CN102175202A - Ice cover thickness predicting method based on fuzzy logic - Google Patents
Ice cover thickness predicting method based on fuzzy logic Download PDFInfo
- Publication number
- CN102175202A CN102175202A CN 201110031728 CN201110031728A CN102175202A CN 102175202 A CN102175202 A CN 102175202A CN 201110031728 CN201110031728 CN 201110031728 CN 201110031728 A CN201110031728 A CN 201110031728A CN 102175202 A CN102175202 A CN 102175202A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- covering thickness
- ice covering
- icing
- fuzzy logic
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an ice cover thickness predicting method based on fuzzy logic. The method comprises the following steps of: firstly acquiring ice cover data: ambient temperature, ambient humidity, ambient wind speed and lead temperature; then, establishing an ice cover thickness predicting model; and finally obtaining ice cover thickness. The ice cover thickness predicting method based on fuzzy logic is suitable for making a general assessment on objects or phenomena which are influenced by various factors and have uncertain conclusions. The ice cover thickness of a power transmission line can be obtained by the method according to the data of ambient temperature, ambient humidity, ambient wind speed and lead temperature of an ice cover site, and the data are from on-site ice cover data monitored by an online ice cover monitoring system in real time, therefore the problem that the traditional ice cover predicting model is lack of on-site data sources and has poor accuracy.
Description
Technical field
The invention belongs to the powerline ice-covering monitoring technical field, be specifically related to a kind of ice covering thickness Forecasting Methodology based on fuzzy logic.
Background technology
Powerline ice-covering regular meeting causes line insulator ice sudden strain of a muscle accident, inhomogeneous icing or do not deice accident the same period, and the overload accident, ice coating wire is waved accident.Once serious wire icing of transmission line accident can cause enormous economic loss, and has a strong impact on social life.
Though existing achievement in research has related to the various relations between icing formation and the meteorological condition, but existing ice covering thickness forecast model all sums up by wind tunnel test, its valid data from the icing field monitoring are considerably less, so it is further perfect that existing ice covering thickness forecast model needs, could allow achievement in research ripe more and accurate.
Summary of the invention
The purpose of this invention is to provide a kind of ice covering thickness Forecasting Methodology, solved the problem that existing icing forecast model field data source lacks, degree of accuracy is not enough based on fuzzy logic.
The technical solution adopted in the present invention is, a kind of ice covering thickness Forecasting Methodology based on fuzzy logic is specifically implemented according to following steps:
Step 1: obtain the icing data: environment temperature, ambient humidity, ambient wind velocity and conductor temperature;
Step 2: the numerical value of environment temperature, ambient humidity, ambient wind velocity and the conductor temperature that obtains according to step 1, set up the ice covering thickness forecast model;
Step 3: the ice covering thickness forecast model according to step 2 obtains, calculate ice covering thickness.
Characteristics of the present invention also are,
The environment temperature in the step 1 wherein, ambient humidity, ambient wind velocity and conductor temperature, gather by the icing on-line monitoring system, the structure of icing on-line monitoring system is: comprise MSP430F247, be connected with system power supply on the MSP430F247 respectively, liquid crystal display and clock module, icing data acquisition and processing module, data storage cell and communication module, communication module comprises Zigbee communication module and GPRS communication module, system power supply is connected with controller, controller is also respectively at sun power, accumulator is connected, icing data acquisition and processing module comprise the icing information process unit, the input end of icing information process unit respectively with Temperature Humidity Sensor, air velocity transducer and temperature sensor are connected.
Wherein step 2 is set up the ice covering thickness forecast model, specifically implements according to following steps:
A. Fuzzy processing obtains the membership function of variable;
B. establish fuzzy rule;
C. set up the fuzzy prediction model.
Step a Fuzzy processing wherein, specifically implement: adopt four inputs, one export structure according to following steps, four input variables are consistent with output variable to be divided into five fuzzy subset: NB: very low/little, NS: lower/little, O: medium, PS: higher/big and PB: very high/big, the membership function of each variable adopts triangular function.
Wherein step b establishes fuzzy rule, specifically implement: environment temperature, ambient humidity, ambient wind velocity, conductor temperature and ice covering thickness are carried out statistical study conclude according to following steps, to every rule definition intensity G (k), be that the degree of membership u (k) that each data of composition rule belong to its fuzzy subset multiplies each other, k is the sequence number of rule, as shown in the formula
G(k)＝u(k)
ET×u(k)
EH×u(k)
EW×u(k)
CT.
Wherein, G (k) expression intensity; U (k)
ETThe size of expression environment temperature degree of membership; U (k)
EHThe size of expression ambient humidity degree of membership; U (k)
EWThe size of expression ambient wind velocity degree of membership; U (k)
CTThe size of expression conductor temperature degree of membership; The rule that falls into contradictions occurs, and then according to its intensity size, by going to stay big principle to accept or reject for a short time, finally establishes fuzzy rule.
Wherein step c sets up the fuzzy prediction model, specifically implement according to following steps: the fuzzy rule that the input variable that obtains according to step 1, the membership function that step a obtains and step b obtain, set up the ice covering thickness forecast model by the Fuzzy logic fuzzy logic toolbox among the MATLAB.
The invention has the beneficial effects as follows that the fuzzy logic method that model adopts has the characteristics of multifactor analysis-by-synthesis, be fit to the things with uncertain conclusion or the phenomenon that are subjected to multiple factor affecting are made total evaluation.The method needs environment temperature, ambient humidity, ambient wind velocity and the conductor temperature at icing scene, the on-the-spot icing data that these are monitored in real time data from the icing on-line monitoring system, thus draw electric power line ice-covering thickness.
Description of drawings
Fig. 1 is the process flow diagram of the inventive method;
Fig. 2 is the structural representation of the icing on-line monitoring system that adopts in the inventive method;
Fig. 3 is the membership function of input variable environment temperature among the embodiment;
Fig. 4 is the membership function of input variable ambient humidity among the embodiment;
Fig. 5 is the membership function of input variable ambient wind velocity among the embodiment;
Fig. 6 is the membership function of input variable conductor temperature among the embodiment;
Fig. 7 is the membership function of output variable ice covering thickness among the embodiment.
Among the figure, 1.MSP430F247,2. system power supply, 3. liquid crystal display and clock module, 4. icing information process unit, 5. Temperature Humidity Sensor, 6. air velocity transducer, 7. humidity sensor, 8. sun power, 9. controller, 10. accumulator, 11. data are deposited defeated unit, 12.Zigbee communication module, 13.GPRS communication module.
Embodiment
The present invention is described in detail below in conjunction with the drawings and specific embodiments.
The present invention is based on the ice covering thickness Forecasting Methodology of fuzzy logic, as shown in Figure 1, specifically implement according to following steps:
Step 1: obtain the icing data, adopt the powerline ice-covering on-line monitoring system, these 4 icing influence factors of the environment temperature when monitoring icing in real time, ambient humidity, ambient wind velocity and conductor temperature are as the input variable of ice covering thickness forecast model.The structure of icing on-line monitoring system as shown in Figure 2, comprise MSP430F2471, be connected with system power supply 2 on the MSP430F2471 respectively, liquid crystal display and clock module 3, icing data acquisition and processing module, data storage cell 11 and communication module, communication module comprises Zigbee communication module 12 and GPRS communication module 13, system power supply 2 is connected with controller 9, controller 9 is also respectively at sun power 8, accumulator 10 is connected, icing data acquisition and processing module comprise icing information process unit 4, the input end of icing information process unit 4 respectively with Temperature Humidity Sensor 5, air velocity transducer 6 and temperature sensor 7 are connected.
A shaft tower monitoring unit is installed on overhead line structures, is utilized sun power 8 and accumulator 10 charging work, can realize round-the-clock monitoring extra high voltage line and environmental parameter.Monitoring unit real-time Monitoring Line microclimate condition and circuit icing situation, monitoring information is sent to Surveillance center by GPRS communication module 13.
Step 2: set up the ice covering thickness forecast model of fuzzy logic, specifically implement according to following steps:
A. Fuzzy processing: obfuscation is meant input is converted to fuzzy set, be about to survey the fuzzy subset that physical quantity is converted into different language value in the corresponding domain of this linguistic variable, a plurality of inputs for fuzzy logic model, the fuzzification process of each input quantity all is the same, and the prerequisite of carrying out fuzzy reasoning is to import all to pass through Fuzzy processing.Icing predictive fuzzy logical model adopts four inputs, one export structure.Based on fuzzy theory, determine the fuzzy set of each variable.In order to obtain the higher forecasting precision, four input variables and consistent five fuzzy subset: NB (very low/little), NS (lower/little), O (medium), PS (higher/big) and a PB (very high/big) of being divided into of output variable.Based on the icing database that has obtained is added up and existing experience, the membership function of each variable all adopts triangular function among the present invention.
B. establish fuzzy rule: fuzzy rule is the core of fuzzy model, and it is equivalent to the correction module or the compensating module of fuzzy model.The generation method of fuzzy rule has two kinds substantially: a kind of is the practical experience and the knowledge of the field long-term accumulation institute study or relates to according to expert or operating personnel, concludes summary and draws; Another kind is to analyze in the data to existing input-output, concludes to sum up to draw.Because of at present very few to the research of icing fuzzy analysis, expertise lacks, so take second method that a large amount of icing data (comprising environment temperature, ambient humidity, ambient wind velocity, conductor temperature) and the ice covering thickness that the icing on-line monitoring system is obtained carried out the statistical study conclusion.
In many fuzzy rules that constitute, may the fuzzy rule conflict can appear owing to reasons such as Monitoring Data errors, and promptly the fuzzy subset of some regular former piece (input variable) is the same, and the fuzzy subset of consequent (output variable) is different.For the fuzzy rule to contradiction screens choice, to every rule definition intensity G (k), promptly each data of composition rule degree of membership u (k) of belonging to its fuzzy subset multiplies each other, and k be regular sequence number, suc as formula (1):
G(k)＝u(k)
ET×u(k)
EH×u(k)
EW×u(k)
CT (1)
Wherein, G (k) expression intensity; U (k)
ETThe size of expression environment temperature degree of membership; U (k)
EHThe size of expression ambient humidity degree of membership; U (k)
EWThe size of expression ambient wind velocity degree of membership; U (k)
CTThe size of expression conductor temperature degree of membership;
Principle is accepted or rejected in screening: the rule that falls into contradictions occurs, and then according to its intensity size, decides what to use by " going to stay for a short time big " principle.Finally can establish fuzzy rule.
C. set up the fuzzy prediction model: obtain the fuzzy rule that its subordinate function and step b obtain according to the resulting input variable of step 1, step a, set up the ice covering thickness forecast model by the Fuzzy logic fuzzy logic toolbox among the MATLAB.
Step 3: the ice covering thickness forecast model is according to four parameters of input, obtain the output variable ice covering thickness: the ice covering thickness forecast model is set up, environment temperature, ambient humidity, ambient wind velocity and the conductor temperature of the transmission line of electricity that real-time monitors be input in the model can obtain output quantity, i.e. ice covering thickness.This draws process and comes analysis and judgement to go out according to input value through fuzzy rule, finishes by means of MATLAB software.
Fuzzy logic method is fit to the things with uncertain conclusion or the phenomenon that are subjected to multiple factor affecting are made total evaluation, and powerline ice-covering has tangible ambiguity and uncertainty, simplify the design of ice covering thickness forecast model with fuzzy logic, go to describe input, rule and output with natural language, its result more meets people's requirement, more near the form of thinking of people's intuitivism apprehension.
Embodiment
The field data of utilizing the icing on-line monitoring system to obtain, the on-the-spot icing Monitoring Data (500kV pacifies an expensive loop line, 220kV chicken sun two times, the triumphant beautiful line of 220kV, the indiscriminate two wires of 110kV, 220kV Suo Gan two loop lines, 220kV copper multitude line, 110kV soil Yang Song thatch line and 220kV and practises duck one loop line) of having collected 8 transmission lines of electricity of Guizhou electrical network.
Press the fuzzy logic model analytical procedure, at first these circuits are carried out comprehensive statistics from the icing data in year January in Dec, 2008 to 2009, the variation range that draws data such as environment temperature ET, ambient humidity EH, ambient wind velocity EW, conductor temperature CT and ice covering thickness IT is respectively :-8 ℃～17 ℃, 32%～99%, 0m/s～8.6m/s ,-12 ℃～16 ℃ and 0mm～23.39mm.The membership function of 4 input variables such as Fig. 3, Fig. 4, Fig. 5, shown in Figure 6 and output variable are as shown in Figure 7.Because the icing environment constantly changes and icing data monitoring frequency is 1 time/15min, so the data variation scope is not interior variation of scope that necessarily is confined to above statistics, in order to make data area can contain various icing situations and to be convenient to the obfuscation analysis, the variation range of above environment temperature ET, ambient humidity EH, ambient wind velocity EW, conductor temperature CT and ice covering thickness IT suitably enlarged be adjusted into-20 ℃～20 ℃, 0%～100%, 0m/s～20m/s ,-20 ℃～20 ℃ and 0mm～30mm.Carrying out statistical induction at the icing data of these 8 transmission lines of electricity sums up, draw 78 initial fuzzy rules in conjunction with expertise, accept or reject principle by screening, 25 rules have finally been obtained, fuzzy rule adopts ifET is ... andEH is ... and EW is ... and CT is ... then IT is ... this fuzzy language is described, and it is as shown in table 1 to list the part rule:
Table 1 fuzzy reasoning table
When four factors belong to different fuzzy subset, judge the fuzzy subset of ice covering thickness one by one.After fuzzy rule is established, just can be by means of setting up the ice covering thickness forecast model in the Fuzzy logic fuzzy logic toolbox among the MATLAB.
Claims (6)
1. the ice covering thickness Forecasting Methodology based on fuzzy logic is characterized in that, specifically implements according to following steps:
Step 1: obtain the icing data: environment temperature, ambient humidity, ambient wind velocity and conductor temperature;
Step 2: the numerical value of environment temperature, ambient humidity, ambient wind velocity and the conductor temperature that obtains according to step 1, set up the ice covering thickness forecast model;
Step 3: the ice covering thickness forecast model according to step 2 obtains, calculate ice covering thickness.
2. the ice covering thickness Forecasting Methodology based on fuzzy logic according to claim 1, it is characterized in that, environment temperature in the described step 1, ambient humidity, ambient wind velocity and conductor temperature, gather by the icing on-line monitoring system, the structure of icing on-line monitoring system is: comprise MSP430F247 (1), be connected with system power supply (2) on the MSP430F247 (1) respectively, liquid crystal display and clock module (3), icing data acquisition and processing module, data storage cell (11) and communication module, communication module comprises Zigbee communication module (12) and GPRS communication module (13), described system power supply (2) is connected with controller (9), controller (9) is also respectively at sun power (8), accumulator (10) is connected, described icing data acquisition and processing module comprise icing information process unit (4), the input end of icing information process unit (4) respectively with Temperature Humidity Sensor (5), air velocity transducer (6) and temperature sensor (7) are connected.
3. the ice covering thickness Forecasting Methodology based on fuzzy logic according to claim 1 is characterized in that described step 2 is set up the ice covering thickness forecast model, specifically implements according to following steps:
A. Fuzzy processing obtains the membership function of variable;
B. establish fuzzy rule;
C. set up the fuzzy prediction model.
4. the ice covering thickness Forecasting Methodology based on fuzzy logic according to claim 3, it is characterized in that, described step a Fuzzy processing, specifically implement: adopt four inputs, one export structure according to following steps, four input variables are consistent with output variable to be divided into five fuzzy subset: NB: very low/little, NS: lower/little, O: medium, PS: higher/big and PB: very high/big, the membership function of each variable adopts triangular function.
5. the ice covering thickness Forecasting Methodology based on fuzzy logic according to claim 3, it is characterized in that, described step b establishes fuzzy rule, specifically implement: environment temperature, ambient humidity, ambient wind velocity, conductor temperature and ice covering thickness are carried out statistical study conclude according to following steps, to every rule definition intensity G (k), promptly each data of composition rule degree of membership u (k) of belonging to its fuzzy subset multiplies each other, and k be regular sequence number, as shown in the formula
G(k)＝u(k)
ET×u(k)
EH×u(k)
EW×u(k)
CT.
Wherein, G (k) expression intensity; U (k)
ETThe size of expression environment temperature degree of membership; U (k)
EHThe size of expression ambient humidity degree of membership; U (k)
EWThe size of expression ambient wind velocity degree of membership; U (k)
CTThe size of expression conductor temperature degree of membership; The rule that falls into contradictions occurs, and then according to its intensity size, by going to stay big principle to accept or reject for a short time, finally establishes fuzzy rule.
6. the ice covering thickness Forecasting Methodology based on fuzzy logic according to claim 3, it is characterized in that, described step c sets up the fuzzy prediction model, specifically implement according to following steps: the fuzzy rule that the input variable that obtains according to step 1, the membership function that step a obtains and step b obtain, set up the ice covering thickness forecast model by the Fuzzy logic fuzzy logic toolbox among the MATLAB.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110031728 CN102175202A (en) | 2011-01-30 | 2011-01-30 | Ice cover thickness predicting method based on fuzzy logic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110031728 CN102175202A (en) | 2011-01-30 | 2011-01-30 | Ice cover thickness predicting method based on fuzzy logic |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102175202A true CN102175202A (en) | 2011-09-07 |
Family
ID=44518413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110031728 Pending CN102175202A (en) | 2011-01-30 | 2011-01-30 | Ice cover thickness predicting method based on fuzzy logic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102175202A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102721373A (en) * | 2012-06-26 | 2012-10-10 | 西安金源电气股份有限公司 | Online electrified railway overhead contact line icing monitoring system |
| CN103413176A (en) * | 2013-08-27 | 2013-11-27 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Method for quantitatively evaluating necessity of monitoring icing on transmission line |
| CN104655030A (en) * | 2015-02-16 | 2015-05-27 | 国网安徽省电力公司铜陵供电公司 | Power transmission line icing detecting and early-warning device |
| CN107402083A (en) * | 2017-07-27 | 2017-11-28 | 南京大学 | Ultra-high-tension power transmission line icing monitoring method based on distributing optical fiber sensing |
| CN111815073A (en) * | 2020-08-06 | 2020-10-23 | 内蒙古工业大学 | Grassland biomass prediction method and device, electronic equipment and storage medium |
| CN115292656A (en) * | 2022-09-22 | 2022-11-04 | 北京弘象科技有限公司 | Aircraft ice accretion prediction method and device based on fuzzy logic |
| CN117404262A (en) * | 2023-11-24 | 2024-01-16 | 湖南防灾科技有限公司 | Control method and controller of fan air-heat deicing system based on fuzzy control |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6434849B1 (en) * | 2000-01-24 | 2002-08-20 | Pruftechnik Dieter Busch Ag | Method for determining a lateral and/or angular offset between two rotatable parts |
| CN101621190A (en) * | 2009-06-17 | 2010-01-06 | 西安工程大学 | System for online monitoring icing and deicing processes of power transmission line |
-
2011
- 2011-01-30 CN CN 201110031728 patent/CN102175202A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6434849B1 (en) * | 2000-01-24 | 2002-08-20 | Pruftechnik Dieter Busch Ag | Method for determining a lateral and/or angular offset between two rotatable parts |
| CN101621190A (en) * | 2009-06-17 | 2010-01-06 | 西安工程大学 | System for online monitoring icing and deicing processes of power transmission line |
Non-Patent Citations (3)
| Title |
|---|
| 《交通科技与经济》 20101231 胡文君等 异常情况下交叉口信号模糊逻辑控制 , 第4期 * |
| 《华东电力》 20101031 欧阳丽莎等 覆冰在线监测技术在1000kV特高压输电线路中的应用 第38卷, 第10期 * |
| 《微型计算机控制技术》 20031231 孔峰等 模糊控制和神经网络控制 , * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102721373A (en) * | 2012-06-26 | 2012-10-10 | 西安金源电气股份有限公司 | Online electrified railway overhead contact line icing monitoring system |
| CN102721373B (en) * | 2012-06-26 | 2015-07-29 | 西安金源电气股份有限公司 | A kind of electrification railway contact net icing on-line monitoring system |
| CN103413176A (en) * | 2013-08-27 | 2013-11-27 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Method for quantitatively evaluating necessity of monitoring icing on transmission line |
| CN104655030A (en) * | 2015-02-16 | 2015-05-27 | 国网安徽省电力公司铜陵供电公司 | Power transmission line icing detecting and early-warning device |
| CN104655030B (en) * | 2015-02-16 | 2017-08-11 | 国网安徽省电力公司铜陵供电公司 | A kind of powerline ice-covering detection and prior-warning device |
| CN107402083A (en) * | 2017-07-27 | 2017-11-28 | 南京大学 | Ultra-high-tension power transmission line icing monitoring method based on distributing optical fiber sensing |
| CN111815073A (en) * | 2020-08-06 | 2020-10-23 | 内蒙古工业大学 | Grassland biomass prediction method and device, electronic equipment and storage medium |
| CN115292656A (en) * | 2022-09-22 | 2022-11-04 | 北京弘象科技有限公司 | Aircraft ice accretion prediction method and device based on fuzzy logic |
| CN115292656B (en) * | 2022-09-22 | 2022-12-20 | 北京弘象科技有限公司 | Aircraft ice accretion prediction method and device based on fuzzy logic |
| CN117404262A (en) * | 2023-11-24 | 2024-01-16 | 湖南防灾科技有限公司 | Control method and controller of fan air-heat deicing system based on fuzzy control |
| CN117404262B (en) * | 2023-11-24 | 2024-06-04 | 湖南防灾科技有限公司 | Control method and controller of fan air-heat deicing system based on fuzzy control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102175202A (en) | Ice cover thickness predicting method based on fuzzy logic | |
| Wang et al. | Decision tree based online stability assessment scheme for power systems with renewable generations | |
| CN111753893A (en) | Wind turbine generator power cluster prediction method based on clustering and deep learning | |
| CN106228278A (en) | Photovoltaic power prognoses system | |
| Guo et al. | Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning | |
| CN102982393B (en) | A kind of on-line prediction method of electric transmission line dynamic capacity | |
| CN105809287A (en) | High-voltage transmission line icing process integrated prediction method | |
| CN103235981A (en) | Wind power quality trend predicting method | |
| CN102789447A (en) | Method for analyzing ice and climate relationship on basis of grey MLR (Multiple Linear Regression) | |
| CN202734796U (en) | Icing thickness monitoring system | |
| CN103617447B (en) | The evaluation system of intelligent substation and evaluation methodology | |
| CN105046584A (en) | K-MEANS algorithm-based ideal line loss rate calculation method | |
| CN110929924A (en) | Small hydropower station power generation capacity prediction system based on cloud edge fusion framework and implementation method thereof | |
| Xiaolan et al. | One-month ahead prediction of wind speed and output power based on EMD and LSSVM | |
| CN117335411B (en) | Medium-and-long-term power generation capacity prediction method for photovoltaic power station group | |
| CN102175203B (en) | Method for analyzing icing prominent influence factors of power transmission line | |
| CN103632314A (en) | Probability statistics-based method for modeling generalized node characteristics | |
| CN105354761B (en) | Safety and efficiency evaluation method and system for accessing wind power into power grid | |
| CN117473384A (en) | Power grid line safety constraint identification method, device, equipment and storage medium | |
| Hu et al. | Operational reliability evaluation method based on big data technology | |
| Zhao et al. | Short-term load forecasting based on RBF neural network | |
| Zhang et al. | Analysis of influencing factors of transmission line loss based on GBDT algorithm | |
| CN110533213A (en) | Transmission line of electricity defect Risk Modeling and its prediction technique based on support vector machines | |
| Zhang et al. | Power forecasting of solar photovoltaic power systems based on similar day and M5'model trees | |
| CN107451697A (en) | A kind of wind power prediction method based on complex data reparation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20110907 |