CN110705806A - Electric quantity prediction method based on capacity utilization hours - Google Patents
Electric quantity prediction method based on capacity utilization hours Download PDFInfo
- Publication number
- CN110705806A CN110705806A CN201910981522.7A CN201910981522A CN110705806A CN 110705806 A CN110705806 A CN 110705806A CN 201910981522 A CN201910981522 A CN 201910981522A CN 110705806 A CN110705806 A CN 110705806A
- Authority
- CN
- China
- Prior art keywords
- electric quantity
- industry
- years
- equal
- growth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 2
- 230000000737 periodic effect Effects 0.000 abstract description 3
- 239000002184 metal Substances 0.000 description 6
- 229910052751 metal Inorganic materials 0.000 description 6
- 238000005457 optimization Methods 0.000 description 5
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 4
- 238000003723 Smelting Methods 0.000 description 4
- 230000000739 chaotic effect Effects 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000005065 mining Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000003490 calendering Methods 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000005406 washing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- 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)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an electric quantity prediction method based on capacity utilization hours, which respectively predicts the electric quantity of industries according to different conditions of various industries, has close variation trends, predicts the electric quantity of the industries by taking the capacity utilization hours as a coefficient, has large variation trend difference, checks the average capacity utilization hours according to different variation trends of GDP (product data processing) of the industries so as to predict the electric quantity of the industries, and then sums the electric quantity to obtain an electric quantity prediction result. Compared with the general intelligent algorithm for predicting the electric quantity, the method is simpler and more feasible, and avoids uncertainty caused by self-learning in parameter estimation in the intelligent algorithm, so that when a periodic electric quantity prediction result is issued as a decision basis, the method is more accurate, and the data change is stable and the load actual operation trend is carried out.
Description
Technical Field
The invention belongs to the field of power consumption prediction of a power grid, and particularly relates to a capacity utilization hour number-based power prediction method.
Background
In power grid planning, power supply capacity and power supply capacity of a power grid are determined in order to accurately track loads, electric quantity and power balance of the power grid are achieved, electric quantity prediction is generally carried out for the purpose, and a direct prediction method is mostly adopted.
Aiming at the characteristics of less available related historical data, more complex influence factors and the like in medium-long term electric quantity prediction, the north China electric power university provides an optimized combined prediction model based on an improved GM (1,1) and a support vector machine. The model combines an improved gray prediction model and a support vector machine model, and adopts a frog-leaping optimization algorithm to calculate the weight of each single model in the combined prediction model so as to construct the combined prediction model based on frog-leaping optimization.
The optimized combined prediction model is applied to medium-long term electric quantity prediction in China, electric quantity in 1991-2005 in China is selected for analysis, electric quantity in 2006-2010 is predicted, and the electric quantity is compared with a common combined prediction model and each single model.
Aiming at the problems that the traditional medium-and-long-term electric quantity prediction method is single in thought and influences the medium-and-long-term electric quantity prediction precision due to neglect of internal connection among electric quantity predictions of different levels, the south China university provides a novel medium-and-long-term electric quantity prediction method based on electric industry classification.
Firstly, designing a power utilization industry classification principle and method suitable for power quantity prediction; then, on the basis of a prediction method with 8 characteristic complementation, establishing an optimal combination prediction model, and respectively predicting the whole area to be predicted and the electric quantity requirements of each power utilization industry annually and quarterly; and finally, a two-dimensional two-stage coordination model is established by using a multi-stage prediction coordination theory, the predicted value of the electric quantity in the previous step is corrected, the prediction precision is improved, and the predicted values of the electric quantity of the whole area with unified upper and lower stages and the predicted values of the electric quantity of the future year and the quarter of each industry are obtained.
The Chinese agriculture university classifies the electric quantity and the electric quantity increment development law according to the electric quantity characteristics of different regions, and provides a corresponding electric quantity and electric quantity increment prediction model. Based on the initial value sensitivity of the chaotic motion and the analysis of the chaotic optimization searching process, a parallel self-adaptive chaotic optimization method is provided. On the basis, the parallel self-adaptive chaotic optimization method is used for determining the parameters of the electric quantity prediction model, and specific implementation steps and main measures are provided.
Disclosure of Invention
The invention aims to provide an electric quantity prediction method based on capacity utilization hours.
Due to the fact that economic situations of various industries are unstable, corresponding relations between capacity and electric quantity do not exist in all the industries at the same time, the method is only suitable for being used by some industries in a certain specific time period, and under the condition that the economic situations of the industries are favorable or stable, the method can be used for short-term industry electric quantity prediction.
And respectively predicting according to different conditions of each industry, predicting the industry electric quantity by taking the capacity utilization hours as a coefficient when the variation trends are close, and checking the average capacity utilization hours according to different variation trends of the GDP (product data package) of the industry so as to predict the industry electric quantity, wherein the variation trends are large.
And then summing to obtain an electric quantity prediction result.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a method for predicting electric quantity based on capacity utilization hours comprises the following steps:
(1) when the i-th annual electric quantity of a certain business n is Wn _ i, the running capacity is Sn _ i, and the average utilization hour number of the capacity is Kn, Kn can be calculated by the formula (1):
m in the formula represents the counted years;
(2) the increment of the electric quantity of the ith year relative to the previous year is delta Wn _ i, and the average increment of the m years is
n _ m, the growth stability Hn _ m of the industry n in m years is defined as shown in a formula (2),
setting a limit value epsilon, wherein for industries with larger Hn _ m values (Hn _ m > epsilon), the growth of the industries is not stable, otherwise, the growth is stable, and for the condition that delta Wi & delta Wi-1 is less than 0, an inflection point appears in the growth, and the growth trend changes rapidly;
(3) depending on whether there are inflection points and growth stationarity,
1) setting conditions A as delta Wi & delta Wi-1>0 and overall Hn _ m < epsilon for all years;
2) setting conditions B as delta Wi & delta Wi-1>0 and overall Hn _ m > epsilon in all years;
3) setting condition C to the presence of one or more years Δ Wi-1<0 and Hn _ m > ε;
4) setting other conditions as a condition D;
(4) the following prediction methods are respectively adopted for industries meeting different conditions,
1) satisfies the condition A, is calculated by adopting the formula (3),
Wn_i+1＝KnSn_i+1＝Kn(Sn_i+ΔSn_i) (3)
wherein, the delta Sn _ i is the capacity of a transformer which is newly built and put into operation in the ith year;
2) if the condition B is satisfied, it reflects that the power increase significantly changes due to the industry policy, and for this reason, the change of the major economic development index GDP is predicted in more detail by the small segment capacity utilization, where equation (1) is adjusted to equation (4),
p represents the number of segments according to GDP, Kn-j represents the number of hours of capacity utilization of the jth segment, the period is stable due to certain continuity of an economic promotion policy, but the initial stage is set to have large fluctuation, and the segments are mainly used for processing the fluctuation;
3) if the condition C is satisfied, the segmentation of the inflection point is increased,
assuming that the number of times of occurrence of Δ Wi · Δ Wi-1<0 in m years is q, the first occurrence is l years, l < ═ m, the power of the year is denoted as Wn _ l, and the power of the q-th corresponding year is Wl + Δ mq-1, where Δ mq-1 represents the difference between the q-th and 1-th times; adopting a calculation method of the condition B in each section;
4) the condition D is satisfied to show that the whole is stable, but the local inflection point appears, generally in the traditional industry, the inflection point is segmented, and a prediction method of the condition A is adopted in each segment.
Compared with the prior art, the invention has the following beneficial effects:
compared with the general intelligent algorithm for predicting the electric quantity, the method is simpler and more feasible, avoids uncertainty caused by self-learning in parameter estimation in the intelligent algorithm, ensures that when a periodic electric quantity prediction result is issued as a decision basis, the method is more accurate, the data change is stable, the load actually runs, the public confidence is stronger, and the social recognition is facilitated. The method adopts a linear prediction method, is more adaptive to the electric quantity change characteristic than the ordinary non-intelligent methods such as quadratic or spline curve prediction and the like, avoids the occurrence of abnormal distortion points, and can more accurately control the investment scale when being used for guiding the planning and construction of the power grid.
Drawings
FIG. 1 is a line graph of electric quantity data of 2013-2016 year in the field of information transmission, computer service and software industry in a certain area according to an embodiment;
FIG. 2 is a line graph of electric quantity data of 2013-2016 year in agriculture, forestry, animal husbandry and fishery in a certain area in an embodiment;
FIG. 3 is a line graph of electric quantity data of 2013 and 2016 years in certain area of the embodiment;
FIG. 4 shows the result of electric quantity data prediction and the error analysis of the result in each industry in a certain area.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Example one
As shown in fig. 1-4, a method for predicting capacity based on hours of capacity utilization includes the following steps:
the method comprises the following steps: calculating to obtain the average utilization hours of the capacity of a certain business n;
step two: calculating to obtain the increase smoothness of the industry n in the specific year in the number of m years in the step one;
step three: judging whether an inflection point and growth stability exist according to the growth value of the n industry in the specific year, the number of the m years;
step four: and predicting the electric quantity of the industries meeting different conditions.
The average number of hours of capacity utilization of a certain business n is calculated as follows:
when the i-th annual electric quantity of a certain business n is Wn _ i, the running capacity is Sn _ i, and the average utilization hour number of the capacity is Kn, Kn can be calculated by the formula (1):
in the above formula, m represents the number of years counted.
The method for calculating the growth smoothness of the industry n in a specific year in parts of m years comprises the following steps:
the increment of the electric quantity of the ith year relative to the previous year is delta Wn _ i, and the average increment of the m years is
Defining the growth smoothness Hn _ m of the industry n in m years as shown in the formula (2),
and setting a limit value epsilon, wherein for the industry with a larger Hn _ m value (Hn _ m > epsilon), the growth of the industry is not stable, otherwise, the growth is relatively stable, and for the condition that delta Wi & delta Wi-1 is less than 0, an inflection point appears in the growth, and the growth trend changes rapidly.
Judging whether an inflection point and growth stability exist in the growth value of the industry n in the specific year, number of parts and m years;
setting conditions A as delta Wi & delta Wi-1>0 and overall Hn _ m < epsilon for all years;
the electric quantity prediction method meeting the condition A industry adopts the formula (3) to calculate,
Wn_i+1＝KnSn_i+1＝Kn(Sn_i+ΔSn_i) (3)
and delta Sn _ i is the capacity of the transformer for completing the construction of newly added operation in the ith year.
Example two
A method for predicting electric quantity based on capacity utilization hours comprises the following steps:
the method comprises the following steps: calculating to obtain the average utilization hours of the capacity of a certain business n;
step two: calculating to obtain the increase smoothness of the industry n in the specific year in the number of m years in the step one;
step three: judging whether an inflection point and growth stability exist according to the growth value of the n industry in the specific year, the number of the m years;
step four: and predicting the electric quantity of the industries meeting different conditions.
The average number of hours of capacity utilization of a certain business n is calculated as follows:
when the i-th annual electric quantity of a certain business n is Wn _ i, the running capacity is Sn _ i, and the average utilization hour number of the capacity is Kn, Kn can be calculated by the formula (1):
in the above formula, m represents the number of years counted.
The method for calculating the growth smoothness of the industry n in a specific year in parts of m years comprises the following steps:
the increment of the electric quantity of the ith year relative to the previous year is delta Wn _ i, and the average increment of the m years is
Defining the growth smoothness Hn _ m of the industry n in m years as shown in the formula (2),
and setting a limit value epsilon, wherein for the industry with a larger Hn _ m value (Hn _ m > epsilon), the growth of the industry is not stable, otherwise, the growth is relatively stable, and for the condition that delta Wi & delta Wi-1 is less than 0, an inflection point appears in the growth, and the growth trend changes rapidly.
Judging whether an inflection point and a growth stability score exist in the growth value of the industry n in the specific year number of m years;
setting conditions B as delta Wi & delta Wi-1>0 and overall Hn _ m > epsilon in all years;
the electric quantity prediction method meeting the condition B industry reflects that the electric quantity growth is obviously changed due to the industry policy, so that the change of the main economic development index GDP is predicted in more detail by using the small utilization of the segment capacity, wherein the formula (1) is adjusted to the formula (4),
where p represents the number of segments according to GDP, Kn-j represents the number of hours of capacity utilization in the j-th segment, and the duration is relatively smooth due to certain continuity of economic promotion policy, but the segment is mainly used for processing the fluctuation at the beginning of the establishment.
EXAMPLE III
A method for predicting electric quantity based on capacity utilization hours comprises the following steps:
the method comprises the following steps: calculating to obtain the average utilization hours of the capacity of a certain business n;
step two: calculating to obtain the increase smoothness of the industry n in the specific year in the number of m years in the step one;
step three: judging whether an inflection point and growth stability exist according to the growth value of the n industry in the specific year, the number of the m years;
step four: and predicting the electric quantity of the industries meeting different conditions.
The average number of hours of capacity utilization of a certain business n is calculated as follows:
when the i-th annual electric quantity of a certain business n is Wn _ i, the running capacity is Sn _ i, and the average utilization hour number of the capacity is Kn, Kn can be calculated by the formula (1):
in the above formula, m represents the number of years counted.
The method for calculating the growth smoothness of the industry n in a specific year in parts of m years comprises the following steps:
year i relative to the previous yearThe increment of the electric quantity is delta Wn _ i, and the average increment of m years isDefining the growth smoothness Hn _ m of the industry n in m years as shown in the formula (2),
and setting a limit value epsilon, wherein for the industry with a larger Hn _ m value (Hn _ m > epsilon), the growth of the industry is not stable, otherwise, the growth is relatively stable, and for the condition that delta Wi & delta Wi-1 is less than 0, an inflection point appears in the growth, and the growth trend changes rapidly.
Judging whether an inflection point and a growth stability score exist in the growth value of the industry n in the specific year number of m years;
setting condition C to the presence of one or more years Δ Wi-1<0 and Hn _ m > ε;
and if the electric quantity prediction method in the industry meeting the condition C is met, increasing sections of inflection points.
Calculating the segment of the inflection point, wherein the number of times of occurrence of delta Wi & delta Wi-1<0 in m years is q, the first occurrence is l years, l < ═ m, the electric quantity of the current year is recorded as Wn _ l, the electric quantity of the q-th corresponding year is Wl + delta mq-1, and delta mq-1 represents the difference between the q-th time and the 1-th time; and adopting an electric quantity calculation method of the condition B in each section.
Example four
A method for predicting electric quantity based on capacity utilization hours comprises the following steps:
the method comprises the following steps: calculating to obtain the average utilization hours of the capacity of a certain business n;
step two: calculating to obtain the increase smoothness of the industry n in the specific year in the number of m years in the step one;
step three: judging whether an inflection point and growth stability exist according to the growth value of the n industry in the specific year, the number of the m years;
step four: and predicting the electric quantity of the industries meeting different conditions.
The average number of hours of capacity utilization of a certain business n is calculated as follows:
when the i-th annual electric quantity of a certain business n is Wn _ i, the running capacity is Sn _ i, and the average utilization hour number of the capacity is Kn, Kn can be calculated by the formula (1):
in the above formula, m represents the number of years counted.
The method for calculating the growth smoothness of the industry n in a specific year in parts of m years comprises the following steps:
the increment of the electric quantity of the ith year relative to the previous year is delta Wn _ i, and the average increment of the m years is
Defining the growth smoothness Hn _ m of the industry n in m years as shown in the formula (2),
and setting a limit value epsilon, wherein for the industry with a larger Hn _ m value (Hn _ m > epsilon), the growth of the industry is not stable, otherwise, the growth is relatively stable, and for the condition that delta Wi & delta Wi-1 is less than 0, an inflection point appears in the growth, and the growth trend changes rapidly.
Judging whether an inflection point and a growth stability score exist in the growth value of the industry n in the specific year number of m years;
the other cases than the first to third conditions A, B, C of the above-described embodiments are set as the condition D.
The condition D is met, the total stable electricity consumption of the industry is shown, but inflection points appear locally, and the industry is generally the traditional industry. And (4) segmenting at the inflection point, and adopting an electric quantity prediction method of the condition A in each segment.
Compared with the general intelligent algorithm for predicting the electric quantity, the method is simpler and more feasible, avoids uncertainty caused by self-learning in parameter estimation in the intelligent algorithm, ensures that when a periodic electric quantity prediction result is issued as a decision basis, the method is more accurate, the data change is stable, the load actually runs, the public confidence is stronger, and the social recognition is facilitated. The method adopts a linear prediction method, is more adaptive to the electric quantity change characteristic than the ordinary non-intelligent methods such as quadratic or spline curve prediction and the like, avoids the occurrence of abnormal distortion points, and can more accurately control the investment scale when being used for guiding the planning and construction of the power grid.
The working process of the invention is described by taking a power grid in a certain area as an example as follows:
(1) acquiring GDP statistical data of various industries of economic development of the region;
(2) acquiring annual electric quantity statistical data of various industries in the region;
(3) calculating the growth smoothness index Hn _ m of each industry;
(4) determining an industry adaptive condition, and predicting electric quantity;
the curve corresponding to the smoother change is shown in figure 1,
the prediction data in 2017 can be calculated by adopting the formula (3).
For the condition B that the growth trend is not stable, as shown in fig. 2, the capacity utilization hour is calculated by using the formula (4) in a segmented manner, and then the predicted power consumption value in 2017 is calculated by using the formula (3).
Here, 5 segments are taken according to GDP, and each industry is segmented and accessed as follows:
1) coal mining and washing industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 1397. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 1125.
When GDP is more than or equal to 5% and less than or equal to 10%, K value is 1507. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 1032
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1764. GDP is more than or equal to-20% and less than or equal to-10%, K value is 1032, and K value is 985.
2) Ferrous metal ore mining and dressing industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 1218. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 1125.
When the GDP is more than or equal to 5 percent and less than or equal to 10 percent, the K value is 1588. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 1137
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1957. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1042.
3) Non-metallic mineral product industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 2527. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 2423.
When GDP is more than or equal to 5 percent and less than or equal to 10 percent, the K value is 2631. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 2162
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 2936. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1790.
4) Ferrous metal smelting and calendering
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 2211. GDP is more than or equal to 5 percent and less than or equal to 0 percent, and the K value is 2148.
When GDP is more than or equal to 5% and less than or equal to 10%, K value is 2419. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 2086
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 2728. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 2052.
5) Non-ferrous metal smelting and rolling processing industry
When GDP is more than or equal to 0 and less than or equal to 10 percent, the K value is 1532. GDP is more than or equal to-10% and less than or equal to 0%, and the K value is 1336.
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1607. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1257
When the GDP is more than or equal to 20% and less than or equal to 30%, the K value is 2815. GDP is more than or equal to-30 percent and less than or equal to-20 percent, and the K value is 1058.
For the corner having a corner satisfying C, as shown in fig. 3, the corner segmentation process according to condition 4,
here, 5 segments are taken according to GDP, and each industry is segmented and accessed as follows:
1) coal mining and washing industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 1397. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 1125.
When GDP is more than or equal to 5% and less than or equal to 10%, K value is 1507. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 1032
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1764. GDP is more than or equal to-20% and less than or equal to-10%, K value is 1032, and K value is 985.
2) Ferrous metal ore mining and dressing industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 1218. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 1125.
When the GDP is more than or equal to 5 percent and less than or equal to 10 percent, the K value is 1588. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 1137
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1957. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1042.
3) Non-metallic mineral product industry
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 2527. GDP is more than or equal to-5% and less than or equal to 0%, and the K value is 2423.
When GDP is more than or equal to 5 percent and less than or equal to 10 percent, the K value is 2631. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 2162
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 2936. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1790.
4) Ferrous metal smelting and calendering
When GDP is more than or equal to 0 and less than or equal to 5 percent, the K value is 2211. GDP is more than or equal to 5 percent and less than or equal to 0 percent, and the K value is 2148.
When GDP is more than or equal to 5% and less than or equal to 10%, K value is 2419. GDP is more than or equal to-10% and less than or equal to-5%, and K value is 2086
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 2728. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 2052.
5) Non-ferrous metal smelting and rolling processing industry
When GDP is more than or equal to 0 and less than or equal to 10 percent, the K value is 1532. GDP is more than or equal to-10% and less than or equal to 0%, and the K value is 1336.
When the GDP is more than or equal to 10 percent and less than or equal to 20 percent, the K value is 1607. GDP is more than or equal to-20 percent and less than or equal to-10 percent, and the K value is 1257
When the GDP is more than or equal to 20% and less than or equal to 30%, the K value is 2815. GDP is more than or equal to-30 percent and less than or equal to-20 percent, and the K value is 1058.
The electric quantity prediction results and result error analysis of each industry are shown in the attached figure 4.
The embodiments described above are only preferred embodiments of the invention and are not exhaustive of the possible implementations of the invention. Any obvious modifications to the above would be obvious to those of ordinary skill in the art, but would not bring the invention so modified beyond the spirit and scope of the present invention.
Claims (10)
1. A method for predicting electric quantity based on capacity utilization hours is characterized by comprising the following steps:
the method comprises the following steps: calculating to obtain the average utilization hours of the capacity of a certain business n;
step two: calculating to obtain the increase smoothness of the industry n in the specific year in the number of m years in the step one;
step three: judging whether an inflection point and growth stability exist according to the growth value of the n industry in the specific year, the number of the m years;
step four: and predicting the electric quantity of the industries meeting different conditions.
2. The method of claim 1, wherein the capacity utilization hours based power prediction method comprises: the average number of hours of capacity utilization of a certain business n is calculated as follows:
the i-th annual electric quantity of a certain business n is Wn_iAt a transport capacity of Sn_iThe number of capacity average utilization hours is KnThen K isnCan be calculated by the formula (1):
in the above formula, m represents the number of years counted.
3. The method of claim 2, wherein the capacity utilization hours based power prediction method comprises: the method for calculating the growth smoothness of the industry n in a specific year in parts of m years comprises the following steps:
the increment of the electric quantity of the ith year relative to the previous year is delta Wn_iAverage increment of m years isDefining the growth smoothness H of the industry n in m yearsn_mIs shown in a formula (2),
setting a limit value epsilon for Hn_mHigh value industry (H)n_m>Epsilon) indicates that the industry is not growing smoothly, and vice versa, for Δ Wi·ΔWi-1<The case of 0 indicates that an inflection point appears in the growth, and the growth trend changes sharply.
4. The method of claim 3, wherein the capacity utilization hours based power prediction method comprises: judging whether the inflection point and the growth stability exist in the growth value of the industry n in a specific year, namely m years or not is divided into four conditions:
1) setting the condition A as Δ W for all yearsi·ΔWi-1>0 and overall Hn_m<ε；
2) Setting the condition B as DeltaW for all yearsi·ΔWi-1>0 and overall Hn_m>ε；
3) Setting condition C as the presence of one or more years Δ Wi·ΔWi-1<0 and Hn_m>ε；
4) The other case is set as condition D.
5. The method of claim 4, wherein the capacity utilization hours based power prediction method comprises:
the electric quantity prediction method meeting the condition A industry adopts the formula (3) to calculate,
Wn_i+1＝KnSn_i+1＝Kn(Sn_i+ΔSn_i) (3)
wherein, Delta Sn_iAnd the capacity of the newly added and put into operation transformer is built for the ith year.
6. The method of claim 4, wherein the capacity utilization hours based power prediction method comprises:
the electric quantity prediction method meeting the condition B industry reflects that the electric quantity growth is obviously changed due to the industry policy, so that the change of the main economic development index GDP is predicted in more detail by using the small utilization of the segment capacity, wherein the formula (1) is adjusted to the formula (4),
where p represents the number of segments according to GDP, Kn-jThe number of hours of capacity utilization representing the jth segment is stable due to certain continuity of economic promotion policies, but the segment is mainly used for processing fluctuation at the beginning of the establishment.
7. The method of claim 4, wherein the capacity utilization hours based power prediction method comprises: and if the electric quantity prediction method in the industry meeting the condition C is met, increasing sections of inflection points.
8. The method of claim 7, wherein the capacity utilization hours based power prediction method comprises: the calculation of the segments of the inflection points, assuming that Δ W occurs in m yearsi·ΔWi-1<The number of 0 is q, the first occurrence is l years, l<M, the current year electricity is marked as Wn_lThe electric quantity of the q-th corresponding year is Wl+Δmq-1Wherein Δ mq-1 represents the difference between the qth and 1 st times; and adopting an electric quantity calculation method of the condition B in each section.
9. The method of claim 4, wherein the capacity utilization hours based power prediction method comprises: the satisfaction of the condition D shows that the power consumption of the industry is generally stable, but inflection points occur locally.
10. The method of claim 9, wherein the capacity utilization hours based power prediction method comprises: and (4) segmenting at the inflection point, and adopting an electric quantity prediction method of the condition A in each segment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910981522.7A CN110705806B (en) | 2019-10-16 | 2019-10-16 | Electric quantity prediction method based on capacity utilization hours |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910981522.7A CN110705806B (en) | 2019-10-16 | 2019-10-16 | Electric quantity prediction method based on capacity utilization hours |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110705806A true CN110705806A (en) | 2020-01-17 |
| CN110705806B CN110705806B (en) | 2023-04-07 |
Family
ID=69199753
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910981522.7A Active CN110705806B (en) | 2019-10-16 | 2019-10-16 | Electric quantity prediction method based on capacity utilization hours |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110705806B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598357A (en) * | 2020-05-29 | 2020-08-28 | 江苏蔚能科技有限公司 | Monthly power consumption prediction method based on capacity utilization hours and Gaussian distribution |
| CN111784083A (en) * | 2020-08-06 | 2020-10-16 | 国网湖南省电力有限公司 | Prediction model establishing method based on electric power big data and power grid load scheduling method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104517160A (en) * | 2014-12-18 | 2015-04-15 | 国网冀北电力有限公司 | Novel electricity market prediction system and method based on capacity utilization characteristics |
| US20160188753A1 (en) * | 2014-12-25 | 2016-06-30 | State Grid Corporation Of China | Power Grid Development Stage Division Method Based on Logistic Model |
| CN109858728A (en) * | 2018-12-03 | 2019-06-07 | 国网浙江省电力有限公司台州供电公司 | Load forecasting method based on branch trade Analysis of Electrical Characteristics |
-
2019
- 2019-10-16 CN CN201910981522.7A patent/CN110705806B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104517160A (en) * | 2014-12-18 | 2015-04-15 | 国网冀北电力有限公司 | Novel electricity market prediction system and method based on capacity utilization characteristics |
| US20160188753A1 (en) * | 2014-12-25 | 2016-06-30 | State Grid Corporation Of China | Power Grid Development Stage Division Method Based on Logistic Model |
| CN109858728A (en) * | 2018-12-03 | 2019-06-07 | 国网浙江省电力有限公司台州供电公司 | Load forecasting method based on branch trade Analysis of Electrical Characteristics |
Non-Patent Citations (1)
| Title |
|---|
| 程超: "基于时间序列法和回归分析法的改进月售电量预测方法研究", 《CNKI中国知网》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598357A (en) * | 2020-05-29 | 2020-08-28 | 江苏蔚能科技有限公司 | Monthly power consumption prediction method based on capacity utilization hours and Gaussian distribution |
| CN111598357B (en) * | 2020-05-29 | 2023-08-08 | 江苏蔚能科技有限公司 | Month electricity consumption prediction method based on capacity utilization hours and Gaussian distribution |
| CN111784083A (en) * | 2020-08-06 | 2020-10-16 | 国网湖南省电力有限公司 | Prediction model establishing method based on electric power big data and power grid load scheduling method |
| CN111784083B (en) * | 2020-08-06 | 2023-11-21 | 国网湖南省电力有限公司 | Prediction model establishment method based on electric power big data and power grid load scheduling method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110705806B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ye et al. | A novel forecasting method based on multi-order fuzzy time series and technical analysis | |
| Li et al. | Clothing sale forecasting by a composite GRU–Prophet model with an attention mechanism | |
| CN111353656A (en) | Steel enterprise oxygen load prediction method based on production plan | |
| CN109685277A (en) | Electricity demand forecasting method and device | |
| CN110705806B (en) | Electric quantity prediction method based on capacity utilization hours | |
| CN109242169B (en) | Short-term load prediction method for large power customer | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| Wang et al. | Strip hardness prediction in continuous annealing using multiobjective sparse nonlinear ensemble learning with evolutionary feature selection | |
| CN116526473A (en) | Particle swarm optimization LSTM-based electrothermal load prediction method | |
| CN106780018A (en) | A kind of stock certificate data mining model reappeared based on history and system | |
| CN113705929A (en) | Spring festival holiday load prediction method based on load characteristic curve and typical characteristic value fusion | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| Tundo et al. | Fuzzy Inference System Tsukamoto–Decision Tree C 4.5 in Predicting the Amount of Roof Tile Production in Kebumen | |
| CN109214610B (en) | Saturated power load prediction method based on long-term and short-term memory neural network | |
| CN113177355B (en) | Power load prediction method | |
| Xian et al. | A novel fuzzy time series model based on improved sparrow search algorithm and CEEMDAN | |
| CN117521511A (en) | Granary temperature prediction method based on improved wolf algorithm for optimizing LSTM | |
| CN117390960A (en) | Intelligent analysis method for machining precision of numerical control machine tool | |
| CN115936184B (en) | Load prediction matching method suitable for multi-user types | |
| CN109919389B (en) | Sea surface temperature time sequence prediction method based on PSO (particle swarm optimization) double-objective optimization | |
| Li et al. | Forex prediction based on SVR optimized by artificial fish swarm algorithm | |
| Liu | The prediction model and system of stock rise and fall based on BP neural network | |
| CN114820086A (en) | Agricultural industry chain data processing method and agricultural industry transaction flow prediction system | |
| CN115271256A (en) | Intelligent ordering method under multi-dimensional classification | |
| Yoon et al. | Methodology for improving the performance of demand forecasting through machine learning |
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 |