CN108196317B - Meteorological prediction method for micro-grid system - Google Patents
Meteorological prediction method for micro-grid system Download PDFInfo
- Publication number
- CN108196317B CN108196317B CN201810116434.6A CN201810116434A CN108196317B CN 108196317 B CN108196317 B CN 108196317B CN 201810116434 A CN201810116434 A CN 201810116434A CN 108196317 B CN108196317 B CN 108196317B
- Authority
- CN
- China
- Prior art keywords
- weather
- information
- meteorological
- time
- bureau
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
The invention discloses a weather prediction method for a micro-grid system, which comprises the following specific steps: step one, collecting local meteorological information R at time t regularlytAnd storing the data; step two, acquiring the following data with the same address and the same time point as the address and the time point in the step one from the national weather bureau: acquiring and storing historical and real meteorological information of a meteorological bureau; acquiring historical forecast weather information of the weather bureau corresponding to the real weather information of the history of the weather bureau, wherein the historical forecast weather information of the weather bureau is called F1t(ii) a Obtaining future weather forecast information of a weather bureau, wherein the future weather forecast information of the weather bureau is F1'tRepresents; step three, predicting the meteorological information at the next moment by adopting a smoothing index method: step four, utilizing a linear regression method to convert F1t、F2tas input, RtFitting an optimized meteorological information regression model as a target column, and predicting meteorological information of a future period of time according to the model; the invention obtains more accurate meteorological prediction data.
Description
Technical Field
The invention relates to the technical field of micro-grids, in particular to a weather prediction method for a micro-grid system.
Background
With the continuous expansion of the power grid scale, the defects of a super-large-scale power system are increasingly highlighted, the cost is high, the operation difficulty is high, and the requirements of users on higher safety and reliability and diversified power supply requirements are difficult to adapt. Especially, after several large-area power failure accidents occur in succession worldwide in recent years, the vulnerability of the grid is sufficiently exposed, and thus distributed power generation is proposed. Renewable energy power generation has become an important driving force for the development of power systems, is an important component of smart grids, and will play an increasingly important role in future power systems. Therefore, various countries in the world begin to pay attention to an environment-friendly, efficient and flexible power generation mode, namely distributed power generation. In order to eliminate various problems of distributed power generation, provide a micro-grid for coordinating contradictions between a large power grid and a distributed power supply and fully mining the value and benefit of the distributed power supply for the power grid and users.
The micro-grid is a relatively independent self-generation self-utilization power grid system, and because the capacities of the power supply side and the power utilization side of the micro-grid are smaller than those of a large power grid, the self-regulation and control capability is limited, and the situation of excess electric quantity or shortage of electric quantity sometimes occurs, so that the generated energy and the power consumption are required to be predicted in advance, and the more accurate the prediction of the generated energy and the power consumption is, the more beneficial the decision of the micro-grid is. In the microgrid, the energy source of power generation is mainly new energy (such as photovoltaic power generation, fan power generation and the like), the power generation amount of the new energy is closely related to weather factors, the accuracy of weather information determines the upper limit of power generation amount prediction to a certain extent, and the power consumption of a user is also greatly related to the weather factors. The micro-grid is relatively small in scale and small in floor area, so weather information of a relatively precise geographical position is needed. However, the real-time weather information and the predicted weather information provided by the national weather service are not very accurate in space, and therefore, some method is needed to solve the problem. The problems of low prediction precision and weather prediction under the network-free condition exist in the current new energy power generation amount.
Disclosure of Invention
the invention aims to solve the technical problem of overcoming the defects of the prior art and provides a meteorological prediction method for a microgrid system.
The invention adopts the following technical scheme for solving the technical problems:
the invention provides a meteorological prediction method for a micro-grid system, which comprises the following steps:
Step one, collecting local meteorological information R at time t regularlytAnd storing the data;
Step two, acquiring the following data with the same address and the same time point as the address and the time point in the step one from the national weather bureau:
Acquiring and storing historical and real meteorological information of a meteorological bureau;
Obtaining and comparing the historical truth of the meteorological bureauThe weather bureau historical predicted weather information corresponding to the weather information of (a), the weather bureau historical predicted weather information is called F1t；
Obtaining future weather forecast information of a weather bureau, wherein the future weather forecast information of the weather bureau is F1'tRepresents;
Step three, predicting the meteorological information at the next moment by adopting a smoothing index method:
The specific process of the smoothing index method is as follows:
(1) The local meteorological information R at the known time ttAnd weather forecast information of weather bureau at t-1
F1't-1；
(2) Training smoothing coefficientsRequire thatThe magnitude of the smoothing factor is according to F1't-1And RtIs obtained by the training of formula (1)
wherein R ist+1Local weather information representing the time t + 1;
(3) Training a determination from step (2)a value;
(4) Is represented by the following formula (1) andthe predicted weather value at the time t obtained by the smoothing index method is F2t，
Step four, utilizing a linear regression method to convert F1t、F2tAs input, RtAnd fitting an optimized meteorological information regression model as an object list, and predicting meteorological information of a future period of time according to the model.
As a further optimization scheme of the weather prediction method for the micro-grid system, the fourth step is as follows:
Using a linear regression method, F1t、F2tas input, RtFitting an optimized meteorological information regression model as a target column;
Wherein R ist＝{rt1,rt2,...,rti,...,rtn}，rtiLocal weather information R representing time ttthe ith weather type, n represents the type of the weather type, Rta total of n weather types, F1t＝{f1t1,f1t2,...,f1ti，...,f1tn}，f1tirepresentation F1tOf the ith weather type, F1ta total of n weather types, local forecast weather information F2t＝{f2t1,f2t2,...,f2ti，...,f2tn}，f2tirepresentation F2tOf the ith weather type, F2tA total of n weather types;
Taking R at different times according to tt,F1t,F2tTraining a meteorological information regression model as follows:
Wherein the superscript T denotes the matrix transposition, cT＝[c1,c2,...,ci,...,cn]TIs a parameter of the linear regression model, ciRepresents the ith parameter, and c has n parameters in total; thetaT＝[θ1,θ2,...,θi,...,θn]Tis a parameter of a linear regression model，θirepresents the ith parameter, and theta has n parameters in total; gamma rayT＝[γ1,γ2,...,γi,...,γn]TIs a parameter of a linear regression model, gammaiRepresents the ith parameter, and gamma has n parameters in total;
Obtaining a relative R according to a trained meteorological information regression modeltWeather information predicted value R of next momentt'+1Obtained from the formula (4)
As a further optimization scheme of the weather prediction method for the micro-grid system, the method further comprises the following steps after the fourth step:
According to real-time acquired RtAnd training a K-neighbor model corresponding to the weather type at the time t, and calculating the predicted weather information through the trained K-neighbor model to obtain a real-time weather type for displaying the weather information in an off-line state.
As a further optimization scheme of the weather prediction method for the micro-grid system, in the first step, the local weather information R at the t moment is regularly acquired by a local weather information collectortAnd stored.
the further optimization scheme of the weather prediction method for the micro-grid system is completed by using a crawler library related to Python.
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
the invention obtains more accurate meteorological forecast data with higher position accuracy by fusing online meteorological data with local meteorological data, and simultaneously realizes the display of the weather type in an offline state by utilizing a K-nearest neighbor algorithm.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Based on the problems in the current practical research, the invention provides a weather prediction method for a micro-grid system, which comprises a local weather information collector, a weather information crawler, a local weather information predictor, an optimized weather information model output device and a real-time weather type display, wherein the local weather information collector collects relevant weather information (such as temperature, humidity and the like) by using a sensor which is locally installed; the weather information crawler mainly comprises two parts, wherein the first part is historical real weather information of a crawled meteorological station, and the second part is historical predicted weather information of the crawled meteorological station; the local weather information predictor is used for predicting weather information in a period of time in the future according to the weather information acquired by the local collector; the optimized meteorological information model output device is used for training an optimized meteorological information model according to historical predicted weather information of a meteorological station, which is crawled by a meteorological information crawler, and meteorological information predicted by a meteorological information predictor, and then comparing the predicted weather information with information collected by a local meteorological information collector; and the real-time weather type display predicts the real-time weather type (sunny days, cloudy days and the like) according to the weather information value output by the optimized weather information model.
the invention provides a weather prediction method for a microgrid system, which comprises a local weather information collector, a weather information crawler, a local weather information predictor, an optimized weather information model output device and a real-time weather type display, and solves the problem that the adopted predicted weather information is inaccurate when the generated energy and the power consumption are predicted in the microgrid.
The invention designs a weather prediction method for a micro-grid system.A local weather information collector collects relevant weather information (such as temperature, humidity and the like) by using a sensor which is locally installed; the weather information crawler mainly comprises two parts, wherein the first part is used for crawling historical real weather information of a weather station, and the second part is used for crawling predicted weather information of the weather station; the local weather information predictor is used for predicting weather information in a future period of time by using a smoothing index algorithm according to the weather information acquired by the local collector; training data of an optimized meteorological information model output device are historical predicted weather information of a meteorological station and predicted meteorological information of a local meteorological information predictor, which are crawled by a meteorological information crawler, a training target is real meteorological information acquired by a local meteorological information acquisition device, an optimized meteorological information model is trained by utilizing a linear regression algorithm, and meteorological information of a future period of time is predicted according to the model; and the predicted weather information is used as the input of the real-time weather type display, and the real-time weather type is given by utilizing a K-nearest neighbor algorithm.
One, architecture
fig. 1 shows a block diagram of the present invention, which mainly consists of five parts: the system comprises a local meteorological information collector, a meteorological information crawler, a local meteorological information predictor, an optimized meteorological information model output device and a real-time meteorological display, wherein the local meteorological information collector collects relevant meteorological information (such as temperature, humidity and the like) by using a locally-installed sensor; the weather information crawler mainly comprises two parts, wherein the first part is historical real weather information of a crawled meteorological station, and the second part is historical predicted weather information of the crawled meteorological station; the local weather information predictor is used for predicting weather information in a period of time in the future according to the weather information acquired by the local collector; the optimized meteorological information model output device is used for training an optimized meteorological information model according to historical predicted weather information of a meteorological station, which is crawled by a meteorological information crawler, and meteorological information predicted by a meteorological information predictor, and then comparing the predicted weather information with information collected by a local meteorological information collector; and the real-time weather type display predicts the real-time weather type (sunny days, cloudy days and the like) according to the weather information value output by the optimized weather information model.
The following is a detailed description:
Local meteorological information collector: storing local historical meteorological information data and collecting local meteorological data in real time. And the data collected from the terminal sensor is transmitted and written into the database, so that convenience is provided for later data reading and processing.
Weather information crawler: the crawler is to use Python language tool to automatically download data from the network, and mainly comprises two modules, wherein the first module is used for crawling real historical meteorological data from a national meteorological bureau website and comparing the real historical meteorological data with corresponding locally acquired meteorological data, and the data can be found to be not completely consistent, because the position precision of the meteorological data acquired by the meteorological bureau is not high, the meteorological information of the place where the micro-grid is located can not be accurately described. The second module crawls predicted weather information from a weather bureau, wherein the predicted weather information comprises historical predicted weather information and future predicted weather information, and the historical predicted weather information is combined with the weather information predicted by the local weather information predictor to train an optimized weather information model.
Local weather information predictor: the module is set to predict weather information at intervals in the future by using a smoothing index algorithm, and the predicted time corresponds to the predicted weather data crawled by the weather information crawler.
optimizing a meteorological information model output device: the module mainly has the function of approaching the collected local meteorological information at corresponding time as far as possible by utilizing two groups of predicted meteorological data from the meteorological information crawler and the local meteorological information predictor respectively. The method comprises the following specific steps: and (3) by utilizing a linear regression algorithm, taking the two predicted meteorological data as input, taking the local meteorological data as a target list (output), fitting an optimized meteorological information regression model, and predicting meteorological information of a period of time in the future according to the model, wherein the position accuracy of the meteorological information is higher, and the meteorological information is more in line with the environment of the microgrid.
Real-time weather-type displays: the module has the functions that weather information predicted by the optimized weather information model output device is used as input according to data collected by the local collector and the weather type in the weather crawler at the corresponding time, and then the real-time weather type is given by utilizing a K-nearest neighbor algorithm.
Second, the method flow
1. Local meteorological information collector:
TABLE 1 forms of data storage (examples)
the collected meteorological data are stored according to the format of the table 1, each meteorological data are collected from the sensors by taking time as an index and are stored for other steps, and the real data are marked as R.
2. weather information crawler:
the first module crawls and stores historical real meteorological information, the storage format is the same as that of the table 1, and the time granularity is consistent with that of the table 1; the second module mainly has the function of crawling predicted meteorological data corresponding to the real meteorological information, namely historical predicted meteorological information F1further, future weather forecast information, also called future predicted weather information F ', is crawled'1. The above steps are done using a Python-related crawler library.
3. Local weather information predictor: the module is set to predict weather information at intervals in the future by using a smoothing index algorithm, and the predicted time corresponds to the time granularity of the predicted weather data crawled by the weather information crawler.
The specific process of the smoothing exponential algorithm is as follows:
(1) The local weather information at the moment and the local weather prediction information at the moment are known;
(2) Training smoothing coefficients(claim for) The magnitude of the smoothing coefficient is based on the past prediction number F2Compared with the actual number R, trained according to equation (1)
Wherein R isnextrepresenting the real weather data at the next moment.
(3) From step (2), a determination can be trainedTherefore, the meteorological data at the next moment can be predicted according to the meteorological information at the previous moment.
4. optimizing a meteorological information model output device:
The module mainly has the function of approaching the collected local meteorological information at corresponding time as far as possible by utilizing two groups of predicted meteorological data from the meteorological information crawler and the local meteorological information predictor respectively. The method comprises the following specific steps: two predicted meteorological data F are processed by linear regression algorithm1、F2The local meteorological data R is used as an input and is used as a target column (output), an optimized meteorological information regression model is fitted, and meteorological information of a future period of time is predicted according to the model. Local meteorological information set R ═ R1,r2,...,ri,...,rnIn which r isiIndicating the ith weather type and historical predicted weather information F1＝{f11,f12,...,f1i，...,f1nIn which f1iindicating the ith weather type, local forecast weather information F2＝{f21,f22,...,f2i，...,f2n}。
according to the regression equation:
wherein f isPrediction 1，fPrediction 2，...,fPrediction of i...,fpredicting nIs the weather type to be predicted, uses the real local weather information when training the model, ci,θi,γiRespectively representing parameters in the linear regression training process. Finally, R is putnextAnd F'1as input, a set of optimized predicted weather information F can be obtainedPrediction＝{fPrediction 1，fprediction 2,...,fprediction of i，...,fPredicting n}。FPredictionCan better reflect meteorological information, has higher position accuracy and is suitable for other micro-gridsThe module provides more accurate data, optimizes the operation of the microgrid and improves the benefit of the microgrid.
5. Real-time weather-type displays:
The module mainly has the function that the local meteorological information at the A moment is R, for example, according to the data collected by the local collector and the weather type in the meteorological crawler at the corresponding timeAAnd the corresponding weather type is sunny, the model K-neighbor model is trained according to the real weather value, the weather information predicted by the optimized weather information model output device is used as input, and the K-neighbor model is used for providing the real-time weather type, so that the off-line weather information can be displayed, and the off-line weather information is more accurate.
The invention provides a method for optimizing a microgrid based on meteorological information, which mainly comprises five parts, namely a local meteorological information collector, a meteorological information crawler, a local meteorological information predictor, an optimized meteorological information model output device, a real-time weather type display and the like, wherein more accurate meteorological prediction data with higher position accuracy are obtained by fusing online meteorological data with local meteorological data, and the weather type display in an offline state is realized by utilizing the locally collected meteorological data and a K-nearest neighbor algorithm.
For convenience of description, we assume the following application examples:
The micro-grid system of a certain school subject building comprises a photovoltaic power generation system, a fan power generation system, a classroom power utilization system and an energy management system, and the system is specifically described below as an example.
(1) local meteorological information collector. The system collects temperature, humidity, wind direction, wind speed, atmospheric pressure and irradiance through a sensor and stores the temperature, humidity, wind direction, wind speed, atmospheric pressure and irradiance in a database.
(2) Weather information crawler. And downloading weather information of the weather station through a Python crawler, wherein the weather information comprises historical real weather information and predicted weather information, and the predicted weather information comprises historical predicted weather information and future predicted weather information. The types of the climbed weather are temperature, humidity, wind direction, wind speed, atmospheric pressure, irradiance and weather types (sunny days, rainy days and the like), and the time granularity is consistent with that of the local weather information collector.
(3) Local weather information predictor. And predicting the weather information value in a future period of time by using a smoothing exponential algorithm according to the existing collected historical weather information.
(4) and optimizing a meteorological information model output device. The module mainly has the function of approaching the collected local meteorological information at corresponding time as far as possible by utilizing two groups of predicted meteorological data from the meteorological information crawler and the local meteorological information predictor respectively. The method comprises the following specific steps: using a linear regression method, F1t、F2tAs input, RtFitting an optimized meteorological information regression model as a target column;
Wherein R ist＝{rt1,rt2,...,rti,...,rtn}，rtiLocal weather information R representing time ttThe ith weather type, n represents the type of the weather type, RtA total of n weather types, F1t＝{f1t1,f1t2,...,f1ti，...,f1tn}，f1tirepresentation F1tOf the ith weather type, F1tA total of n weather types, local forecast weather information F2t＝{f2t1,f2t2,...,f2ti，...,f2tn}，f2tiRepresentation F2tof the ith weather type, F2tA total of n weather types;
Taking R at different times according to tt,F1t,F2tTraining a meteorological information regression model as follows:
Wherein the superscript T denotes the matrix transposition, cT＝[c1,c2,...,ci,...,cn]TIs a parameter of the linear regression model, ciRepresents the ith parameter, and c has n parameters in total; thetaT＝[θ1,θ2,...,θi,...,θn]Tis a parameter of the linear regression model, θiRepresents the ith parameter, and theta has n parameters in total; gamma rayT＝[γ1,γ2,...,γi,...,γn]TIs a parameter of a linear regression model, gammaiRepresents the ith parameter, and gamma has n parameters in total;
Obtaining a relative R according to a trained meteorological information regression modeltWeather information predicted value R of next momentt'+1Obtained from the formula (4)
(5) And a real-time information display. And obtaining a real-time weather type by using a K-nearest neighbor algorithm according to the acquired meteorological information, and displaying the weather type on a micro-grid control screen.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (5)
1. A weather prediction method for a micro-grid system is characterized by comprising the following steps:
step one, collecting local meteorological information R at time t regularlytand storing the data;
Step two, acquiring the following data with the same address and the same time point as the address and the time point in the step one from the national weather bureau:
Acquiring and storing historical and real meteorological information of a meteorological bureau;
Acquiring historical forecast weather information of the weather bureau corresponding to the real weather information of the history of the weather bureau, wherein the historical forecast weather information of the weather bureau is called F1t；
Obtaining future weather forecast information of a weather bureau, wherein the future weather forecast information of the weather bureau is F1'tRepresents;
Step three, predicting the meteorological information at the next moment by adopting a smoothing index method:
The specific process of the smoothing index method is as follows:
(1) The local meteorological information R at the known time ttAnd weather bureau future weather forecast information F1 'at time t-1't-1；
(2) Training smoothing coefficientsRequire thatThe magnitude of the smoothing factor is according to F1't-1And RtIs obtained by the training of formula (1)
Wherein R ist+1Local weather information representing the time t + 1;
(3) training a determination from step (2)A value;
(4) is represented by the following formula (1) andThe predicted weather value at the time t obtained by the smoothing index method is F2t，
Step four, utilizing a linear regression method to convert F1t、F2tAs input, RtAnd fitting an optimized meteorological information regression model as an object list, and predicting meteorological information of a future period of time according to the model.
2. The weather prediction method for the microgrid system as claimed in claim 1, wherein the fourth step is as follows:
Using a linear regression method, F1t、F2tAs input, Rtfitting an optimized meteorological information regression model as a target column;
Wherein R ist＝{rt1,rt2,...,rti,...,rtn}，rtiLocal weather information R representing time ttThe ith weather type, n represents the type of the weather type, RtA total of n weather types, F1t＝{f1t1,f1t2,...,f1ti，...,f1tn}，f1tiRepresentation F1tof the ith weather type, F1tA total of n weather types, local forecast weather information F2t＝{f2t1,f2t2,...,f2ti，...,f2tn}，f2tiRepresentation F2tOf the ith weather type, F2tA total of n weather types;
Taking R at different times according to tt,F1t,F2tTraining a meteorological information regression model as follows:
wherein the superscript T denotes the matrix transposition, cT＝[c1,c2,...,ci,...,cn]TIs a parameter of the linear regression model, ciRepresents the ith parameter, and c has n parameters in total; thetaT＝[θ1,θ2,...,θi,...,θn]TIs a parameter of the linear regression model, θiRepresents the ith parameter, and theta has n parameters in total; gamma rayT＝[γ1,γ2,...,γi,...,γn]TIs a parameter of a linear regression model, gammaiRepresents the ith parameter, and gamma has n parameters in total;
Obtaining a relative R according to a trained meteorological information regression modeltWeather information predicted value R 'at next moment't+1obtained from the formula (4)
3. The weather forecasting method for the microgrid system as recited in claim 1, characterized in that the step four is followed by the steps of:
according to real-time acquired RtAnd training a K-neighbor model corresponding to the weather type at the time t, and calculating the predicted weather information through the trained K-neighbor model to obtain a real-time weather type for displaying the weather information in an off-line state.
4. The weather prediction method for the microgrid system as claimed in claim 1, characterized in that in the first step, the local weather information R at the time t is collected by the local weather information collector at regular timetAnd stored.
5. The weather forecasting method for the microgrid system as claimed in claim 1, characterized in that the second step is performed by using a crawler library related to 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 CN108196317A (en) | 2018-06-22 |
| CN108196317B true 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) |
Families Citing this family (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 |
| CN109541728B (en) * | 2018-10-18 | 2020-12-01 | 国网山东省电力公司应急管理中心 | Meteorological early warning method for power grid engineering project |
| 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 |
| 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 |
| 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 |
| CN112489387B (en) * | 2020-12-04 | 2022-11-22 | 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 |
|---|
| 一种改进的指数平滑负荷预测方法研究;谭风雷 等;《电力需求侧管理》;20161130;第22-26页 * |
| 基于三次指数平滑模型的雾霾天气分析与预测;侯琼煌;《环境保护科学》;20141231;第73-77页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108196317A (en) | 2018-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108196317B (en) | Meteorological prediction method for micro-grid system | |
| US11537091B2 (en) | Multi-scale optimization framework for smart energy systems | |
| JP5940922B2 (en) | Renewable energy prediction device | |
| CN102426674B (en) | Power system load prediction method based on Markov chain | |
| Alassery et al. | An artificial intelligence-based solar radiation prophesy model for green energy utilization in energy management system | |
| JP2006033908A (en) | Method, device and program for estimating amount of power generation of solar light generating system | |
| CN110737876B (en) | Regional power grid photovoltaic power prediction optimization method and device | |
| CN103718129A (en) | Method and device for determining the power output by a photovoltaic installation | |
| CN114021420A (en) | Distributed photovoltaic ultra-short-term power generation prediction method and system | |
| KR20140087965A (en) | System for predicting energy producing quantity | |
| KR20210013565A (en) | Weather data-based wireless sensor network node solar energy collection power prediction algorithm | |
| CN116865236A (en) | Medium-and-long-term power generation capacity prediction method and system based on new energy power generation | |
| CN102769298B (en) | Forecasting method and forecasting system for solar grid-connection generated power | |
| Chen et al. | Towards the applicability of solar nowcasting: A practice on predictive PV power ramp-rate control | |
| CN114895380A (en) | Solar radiation prediction method, device, equipment and medium | |
| Gao et al. | Adversarial discriminative domain adaptation for solar radiation prediction: A cross-regional study for zero-label transfer learning in Japan | |
| CN117277304A (en) | Photovoltaic power generation ultra-short-term power prediction method and system considering sunrise and sunset time | |
| CN110752622B (en) | Affine state estimation method for power distribution network | |
| Wang et al. | Quantifying the value of probabilistic forecasting for power system operation planning | |
| Belmahdi et al. | Forecasting solar radiation using machine learning method: new optimization algorithm | |
| CN110705769B (en) | New energy power generation power prediction optimization method and device | |
| CN112560325B (en) | Prediction method, system, equipment and storage medium for electricity conversion service | |
| Wang et al. | Economics of physics-based solar forecasting in power system day-ahead scheduling | |
| Kartini et al. | Development hybrid model deep learning neural network (dl-nn) for probabilistic forecasting solar irradiance on solar cells to improve economics value added | |
| Ku et al. | Self-learning mechanism for prediction of energy consumption and generation |
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 |