CN108196317A - A kind of Predictive meteorological methods for micro-grid system - Google Patents
A kind of Predictive meteorological methods for micro-grid system Download PDFInfo
- Publication number
- CN108196317A CN108196317A CN201810116434.6A CN201810116434A CN108196317A CN 108196317 A CN108196317 A CN 108196317A CN 201810116434 A CN201810116434 A CN 201810116434A CN 108196317 A CN108196317 A CN 108196317A
- Authority
- CN
- China
- Prior art keywords
- weather
- weather information
- information
- bureau
- local
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
Landscapes
- Environmental & Geological Engineering (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
It is specific as follows the invention discloses a kind of Predictive meteorological methods for micro-grid system：Step 1: the local weather information R of timing acquiring t momenttAnd it stores；Step 2: obtain the data below that address is identical with the address in step 1, time point is identical with time point in step 1 from National Meteorological Bureau：It obtains the true weather information of weather bureau's history and stores；It obtains and is known as F1 with the corresponding weather bureau's historical forecast weather information of the true weather information of weather bureau's history, weather bureau's historical forecast weather informationt；Obtain weather bureau's long-range weather forecast information, weather bureau long-range weather forecast information F1'tIt represents；Step 3: subsequent time weather information is predicted using Smoothness Index method：Step 4: using linear regression method, by F1t、F2tAs input, RtAs target column, an optimization weather information regression model is fitted, and goes out the weather information of following a period of time according to the model prediction；The present invention obtains more accurate weather prognosis data.
Description
Technical field
The present invention relates to micro-capacitance sensor technical fields, particularly a kind of Predictive meteorological methods for micro-grid system.
Background technology
With the continuous expansion of power grid scale, the drawbacks of ultra-large electric system, also increasingly shows especially, of high cost, operation
Difficulty is big, it is difficult to adapt to the higher and higher security and reliability requirement of user and diversified power demands.Especially in recent years
To come in the range of the world after large area blackout several times occurs in succession, the fragility of power grid fully exposes out, therefore point
Schedule has been put in cloth power generation.Renewable energy power generation has become the important impetus of power system development, is intelligent electricity
The important component of net, and more and more important role will be played the part of in Future Power System.Then countries in the world are opened one after another
Begin to pay close attention to environmentally friendly, efficient and flexible generation mode --- distributed power generation.In order to eliminate the various problems of distributed power generation,
To coordinate the contradiction between bulk power grid and distributed generation resource, fully excavate value that distributed generation resource brought for power grid and user and
Benefit, it is proposed that micro-capacitance sensor.
Micro-capacitance sensor is relatively independent generate power for their own use a network system, due to the supply side and use of micro-capacitance sensor
The capacity of electric side is smaller for bulk power grid, and the controllable ability of itself is limited, sometimes will appear electricity it is superfluous or
The situation of person's electricity shortage, thus needs our look-aheads to go out generated energy and electricity consumption, and generated energy and electricity demand forecasting are got over
It is accurately more advantageous to the decision of micro-capacitance sensor.In micro-capacitance sensor, the energy source of power generation is mainly new energy (such as photovoltaic generation, wind turbine
Power generation etc.), and generation of electricity by new energy amount and weather conditions are closely bound up, to a certain extent for, the order of accuarcy of Weather information
Determine the upper limit of generated energy prediction, similary user power utilization amount is also very big with weather conditions correlation.The scale of micro-capacitance sensor is opposite
All smaller, floor space is not very big, so needing relatively precisely to manage the Weather information of position.However, National Meteorological Bureau
The real-time weather information being capable of providing and the information space accuracy that predicts the weather are not too high, and therefore, it is necessary to certain methods solutions
Certainly this problem.Generation of electricity by new energy amount has that precision of prediction is not high and without weather forecasting under network condition at present.
Invention content
The technical problems to be solved by the invention are overcome the deficiencies in the prior art and provide a kind of for micro-grid system
Predictive meteorological methods, the present invention with local meteorological data by merging to obtain more accurate, position precision higher on line
Weather prognosis data.
The present invention uses following technical scheme to solve above-mentioned technical problem：
According to a kind of Predictive meteorological methods for micro-grid system proposed by the present invention, include the following steps：
Step 1: the local weather information R of timing acquiring t momenttAnd it stores；
Step 2: being obtained from National Meteorological Bureau, address is identical with the address in step 1, the time in time point and step 1
The identical data below of point：
It obtains the true weather information of weather bureau's history and stores；
It obtains and the corresponding weather bureau's historical forecast weather information of the true weather information of weather bureau's history, the meteorology
Office's historical forecast weather information is known as F1t；
Obtain weather bureau's long-range weather forecast information, weather bureau long-range weather forecast information F1'tIt represents；
Step 3: subsequent time weather information is predicted using Smoothness Index method：
The detailed process of Smoothness Index method is as follows：
(1) the local weather information R of t moment known totAnd weather bureau's long-range weather forecast information at t-1 moment
F1′t-1；
(2) training smoothing factorIt is required thatThe size of smoothing factor is according to F1't-1And Rt, by formula (1)
Training obtains
Wherein, Rt+1Represent the local weather information at t+1 moment；
(3) one is trained by step (2) to determineValue；
(4) by formula (1) andIt obtains, the meteorological value of t moment prediction obtained by Smoothness Index method is F2t,
Step 4: using linear regression method, by F1t、F2tAs input, RtAs target column, an optimization is fitted
Weather information regression model, and go out according to the model prediction weather information of following a period of time.
Scheme, step are advanced optimized as a kind of Predictive meteorological methods for micro-grid system of the present invention
Four is specific as follows：
Using linear regression method, by F1t、F2tAs input, RtAs target column, the meteorological letter of an optimization is fitted
Cease regression model；
Wherein, Rt={ rt1,rt2,...,rti,...,rtn, rtiRepresent the local weather information R of t momenttI-th kind of meteorology
Type, n represent the type of weather category, RtOne shared n kinds weather category, F1t={ f1t1,f1t2,...,f1ti...,
f1tn, f1tiRepresent F1tI-th kind of weather category, F1tOne shared n kinds weather category, it is local to predict weather information F2t=
{f2t1,f2t2,...,f2ti..., f2tn, f2tiRepresent F2tI-th kind of weather category, F2tOne shared n kinds weather category；
R when taking different moments according to tt,F1t,F2tTraining weather information regression model is as follows：
Wherein, subscript T representing matrixes transposition, cT=[c1,c2,...,ci,...,cn]TIt is the parameter of linear regression model (LRM),
ciRepresent i-th of parameter, c mono- shares n parameter；θT=[θ1,θ2,...,θi,...,θn]TIt is the parameter of linear regression model (LRM),
θiRepresent i-th of parameter, θ mono- shares n parameter；γT=[γ1,γ2,...,γi,...,γn]TIt is linear regression model (LRM)
Parameter, γiRepresent i-th of parameter, γ mono- shares n parameter；
Weather information regression model according to training is obtained relative to RtThe weather information predicted value R at lower a momentt'+1By
Formula (4) obtains
Scheme, step are advanced optimized as a kind of Predictive meteorological methods for micro-grid system of the present invention
It is further comprising the steps of after four：
According to the R acquired in real timetAnd the weather pattern of t moment is corresponded to train K- Neighborhood Models, by the meteorology of prediction
Real-time weather type is calculated in the trained good K- Neighborhood Models of information, be used to implement off-line state Weather information it is aobvious
Show.
Scheme, step are advanced optimized as a kind of Predictive meteorological methods for micro-grid system of the present invention
In one, using the local weather information R of local meteorological information acquisition device timing acquiring t momenttAnd it stores.
Scheme, step are advanced optimized as a kind of Predictive meteorological methods for micro-grid system of the present invention
Second is that completed with reptile library related Python.
The present invention compared with prior art, has following technique effect using above technical scheme：
The present invention with local meteorological data by merging to obtain more accurate, the higher meteorology of position precision on line
Prediction data, while utilize the display of weather pattern under K- nearest neighbor algorithms realization off-line state.
Description of the drawings
Fig. 1 is the flow chart of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with the accompanying drawings and the specific embodiments
The present invention will be described in detail.
Based on the problems in current practical study, the present invention proposes a kind of weather prognosis side for micro-grid system
Method, it includes local meteorological information acquisition device, weather information reptile device, local weather information fallout predictor, optimization weather information mould
Type follower and real-time weather types of display, wherein local meteorological information acquisition device is exactly with locally-installed sensor
Acquire relevant weather information (such as temperature, humidity etc.)；Weather information reptile device mainly includes two parts, and first part is
Weather site history real weather information is crawled, second part is to crawl weather station historical forecast Weather information；Local meteorological letter
Breath fallout predictor is exactly the weather information in the weather information prediction a period of time in future acquired according to local collector；Optimize gas
The weather station history that image information model follower is crawled according to weather information reptile device predict the weather information and weather information it is pre-
The weather information of device prediction is surveyed, then is compared with the information of local meteorological information acquisition device acquisition, it is meteorological to train an optimization
Information model；The weather information value that real-time weather types of display is exported according to optimization weather information model, predicts real-time day
Gas type (fine day, cloudy day etc.).
The present invention provides a kind of local meteorological information acquisition device, weather information reptile device, local weather information predictions
A kind of weather prognosis for micro-grid system of device, optimization weather information model follower and real-time weather types of display
Method solves the problem of when generated energy and electricity consumption are predicted in micro-capacitance sensor, the prediction weather information of use is inaccurate.
The present invention devises a kind of Predictive meteorological methods for micro-grid system, and local meteorological information acquisition device is exactly
Relevant weather information (such as temperature, humidity etc.) is acquired with locally-installed sensor；Weather information reptile device mainly wraps
Two parts are included, first part is to crawl weather site history real weather information, and second part is to crawl weather station to predict the weather
Information；Local weather information fallout predictor is exactly to be predicted according to the weather information that local collector acquires using Smoothness Index algorithm
Weather information in a period of time in future；The training data for optimizing weather information model follower is that weather information reptile device is climbed
Predict the weather information and the weather information of local weather information fallout predictor prediction of the weather station history taken, training objective is this
The true weather information of ground weather information collector acquisition trains an optimization weather information mould using linear regression algorithm
Type, and go out according to the model prediction weather information of following a period of time；Using the weather information of prediction as real-time weather type
The input of display recycles K- nearest neighbor algorithms to provide real-time weather type.
First, architecture
Fig. 1 gives the module map of the present invention, is mainly made of five parts：Local meteorological information acquisition device, weather information
Reptile device, local weather information fallout predictor, optimization weather information model follower and real-time weather types of display, wherein
Local meteorological information acquisition device is exactly to acquire relevant weather information (such as temperature, humidity with locally-installed sensor
Deng)；Weather information reptile device mainly includes two parts, and first part is to crawl weather site history real weather information, and second
Part is to crawl weather station historical forecast Weather information；Local weather information fallout predictor is exactly to be acquired according to local collector
Weather information in weather information prediction a period of time in future；Optimize weather information model follower according to weather information reptile
The weather station history that device crawls predict the weather information and weather information fallout predictor prediction weather information, then with local meteorology
The information of information acquisition device acquisition compares, and trains an optimization weather information model；Real-time weather types of display according to
Optimize the weather information value of weather information model output, predict real-time weather pattern (fine day, cloudy day etc.).
It is specific below to introduce：
Local meteorological information acquisition device：The local history weather information data of storage and the local meteorological data of acquisition in real time.
It is written in database from the collected data transmission of end sensor, is provided conveniently for digital independent below and processing.
Weather information reptile device：So-called reptile is exactly to use Python tool automatically downloading data from network, mainly
There are two modules, and the first module is to swash that the true meteorological data of history is taken to adopt with corresponding local from national weather board web
The meteorological data of collection compares, it is found that data are not fully consistent, because the meteorological data positional precision of weather bureau's acquisition is not
It is high, it is impossible to the weather information in accurate description micro-capacitance sensor location.Second module crawls the weather information of prediction from weather bureau, this
Including historical forecast weather information and future anticipation weather information, historical forecast weather information and local weather information are pre-
The weather information for surveying device prediction is combined training optimization weather information model.
Local weather information fallout predictor：Module setting will utilize the prediction of Smoothness Index algorithm not at regular intervals
Carry out the weather information of a period of time, this period of prediction is corresponding with the prediction meteorological data that weather information reptile device crawls.
Optimize weather information model follower：The effect of the module is mainly using respectively from weather information reptile device
The local of collected corresponding time is approached as far as possible with the meteorological datas of two groups of predictions of local weather information fallout predictor
Weather information.Specific practice：Using linear regression algorithm, two prediction meteorological datas as input, local meteorological data is worked as
Target column (output) is done, fits an optimization weather information regression model, and following a period of time is gone out according to the model prediction
Weather information, which is more in line with the environment residing for micro-capacitance sensor.
Real-time weather types of display：The function of the module is mainly the data that are acquired according to local collector and right
Weather pattern in meteorological reptile device between seasonable, weather information using the prediction of optimization weather information model follower as inputting,
K- nearest neighbor algorithms is recycled to provide real-time weather type.
2nd, method flow
1. local meteorological information acquisition device：
1 data storage format of table (example)
The meteorological data that acquisition comes according to table 1 form store, it is using time as index acquired from sensor it is each
Meteorological data simultaneously stores, and is used for other steps, which is denoted as R.
2. weather information reptile device：
First module crawls the true weather information of history and stores, and storage format is as table 1, time granularity
Also it is consistent with table 1；Second functions of modules mainly crawl with the corresponding prediction meteorological data of true weather information,
It is called historical forecast weather information F1, in addition also to crawl following weather forecast information, also referred to as future anticipation weather information
F'1.What above step was completed with reptile library related Python.
3. local weather information fallout predictor：Module setting will utilize Smoothness Index algorithm to predict at regular intervals
The prediction meteorological data time that the weather information of following a period of time, this period of prediction and weather information reptile device crawl
Granularity is corresponding.
The detailed process of Smoothness Index algorithm is as follows：
(5) the known local weather information at this moment and the local weather prognosis information at this moment；
(6) training smoothing factor(it is required that), the size of smoothing factor is according to past prediction number F2With
Actual number R compares, according to formula (1) train come
Wherein RnextRepresent the true meteorological data of subsequent time.
(3) one can be trained by step (2) to determineValue, this will can be predicted according to the weather information of eve
The meteorological data of subsequent time.
4. optimize weather information model follower：
The effect of the module mainly utilizes two respectively from weather information reptile device and local weather information fallout predictor
The meteorological data of prediction is organized to approach the local weather information of collected corresponding time as far as possible.Specific practice：Utilize line
Property regression algorithm, two prediction meteorological data F1、F2As input, local meteorological data R is as target column (output), fitting
Go out an optimization weather information regression model, and go out the weather information of following a period of time according to the model prediction.It is local meteorological
Information collection R={ r1,r2,...,ri,...,rn, wherein riRepresent i-th kind of weather category, historical forecast weather information F1=
{f11,f12,...,f1i..., f1n, wherein f1iRepresent i-th kind of weather category, it is local to predict weather information F2={ f21,
f22,...,f2i..., f2n}。
It is as follows according to regression equation：
Wherein fPrediction 1, fPrediction 2..., fPredict i...,fPredict nIt is the weather category to be predicted, with true when training pattern
Local weather information, ci,θi,γiThe parameter in linear regression training process is represented respectively.Finally, RnextAnd F'1As defeated
Enter, the prediction weather information F after one group of optimization can be obtainedPrediction={ fPrediction 1, fPrediction 2,...,fPredict i..., fPredict n}。FPredictionIt can be more
Good embodiment weather information, position precision higher provide more accurately data for other modules in micro-capacitance sensor, optimize micro- electricity
The operation of net improves the benefit of micro-capacitance sensor.
5. real-time weather types of display：
The function of the module is mainly in the data acquired according to local collector and the meteorological reptile device for corresponding to the time
Weather pattern, such as A moment locals weather information are RA, corresponding weather pattern is fine day, is trained according to true weather value
Model K- Neighborhood Models using the weather information of optimization weather information model follower prediction as input, recycle K- neighbour's moulds
Type provides real-time weather type, can thus realize the display of the Weather information of off-line state, while more accurate.
The present invention proposes a kind of method of the optimization micro-capacitance sensor based on weather information, is mainly adopted by local weather information
Storage, weather information reptile device, local weather information fallout predictor, optimization weather information model follower and real-time weather type
Five part such as display forms, and by merging to obtain with local meteorological data on line, more accurate, position precision is higher
Weather prognosis data, while using the meteorological data locally acquired weather pattern under off-line state is realized using K- nearest neighbor algorithms
Display.
For the convenience of description, we assume that there is following application example：
Certain school's subject building micro-grid system, including photovoltaic generation, wind turbine power generation, classroom electricity consumption and energy management system
System, below just specifically introduced by taking this system as an example.
(1) local meteorological information acquisition device.The system passes through sensor collecting temperature, humidity, wind direction, wind speed, atmospheric pressure
And irradiation level, it is stored in inside database.
(2) weather information reptile device.The Weather information of weather station is downloaded by Python reptiles, including the true gas of history
Image information and prediction weather information, wherein prediction weather information includes historical forecast weather information again and future anticipation meteorology is believed
Breath.The weather category crawled be temperature, humidity, wind direction, wind speed, atmospheric pressure, irradiation level and weather pattern (fine day, rainy day etc.),
And time granularity is consistent with local meteorological information acquisition device.
(3) local weather information fallout predictor.Smoothness Index algorithm is utilized according to existing collected history weather information
The weather information value of prediction following a period of time.
(4) optimize weather information model follower.The effect of the module is mainly using respectively from weather information reptile
The meteorological datas of two groups of predictions of device and local weather information fallout predictor approaches the sheet of collected corresponding time as far as possible
Ground weather information.Specific practice：Using linear regression method, by F1t、F2tAs input, RtAs target column, one is fitted
Optimize weather information regression model；
Wherein, Rt={ rt1,rt2,...,rti,...,rtn, rtiRepresent the local weather information R of t momenttI-th kind of meteorology
Type, n represent the type of weather category, RtOne shared n kinds weather category, F1t={ f1t1,f1t2,...,f1ti...,
f1tn, f1tiRepresent F1tI-th kind of weather category, F1tOne shared n kinds weather category, it is local to predict weather information F2t=
{f2t1,f2t2,...,f2ti..., f2tn, f2tiRepresent F2tI-th kind of weather category, F2tOne shared n kinds weather category；
R when taking different moments according to tt,F1t,F2tTraining weather information regression model is as follows：
Wherein, subscript T representing matrixes transposition, cT=[c1,c2,...,ci,...,cn]TIt is the parameter of linear regression model (LRM),
ciRepresent i-th of parameter, c mono- shares n parameter；θT=[θ1,θ2,...,θi,...,θn]TIt is the parameter of linear regression model (LRM),
θiRepresent i-th of parameter, θ mono- shares n parameter；γT=[γ1,γ2,...,γi,...,γn]TIt is linear regression model (LRM)
Parameter, γiRepresent i-th of parameter, γ mono- shares n parameter；
Weather information regression model according to training is obtained relative to RtThe weather information predicted value R at lower a momentt'+1By
Formula (4) obtains
(5) real time information display.According to collected weather information, real-time weather is obtained using K- nearest neighbor algorithms
Type, and be shown on micro-capacitance sensor control flow.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, and appoints
What those familiar with the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in, all
It should cover within the scope of the present invention.
Claims (5)
1. a kind of Predictive meteorological methods for micro-grid system, which is characterized in that include the following steps：
Step 1: the local weather information R of timing acquiring t momenttAnd it stores；
Step 2: being obtained from National Meteorological Bureau, address is identical with the address in step 1, time point phase in time point and step 1
Same data below：
It obtains the true weather information of weather bureau's history and stores；
It obtains and the corresponding weather bureau's historical forecast weather information of the true weather information of weather bureau's history, weather bureau's history
Prediction weather information is known as F1t；
Obtain weather bureau's long-range weather forecast information, weather bureau long-range weather forecast information F1'tIt represents；
Step 3: subsequent time weather information is predicted using Smoothness Index method：
The detailed process of Smoothness Index method is as follows：
(1) the local weather information R of t moment known totAnd the weather bureau long-range weather forecast information F1 ' at t-1 momentt-1；
(2) training smoothing factorIt is required thatThe size of smoothing factor is according to F1't-1And Rt, trained by formula (1)
It arrives
Wherein, Rt+1Represent the local weather information at t+1 moment；
(3) one is trained by step (2) to determineValue；
(4) by formula (1) andIt obtains, the meteorological value of t moment prediction obtained by Smoothness Index method is F2t,
Step 4: using linear regression method, by F1t、F2tAs input, RtAs target column, it is meteorological to fit an optimization
Information regression model, and go out according to the model prediction weather information of following a period of time.
2. a kind of Predictive meteorological methods for micro-grid system according to claim 1, which is characterized in that step 4 has
Body is as follows：
Using linear regression method, by F1t、F2tAs input, RtAs target column, fit an optimization weather information and return
Model；
Wherein, Rt={ rt1,rt2,...,rti,...,rtn, rtiRepresent the local weather information R of t momenttI-th kind of weather category,
N represents the type of weather category, RtOne shared n kinds weather category, F1t={ f1t1,f1t2,...,f1ti..., f1tn, f1tiTable
Show F1tI-th kind of weather category, F1tOne shared n kinds weather category, it is local to predict weather information F2t={ f2t1,f2t2,...,
f2ti..., f2tn, f2tiRepresent F2tI-th kind of weather category, F2tOne shared n kinds weather category；
R when taking different moments according to tt,F1t,F2tTraining weather information regression model is as follows：
Wherein, subscript T representing matrixes transposition, cT=[c1,c2,...,ci,...,cn]TIt is the parameter of linear regression model (LRM), ciIt represents
I-th of parameter, c mono- share n parameter；θT=[θ1,θ2,...,θi,...,θn]TIt is the parameter of linear regression model (LRM), θiIt represents
I-th of parameter, θ mono- share n parameter；γT=[γ1,γ2,...,γi,...,γn]TIt is the parameter of linear regression model (LRM),
γiRepresent i-th of parameter, γ mono- shares n parameter；
Weather information regression model according to training is obtained relative to RtThe weather information predicted value R ' at lower a momentt+1By formula
(4) it obtains
3. a kind of Predictive meteorological methods for micro-grid system according to claim 1, which is characterized in that after step 4
It is further comprising the steps of：
According to the R acquired in real timetAnd the weather pattern of t moment is corresponded to train K- Neighborhood Models, the weather information of prediction is passed through
Real-time weather type is calculated in trained K- Neighborhood Models, is used to implement the display of the Weather information of off-line state.
A kind of 4. Predictive meteorological methods for micro-grid system according to claim 1, which is characterized in that step 1
In, using the local weather information R of local meteorological information acquisition device timing acquiring t momenttAnd it stores.
5. a kind of Predictive meteorological methods for micro-grid system according to claim 1, which is characterized in that step 2 is
It is completed with reptile library related Python.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810116434.6A CN108196317B (en) | 2018-02-06 | 2018-02-06 | Meteorological prediction method for micro-grid system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810116434.6A CN108196317B (en) | 2018-02-06 | 2018-02-06 | Meteorological prediction method for micro-grid system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108196317A true CN108196317A (en) | 2018-06-22 |
| CN108196317B CN108196317B (en) | 2019-12-13 |
Family
ID=62592546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810116434.6A Active CN108196317B (en) | 2018-02-06 | 2018-02-06 | Meteorological prediction method for micro-grid system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108196317B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358381A (en) * | 2018-09-12 | 2019-02-19 | 浙江省气象科学研究所 | A kind of website forecast correction wind method |
| CN109471205A (en) * | 2018-10-18 | 2019-03-15 | 国网山东省电力公司应急管理中心 | A kind of monitoring and pre-alarming method based on gridding meteorological data in grid operation |
| CN109541728A (en) * | 2018-10-18 | 2019-03-29 | 国网山东省电力公司应急管理中心 | A kind of electricity power engineering project meteorologic early-warning method |
| CN111339392A (en) * | 2020-03-27 | 2020-06-26 | 中国科学院大气物理研究所 | Sky blue index determination method and system based on meteorological elements |
| CN111695736A (en) * | 2020-06-15 | 2020-09-22 | 河北锐景能源科技有限公司 | Photovoltaic power generation short-term power prediction method based on multi-model fusion |
| CN112489387A (en) * | 2020-12-04 | 2021-03-12 | 广东电网有限责任公司江门供电局 | Power distribution construction site safety early warning method based on weather monitoring |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634721A (en) * | 2009-04-15 | 2010-01-27 | 华东师范大学第二附属中学 | Historical data based intelligent early warning system for typhoon and flood |
| CN101893726A (en) * | 2010-07-23 | 2010-11-24 | 北京师范大学 | Aeolian sand disaster simulating device and method |
| CN103499846A (en) * | 2013-09-03 | 2014-01-08 | 百度在线网络技术（北京）有限公司 | Method and equipment for predicting weather conditions |
-
2018
- 2018-02-06 CN CN201810116434.6A patent/CN108196317B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634721A (en) * | 2009-04-15 | 2010-01-27 | 华东师范大学第二附属中学 | Historical data based intelligent early warning system for typhoon and flood |
| CN101893726A (en) * | 2010-07-23 | 2010-11-24 | 北京师范大学 | Aeolian sand disaster simulating device and method |
| CN103499846A (en) * | 2013-09-03 | 2014-01-08 | 百度在线网络技术（北京）有限公司 | Method and equipment for predicting weather conditions |
Non-Patent Citations (2)
| Title |
|---|
| 侯琼煌: "基于三次指数平滑模型的雾霾天气分析与预测", 《环境保护科学》 * |
| 谭风雷 等: "一种改进的指数平滑负荷预测方法研究", 《电力需求侧管理》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358381A (en) * | 2018-09-12 | 2019-02-19 | 浙江省气象科学研究所 | A kind of website forecast correction wind method |
| CN109471205A (en) * | 2018-10-18 | 2019-03-15 | 国网山东省电力公司应急管理中心 | A kind of monitoring and pre-alarming method based on gridding meteorological data in grid operation |
| CN109541728A (en) * | 2018-10-18 | 2019-03-29 | 国网山东省电力公司应急管理中心 | A kind of electricity power engineering project meteorologic early-warning method |
| CN109471205B (en) * | 2018-10-18 | 2022-01-04 | 国网山东省电力公司应急管理中心 | Monitoring and early warning method based on gridding meteorological data in power grid operation |
| CN111339392A (en) * | 2020-03-27 | 2020-06-26 | 中国科学院大气物理研究所 | Sky blue index determination method and system based on meteorological elements |
| CN111339392B (en) * | 2020-03-27 | 2023-02-03 | 中国科学院大气物理研究所 | Sky blue index determination method and system based on meteorological elements |
| CN111695736A (en) * | 2020-06-15 | 2020-09-22 | 河北锐景能源科技有限公司 | Photovoltaic power generation short-term power prediction method based on multi-model fusion |
| CN111695736B (en) * | 2020-06-15 | 2023-04-21 | 河北锐景能源科技有限公司 | Photovoltaic power generation short-term power prediction method based on multi-model fusion |
| CN112489387A (en) * | 2020-12-04 | 2021-03-12 | 广东电网有限责任公司江门供电局 | Power distribution construction site safety early warning method based on weather monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108196317B (en) | 2019-12-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108196317A (en) | A kind of Predictive meteorological methods for micro-grid system | |
| Zhang et al. | A review of urban energy systems at building cluster level incorporating renewable-energy-source (RES) envelope solutions | |
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| Zhao et al. | Multi-objective optimization of stand-alone hybrid PV-wind-diesel-battery system using improved fruit fly optimization algorithm | |
| CN106651200A (en) | Electrical load management method and system for industrial enterprise aggregate user | |
| CN107591844A (en) | Consider the probabilistic active distribution network robust reconstructing method of node injecting power | |
| KR101476522B1 (en) | System for predicting energy producing quantity | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| Zhang et al. | Data augmentation for improving heating load prediction of heating substation based on TimeGAN | |
| CN103699944A (en) | Wind and photovoltaic generation power prediction system with multiple prediction modes | |
| Yuan et al. | Attention mechanism-based transfer learning model for day-ahead energy demand forecasting of shopping mall buildings | |
| CN104463356A (en) | Photovoltaic power generation power prediction method based on multi-dimension information artificial neural network algorithm | |
| US20240054267A1 (en) | Method for planning a layout of a renewable energy site | |
| CN109449987A (en) | The power system simulation method and system of new energy power generation grid-connection | |
| CN116128094A (en) | Industrial park energy management system and method based on digital twinning | |
| CN103996087A (en) | Method and system for forecasting new energy power generation power | |
| CN112182951A (en) | Land utilization planning method considering multiple uncertainties | |
| CN115455811A (en) | Photovoltaic power station battery panel arrangement method based on digital twinning and deep reinforcement learning | |
| CN109961182A (en) | Power supply data management method and device, computer equipment and storage medium | |
| CN109087215A (en) | More Power Output for Wind Power Field joint probability density prediction techniques | |
| CN117039852A (en) | Power prediction method, device, equipment and storage medium of wind-solar-water complementary power station | |
| Jimenez et al. | The role of artificial intelligence in Latin Americas energy transition | |
| Tiwari | Wind speed forecasting methods for wind energy generation | |
| Gao et al. | Adversarial discriminative domain adaptation for solar radiation prediction: A cross-regional study for zero-label transfer learning in Japan | |
| CN110147908A (en) | A kind of wind power forecasting method based on three-dimensional optimal similarity and improvement cuckoo algorithm |
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 |