CN111949940B - Transformer overload prediction method, system and storage medium for transformer area based on regression model - Google Patents
Transformer overload prediction method, system and storage medium for transformer area based on regression model Download PDFInfo
- Publication number
- CN111949940B CN111949940B CN202010595692.4A CN202010595692A CN111949940B CN 111949940 B CN111949940 B CN 111949940B CN 202010595692 A CN202010595692 A CN 202010595692A CN 111949940 B CN111949940 B CN 111949940B
- Authority
- CN
- China
- Prior art keywords
- transformer
- overload
- load
- tendency
- prediction
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000002045 lasting effect Effects 0.000 claims abstract description 12
- 230000005611 electricity Effects 0.000 claims description 15
- 238000013178 mathematical model Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 2
- 230000006698 induction Effects 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000001131 transforming effect Effects 0.000 abstract description 2
- 238000012886 linear function Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000003102 growth factor Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression 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
- G06Q10/04—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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Optimization (AREA)
- General Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Mathematical Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Water Supply & Treatment (AREA)
- Algebra (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to a transformer overload prediction technology for a transformer area, which is a regression model-based transformer overload prediction method, a regression model-based transformer overload prediction system and a regression model-based transformer overload prediction storage medium, can effectively predict the overload condition of a transformer area, and provides powerful data support for a routing inspection plan and a transformer upgrading and transforming plan. The method comprises the following steps: screening the transformer with the maximum load lasting for more than a preset time as an overload tendency transformer according to the filling coefficient of the transformer load curve, and acquiring the minimum value of the load rate of the overload tendency occurrence interval; predicting the annual power utilization maximum load value of a plurality of years through a regression model to obtain a load increase coefficient of two adjacent years; and according to the prediction result, the minimum value of the load rate of the overload tendency generation interval of the overload tendency transformer in the next year is obtained through prediction by combining the minimum value of the load rate of the overload tendency generation interval of the overload tendency transformer and the load growth coefficients of two adjacent years, so that a prediction list of the overload transformer is obtained.
Description
Technical Field
The invention relates to a transformer overload prediction technology in a transformer area, in particular to a transformer overload prediction method, a transformer overload prediction system and a storage medium in the transformer area based on a regression model.
Background
The distribution transformer area is used as the last level power supply unit facing low-voltage users, and the running state of the power supply equipment of the distribution transformer area directly influences the power supply quality in the distribution transformer area. The heavy overload operation of the equipment is one of the main reasons causing failure and power failure, and the heavy overload phenomenon is usually accompanied by three-phase imbalance, voltage deviation and other problems, which seriously affect the safe and reliable power utilization of users. In addition, the equipment is in a heavy overload state for a long time, so that abnormal loss of elements is accelerated, the service life of the equipment is shortened, and fault hidden dangers and operation risks are brought to a power grid. Therefore, heavy overload management in the distribution area is always an important content of operation, maintenance and overhaul work of the distribution network.
Disclosure of Invention
The invention provides a transformer overload prediction method, a transformer overload prediction system and a storage medium based on a regression model, which are combined with historical overload or overload tendency data, and the load condition of a transformer in a transformer area is predicted and evaluated through a regression prediction maximum load theoretical model, so that the overload condition of the transformer in the transformer area can be effectively predicted, and powerful data support is provided for an inspection plan and a transformer upgrading and reconstruction plan.
The transformer overload prediction method based on the regression model comprises the following steps:
s1, according to the filling coefficient of the transformer load curve, screening the transformer with the maximum load lasting for more than a preset time as an overload tendency transformer, wherein the lasting preset time is an overload tendency generation interval; acquiring the minimum instantaneous load rate of the overload tendency transformer in the overload tendency generation interval as the minimum load rate of the overload tendency generation interval;
s2, predicting the annual power utilization maximum load value of the region to which the transformer belongs for several years through a regression model; obtaining the load increase coefficient of the adjacent two years in the area according to the maximum annual power utilization load value of the adjacent two years;
and S3, according to the prediction result of the regression model on the annual maximum load value of the regional power consumption of several years, judging whether the product of the load growth coefficient of two adjacent years and the minimum load rate of the overload tendency occurrence interval of a certain year is greater than 1 or not by combining the load growth coefficient of two adjacent years and the minimum load rate of the overload tendency occurrence interval of the certain year, and thus obtaining the prediction list of the overload transformer in the next year of the certain year.
The transformer overload prediction system based on the regression model comprises:
the overload tendency transformer screening module is used for screening the transformer with the maximum load lasting for more than a preset time as the overload tendency transformer according to the filling coefficient of the transformer load curve, and the lasting preset time is an overload tendency generation interval; acquiring the minimum instantaneous load rate of the overload tendency transformer in the overload tendency generation interval as the minimum load rate of the overload tendency generation interval;
the annual electricity maximum load value prediction module is used for predicting annual electricity maximum load values of a plurality of years in a region to which the transformer belongs through a regression model and obtaining load growth coefficients of two adjacent years in the region according to the annual electricity maximum load values of the two adjacent years;
and the overload transformer prediction module is used for judging whether the product of the load growth coefficient of two adjacent years and the minimum load rate of the overload tendency generation interval of a certain year is greater than 1 according to the prediction result of the regression model on the annual maximum load value of the area of a plurality of years, so as to obtain the next-year overload transformer prediction list of the certain year.
According to the storage medium of the present invention, computer instructions are stored thereon, and when the computer instructions are executed by a processor, the steps of the transformer overload prediction method of the present invention are realized.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention firstly applies the regression prediction maximum load theoretical model and the historical overload or overload tendency transformer actual data to the transformer overload assessment method of the transformer area, and the transformer overload assessment method of the transformer area spans the theoretical model and the actual data and utilizes the actual load data and the prediction growth rate coefficient to carry out overload prediction, thereby scientifically and effectively providing data support for the routing inspection plan and the transformer upgrading and reconstruction plan.
2. The method not only considers the transformer data with overload or overload tendency due to high load rate of historical continuous set time (for example, more than or equal to 2 hours), but also indirectly predicts the future transformer overload condition by predicting the maximum load value increase ratio, and is mainly used for finding out heavy overload hidden danger in time and arranging an optimized equipment upgrading and transforming plan.
Drawings
FIG. 1 is a flow chart of a transformer overload prediction method for a transformer area based on a regression model;
fig. 2 is a graph showing a load factor in an overload tendency occurrence interval.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, but the present invention is not limited thereto.
Referring to fig. 1, the method for predicting transformer overload in a transformer area based on a regression model includes the following steps:
step one, screening overload tendency transformers
The load capacity of a transformer is related to many factors, but is largely related to three aspects, namely the ambient temperature, the fill factor of the load curve and the duration of the maximum load. Therefore, the invention mainly considers from the three aspects, and the transformer with overload or overload trend (also called overload trend) is taken out through screening of effective rules according to the historical data of the transformer, and the change of the future load trend is judged through a regression model.
The overload of a transformer is typically defined as: instantaneous load rate (instantaneous power consumption) integral multiplying power/distribution capacity, instantaneous load rate FkThe calculation formula of (2) is self-defined as: fk＝(EkT)/C, wherein EkThe method is characterized in that the method is instantaneous power utilization, T is comprehensive multiplying power, C is distribution capacity, 96 points (namely, the instantaneous power utilization is collected once every 15 minutes and is also called as power load points) are set for collecting the instantaneous power utilization every day, and k is 1,2,3.. 96; and when the instantaneous load rate is greater than 1 and continues to be greater than or equal to 2 hours (namely at least 8 electric load points are continuously obtained), judging that the transformer is overloaded.
Since the overload operation capacity of the transformer is directly influenced by the ambient temperature, the ambient temperature is reduced, the overload capacity of the transformer is improved, and conversely, the overload capacity of the transformer is reduced when the ambient temperature is higher. Since the maximum electrical load generally continues to increase and is usually the highest in summer and winter, the overload screening range is reduced in order to better predict future overload transformers, whereby the screening range is defined as follows: when selecting the overload tendency transformer, data in a time period (such as 14:00-20:00) of 7 and 8 months afternoon with the highest ambient temperature are mainly selected.
The filling factor of the load curve of the transformer determines the overload capacity of the transformer, and the larger the filling factor of the load curve is, the lower the overload capacity of the transformer is, and vice versa, the higher the overload capacity of the transformer is, in the same time when the maximum load lasts. The filling factor of the load curve, also called load factor, represents the degree of unevenness of the load curve, and is expressed by the formula: kL＝Pav/PMAXI.e. the fill factor KLEqual to the average load PavDivided by the maximum load PMAX. Therefore, the transformer with the filling coefficient of the load curve larger than 0.5 can be screened, and the overload capacity of the transformer is relatively low. In the invention, the filling coefficient of the load curve reflects the average load condition in a period of time, namely the average load rate in a certain period of time.
When the filling factor is fixed, the longer the maximum load duration is, the lower the transformer overload capacity is, whereas the shorter the maximum load duration is, the higher the transformer overload capacity is. Therefore, according to the filling coefficient of the load curve of the transformer, the transformer with the maximum load lasting for more than a preset time (for example, 2 hours) is screened as the overload tendency transformer. For example, data in the time period (e.g. 14:00-20:00) of afternoon of 7 and 8 months of the last year may be screened, and a list of transformers with the filling factor of the load curve in the interval greater than 0.5 (which is the first preset value of the present embodiment) and the instantaneous load rate continuously exceeding 0.8 (which is the second preset value of the present embodiment) may be selected as the transformer with the overload tendency, and the time period occurring is referred to as the overload tendency occurrence interval. Then, the minimum instantaneous load rate of the transformer with overload tendency in the overload tendency occurrence interval (namely, the instantaneous load rate F in the overload tendency interval) is obtainedkCan be obtained by the minimum instantaneous power within the overload tendency interval), and is the minimum value of the load rate of the transformer with overload tendency in the overload tendency generation interval, which is simply called the minimum value of the load rate of the overload tendency generation interval
Where y is the year, as shown in FIG. 2.
Storage screenThe selected transformer with overload tendency has related data, such as number N of transformer, and minimum value of load rate between overload tendency occurrence intervals
Wherein the minimum instantaneous load rate is determined according to the instantaneous load rate FkWhen the instantaneous electricity consumption of the transformer with the overload tendency in the overload tendency occurrence interval is minimum, the corresponding instantaneous load rate is the minimum instantaneous load rate.
Step two, predicting the annual power utilization maximum load value (in the embodiment, the annual maximum power utilization load value) of the region of the transformer for a plurality of years through a regression model
In the step, various regression models (such as exponential functions, linear functions, power functions, logarithmic functions and polynomial functions) are selected for calculation by using data obtained from various items in the past year, the calculation results of the various regression models are compared with historical curves or error value calculation is carried out, and the regression model which best meets the actual situation is selected for predicting the future maximum load value.
According to the historical data of the maximum value of each load, various regression models (such as exponential function, linear function, power function, logarithmic function, polynomial function and the like) are selected for calculation, and the future maximum load value is predicted, so that the growth rate of the maximum load value is obtained. Predicting the annual electricity maximum load value of the next year as a dependent variable and the year of the next year as an independent variable, establishing a mathematical model, repeatedly calculating to complete the prediction of the annual electricity maximum load value of a plurality of years, and obtaining a load increase coefficient X of the transformer in the next year (for example, y 2) relative to the previous year (for example, y 1) according to the annual electricity maximum load values of the previous year and the next yeary1y2(the ratio of the maximum load value in y1 year to the maximum load value in y2 year), namely the load increase coefficients of two adjacent years.
In the process of establishing a mathematical model, after the annual power consumption maximum load value is respectively predicted by utilizing multiple types of regression models, counting and summarizing the prediction results of all the regression models, and carrying out visual verification on the prediction results of all the regression models (excluding the prediction result of extremely high growth rate) by combining the actual construction condition of a region so as to complete the comprehensive analysis of the actual condition and obtain the final power consumption load prediction result; and comparing the power load prediction waveform curve corresponding to the multi-type regression model with the historical load curve, screening the power load prediction waveform curve with the most similar overall trend, and selecting a regression model function corresponding to the power load prediction waveform curve as a mathematical model for load prediction.
That is, when the regression model is used for analysis, the analysis method is based on the analysis of the relationship between independent variables and dependent variables, and the analysis method needs to establish a mathematical regression equation (i.e. a mathematical model); and then using the historical data of multiple years for expansion to predict the maximum load value of each year.
In this embodiment, the following mathematical models are established by taking the maximum load value data of each year in a certain area as a dependent variable:
linear function: y ═ ax + b
Polynomial function: y is ax2+bx+c
Exponential function: y ═ aebx
Power function: y is axb
Logarithmic function: y ═ aln (x) + b
In the above mathematical model, Y is the maximum load value (MW) predicted in the next year, x is the year, a, b, and c are all regression coefficients, and the prediction results are shown in table 1.
TABLE 1 prediction of maximum load in future two years in a certain area
In table 1, the measured annual maximum load values between 2013 and 2019 are historical data; and 2020 and 2021 are predicted maximum load values for the next two years.
Step three, judging whether the transformer has overload tendency in a certain year according to the prediction result of the annual maximum power load value of the regression model for a plurality of years
According to regression model pairJudging whether a certain year (such as y1 years) has an overload tendency transformer or not according to the annual maximum power load value prediction result of a plurality of years, if not, eliminating, and if so, acquiring the minimum load rate value of the overload tendency transformer in the overload tendency occurrence interval in y1 years
Load increase coefficient X of y2 year relative to y1 year according to predictiony1y2Increase the load by a factor Xy1y2Minimum value of load rate of y1 year overload tendency occurrence interval
Multiplying, predicting to obtain the minimum value of the load rate of the overload tendency generation interval in y 2:
by judging the minimum value of the load rate of the y2 year overload tendency occurrence interval
And if the load rate of y2 year is more than 1, judging whether the load rate of y2 year is more than or equal to 100% for a preset time (for example, 2 hours) to obtain a prediction list of y2 year overload transformers.
In this embodiment, the maximum electrical load (i.e., the maximum load value) in 2020 is obtained by regression model prediction, and thus the load increase coefficient X is obtained20192020(if there is no special case, the mean can be calculated by weighted average) as shown in Table 2:
TABLE 2 load growth factor in 2019 and 2020 in certain area
The calculation formula of the minimum load rate of the overload tendency generation interval in 2020 is as follows:
in overload-prone transformers (N)
If 1 or more, N is predicted to be overloaded in 2020.
In addition, the invention also correspondingly provides a transformer overload prediction system based on the regression model, which comprises the following steps:
the overload tendency transformer screening module is used for realizing the step S1 of the invention, and screening the transformer with the maximum load lasting for more than a preset time as the overload tendency transformer according to the filling coefficient of the transformer load curve, wherein the lasting preset time is an overload tendency generation interval; acquiring the minimum instantaneous load rate of the overload tendency transformer in the overload tendency generation interval as the minimum load rate of the overload tendency generation interval;
the annual electricity maximum load value prediction module is used for realizing the step S2 of the invention, predicting annual electricity maximum load values of a plurality of years in the area to which the transformer belongs through a regression model, and obtaining load growth coefficients of two adjacent years in the area according to the annual electricity maximum load values of the two adjacent years;
and the overload transformer prediction module is used for realizing the step S3 of the invention, and judging whether the product of the load growth coefficient of two adjacent years and the load rate minimum value of the overload tendency occurrence interval of a certain year is more than 1 according to the prediction result of the regression model on the annual maximum load value of the area of a plurality of years, so as to obtain the next-year overload transformer prediction list of the certain year.
Based on the same concept, the present invention also proposes a storage medium having stored thereon computer instructions which, when executed by a processor, implement steps S1-S3 of the transformer overload prediction method of the present invention.
The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention is not limited thereby, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the protection scope of the present invention.
Claims (7)
1. The transformer overload prediction method based on the regression model is characterized by comprising the following steps of:
s1, according to the filling coefficient of the transformer load curve, screening the transformer with the maximum load lasting for more than a preset time as an overload tendency transformer, wherein the lasting preset time is an overload tendency generation interval; acquiring the minimum instantaneous load rate of the overload tendency transformer in the overload tendency generation interval as the minimum load rate of the overload tendency generation interval;
s2, predicting the annual power utilization maximum load value of the region to which the transformer belongs for several years through a regression model; obtaining the load increase coefficient of the adjacent two years in the area according to the maximum annual power utilization load value of the adjacent two years;
s3, according to the prediction result of the regression model on the annual maximum load value of the regional power consumption of several years, judging whether the product of the load growth coefficient of two adjacent years and the minimum load rate of the overload tendency occurrence interval of a certain year is greater than 1 or not by combining the load growth coefficient of two adjacent years and the minimum load rate of the overload tendency occurrence interval of the certain year, and thus obtaining a prediction list of the overload transformer of the next year of the certain year;
step S1, taking the transformer with overload or overload tendency out through screening of effective rules according to the historical data of the transformer in consideration of the load capacity of the transformer, the environmental temperature, the filling coefficient of a load curve and the duration of the maximum load, and judging the change of the future load trend through a regression model; selecting a transformer list with the filling coefficient of a load curve in an overload tendency generation interval larger than a first preset value and the instantaneous load rate continuously exceeding a second preset value in the overload tendency generation interval as an overload tendency transformer;
storing relevant data of the screened transformer with the overload tendency, wherein the relevant data comprises a transformer number N and a load rate minimum value of an overload tendency occurrence interval; when the instantaneous electricity consumption of the overload tendency transformer in the overload tendency occurrence interval is minimum, the corresponding instantaneous load rate is the minimum instantaneous load rate.
2. The method for predicting transformer overload of distribution room according to claim 1, wherein the first preset value is 0.5, and the second preset value is 0.8.
3. The transformer overload prediction method according to claim 1, wherein in step S2, the maximum annual power load value of the past year is predicted as a dependent variable and the year of the past year is predicted as an independent variable, a mathematical model is established, and the prediction of the maximum annual power load value for several years is completed by repeated calculations.
4. The transformer overload prediction method of the transformer area according to claim 3, wherein in the establishment process of the mathematical model, after the annual power utilization maximum load value is predicted by using multiple types of regression models respectively, the prediction results of all the regression models are subjected to statistical induction, the prediction results of all the regression models are subjected to visual verification by combining the actual construction conditions of the area, the prediction results of the extremely high growth rate are eliminated, the comprehensive analysis of the actual conditions is completed, and the final power utilization load prediction result is obtained; and comparing the power load prediction waveform curve corresponding to the multi-type regression model with the historical load curve, screening the power load prediction waveform curve with the most similar overall trend, and selecting a regression model function corresponding to the power load prediction waveform curve as a mathematical model for load prediction.
5. The transformer overload prediction method of claim 1, wherein in step S3, after the minimum value of the overload tendency occurrence interval load rates of the next year of the certain year is obtained through prediction, the prediction list of the overload transformers of the next year of the certain year is obtained by determining whether the minimum value of the overload tendency occurrence interval load rates of the next year of the certain year is greater than 1.
6. Transformer overload prediction system of transformer district based on regression model, its characterized in that includes:
the overload tendency transformer screening module is used for screening the transformer with the maximum load lasting for more than a preset time as the overload tendency transformer according to the filling coefficient of the transformer load curve, and the lasting preset time is an overload tendency generation interval; acquiring the minimum instantaneous load rate of the overload tendency transformer in the overload tendency generation interval as the minimum load rate of the overload tendency generation interval;
the annual electricity maximum load value prediction module is used for predicting annual electricity maximum load values of a plurality of years in a region to which the transformer belongs through a regression model and obtaining load growth coefficients of two adjacent years in the region according to the annual electricity maximum load values of the two adjacent years;
the overload transformer prediction module is used for judging whether the product of the load growth coefficient of two adjacent years and the minimum load rate of an overload tendency generation interval of a certain year is greater than 1 according to the prediction result of the regression model on the annual maximum load value of the area of a plurality of years, so as to obtain a next-year overload transformer prediction list of the certain year;
the overload tendency transformer screening module takes the overload or overload tendency transformer out through effective rule screening according to the historical data of the transformer in consideration of the three aspects of the load capacity and the environmental temperature of the transformer, the filling coefficient of a load curve and the duration time of the maximum load, and then judges the change of the future load tendency of the overload or overload tendency transformer through a regression model; selecting a transformer list with the filling coefficient of a load curve in an overload tendency generation interval larger than a first preset value and the instantaneous load rate continuously exceeding a second preset value in the overload tendency generation interval as an overload tendency transformer;
storing relevant data of the screened transformer with the overload tendency, wherein the relevant data comprises a transformer number N and a load rate minimum value of an overload tendency occurrence interval; when the instantaneous electricity consumption of the overload tendency transformer in the overload tendency occurrence interval is minimum, the corresponding instantaneous load rate is the minimum instantaneous load rate.
7. Storage medium having stored thereon computer instructions, characterized in that said computer instructions, when executed by a processor, carry out the steps of the transformer overload prediction method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010595692.4A CN111949940B (en) | 2020-06-28 | 2020-06-28 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010595692.4A CN111949940B (en) | 2020-06-28 | 2020-06-28 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111949940A CN111949940A (en) | 2020-11-17 |
| CN111949940B true CN111949940B (en) | 2021-08-13 |
Family
ID=73337223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010595692.4A Active CN111949940B (en) | 2020-06-28 | 2020-06-28 | Transformer overload prediction method, system and storage medium for transformer area based on regression model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111949940B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107704963A (en) * | 2017-10-13 | 2018-02-16 | 国电南瑞科技股份有限公司 | A kind of charging electric vehicle load forecasting method for considering spatial and temporal distributions |
| CN109117974A (en) * | 2017-06-26 | 2019-01-01 | 中国电力科学研究院 | A kind of distribution net platform region heavy-overload methods of risk assessment and device |
| CN109242132A (en) * | 2018-06-05 | 2019-01-18 | 国网江苏省电力有限公司南通供电分公司 | Subregion peak load prediction technique based on MapReduce frame |
| CN109546652A (en) * | 2018-12-24 | 2019-03-29 | 国网湖南省电力有限公司 | The Methods of electric load forecasting of distribute-electricity transformer district |
| CN110009136A (en) * | 2019-03-12 | 2019-07-12 | 国网江西省电力有限公司电力科学研究院 | A kind of load forecasting method of distribution transformer and distribution line |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109978318B (en) * | 2018-12-21 | 2020-12-29 | 广东电网有限责任公司 | Low-voltage transformer area low-voltage risk assessment method based on distribution network load prediction |
| CN110263995B (en) * | 2019-06-18 | 2022-03-22 | 广西电网有限责任公司电力科学研究院 | Distribution transformer overload prediction method considering load increase rate and user power utilization characteristics |
| CN110807550B (en) * | 2019-10-30 | 2023-11-24 | 国网上海市电力公司 | Distribution transformer overload recognition and early warning method based on neural network and terminal equipment |
-
2020
- 2020-06-28 CN CN202010595692.4A patent/CN111949940B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117974A (en) * | 2017-06-26 | 2019-01-01 | 中国电力科学研究院 | A kind of distribution net platform region heavy-overload methods of risk assessment and device |
| CN107704963A (en) * | 2017-10-13 | 2018-02-16 | 国电南瑞科技股份有限公司 | A kind of charging electric vehicle load forecasting method for considering spatial and temporal distributions |
| CN109242132A (en) * | 2018-06-05 | 2019-01-18 | 国网江苏省电力有限公司南通供电分公司 | Subregion peak load prediction technique based on MapReduce frame |
| CN109546652A (en) * | 2018-12-24 | 2019-03-29 | 国网湖南省电力有限公司 | The Methods of electric load forecasting of distribute-electricity transformer district |
| CN110009136A (en) * | 2019-03-12 | 2019-07-12 | 国网江西省电力有限公司电力科学研究院 | A kind of load forecasting method of distribution transformer and distribution line |
Non-Patent Citations (2)
| Title |
|---|
| Heavy Overload Forecasting of Distribution Transformers Based on XGBoost;Qian WU 等;《2019 IEEE PES Asia-Pacific Power and Energy Engineering Conference 》;20200213;第1-5页 * |
| 长汀电网负荷预测及低电压问题的应用研究;谢志坤;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20190515(第（2019）05期);C042-782 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111949940A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190792B (en) | Method and system for determining configuration of distributed power supply in power distribution network | |
| CN110490454B (en) | Distribution network asset operation efficiency calculation method based on distribution network equipment operation efficiency evaluation | |
| CN112668943A (en) | Distribution line health state assessment method and system | |
| CN111310980B (en) | Distribution transformer optimization method considering load distribution and economic operation interval dynamic reconstruction | |
| CN114006410B (en) | Large-scale offshore wind power access point optimization method based on opportunity constraint planning | |
| CN117895579A (en) | Cooperative operation control method, device and equipment of power grid equipment and storage medium | |
| Baroni et al. | Impact of photovoltaic generation on the allowed revenue of the utilities considering the lifespan of transformers: A Brazilian case study | |
| CN107563641B (en) | Disaster-resistant multi-scene differentiation planning method for power distribution network considering disaster preference | |
| CN111949940B (en) | Transformer overload prediction method, system and storage medium for transformer area based on regression model | |
| CN110957724A (en) | Method for evaluating operation mode and grid structure of power distribution network | |
| Leite et al. | Risk mitigation approaches for improved resilience in distribution networks | |
| CN113629733A (en) | Rapid frequency response reserve capacity planning method considering risk preference | |
| CN113793022A (en) | Power grid investment planning scheme generation method and system based on distributed cloud energy storage | |
| CN113326655A (en) | Comprehensive evaluation method and device for reliability and economy of radiation type power distribution network | |
| CN108879662B (en) | Power distribution network sequential control transformation decision method based on safety efficiency cost | |
| CN112381377A (en) | Power grid connection mode evaluation method, device, equipment and storage medium | |
| Mina Mirbagheri et al. | Hosting Capacity analysis: A review and a new evaluation method in case of parameters uncertainty and multi-generator | |
| JP7508318B2 (en) | System cross section generation device, system cross section generation method, and program | |
| CN115829323A (en) | Safety risk assessment method and system for photovoltaic-charging pile-variable frequency load system | |
| CN117744977A (en) | Power distribution network planning determination method, device, equipment, storage medium and program product | |
| Zhu et al. | Research on Wind Power Capacity Evaluation Based on Risk Theory and Unit Commitment Under Multi-Scenarios | |
| CN118449261A (en) | Intelligent detection management method and system for load of public transformer area | |
| CN118195354A (en) | Power distribution system cost evaluation method based on full life cycle | |
| CN118505027A (en) | Low-voltage distribution network area planning method | |
| KR20220109885A (en) | Method of assessment of sectional load and generating capacity in the distribution system |
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 |