CN105139274A - Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network - Google Patents
Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network Download PDFInfo
- Publication number
- CN105139274A CN105139274A CN201510499925.XA CN201510499925A CN105139274A CN 105139274 A CN105139274 A CN 105139274A CN 201510499925 A CN201510499925 A CN 201510499925A CN 105139274 A CN105139274 A CN 105139274A
- Authority
- CN
- China
- Prior art keywords
- neural network
- particle swarm
- wavelet neural
- ice
- covering
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a power transmission line icing prediction method based on a quantum particle swarm and a wavelet nerve network. The power transmission line icing prediction method based on the quantum particle swarm and a wavelet nerve network comprises the following steps of acquiring historical icing meteorological data, namely an ambient temperature, a humidity, a wind speed, a wind direction, an air pressure, a lead temperature and an icing thickness; establishing an icing thickness prediction model by means of the wavelet nerve network; performing initial parameter optimization on the model through adding a quantum particle swarm algorithm of interference factors; and inputting the historical icing data for obtaining a predicated power transmission line icing thickness. The power transmission line icing prediction method has advantages of high prediction precision, high convergence speed, etc. The power transmission line icing prediction method can effectively predicate a line icing change rule and can be applied for power transmission line icing disaster early warning and treatment.
Description
Technical field
The present invention relates to powerline ice-covering disaster alarm field, be specifically related to the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network.
Background technology
In recent years, along with the progressively construction of power infrastructures, the safe and reliable sex chromosome mosaicism of transmission line of electricity is subject to increasing attention.Because transmission line of electricity is exposed in physical environment mostly, its running status is easily subject to the impact of various meteorologic factor.Particularly, Transmission Line in Winter generation icing phenomenon may impact line security is stable, even causes serious harm, causes huge economic loss.Therefore, the thickness of powerline ice-covering is predicted, formulate effective anti-icing countermeasure, thus realize line ice coating disaster alarm and process has Great significance.
At present about the linear forecast model of model and the Nonlinear Prediction Models of powerline ice-covering prediction.It is pointed out that electric power line ice-covering thickness is subject to the impact of numerous meteorologic factor, there is complicated nonlinear relationship between these meteorologic factor and ice covering thickness, the result of employing Nonlinear Prediction Models can be more accurate.Common nonlinear model has grey forecasting model, BP neural network model and fuzzy model.Wherein, BP neural network model does not rely on accurate mathematical model, and has very strong adaptive ability and nonlinear function approximation capability, has good predictive ability.But traditional BP neural network model also exists unique, the overfitting of predicting the outcome, is easily absorbed in local minimum, initial parameter is difficult to problems such as determining.
Summary of the invention
The object of this invention is to provide the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network, this powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network also existing for solving traditional BP neural network model unique, the overfitting of predicting the outcome, being easily absorbed in local minimum, initial parameter is difficult to problems such as determining.
The technical solution adopted for the present invention to solve the technical problems is: this powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network:
Step 1: obtain powerline ice-covering historical data, comprise environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature and ice covering thickness, is normalized the raw data obtained, obtains normalization data;
Step 2: the normalization data utilizing step 1 to obtain builds the ice covering thickness forecast model based on wavelet neural network; Ice covering thickness forecast model based on wavelet neural network comprises input layer, hidden layer and output layer; Described prediction model based on wavelet neural network parameter comprises input layer
, hidden layer neuron and output layer neuron
; Described input layer is environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature after normalization; Described hidden layer neuron is
individual hidden layer node, adjusts according to hands-on precision; Described output layer neuron is ice covering thickness value; Based on wavelet neural network ice covering thickness forecast model described in hidden layer neuron wavelet basis function be formula (2):
(2)
In formula,
with
for flexible translation scale factor,
,
get Morlet small echo:
(3)
Described output layer neuron is by selecting Sigmoid function:
(4)
The input and output of wavelet neural network can be expressed as:
(5)
In formula,
(6)
(7)
(8)
(9)
(10)
In formula (6)-(10),
for number of samples,
,
,
,
for e-learning speed,
for network factor of momentum.
Step 3: the optimum initial parameter of the forecast model utilizing the quanta particle swarm optimization obtaining step 2 adding interference factor to build;
Step 4: the optimum initial parameter of the forecast model utilizing step 3 to obtain, computational prediction model exports, by the output renormalization of model is obtained powerline ice-covering thickness prediction.
Icing historical data in such scheme described in step 1 adopts linear normalization process formula to be formula (1):
To data
linear mapping is reflected in foundation:
(1),
In formula,
,
.
Wavelet neural network described in step 2 is connected weights and parameter by adding in the quanta particle swarm optimization of interference factor in such scheme described in step 3
be mapped as the individual particles in quantum particle swarm; Described particle position evolution equation is:
In formula,
for iterations is
time population current location,
for individual particles optimum position, be expressed as
,
for
between random number,
be
the optimal location of individual particle,
for the global optimum position of population,
for
between random number,
for the converging diverging factor, iterations is
in time, is taken as
for iteration maximum times,
for the average optimal position of population, when population scale is
time,
be expressed as:
Introduce the interference factor of normal distribution in quanta particle swarm optimization in such scheme described in step 3 to change the position of current search particle, thus improve the diversity of population, described interference factor is expressed as:
Wherein,
for controling parameters,
for exporting the random function for normal distribution value; Interference factor introduces judgment standard: when iteration number of times is greater than precocious because of the period of the day from 11 p.m. to 1 a.m, start interference factor, the precocious factor is arranged according to real data.
The quanta particle swarm optimization adding interference factor described in such scheme is when arriving maximum iteration time or permissible error scope, stop iteration obtaining optimal particle, the wavelet neural network dividing demapping to obtain described in right 5 by optimal particle connects weights and parameter
optimal value.
Powerline ice-covering thickness prediction in such scheme described in step 4 exports renormalization by the prediction model based on wavelet neural network trained and obtains.
The present invention has following beneficial effect:
1, the present invention can reach the object of Accurate Prediction electric power line ice-covering thickness, thus provides reference for transmission line of electricity ice damage early warning and settlement, ensures the safety and stability of network system.In addition, the wavelet neural network that the present invention adopts combines wavelet transformation and neural network, has very strong adaptive ability, fault-tolerant ability and robustness, than BP neural network more freedom, and has nonlinear function approximation capability more flexibly.By adopting the quantum particle swarm optimization adding interference factor, total head and the wavelet parameter of optimum wavelet neural network can be obtained, there is unique predicting the outcome.
2, in order to the ice covering thickness research ice damage of Accurate Prediction transmission line of electricity is on the impact of circuit, the present invention is by the historical data of powerline ice-covering, comprise environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature and ice covering thickness, the ice covering thickness of transmission line of electricity is predicted, is with a wide range of applications and economic worth.
Accompanying drawing explanation
Fig. 1 is process flow diagram of the present invention.
Fig. 2 is small echo neural network structure figure in the present invention.
Fig. 3 is the process flow diagram of the quantum telepotation wavelet neural network initial parameter method introducing interference factor in the present invention.
Embodiment
Be described below in conjunction with accompanying drawing 1-accompanying drawing 3 pairs of the preferred embodiments of the present invention, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
Based on a powerline ice-covering Forecasting Methodology for quantum particle swarm and wavelet neural network, comprise the following steps:
Step 1: obtain powerline ice-covering historical data, comprise environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature and ice covering thickness, is normalized the raw data obtained;
Step 2: the normalization data utilizing step 1 to obtain builds the ice covering thickness forecast model based on wavelet neural network;
Step 3: the optimum initial parameter of the forecast model utilizing the quanta particle swarm optimization obtaining step 2 adding interference factor to build;
Step 4: the optimum initial parameter of the forecast model utilizing step 3 to obtain, computational prediction model exports, by the output renormalization of model is obtained powerline ice-covering thickness prediction.
Icing historical data described in described step 1 described in step 1 adopts linear normalization process formula to be formula (1):
To data
linear mapping is reflected in foundation:
,(1)
In formula,
,
.
The ice covering thickness forecast model based on wavelet neural network described in described step 2 comprises input layer, hidden layer and output layer; Described prediction model based on wavelet neural network parameter comprises input layer
, hidden layer neuron and output layer neuron
; Described input layer is environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature after normalization; Described hidden layer neuron is
individual hidden layer node, adjusts according to hands-on precision; Described output layer neuron is ice covering thickness value.
Described in described step 2 based on wavelet neural network ice covering thickness forecast model described in hidden layer neuron wavelet basis function be formula (2):
(2)
In formula,
with
for flexible translation scale factor,
,
get Morlet small echo:
(3)
Described output layer neuron is by selecting Sigmoid function:
(4)
The input and output of wavelet neural network can be expressed as:
(5)
In formula,
(6)
(7)
(8)
(9)
(10)
In formula,
for number of samples,
,
,
,
for e-learning speed,
for network factor of momentum.
The concrete steps of described step 2 are:
Environment temperature after normalization, humidity, wind speed, wind direction, air pressure, conductor temperature are inputted as forecast model, exported by ice covering thickness as forecast model, namely forecast model is input as
, wherein
represent environment temperature,
represent ambient humidity,
represent ambient wind velocity,
represent ambient wind to,
represent ambient pressure,
represent line wire temperature, forecast model exports and is
represent ice covering thickness, hidden layer neuron quantity is
, namely 13.
E-learning speed is set to 0.6, and network factor of momentum is set to 0.04, namely
=
=
=
=0.6,
.
Wavelet neural network described in step 2 is connected weights and parameter by adding in the quanta particle swarm optimization of interference factor described in described step 3
be mapped as the individual particles in quantum particle swarm; Described particle position evolution equation is formula (11):
(11)
In formula,
for iterations is
time population current location,
for individual particles optimum position, be expressed as
,
for
between random number,
be
the optimal location of individual particle,
for the global optimum position of population,
for
between random number,
for the converging diverging factor, iterations is
in time, is taken as
(12)
for iteration maximum times,
for the average optimal position of population, when population scale is
time,
be expressed as:
(13)
Introduce the interference factor of normal distribution in quanta particle swarm optimization described in described step 3 to change the position of current search particle, thus improve the diversity of population, described interference factor is expressed as:
(15)
Wherein,
for controling parameters,
for exporting the random function for normal distribution value; Interference factor introduces judgment standard: when iteration number of times is greater than precocious because of the period of the day from 11 p.m. to 1 a.m, start interference factor, the precocious factor is arranged according to real data.
The specific implementation step of this step is:
initialization population, maps wavelet neural network and connects weights and parameter
be mapped as the individual particles in quantum particle swarm, namely
(14)
arranging maximum iteration time is 1000, namely
, calculate the fitness value of particle;
relatively individual particles optimal location
with integral particles group optimal location
if individual particles position is better than integral particles group optimal location, upgrade integral particles group optimal location;
upgrade
;
upgrade particle position;
judge whether iterations is greater than the precocious factor, if then add interference factor to population;
judge whether iterations reaches maximal value, then repeats step if not
-
.
judge whether to obtain optimal location, if then result is mapped as wavelet neural network to connect weights and parameter
.
using 2/3 of icing historical data as test sample book, 1/3 as test samples, the performance of test forecast model.
The described quanta particle swarm optimization adding interference factor, when arriving maximum iteration time or permissible error scope, stops iteration obtaining optimal particle, divides the wavelet neural network described in demapping acquisition to connect weights and parameter by optimal particle
optimal value.
Powerline ice-covering thickness prediction exports renormalization by the prediction model based on wavelet neural network trained and obtains.
The above embodiment is the preferred embodiments of the present invention, be noted that for a person skilled in the art, it still can be modified to the technical scheme described in previous embodiment, or equivalent replacement is carried out to wherein portion of techniques feature, within the spirit and principles in the present invention all, the amendment made or equivalent replacement, all should belong in right of the present invention.
Claims (6)
1. based on a powerline ice-covering Forecasting Methodology for quantum particle swarm and wavelet neural network, it is characterized in that: this powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network:
Step 1: obtain powerline ice-covering historical data, comprise environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature and ice covering thickness, is normalized the raw data obtained, obtains normalization data;
Step 2: the normalization data utilizing step 1 to obtain builds the ice covering thickness forecast model based on wavelet neural network; Ice covering thickness forecast model based on wavelet neural network comprises input layer, hidden layer and output layer; Described prediction model based on wavelet neural network parameter comprises input layer
, hidden layer neuron and output layer neuron
; Described input layer is environment temperature, humidity, wind speed, wind direction, air pressure, conductor temperature after normalization; Described hidden layer neuron is
individual hidden layer node, adjusts according to hands-on precision; Described output layer neuron is ice covering thickness value; Based on wavelet neural network ice covering thickness forecast model described in hidden layer neuron wavelet basis function be formula (2):
(2)
In formula,
with
for flexible translation scale factor,
,
get Morlet small echo:
(3)
Described output layer neuron is by selecting Sigmoid function:
(4)
The input and output of wavelet neural network can be expressed as:
(5)
In formula,
(6)
(7)
(8)
(9)
(10)
In formula (6)-(10),
for number of samples,
,
,
,
for e-learning speed,
for network factor of momentum;
Step 3: the optimum initial parameter of the forecast model utilizing the quanta particle swarm optimization obtaining step 2 adding interference factor to build;
Step 4: the optimum initial parameter of the forecast model utilizing step 3 to obtain, computational prediction model exports, by the output renormalization of model is obtained powerline ice-covering thickness prediction.
2. the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network according to claim 1, is characterized in that: the icing historical data described in described step 1 adopts linear normalization process formula to be formula (1):
To data
linear mapping is reflected in foundation:
(1),
In formula,
,
.
3. the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network according to claim 1 and 2, is characterized in that: the wavelet neural network described in step 2 is connected weights and parameter by adding in the quanta particle swarm optimization of interference factor described in described step 3
be mapped as the individual particles in quantum particle swarm; Described particle position evolution equation is:
In formula,
for iterations is
time population current location,
for individual particles optimum position, be expressed as
,
for
between random number,
be
the optimal location of individual particle,
for the global optimum position of population,
for
between random number,
for the converging diverging factor, iterations is
in time, is taken as
for iteration maximum times,
for the average optimal position of population, when population scale is
time,
be expressed as:
。
4. the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network according to claim 3, it is characterized in that: introduce the interference factor of normal distribution in the quanta particle swarm optimization described in described step 3 to change the position of current search particle, thus improve the diversity of population, described interference factor is expressed as:
Wherein,
for controling parameters,
for exporting the random function for normal distribution value; Interference factor introduces judgment standard: when iteration number of times is greater than precocious because of the period of the day from 11 p.m. to 1 a.m, start interference factor, the precocious factor is arranged according to real data.
5. the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network according to claim 4, it is characterized in that: the described quanta particle swarm optimization adding interference factor is when arriving maximum iteration time or permissible error scope, stop iteration obtaining optimal particle, the wavelet neural network dividing demapping to obtain described in right 5 by optimal particle connects weights and parameter
optimal value.
6. the powerline ice-covering Forecasting Methodology based on quantum particle swarm and wavelet neural network according to claim 5, is characterized in that: the powerline ice-covering thickness prediction described in described step 4 exports renormalization by the prediction model based on wavelet neural network trained and obtains.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510499925.XA CN105139274A (en) | 2015-08-16 | 2015-08-16 | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510499925.XA CN105139274A (en) | 2015-08-16 | 2015-08-16 | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105139274A true CN105139274A (en) | 2015-12-09 |
Family
ID=54724609
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510499925.XA Pending CN105139274A (en) | 2015-08-16 | 2015-08-16 | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105139274A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107784395A (en) * | 2017-10-27 | 2018-03-09 | 云南电网有限责任公司电力科学研究院 | A kind of electric power line ice-covering thickness Forecasting Methodology based on LSTM artificial neural networks |
CN108182514A (en) * | 2017-12-13 | 2018-06-19 | 国网湖南省电力有限公司 | A kind of power grid icing waves Risk Forecast Method, system and storage medium |
CN108255784A (en) * | 2018-01-15 | 2018-07-06 | 广西师范大学 | Multi-layer quantum D(4)The method that quantum wire design is realized in wavelet package transforms and inverse transformation |
CN108345955A (en) * | 2017-11-24 | 2018-07-31 | 北京国网富达科技发展有限责任公司 | A kind of powerline ice-covering short term prediction method, device and storage medium |
CN108460459A (en) * | 2017-02-22 | 2018-08-28 | 大连云海创新科技有限公司 | The method of temperature foh in unmanned aerial vehicle remote sensing thermometric based on wavelet neural network |
CN108921278A (en) * | 2018-06-11 | 2018-11-30 | 福建省计量科学研究院(福建省眼镜质量检验站) | A kind of platform potential difference calculation method of apparatus for calibrating water meter |
CN109522627A (en) * | 2018-11-01 | 2019-03-26 | 西安电子科技大学 | Fan blade icing prediction technique based on SCADA data |
CN110188914A (en) * | 2019-03-25 | 2019-08-30 | 华北电力大学 | A kind of intelligent Forecasting for grid power transmission route ice covering thickness |
CN110361966A (en) * | 2018-06-23 | 2019-10-22 | 四川大学 | A kind of trend forecasting method based on two hidden-layer quantum wire cycling element neural network |
CN110458317A (en) * | 2019-05-21 | 2019-11-15 | 广东电网有限责任公司 | A kind of method and system of powerline ice-covering disaster prediction of the development trend |
CN110909453A (en) * | 2019-11-01 | 2020-03-24 | 中国地质大学(武汉) | EEMD-based power transmission line icing grade prediction method |
CN111210086A (en) * | 2020-01-15 | 2020-05-29 | 杭州华网信息技术有限公司 | National power grid icing disaster prediction method |
CN112116162A (en) * | 2020-09-26 | 2020-12-22 | 国家电网公司华中分部 | Power transmission line icing thickness prediction method based on CEEMDAN-QFAOA-LSTM |
CN113783895A (en) * | 2021-11-10 | 2021-12-10 | 山东凤和凰城市科技有限公司 | Network security situation sensing method based on particle swarm optimization |
CN114297807A (en) * | 2022-03-09 | 2022-04-08 | 中国空气动力研究与发展中心低速空气动力研究所 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
CN114792174A (en) * | 2022-06-23 | 2022-07-26 | 国网天津市电力公司电力科学研究院 | Distribution network line meteorological prediction method based on wavelet neural network |
CN115630101A (en) * | 2022-10-24 | 2023-01-20 | 淮阴工学院 | Hydrological parameter intelligent monitoring and water resource big data management system |
CN116306893A (en) * | 2023-05-24 | 2023-06-23 | 华东交通大学 | Contact net icing early warning method |
CN117313537A (en) * | 2023-09-28 | 2023-12-29 | 国网吉林省电力有限公司松原供电公司 | Data-driven icing prediction method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040199481A1 (en) * | 1998-10-06 | 2004-10-07 | Hartman Eric Jon | Bayesian neural networks for optimization and control |
US20090125285A1 (en) * | 2007-11-13 | 2009-05-14 | Gugaliya Jinendra K | Decomposition of nonlinear dynamics using multiple model approach and gap metric analysis |
CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
CN104484715A (en) * | 2014-11-28 | 2015-04-01 | 江苏大学 | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method |
-
2015
- 2015-08-16 CN CN201510499925.XA patent/CN105139274A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040199481A1 (en) * | 1998-10-06 | 2004-10-07 | Hartman Eric Jon | Bayesian neural networks for optimization and control |
US20090125285A1 (en) * | 2007-11-13 | 2009-05-14 | Gugaliya Jinendra K | Decomposition of nonlinear dynamics using multiple model approach and gap metric analysis |
CN103729695A (en) * | 2014-01-06 | 2014-04-16 | 国家电网公司 | Short-term power load forecasting method based on particle swarm and BP neural network |
CN104484715A (en) * | 2014-11-28 | 2015-04-01 | 江苏大学 | Neural network and particle swarm optimization algorithm-based building energy consumption predicting method |
Non-Patent Citations (3)
Title |
---|
徐文龙 等: "基于干扰因子的QPSO算法改进", 《微电子学与计算机》 * |
李奇茂: "输电线覆冰负荷预测模型的数据驱动方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
潘玉民 等: "基于量子粒子群优化的小波神经网络预测模型", 《信息与控制》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108460459A (en) * | 2017-02-22 | 2018-08-28 | 大连云海创新科技有限公司 | The method of temperature foh in unmanned aerial vehicle remote sensing thermometric based on wavelet neural network |
CN107784395A (en) * | 2017-10-27 | 2018-03-09 | 云南电网有限责任公司电力科学研究院 | A kind of electric power line ice-covering thickness Forecasting Methodology based on LSTM artificial neural networks |
CN108345955A (en) * | 2017-11-24 | 2018-07-31 | 北京国网富达科技发展有限责任公司 | A kind of powerline ice-covering short term prediction method, device and storage medium |
CN108182514A (en) * | 2017-12-13 | 2018-06-19 | 国网湖南省电力有限公司 | A kind of power grid icing waves Risk Forecast Method, system and storage medium |
CN108255784B (en) * | 2018-01-15 | 2024-01-09 | 宁波亚翔电子科技有限公司 | Multilayer quantum D (4) Method for realizing quantum circuit design by wavelet packet transformation and inverse transformation |
CN108255784A (en) * | 2018-01-15 | 2018-07-06 | 广西师范大学 | Multi-layer quantum D(4)The method that quantum wire design is realized in wavelet package transforms and inverse transformation |
CN108921278A (en) * | 2018-06-11 | 2018-11-30 | 福建省计量科学研究院(福建省眼镜质量检验站) | A kind of platform potential difference calculation method of apparatus for calibrating water meter |
CN108921278B (en) * | 2018-06-11 | 2022-05-03 | 福建省计量科学研究院(福建省眼镜质量检验站) | Station difference calculation method for water meter calibrating device |
CN110361966A (en) * | 2018-06-23 | 2019-10-22 | 四川大学 | A kind of trend forecasting method based on two hidden-layer quantum wire cycling element neural network |
CN110361966B (en) * | 2018-06-23 | 2022-05-27 | 四川大学 | Trend prediction method based on double-hidden-layer quantum circuit circulation unit neural network |
CN109522627A (en) * | 2018-11-01 | 2019-03-26 | 西安电子科技大学 | Fan blade icing prediction technique based on SCADA data |
CN109522627B (en) * | 2018-11-01 | 2022-12-02 | 西安电子科技大学 | Fan blade icing prediction method based on SCADA (Supervisory control and data acquisition) data |
CN110188914A (en) * | 2019-03-25 | 2019-08-30 | 华北电力大学 | A kind of intelligent Forecasting for grid power transmission route ice covering thickness |
CN110458317A (en) * | 2019-05-21 | 2019-11-15 | 广东电网有限责任公司 | A kind of method and system of powerline ice-covering disaster prediction of the development trend |
CN110909453A (en) * | 2019-11-01 | 2020-03-24 | 中国地质大学(武汉) | EEMD-based power transmission line icing grade prediction method |
CN111210086B (en) * | 2020-01-15 | 2023-09-22 | 国网安徽省电力有限公司宁国市供电公司 | National power grid icing disaster prediction method |
CN111210086A (en) * | 2020-01-15 | 2020-05-29 | 杭州华网信息技术有限公司 | National power grid icing disaster prediction method |
CN112116162A (en) * | 2020-09-26 | 2020-12-22 | 国家电网公司华中分部 | Power transmission line icing thickness prediction method based on CEEMDAN-QFAOA-LSTM |
CN113783895A (en) * | 2021-11-10 | 2021-12-10 | 山东凤和凰城市科技有限公司 | Network security situation sensing method based on particle swarm optimization |
CN114297807B (en) * | 2022-03-09 | 2022-06-03 | 中国空气动力研究与发展中心低速空气动力研究所 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
CN114297807A (en) * | 2022-03-09 | 2022-04-08 | 中国空气动力研究与发展中心低速空气动力研究所 | Method for optimizing parameters of flute-shaped tube structure of anti-icing system |
CN114792174A (en) * | 2022-06-23 | 2022-07-26 | 国网天津市电力公司电力科学研究院 | Distribution network line meteorological prediction method based on wavelet neural network |
CN115630101A (en) * | 2022-10-24 | 2023-01-20 | 淮阴工学院 | Hydrological parameter intelligent monitoring and water resource big data management system |
CN115630101B (en) * | 2022-10-24 | 2023-10-20 | 淮阴工学院 | Hydrologic parameter intelligent monitoring and water resource big data management system |
CN116306893A (en) * | 2023-05-24 | 2023-06-23 | 华东交通大学 | Contact net icing early warning method |
CN117313537A (en) * | 2023-09-28 | 2023-12-29 | 国网吉林省电力有限公司松原供电公司 | Data-driven icing prediction method and system |
CN117313537B (en) * | 2023-09-28 | 2024-03-08 | 国网吉林省电力有限公司松原供电公司 | Data-driven icing prediction method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105139274A (en) | Power transmission line icing prediction method based on quantum particle swarm and wavelet nerve network | |
Tan et al. | Ultra-short-term wind power prediction by salp swarm algorithm-based optimizing extreme learning machine | |
Zhang et al. | A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms | |
Wang et al. | Wind power interval prediction based on improved PSO and BP neural network | |
Ramedani et al. | Potential of radial basis function based support vector regression for global solar radiation prediction | |
Akbarifard et al. | Predicting sea wave height using Symbiotic Organisms Search (SOS) algorithm | |
Sun et al. | Staged icing forecasting of power transmission lines based on icing cycle and improved extreme learning machine | |
CN103699944A (en) | Wind and photovoltaic generation power prediction system with multiple prediction modes | |
CN108182514A (en) | A kind of power grid icing waves Risk Forecast Method, system and storage medium | |
CN105139264A (en) | Photovoltaic generation capacity prediction method based on particle swarm algorithm wavelet neural network | |
CN104732296A (en) | Modeling method for distributed photovoltaic output power short-term prediction model | |
Cao et al. | Multi-step wind power forecasting model using LSTM networks, similar time series and LightGBM | |
CN114970362B (en) | Power grid load scheduling prediction method and system under multi-energy structure | |
Li et al. | A novel combined prediction model for monthly mean precipitation with error correction strategy | |
CN104657584A (en) | Lorenz-system-based wind speed prediction method | |
CN103020485A (en) | Short-term wind speed forecast method based on beta noise kernel ridge regression technology | |
CN106374531A (en) | Evaluation method for photovoltaic storage energy exchange index of active power distribution network | |
Omeje et al. | Performance of hybrid neuro-fuzzy model for solar radiation simulation at Abuja, Nigeria: A correlation based input selection technique | |
Jiang et al. | Assessing the effect of wind power peaking characteristics on the maximum penetration level of wind power | |
Liu et al. | An optimized short-term wind power interval prediction method considering NWP accuracy | |
CN105844350B (en) | Short-term wind power prediction system based on covariance optimal combination model | |
CN105138729A (en) | Filling method based on PSO-GRNN (Particle Swarm Optimization-Generalized Regression Neural Network) for defect wind speed values of wind turbines in wind power plant | |
CN114330110A (en) | Model training method, photovoltaic power generation power prediction method and system | |
Zhao et al. | Short-term load forecasting based on RBF neural network | |
CN116760006A (en) | Wind power prediction method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20151209 |