing a high, medium and low scheme parameter configuration module which automatically generates and combines with expert experience, wherein the construction mode is as follows:
c1, according to the model of claim 4, automatically generating the parameters needed in the model calculation, and giving parameter calculation steps;
c2, automatically generating parameters of the high, medium and low schemes according to the requirements of the high, medium and low schemes;
c3, providing an expert modification entrance, and manually modifying the automatically generated parameters.
Further: intelligent load prediction calculation is carried out to generate a load prediction result, and the process of generating the prediction result is as follows:
d1, according to the calculation model and the parameter setting, the load prediction results of different calculation models;
d2, integrating and analyzing the calculation results of the large user with a natural growth rate model, an elasticity coefficient model, a unit consumption model and a man-average load model to generate a recommended value;
d3, automatically generating a histogram and a polyline histogram of the method for predicting the annual average high, middle and low according to the prediction result.
A computer program product for electrical load prediction, said computer program product comprising a non-transitory readable storage medium and a computer program, said computer program being tangibly stored on said non-transitory readable storage medium, the computer program being executable by a processor in a computer to perform steps implementing said method for electrical load prediction.
The invention has the beneficial effects that:
1. a plurality of load prediction methods are provided, a plurality of load prediction influence factors are considered, and the load prediction accuracy is improved.
2. The method adopts the high-speed calculation of establishing a computer model to replace manual statistical analysis, reduces errors caused by manual calculation, improves the reliability of load prediction and improves the working efficiency of load prediction.
3. The invention can liberate manpower from complicated and repeated data collection, statistics and calculation, saves more time for the research of other deep level load prediction work and planning work, and enables the power grid planning to adapt to the constantly changing urban development planning.
Drawings
Fig. 1 is a flowchart of a power load prediction method according to the present invention.
FIG. 2 is a comparison graph of the calculated results of different embodiments of the algorithm models of the power load prediction method of the present invention.
Figure 3 is a high, medium, low profile comparison graph of an embodiment of the power load prediction method of the present invention.
Detailed Description
The invention is further illustrated below with reference to fig. 1:
as shown in fig. 1, a method for predicting an electrical load includes the following steps:
A. automatically acquiring historical load characteristic data and historical load prediction condition data;
B. establishing a load prediction data calculation model;
C. constructing a high, medium and low scheme parameter configuration module which automatically generates and combines with expert experience;
D. and intelligently predicting and calculating the load to generate a load prediction result.
In the step A, historical load characteristic data and load calculation condition data are automatically acquired, wherein the historical load characteristic data and the load calculation condition data comprise large user load data, national economy development historical data and forecast data, historical population data and forecast data, historical annual total power load data, region 8760-hour power load data and the like. And verifying the collected load characteristic data, and marking the load characteristic data obviously having abnormity until all the data are verified.
According to the acquired condition data, a prediction model of the large user increasing rate, the unit consumption, the elasticity coefficient and the per-capita electricity quantity is established, a parameter configuration module is generated according to the established algorithm model, parameters are automatically configured, an expert modification entry is provided, and a load prediction result is calculated.
The large user plus growth rate calculation model is as follows:
P＝P(dyh)+P(cg)
P(dyh)＝(P1+P2+...+Pn)*C
wherein P is the predicted annual total load, P (dyh) is the predicted annual user load, P(cg)To predict annual routine load, P(s)In order to predict the conventional load of the previous year, K1-Kn identifies the growth rate from the previous year to the previous N years, α, β and lambda … … N are weighting factors, all the weighting factors are added to be 1, the closer to the historical year of the predicted year, the larger the value of the weighting factor is, the more 5 years are taken in the historical year, p1 … … Pn is the predicted annual power consumption of each large user, C is the coincidence rate, and the coincidence rate is generally 0.92 according to the power utilization law.
If the electricity quantity of a large user in 2018 is 224.8 hundred million kilowatt hours in some place and the electricity quantity of a large user in 2018 is 24.79 million kilowatt hours in 2018, the electricity quantity of the large user in some place is predicted to increase in a staged manner in the future.
Predicted electric quantity + historical conventional electric quantity (1+ conventional electric quantity increase rate) for large user
The results of the calculations are shown in the table below.
Unit: hundred million kilowatt hours
And establishing an elastic coefficient calculation model, wherein the elastic coefficient is the ratio of the average load increase rate to the total domestic production value increase rate, and the total electrical load at the end of the planning period is obtained according to the increase speed of the total domestic production value and the elastic coefficient. Calculating the planned annual elastic coefficient by using an exponential smoothing method:
wherein T isnFor the elasticity coefficient of the predicted year, α, β and lambda … … n are weighting factors, the historical year is taken as 5 years, and the weighting factors are higher closer to the predicted year;
after the elastic coefficient is calculated, the predicted annual load average growth rate can be calculated:
F(p)＝T(n)*GDP％
wherein GDP% is the predicted national production total value growth rate of the predicted year, and the predicted year load is as follows:
P＝P(n-1)*(1+F(p))
for example, the input: the historical electric quantity is 224.8, the first-stage elastic coefficient is 0.97, the second-stage elastic coefficient is 0.8, and the national production total value growth rate of each year is predicted to be 7% in 2019, 6.8% in 2020, 6.8% in 2021, 6.8% in 2022, 6.8% in 2023, 6.8% in 2024 and 7% in 2025. The calculation formula is substituted, and the obtained calculation results are shown in the following table.
Unit: hundred million kilowatt hours
Establishment of industryA unit consumption model for calculating the predicted annual load and calculating the required power load according to the product yield (or output value) and the unit consumption of power consumption in the prediction period, i.e. the unit consumption model
In the formula, Ah represents the demand load of a certain industry prediction period, Ui represents the unit consumption of electricity of various products (calculated according to the output value), and Qi represents the output (or the output value) of various products. Because the data volume such as the product yield is too large and the collection is very difficult, the method is simplified, and the economic prediction data is refined to GDP values of various industries of first, second and third productions.
Firstly, calculating the unit consumption growth rate of a planning year:
wherein F (d)n) For the unit consumption increase rate of the forecast year, α, β and lambda … … n are weighting factors, the historical year is 5 years, the weighting factor is higher closer to the forecast year, and the unit consumption of the forecast year is as follows:
dn＝d(n-1)*F(dn)
calculating unit consumption of different industries by different industries, and finally calculating predicted annual load:
the predicted annual load is the unit consumption of the first industry in the predicted year GDP × + the unit consumption of the second industry in the predicted year GDP × + the unit consumption of the third industry in the predicted year GDP ×.
For example, the input: historical power consumption of the first industry, the second industry and the third industry, historical GDP of the first industry and the third industry, and historical power consumption of urban and rural residents predict the unit consumption growth rate of the first industry and the third industry; predicting GDP of the first two and three industries and increasing rates of electricity consumption of urban and rural residents, wherein in 2018, the unit consumption of the first industry is 0.09, the unit consumption of the second industry is 0.04, the unit consumption of the third industry is 0.04, the increasing rates of the unit consumption are all set to be 1.06, the electricity consumption of the first industry is 448, the electricity consumption of the second industry is 1816, the electricity consumption of the third industry is 2452, the electricity consumption of the residents is 20, and the increasing rate of the electricity consumption of the residents is 1.06, so that the GDP can be obtained:
unit: hundred million kilowatt hours
And establishing a man-average load calculation model, and calculating the planned annual load by utilizing the planned annual population and the planned annual man-average load. The planning year per capita power can be divided into a near-term value and a far-term value, the near-term value is calculated by using a regression analysis method, and the far-term value obtains a national macro planning long-term related target value.
Calculating the recent per-capita load, firstly calculating the per-capita load increase rate:
wherein F (t)n) In order to predict the annual average load growth rate, α, β and lambda … … n are weighting factors, all the weighting factors are added to be 1, the historical year is taken as 5 years, and the weighting factor is higher when the year is closer to the prediction year;
the planned annual average load is as follows:
T(rn)＝T(rn-1)*F(tn)
T＝T(rn)*R
wherein R is the planned annual population.
For example, the input: the historical electric quantity 224.8, and the historical chinning population 438 thousands of people in 2018.
Predicting 442 million people in 2019 year by year in population; 447 ten thousands of people in 2020; 451 million people in 2021; 456 ten thousand in 2022; 460 ten thousand people in 2023; 465 thousands of people in 2024; in 2025 469 thousands of people. The results of the substitution formula calculation are shown in the following table.
Unit: hundred million kilowatt hours
According to the four calculation results, the calculation results of each algorithm model can be summarized as follows:
the calculation results of the four calculation models are shown in fig. 2, for example, the results show that the industrial unit consumption method is slightly deviated from the four calculation models, the unit consumption parameters are properly adjusted at the expert modification inlet configured by the parameter module, and the accuracy of automatic recommendation is gradually improved by continuously combining the expert experience and the automatic recommendation mode. In the parameter configuration module, parameters of high, medium and low schemes can be automatically generated according to the requirements of different schemes; the results of the high, medium and low calculations, and the comparative models of the high, medium and low profiles are generated, as shown in the table below and in fig. 3.
A computer program product for electrical load prediction, said computer program product comprising a non-transitory readable storage medium and a computer program, said computer program being tangibly stored on said non-transitory readable storage medium, the computer program being executable by a processor in a computer to perform steps implementing said method for electrical load prediction.
The method can automatically calculate the prediction results of different prediction models through the establishment of a calculation model and a parameter configuration model combining automation and manual work, reversely optimize the automatic parameter configuration through the mutual comparison of different results, and improve the accuracy of the load prediction result through continuous calculation and optimization.
Claims (7)
1. An electrical load prediction method is characterized by comprising the following steps:
A. automatically acquiring historical load characteristic data and historical load prediction condition data;
B. establishing a load prediction data calculation model;
C. constructing a high, medium and low scheme parameter configuration module which automatically generates and combines with expert experience;
D. and intelligently predicting and calculating the load to generate a load prediction result.
2. The method for predicting the electrical load according to claim 1, wherein the steps of automatically acquiring the historical load characteristic data and the historical load prediction condition data in the step a are as follows:
a1, acquiring historical power load data, and acquiring historical condition data required by load calculation and prediction;
a2, checking the correctness of the historical power load data and the historical condition data;
a3, data with possible exception at the mark.
3. The electrical load forecasting method according to claim 1, wherein the step of building the load forecasting data calculation model in the step B is as follows:
b1, establishing a relevant load prediction model according to the acquired historical condition data and historical load data;
and B2, establishing a large user and natural growth rate model, an elasticity coefficient model, a man-power-average method model, a time series model and an industrial unit consumption model.
4. The method for forecasting electrical load as recited in claim 3, wherein said modeling load forecast data calculation further comprises:
1) the method comprises the following steps of adding a natural growth rate model to a large user, and calculating the predicted electricity utilization data, historical conventional electricity utilization data and the conventional electricity quantity growth rate of the large user, wherein:
P＝P(dyh)+P(cg)
P(dyh)＝(P1+P2+...+Pn)*C
wherein P is the predicted annual total load, P (dyh) is the predicted annual user load, P(cg)To predict annual routine load, P(s)For predicting the annual conventional loadK1-Kn identifies the growth rate from the previous year to the previous N years, α, β and lambda … … N are weighting factors, all the weighting factors are added to be 1, the closer to the historical year of the predicted year, the larger the value of the weighting factor is, the historical year takes 5 years, p1 … … Pn is the predicted annual power consumption of each large user, C is the synchronization rate, and the synchronization rate generally takes 0.92 according to the power utilization law;
2) establishing an elastic coefficient calculation model, wherein the elastic coefficient is the ratio of the average load increase rate to the total domestic production value increase rate, and the total electrical load at the end of the planning period is obtained according to the increase speed of the total domestic production value and the elastic coefficient; calculating the planned annual elastic coefficient by using an exponential smoothing method:
wherein T isnFor the elasticity coefficient of the predicted year, α, β and lambda … … n are weighting factors, the historical year is taken as 5 years, and the weighting factors are higher closer to the predicted year;
after the elastic coefficient is calculated, the predicted annual load average growth rate can be calculated:
F(p)＝T(n)*GDP％
wherein GDP% is the predicted national production total value growth rate of the predicted year, and the predicted year load is as follows:
P＝P(n-1)*(1+F(p))
3) establishing a unit consumption model, calculating the predicted annual load, and calculating the required power load according to the product yield or output value in the prediction period and the unit power consumption, namely
In the formula, Ah represents the demand load of a prediction period of an industry, Ui represents the electricity consumption unit consumption of various products calculated according to output values, and Qi represents the output or output value of various products;
firstly, calculating the unit consumption growth rate of a planning year:
wherein F (d)n) For the unit consumption increase rate of the forecast year, α, β and lambda … … n are weighting factors, the historical year is 5 years, the weighting factor is higher closer to the forecast year, and the unit consumption of the forecast year is as follows:
dn＝d(n-1)*F(dn)
calculating unit consumption of different industries by different industries, and finally calculating predicted annual load:
the predicted annual load is the unit consumption of the first industry of the first predicted year GDP × + the unit consumption of the second industry of the second predicted year GDP × + the unit consumption of the third industry of the third predicted year GDP ×;
4) establishing a man-average load calculation model, and calculating a planning year load by using a planning year population and the planning year man-average load; the planning year per capita power can be divided into a near-term value and a far-term value, the near-term value is calculated by using a regression analysis method, and the far-term value obtains a national macro planning long-term related target value;
calculating the recent per-capita load, firstly calculating the per-capita load increase rate:
wherein F (t)n) In order to predict the annual average load growth rate, α, β and lambda … … n are weighting factors, all the weighting factors are added to be 1, the historical year is taken as 5 years, and the weighting factor is higher when the year is closer to the prediction year;
the planned annual average load is as follows:
T(rn)＝T(rn-1)*F(tn)
T＝T(rn)*R
wherein R is the planned annual population.
5. The method for predicting the electrical load according to claim 1, wherein the step C is constructed in a manner that:
c1, automatically generating parameters required in model calculation, and giving out parameter calculation steps;
c2, automatically generating parameters of the high, medium and low schemes according to the requirements of the high, medium and low schemes;
c3, providing an expert modification entrance.
6. The method for forecasting electrical loads according to any one of claims 1 to 5, characterized in that the procedure of step D is as follows:
d1, according to the calculation model and the parameter setting, the load prediction results of different calculation models;
d2, integrating and analyzing the calculation results of the large user with a natural growth rate model, an elasticity coefficient model, a unit consumption model and a man-average load model to generate a recommended value;
d3, automatically generating a histogram and a polyline histogram of the method for predicting the annual average high, middle and low according to the prediction result.
7. A computer program product for electrical load prediction, the computer program product comprising a non-transitory readable storage medium and a computer program, the computer program being tangibly stored on the non-transitory readable storage medium, the computer program being executable by a processor in a computer to perform steps implementing the electrical load prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010275049.3A CN111461449A (en) | 2020-04-09 | 2020-04-09 | Power load prediction method and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010275049.3A CN111461449A (en) | 2020-04-09 | 2020-04-09 | Power load prediction method and computer program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111461449A true CN111461449A (en) | 2020-07-28 |
Family
ID=71682225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010275049.3A Pending CN111461449A (en) | 2020-04-09 | 2020-04-09 | Power load prediction method and computer program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461449A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232559A (en) * | 2020-10-12 | 2021-01-15 | 国网江西省电力有限公司信息通信分公司 | Short-term prediction method and device for load in power area |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200277A (en) * | 2014-08-12 | 2014-12-10 | 南方电网科学研究院有限责任公司 | Medium-and-long-term power load prediction model establishment method |
| CN107742167A (en) * | 2017-10-19 | 2018-02-27 | 重庆星能电气有限公司 | The accurate planing method of middle voltage distribution networks based on three layers of macroscopical networking constraint |
| CN108304978A (en) * | 2018-05-08 | 2018-07-20 | 国网江西省电力有限公司经济技术研究院 | A kind of mid-term Electric Power Load Forecast method based on data clusters theory |
-
2020
- 2020-04-09 CN CN202010275049.3A patent/CN111461449A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200277A (en) * | 2014-08-12 | 2014-12-10 | 南方电网科学研究院有限责任公司 | Medium-and-long-term power load prediction model establishment method |
| CN107742167A (en) * | 2017-10-19 | 2018-02-27 | 重庆星能电气有限公司 | The accurate planing method of middle voltage distribution networks based on three layers of macroscopical networking constraint |
| CN108304978A (en) * | 2018-05-08 | 2018-07-20 | 国网江西省电力有限公司经济技术研究院 | A kind of mid-term Electric Power Load Forecast method based on data clusters theory |
Non-Patent Citations (1)
| Title |
|---|
| 赵更磊: "基于空间布局的区域化范县配电网研究与规划", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232559A (en) * | 2020-10-12 | 2021-01-15 | 国网江西省电力有限公司信息通信分公司 | Short-term prediction method and device for load in power area |
| CN112232559B (en) * | 2020-10-12 | 2023-06-13 | 国网江西省电力有限公司信息通信分公司 | Short-term prediction method and device for power regional load |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| CN107292766B (en) | Wind power consumption-oriented power system peak regulation means economical evaluation method and system | |
| CN108053082B (en) | Power grid medium and long term load prediction method based on temperature interval decomposition | |
| CN106991524A (en) | A kind of platform area line loss per unit predictor method | |
| CN110796307B (en) | Distributed load prediction method and system for comprehensive energy system | |
| CN112085256B (en) | Full-period load prediction method considering load jump | |
| CN106684915A (en) | Wind-hydrogen coupling power generation system optimization method and device thereof | |
| CN110910026B (en) | Cross-provincial power transmission line loss intelligent management and decision method and system | |
| CN114254838B (en) | Method for determining short-term power load prediction influence factor | |
| CN116845889B (en) | Hierarchical hypergraph neural network-based power load prediction method | |
| CN104699890A (en) | Modeling method of short-term forewarning model for heavy overload of distribution transformer of urban power network | |
| CN107437135A (en) | A kind of novel energy-storing selection method | |
| CN117557009B (en) | Power efficiency monitoring method and system | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| CN111461449A (en) | Power load prediction method and computer program product | |
| CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
| Kuo et al. | A novel framework short-term load forecasting for micro-grid energy management system | |
| CN115983421A (en) | Method and device for analyzing transaction plan of hydroelectric balance power station in hydropower enrichment environment | |
| CN112001522B (en) | STN state network-based private transformer user energy optimization method | |
| CN115759418A (en) | Adjustable capacity prediction method and system for electric power retail customer | |
| CN111049140B (en) | Method and device for analyzing running rationality of power system | |
| Salman et al. | Using recurrent neural network to forecast day and year ahead performance of load demand: A case study of France | |
| CN107730046A (en) | A kind of Power Short-Term Load Forecasting system and method | |
| CN105447598A (en) | Error correction model based load prediction apparatus and method in power system | |
| CN116523273B (en) | Demand response characteristic analysis method for industrial users |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |