CN115330018A - Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM - Google Patents
Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM Download PDFInfo
- Publication number
- CN115330018A CN115330018A CN202210767484.7A CN202210767484A CN115330018A CN 115330018 A CN115330018 A CN 115330018A CN 202210767484 A CN202210767484 A CN 202210767484A CN 115330018 A CN115330018 A CN 115330018A
- Authority
- CN
- China
- Prior art keywords
- temperature
- humidity
- early warning
- control cabinet
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Optimization (AREA)
- Tourism & Hospitality (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an internal environment early warning evaluation method of an intelligent control cabinet based on similar days and Optuna-LightGBM, which comprises the following steps: s1: collecting historical temperature and humidity data and weather data in the electrical control cabinet, and processing missing values in the data; s2, selecting a time period close to the time period to be predicted from the historical data as a model training set through a similar day algorithm; s3: constructing a temperature and humidity prediction model based on Optuna-LightGBM, and performing short-term prediction on the temperature and humidity in the cabinet; s4: temperature and humidity early warning parameters in the electric control cabinet are set, and threshold values are reasonably determined according to different states at different moments, so that temperature and humidity early warning is realized. The invention has the advantages that: according to the intelligent electric control cabinet internal environment early warning assessment method, the similar time periods are selected according to meteorological factors, the similarity of the training set and the training set formed by the time periods to be predicted is improved, and further the generalization capability and precision of the model are improved.
Description
Technical Field
The invention relates to the technical field of early warning of internal environment of an intelligent control cabinet, in particular to an early warning evaluation method of internal environment of an intelligent control cabinet based on similar days and Optuna-LightGBM.
Background
Along with the deep development of intelligent substation modularization construction, more and more microcomputer type electrical equipment are arranged in electrical equipment component cabinet on the spot, face the abominable operational environment of high temperature, high humidity. High temperature and high humidity environment in the cabinet may cause various defects and faults such as short-term critical, short-term serious, long-term hidden danger and the like of intelligent secondary equipment. Aiming at the problems, the research on the temperature and humidity environment early warning control technology of the indoor intelligent control cabinet is developed, and the intelligent control cabinet can better serve the modularized construction of the transformer substation. However, most of the traditional control methods are event-driven such as PID control, namely, when the temperature and humidity are greater than a certain threshold value, the temperature and humidity are out of limit, the problems of low temperature and humidity prediction accuracy and tracking accuracy exist, early warning cannot be timely performed before the internal environment of the control cabinet is suddenly changed, the internal environment of the control cabinet is unstable, the problem of safe and stable operation of intelligent secondary equipment is easily caused, and the use experience of a user is further influenced.
At the present stage, the prediction precision of the temperature and the humidity in the intelligent control cabinet is low, and the early warning threshold value is fixed, so that the threshold value cannot be dynamically adjusted in real time according to the environment in the cabinet, and the problem that early warning cannot be timely realized when the internal environment of the intelligent control cabinet environment control system is suddenly changed exists in the control method.
Disclosure of Invention
In order to solve the difficulty of prediction and early warning of temperature and humidity in the existing intelligent control cabinet, the invention discloses and provides an intelligent control cabinet internal environment early warning and evaluation method based on similar day and Optuna-LightGBM.
In order to solve the above technical problem, the technical implementation of the present invention is as follows:
the intelligent control cabinet internal environment early warning assessment method based on similar days and Optuna-LightGBM comprises the following steps:
s1: collecting historical temperature and humidity data and weather data in the intelligent control cabinet, and processing missing values in the data;
s2, selecting a time period close to the time period to be predicted from the historical data as a model training set through a similar day algorithm;
s3: constructing a temperature and humidity prediction model based on Optuna-LightGBM, and performing short-term prediction on the temperature and humidity in the cabinet;
s4: and temperature and humidity early warning parameters in the intelligent control cabinet are set, and threshold values are reasonably determined according to different states at different moments, so that temperature and humidity early warning is realized.
Preferably, step S1 includes the steps of:
s11: acquiring historical temperature and humidity data and weather data including temperature, humidity and precipitation in the intelligent control cabinet;
and S12, performing near value filling processing on the missing values in the data in the S11, and deleting the time period if a missing condition which is continuous for a long time appears.
Preferably, step S2 includes the steps of:
s21: dividing the historical time sequence into a plurality of time periods with the same time length as the day to be predicted, and constructing day eigenvectors X = | T, W, H, P |, wherein T is the ambient air temperature, W is the surface temperature of the control cabinet, H is the relative humidity, and P is the precipitation;
s22: calculating PEASRON correlation coefficients of each variable and the temperature and the humidity in the day characteristic vector, and giving different variable weights in the day characteristic vector according to the correlation coefficients;
s23: calculating the distance and similarity between the daily feature vector of each time period and the daily weather day feature vector to be predicted by using a DTW algorithm, readjusting DTW distance calculation daily similarity coefficients according to the weight calculated in S22, and selecting a plurality of time periods with the minimum coefficients as a model training set;
the determination method of the weight of each environmental factor in the step S22 is as follows:
wherein corr () is the Pearson correlation coefficient calculation function, T t Ambient temperature time series, T, for the time period to be predicted i For a historical ambient temperature time series of equal length, H t For the time period to be predicted, the ambient humidity time series, H i Is a time series of historical ambient humidity of equal length, W t For the time period to be predicted, the temperature time sequence of the cabinet table, W i For temperature time series of historic cabinets of equal length, P t For time periods to be predicted, precipitation time series, P i Is a historical precipitation time sequence with equal length;
in the step S23, the DTW distance is readjusted according to the weight calculated in S22 in the following manner:
λ i =η T ·DTW(T i ,T t )+η W ·DTW(W i ,W t )+
η H ·DTW(H i ,H t )+η P ·DTW(P i ,P t ),i∈(1,2...,n)
wherein λ i For the day-like coefficient, DTW () is a DTW distance calculation formula.
Preferably, the step S3 of constructing the temperature and humidity prediction model based on Optuna-LightGBM includes the following steps:
s31: establishing input data according to the training set established in the step S2, and constructing derivative features;
s32: inputting the key data in the step S31 into a LightGBM model, confirming the range of model parameters, and optimizing the model parameters through five-fold intersection-Optuna to ensure that the precision of the prediction model is optimal;
the step S31 of feature derivation includes performing time sequence first-order and second-order difference processing on the input features, performing cross derivation on the input features, that is, performing addition, subtraction, multiplication, division processing on the features between the same dimensions, and performing feature equal-frequency and equal-width binning processing on the features.
Preferably, step S4 the setting of the early warning parameters of the temperature and humidity inside the intelligent control cabinet includes the following steps:
s41: drawing a temperature and humidity curve of the next time period according to the prediction data in the step S3, calculating the slope of each time curve in the predicted time period, and multiplying the slope by the temperature and humidity at the time to construct an internal temperature and humidity early warning parameter of the intelligent control cabinet;
s42: calculating the moment of the temperature and humidity inflection point to obtain a corresponding temperature and humidity value and a temperature and humidity change rate, wherein the temperature and humidity early warning parameter value obtained by calculation is a threshold value;
in S41, the temperature and humidity early warning parameter formula in the intelligent control cabinet is as follows:
wherein T is n For predicting the temperature value at the time of prediction, T n-1 As a temperature value at the present moment, t n To predict time of day, t n-1 Is the current time, λ T As a temperature warning parameter, H n To predict the humidity value at the moment of prediction, H n-1 As a value of humidity at the present moment, λ H A humidity early warning parameter;
compared with the prior art, the invention has the advantages that:
(1) According to the intelligent control cabinet internal environment early warning assessment method, the similar time periods are selected according to meteorological factors, so that the similarity of the training set and the training set formed by the time periods to be predicted is improved, and further the generalization capability and precision of the model are improved;
(2) According to the invention, the independent parameter optimization of the model is realized through the Optuna-LightGBM model, the temperature and humidity early warning parameters in the intelligent control cabinet are set, the temperature and humidity early warning under different environmental conditions is realized, and the accuracy of the environmental temperature and humidity early warning in the intelligent control cabinet is improved;
(3) The model built by the method is small in magnitude order of required data, and the LightGBM is a lightweight model and has the advantages of being small in required computing resource and high in running speed.
Drawings
Fig. 1 is a flow chart of an intelligent control cabinet temperature and humidity early warning method.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Referring to fig. 1, an embodiment of the internal environment early warning evaluation method of an intelligent control cabinet based on a similar day and Optuna-LightGBM according to the present invention includes the following steps:
s1, collecting historical temperature and humidity data and weather data in an intelligent control cabinet, and processing missing values in the data; s2, selecting a time period close to the time period to be predicted from the historical data as a model training set through a similar day algorithm; s3: constructing a temperature and humidity prediction model based on Optuna-LightGBM, and performing short-term prediction on the temperature and humidity in the cabinet; s4: the temperature and humidity early warning parameters in the intelligent control cabinet are set, so that the threshold value can be reasonably determined according to different states at different moments, and temperature and humidity early warning is realized.
The step S1 includes the steps of:
s11: acquiring historical temperature and humidity data and weather data including temperature, humidity, precipitation and the like in the intelligent control cabinet;
and S12, performing near value filling processing on missing values in the data in the S11, and if a missing situation with long time continuity occurs, deleting the time slot.
S2, the selection of the model training set based on the similar days comprises the following steps:
s21: dividing the historical time sequence into a plurality of time periods with the same time length as the day to be predicted, and constructing day eigenvectors X = | T, W, H, P |, wherein T is the ambient air temperature, W is the surface temperature of the control cabinet, H is the relative humidity, and P is the precipitation;
s22: calculating PEASRON correlation coefficients of each variable and the temperature and the humidity in the day characteristic vector, and giving different variable weights in the day characteristic vector according to the correlation coefficients;
s23: calculating the distance and similarity between the daily feature vector of each time period and the daily weather day feature vector to be predicted by using a DTW algorithm, readjusting DTW distance calculation daily similarity coefficients according to the weight calculated in S22, and selecting a plurality of time periods with the minimum coefficients as a model training set;
wherein the determination manner of the weight of each environmental factor in the step S22 is as follows
Wherein corr () is the Pearson correlation coefficient calculation function, T t Ambient temperature time series, T, for the time period to be predicted i For a historical ambient temperature time series of equal length, H t For the time period to be predicted, the ambient humidity time series, H i For a historical ambient humidity time series of equal length, W t For the time period to be predicted, the temperature time sequence of the cabinet table, W i For temperature time series of historic cabinets of equal length, P t For time periods to be predicted, precipitation time series, P i Is a time sequence of historical precipitation of equal length. In the step S23, the manner of readjusting the DTW distance according to the weight calculated in step S22 is as follows:
λ i =η T ·DTW(T i ,T t )+η W ·DTW(W i ,W t )+
η H ·DTW(H i ,H t )+η P ·DTW(P i ,P t ),i∈(1,2...,n)
wherein λ i For the day-like coefficient, DTW () is a DTW distance calculation formula.
S3, the construction of the temperature and humidity prediction model based on the Optuna-LightGBM comprises the following steps:
s31: establishing input data according to the training set established in the step S2, and constructing derivative features;
s32: and (4) inputting the key data in the step S31 into the LightGBM model, confirming the range of the model parameters, and optimizing the model parameters through the five-fold intersection-Optuna so as to optimize the precision of the prediction model.
The step S31 of feature derivation includes performing time sequence first-order and second-order difference processing on the input features, performing cross derivation on the input features, that is, performing addition, subtraction, multiplication, and division processing on the features between the same dimensions, and performing feature equal-frequency and equal-width binning processing on the features. The optimized parameters in step S32 are: num _ trees, the tree of the tree; num _ leaves, number of leaves per tree; max _ depth, depth of tree; learning _ rate, learning rate; bagging _ fraction, sample sampling ratio, etc.
S4, the temperature and humidity early warning parameter setting inside the intelligent control cabinet comprises the following steps:
s41: drawing a temperature and humidity curve for 15min in the future according to the prediction data in the step S3, calculating the slope of the curve at each moment, and multiplying the slope by the temperature and humidity at the moment to construct an internal temperature and humidity early warning parameter of the intelligent control cabinet;
s42: and calculating the moment of the inflection point of the temperature and humidity to obtain a corresponding temperature and humidity value and a temperature and humidity change rate, wherein the temperature and humidity early warning parameter value obtained by calculation is a threshold value.
The temperature and humidity early warning parameter formula in the S41 intelligent control cabinet is as follows:
wherein T is n For predicting the temperature value at the time of prediction, T n-1 As a temperature value at the present moment, t n To predict time of day, t n-1 For the current time, λ T As a temperature warning parameter, H n To predict the humidity value at the time of the prediction, H n-1 As a value of humidity at the present moment, λ H Is a humidity early warning parameter. The calculation formula of the middle temperature humidity inflection point in S42 is as follows:
the above description is only an embodiment of the present invention, but the technical features of the present invention are not limited thereto, and any changes or modifications within the technical field of the present invention by those skilled in the art are covered by the present invention.
Claims (5)
1. Similar day and Optuna-LightGBM based internal environment early warning assessment method is characterized in that: the method comprises the following steps:
s1: collecting historical temperature and humidity data and weather data in the intelligent control cabinet, and processing missing values in the data;
s2, selecting a time period close to the time period to be predicted from the historical data as a model training set through a similar day algorithm;
s3: constructing a temperature and humidity prediction model based on Optuna-LightGBM, and performing short-term prediction on the temperature and humidity in the cabinet;
s4: and temperature and humidity early warning parameters in the intelligent control cabinet are set, and threshold values are reasonably determined according to different states at different moments, so that temperature and humidity early warning is realized.
2. The intelligent control cabinet internal environment early warning assessment method based on similar day and Optuna-LightGBM as claimed in claim 1, wherein: the step S1 includes the steps of:
s11: acquiring historical temperature and humidity data and weather data including temperature, humidity and precipitation in the intelligent control cabinet;
and S12, performing near value filling processing on the missing values in the data in the S11, and deleting the time period if a missing condition which is continuous for a long time appears.
3. The intelligent control cabinet internal environment early warning assessment method based on similar day and Optuna-LightGBM as claimed in claim 1, wherein: the step S2 includes the steps of:
s21: dividing the historical time sequence into a plurality of time periods with the same time length as the day to be predicted, and constructing day eigenvectors X = | T, W, H, P |, wherein T is the ambient air temperature, W is the surface temperature of the control cabinet, H is the relative humidity, and P is the precipitation;
s22: calculating PEASRON correlation coefficients of each variable and the temperature and the humidity in the daily feature vector, and giving weights to different variables in the daily feature vector according to the correlation coefficients;
s23: calculating the distance and similarity between the day characteristic vector of each time period and the day meteorological day characteristic vector to be predicted by using a DTW algorithm, readjusting DTW distance calculation day similarity coefficients according to the weight calculated in S22, and selecting a plurality of time periods with the minimum coefficients as a model training set;
the determination method of the weight of each environmental factor in the step S22 is as follows:
wherein corr () is the Pearson correlation coefficient calculation function, T t For a time period to be predicted, ambient temperature time series, T i Is a historical ambient temperature time series of equal length, H t For the time period to be predicted, the ambient humidity time series, H i Is a time series of historical ambient humidity of equal length, W t For the time period to be predicted, the temperature time sequence of the cabinet table, W i For a time series of temperature of the history cabinet table of equal length, P t For time periods to be predicted, precipitation time series, P i Is a historical precipitation time sequence with equal length;
in the step S23, the DTW distance is readjusted according to the weight calculated in S22 in the following manner:
λ i =η T ·DTW(T i ,T t )+η W ·DTW(W i ,W t )+η H ·DTW(H i ,H t )+η P ·DTW(P i ,P t ),i∈(1,2...,n)
wherein λ i For the day-like coefficient, DTW () is a DTW distance calculation formula.
4. The intelligent control cabinet internal environment early warning assessment method based on similar day and Optuna-LightGBM as claimed in claim 1, wherein: s3, the construction of the temperature and humidity prediction model based on the Optuna-LightGBM comprises the following steps:
s31: establishing input data according to the training set established in the step S2, and constructing derivative features;
s32: inputting the data in the step S31 into a LightGBM model, confirming the range of model parameters, and optimizing the model parameters through five-fold intersection-Optuna to ensure that the precision of the prediction model is optimal;
the step S31 of feature derivation includes performing time sequence first-order and second-order difference processing on the input features, performing cross derivation on the input features, that is, performing addition, subtraction, multiplication, division processing on the features between the same dimensions, and performing feature equal-frequency and equal-width binning processing on the features.
5. The intelligent control cabinet internal environment early warning assessment method based on similar day and Optuna-LightGBM as claimed in claim 1, wherein: s4, the temperature and humidity early warning parameter setting inside the intelligent control cabinet comprises the following steps:
s41: drawing a temperature and humidity curve of the next time period according to the prediction data in the step S3, calculating the slope of each time curve in the predicted time period, and multiplying the slope by the temperature and humidity at the time to construct an internal temperature and humidity early warning parameter of the intelligent control cabinet;
s42: calculating the moment of the temperature and humidity inflection point to obtain a corresponding temperature and humidity value and a temperature and humidity change rate, wherein the temperature and humidity early warning parameter value obtained by calculation is a threshold value;
in S41, the temperature and humidity early warning parameter formula in the intelligent control cabinet is as follows:
wherein T is n For predicting the temperature value at the time of prediction, T n-1 As a temperature value at the present moment, t n To predict time of day, t n-1 For the current time, λ T As a temperature warning parameter, H n To predict the humidity value at the moment of prediction, H n-1 As a value of humidity at the present moment, λ H A humidity early warning parameter;
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210767484.7A CN115330018A (en) | 2022-06-30 | 2022-06-30 | Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210767484.7A CN115330018A (en) | 2022-06-30 | 2022-06-30 | Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115330018A true CN115330018A (en) | 2022-11-11 |
Family
ID=83918013
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210767484.7A Pending CN115330018A (en) | 2022-06-30 | 2022-06-30 | Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115330018A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
-
2022
- 2022-06-30 CN CN202210767484.7A patent/CN115330018A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116046187A (en) * | 2023-04-03 | 2023-05-02 | 探长信息技术(苏州)有限公司 | A unusual remote monitoring system of temperature for communication cabinet |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yan et al. | Reviews on uncertainty analysis of wind power forecasting | |
CN111563610B (en) | Building electric load comprehensive prediction method and system based on LSTM neural network | |
Kou et al. | Sparse online warped Gaussian process for wind power probabilistic forecasting | |
Wang et al. | Wind power forecasting based on time series ARMA model | |
CN110380444B (en) | Capacity planning method for distributed wind power orderly access to power grid under multiple scenes based on variable structure Copula | |
CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
CN112186761B (en) | Wind power scene generation method and system based on probability distribution | |
CN112232575A (en) | Comprehensive energy system regulation and control method and device based on multivariate load prediction | |
CN115330018A (en) | Intelligent control cabinet internal environment early warning evaluation method based on similar day and Optuna-LightGBM | |
CN113468790A (en) | Wind speed characteristic simulation method and system based on improved particle swarm optimization | |
CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
CN112381315A (en) | LS-SVM intelligent platform area load prediction method and system based on PSO optimization | |
CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
KR20230076695A (en) | Solar power generation forcasting device and method reflecting solar periodic time variable | |
CN113095547A (en) | Short-term wind power prediction method based on GRA-LSTM-ICE model | |
CN113344243A (en) | Wind speed prediction method and system for optimizing ELM based on improved Harris eagle algorithm | |
Tai et al. | Power prediction of photovoltaic power generation based on LSTM model with additive Attention mechanism | |
CN116760006A (en) | Wind power prediction method, device, equipment and storage medium | |
Ming-guang et al. | Short-term load combined forecasting method based on BPNN and LS-SVM | |
Tan et al. | Study on short-term load forecasting method considering meteorological factors of offshore oilfield group microgrid | |
Hu et al. | Wind power short-term power forecasting based on Improved Grey Wolf algorithm and Optimized Generalized Regression Neural Network | |
CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
Zhang et al. | Wind Tunnel wind Speed Control System Based on PLC Fuzzy Algorithm | |
Mohammed et al. | Ultra-short-term wind power prediction using a hybrid model | |
Liu et al. | Short Term Photovoltaic Power Prediction based on Sparrow Algorithm Optimized Long-short Term Memory Neural Network |
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 |