CN115660893A - Transformer substation bus load prediction method based on load characteristics - Google Patents
Transformer substation bus load prediction method based on load characteristics Download PDFInfo
- Publication number
- CN115660893A CN115660893A CN202211315037.4A CN202211315037A CN115660893A CN 115660893 A CN115660893 A CN 115660893A CN 202211315037 A CN202211315037 A CN 202211315037A CN 115660893 A CN115660893 A CN 115660893A
- Authority
- CN
- China
- Prior art keywords
- load
- transformer substation
- data
- bus
- substation
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a transformer substation bus load prediction method based on load characteristics, which comprises the following steps: dividing the types of the transformer substations according to the influence of the output behaviors of the wind-water power plants in the power supply area; acquiring historical data, extracting a feature vector of a transformer substation, constructing a load prediction model corresponding to the transformer substation, and training the load prediction model by using the feature vector; and after acquiring target time section data before the prediction date and extracting the characteristic vector of the transformer substation, inputting the load prediction model to obtain a load prediction value as a transformer substation bus load prediction result. According to the invention, the influence of the load characteristics on the transformer substation is considered, and an accurate load prediction result can be obtained.
Description
Technical Field
The invention relates to the field of electric energy management, in particular to a transformer substation bus load prediction method based on load characteristics.
Background
The bus load of the transformer substation is a nonlinear system, and the change rule of the bus load has the characteristics of randomness and nonlinearity, so that the relationship between the load and the influence factors of the load is difficult to fit by adopting a unified mathematical model. In some areas, wind and water resources are rich, the number of small power supply unit equipment is large, and the influence degree of the bus load of the transformer substation is large. The bus load of the regional transformer substation can be decomposed into bus power load and local power plant power generation power, the bus power load is high in periodicity, the whole bus power load is stable, and prediction accuracy is high. Due to the influence of the output behavior of a small power supply in a power supply area, the bus load of the transformer substation is easy to change suddenly, the stability is poor, the volatility is strong, and the prediction difficulty is high. The existing transformer substation bus load prediction methods mostly adopt the same model to carry out multi-class load prediction, and different transformer substation bus load characteristics are not considered in a targeted manner.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: in order to solve the problems in the prior art, a transformer substation bus load prediction method based on load characteristics is provided, and an accurate prediction result can be obtained.
In order to solve the technical problems, the invention adopts the technical scheme that:
a transformer substation bus load prediction method based on load characteristics comprises the following steps:
dividing the types of the transformer substations according to the influence of the output behaviors of the wind-water power plants in the power supply area;
acquiring historical data, extracting a feature vector of a transformer substation, constructing a load prediction model corresponding to the transformer substation, and training the load prediction model by using the feature vector;
and after acquiring target time section data before the prediction date and extracting the characteristic vector of the transformer substation, inputting the load prediction model to obtain a load prediction value as a transformer substation bus load prediction result.
Further, according to the influence of the wind-water power plant output behavior in the power supply area, the dividing of the types of the transformer substations specifically comprises:
if the transformer substation is not influenced by the output behavior of the wind power plant, the transformer substation is a pure load station;
if the transformer substation is only influenced by the output behavior of the wind power plant, the transformer substation is a wind power station;
if the transformer substation is only influenced by the output behavior of the hydropower plant, the transformer substation is a hydraulic power station;
and if the transformer substation is simultaneously influenced by the output behavior of the wind power plant, the transformer substation is a wind-water power station.
Further, extracting the feature vector of the substation specifically includes: and extracting a basic characteristic vector and a special characteristic vector, wherein the special characteristic vector corresponds to the type of the power transformation, and combining the basic characteristic vector and the special characteristic vector to obtain the characteristic vector of the transformer substation.
Further, the basic feature vector comprises substation bus load data, weather data and date type data.
Further, if the transformer substation is a pure load station, the special feature vector comprises bus load before one week;
if the transformer substation is a wind power station, the special feature vector comprises wind power plant power generation data;
if the transformer substation is a hydraulic power station, the special feature vector comprises power generation data of a hydraulic power plant;
if the transformer substation is a wind and water power station, the special feature vector comprises a bus net load of a day before the forecast day, and the bus net load is the difference between the actual bus load and the actual generating power of the wind and water power plant.
Further, the load prediction model is an artificial neural network model, if the transformer substation is a pure load station, the corresponding artificial neural network model comprises two hidden layers, the number of neurons of each hidden layer is 100 and 50 respectively, and the activation function is sigmoid; if the transformer substation is a wind power station or a water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 50 respectively, and an activation function is relu; if the transformer substation is a wind and water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 20 respectively, and the activation function is relu.
Further, the target time period data before the prediction day is substation area weather forecast information, local power plant output plan data and bus load of 96 points per day from 12.
Further, after the load prediction model is input to obtain a load prediction value, the method further comprises the following steps: and if the transformer substation is a wind and water power station, adding the load predicted value to the planned power generation power of the power plant on the prediction day to obtain a transformer substation bus load prediction result.
Further, the step of preprocessing the data after acquiring the historical data includes:
if the load data at a certain moment is defective or lost, carrying out linear interpolation patching by using the load data in adjacent front and back time;
if the load data are 0 for several consecutive days, judging the load data as abnormal load data, and deleting the abnormal load data;
and integrating all data in the historical data into a unified preset table.
Further, training the load prediction model using the feature vector specifically includes: and (3) arranging and combining values in the given parameter list to obtain each group of parameters, training the load prediction model under each group of parameter configuration by using the characteristic vector, evaluating the effect of each trained load prediction model by using a cross validation method, and selecting the load prediction model with the best effect.
Compared with the prior art, the invention has the following advantages:
the method comprises the steps of classifying the transformer substations, extracting corresponding characteristic vectors from historical data according to different classifications, constructing corresponding load prediction models, and accurately predicting the bus load by using the load prediction models trained by the characteristic vectors.
Drawings
FIG. 1 is a schematic step diagram of an embodiment of the present invention.
FIG. 2 is a flow chart of an embodiment of the present invention.
FIG. 3 is a comparison graph of the predicted value and the actual value of the current day according to the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and the specific preferred embodiments, without thereby limiting the scope of protection of the invention.
The embodiment provides a method for predicting a bus load of a transformer substation based on load characteristics, which classifies the transformer substations according to the load characteristics, and then predicts the bus load of the transformer substation respectively by an artificial neural network method, as shown in fig. 1 and 2, the method comprises the following steps:
s1) dividing the types of the transformer substations according to the influence of the output behaviors of the wind-water power plants in the power supply area;
s2) acquiring historical data, extracting a characteristic vector of the transformer substation, constructing a load prediction model corresponding to the transformer substation, and training the load prediction model by using the characteristic vector;
and S3) obtaining target time-interval data before the prediction date, extracting the characteristic vector of the transformer substation, and inputting the load prediction model to obtain a load prediction value serving as a transformer substation bus load prediction result.
In step S1), we comprehensively study the current situation of the regional power grid, find that the change rule of the bus load of each substation in the system has its own characteristics, and classify the types of the substations according to the connected load or the type of the power plant as follows:
if the transformer substation is not influenced by the output behavior of the wind power plant, the transformer substation is a pure load station;
if the transformer substation is only influenced by the output behavior of the wind power plant, the transformer substation is a wind power station;
if the transformer substation is only influenced by the output behavior of the hydropower plant, the transformer substation is a hydraulic station;
and if the transformer substation is simultaneously influenced by the output behavior of the wind power plant, the transformer substation is a wind-water power station.
In the step S2), historical data comprises load related data such as weather forecast information of a transformer substation area, output plan data (including actual and planned power generation data) of a local power plant, 96-point load of a bus every day and the like, abnormal data or missing data may exist due to some reasons in the data acquisition process, and data preprocessing is performed through the following steps:
if the load data at a certain moment is defective or lost, carrying out linear interpolation patching by using the load data in adjacent front and back time;
if the load data are 0 for several consecutive days, judging the load data as abnormal load data, and deleting the abnormal load data;
and integrating all data in the historical data into a unified preset table.
Then extracting a feature vector of the transformer substation from the preprocessed historical data, and the specific steps comprise: and extracting the basic characteristic vector and the special characteristic vector, and combining the basic characteristic vector and the special characteristic vector to obtain the characteristic vector of the transformer substation.
The basic characteristic vector in the embodiment comprises transformer substation bus load data, weather data and date type data, wherein the transformer substation bus load data is active power data of a main transformer high-voltage side of a 220kV transformer substation, the daily time range is 00-15 min, the sampling interval is 15min, and 96 groups of data are generated every day. The weather data is weather information of the area where the transformer substation is located, and the weather information comprises the highest temperature, the lowest temperature, the wind speed, the wind direction, the weather condition and the like. The date type data includes a sunday type and whether it is a holiday.
The special feature vector in this embodiment corresponds to the type of power transformation, specifically:
if the transformer substation is a pure load station, the stability of the bus load of the transformer substation is high, and the special feature vector comprises the bus load before one week;
if the transformer substation is a wind power station or a hydraulic power station, the mode of taking the power generation data of the wind power plant and the hydraulic power plant as features is adopted, the special feature vector comprises the corresponding power generation data of the wind power plant or the hydraulic power plant, and the power generation data of the wind power plant or the hydraulic power plant are respectively summed according to the associated stations of the transformer substation. If the station is a double bus, the influence factor of the power plant output on each bus is set to be 0.5;
if the transformer substation is a wind-water power station, the influence of the output action of a small power supply is large, and the bus load can be decomposed into the sum of the bus net load at a certain moment and the power generation power of the power plant at a corresponding moment, namely:
P bus,t ＝P′ bus,t +P sta,t (1)
wherein, P bus,t A load is applied to the bus at a certain time; p' bus,t A bus is a net load at a certain moment; p sta,t The special feature vector comprises a bus net load of a predicted target moment of day before, namely the difference between the actual load of the bus of the predicted target moment of day before and the actual generating power of the wind-water power plant.
The load prediction model in this embodiment is an Artificial Neural Network (ANN) model, and may be expressed as:
z＝f(W T A+b) (2)
wherein a = { a = 1 、a 2 ...a n Is the component of each input, W = { W = 1 、w 2 ...w n The weights corresponding to the components are b is the bias, f is the activation function, and z is the output of the neuron. For a neural network with only one hidden layer, given an input sample X formed by d eigenvectors, = { X = } 1 ,x 2 ,…,x d H, assuming that the number of hidden layer neurons is q, the connection weight between the ith input layer neuron and the h hidden layer neuron is v ih The connection weight and bias between the h hidden layer neuron and the j output layer neuron are w hj When both hidden layer and output layer neurons use the activation function f, the output of the h-th hidden layer neuron is
Then the output of the jth output layer neuron, i.e., the prediction result of the neural network, is:
in order to achieve an accurate prediction result, in the training process of the load prediction model by using the feature vector, the embodiment further optimizes the parameters of the artificial neural network by using a grid optimization and cross validation algorithm, which specifically includes: and (3) arranging and combining values in the given parameter list to obtain each group of parameters, training the load prediction model under each group of parameter configuration by using the characteristic vector, evaluating the effect of each trained load prediction model by using a cross validation method, and selecting the load prediction model with the best effect.
In the finally obtained load prediction model, for different types of substations, selection of hyper-parameters such as the number of hidden layers, the number of neurons and an activation function in the built load prediction model is different, after parameter optimization, if the substation is a pure load station, the corresponding artificial neural network model comprises two hidden layers, the number of neurons of each hidden layer is 100 and 50 respectively, and the activation function is sigmoid; if the transformer substation is a wind power station or a water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 50 respectively, and the activation function is relu; if the transformer substation is a wind and water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 20 respectively, and the activation function is relu.
In this embodiment, because the time point load of the d-th day of the forecast day cannot be obtained, the data of the target time segment before the forecast day is used as the input data of the load forecast model, and the data of the target time segment before the forecast day is the weather forecast information of the transformer substation area before 00 and after and before the forecast day (d-2 th day) 12 to the day before the forecast day (d-1 th day) 12.
In addition, for the transformer substation of the wind and hydraulic power station, because the characteristic vector of the transformer substation eliminates the power generation power of the power plant so as to avoid the influence of the output of the power plant when load prediction is carried out, and the load prediction model predicts the bus load of the net transformer substation, after the output data of the load prediction model is obtained, the data needs to be restored into the bus load of the transformer substation, so that the following steps are also included after the target time period data before the prediction date is input into the load prediction model to obtain the load prediction value: if the transformer substation is a wind and hydraulic station, predicting a load value P' bus,t,d+1 Adding the planned generating power P of the power plant on the forecast day sta,t,d+1 Obtaining the prediction result P of the bus load of the transformer substation bus,t,d+1 。
The following describes a specific process for verifying the accuracy of the load prediction result of the method of the embodiment:
step S1) is executed, 15 220kV transformer substations in a certain area are divided into 4 types including 2 pure load stations, 7 wind power stations, 4 hydraulic power stations and 2 wind and hydraulic power stations, and load prediction is carried out in a targeted manner;
respectively extracting actual and planned power generation data of a wind power plant, planned data of a hydraulic power plant and actual load values of transformer substations from a plurality of systems such as a new energy dispatching operation system, a power dispatching control center system, an iES600 Pro power grid dispatching automation system and the like based on a data center, combining the data and weather forecast information of each transformer substation area to form a historical data set, and then executing the step S2) to obtain load prediction models corresponding to the transformer substations;
selecting data from the historical data set, namely data from day d-2 before day d 12 of the forecast day and data from day d to day d-1 before 12.
Then, the accuracy of the load prediction result of each transformer substation is verified, and the following indexes are adopted:
(1) Prediction error of single-substation bus load i in time period k
The load reference value is shown in table 1, and the 220kV substation bus load reference value is 305MVA.
TABLE 1 value standard table of load reference value
(2) Bus load prediction accuracy rate of day-to-day power substation
In the formula (I), the compound is shown in the specification,
and (4) counting errors of all buses in the time period k, wherein M is the total load number of the buses of the transformer substation evaluated in the subarea, and N is the total time period number of the prediction day. The accuracy of a single busbar can be calculated as M = 1.
According to the indexes, the accuracy of the load prediction result is shown in table 2, and the result shows that the average value of the daily substation bus load prediction accuracy predicted by the model is 96.02%. The ratio of the predicted value and the actual value of the load of a certain bus in 5 months and 10 days is shown in fig. 3, and it can be seen that the predicted value and the actual value of the load have the same trend and the error is also in a reasonable range, which shows that the prediction model of the invention can better predict the bus load of the transformer substation.
TABLE 2 comparison of load prediction accuracy
The foregoing is considered as illustrative of the preferred embodiments of the invention and is not to be construed as limiting the invention in any way. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical spirit of the present invention should fall within the protection scope of the technical scheme of the present invention, unless the technical spirit of the present invention departs from the content of the technical scheme of the present invention.
Claims (10)
1. A transformer substation bus load prediction method based on load characteristics is characterized by comprising the following steps:
dividing the types of the transformer substations according to the influence of the output behaviors of the wind-water power plants in the power supply area;
acquiring historical data, extracting a feature vector of a transformer substation, constructing a load prediction model corresponding to the transformer substation, and training the load prediction model by using the feature vector;
and after acquiring target time section data before the prediction date and extracting the characteristic vector of the transformer substation, inputting the load prediction model to obtain a load prediction value as a transformer substation bus load prediction result.
2. The method for predicting the bus load of the transformer substation based on the load characteristics according to claim 1, wherein the classifying the types of the transformer substations according to the influence of the wind-water power plant output behaviors in the power supply area specifically comprises:
if the transformer substation is not influenced by the output behavior of the wind power plant, the transformer substation is a pure load station;
if the transformer substation is only influenced by the output behavior of the wind power plant, the transformer substation is a wind power station;
if the transformer substation is only influenced by the output behavior of the hydropower plant, the transformer substation is a hydraulic power station;
and if the transformer substation is simultaneously influenced by the output behavior of the wind power plant, the transformer substation is a wind-water power station.
3. The method for predicting the bus load of the substation based on the load characteristics according to claim 1, wherein extracting the feature vector of the substation specifically comprises: and extracting a basic characteristic vector and a special characteristic vector, wherein the special characteristic vector corresponds to the type of the power transformation, and combining the basic characteristic vector and the special characteristic vector to obtain the characteristic vector of the transformer substation.
4. The method of claim 3, wherein the base eigenvector comprises substation bus load data, weather data, date type data.
5. The method of claim 3, wherein the step of predicting the bus load of the substation based on the load characteristic,
if the transformer substation is a pure load station, the special feature vector comprises bus load before one week;
if the transformer substation is a wind power station, the special feature vector comprises power generation data of a wind power plant;
if the transformer substation is a hydraulic power station, the special feature vector comprises power generation data of a hydraulic power plant;
if the transformer substation is a wind and water power station, the special feature vector comprises bus net load of the day before prediction, and the bus net load is the difference between the actual bus load and the actual generating power of the wind and water power plant.
6. The method for predicting the bus load of the transformer substation based on the load characteristics according to claim 1, wherein the load prediction model is an artificial neural network model, if the transformer substation is a pure load station, the corresponding artificial neural network model comprises two hidden layers, the number of neurons of each hidden layer is 100 and 50 respectively, and an activation function is sigmoid; if the transformer substation is a wind power station or a water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 50 respectively, and the activation function is relu; if the transformer substation is a wind and water power station, the corresponding artificial neural network model comprises three hidden layers, the number of neurons of each hidden layer is 100, 50 and 20 respectively, and the activation function is relu.
7. The method for predicting the bus load of the substation based on the load characteristics according to claim 1, wherein the target time period data before the prediction day are substation area weather forecast information, local power plant output plan data and bus 96-point load per day 12.
8. The method for predicting the load of the substation bus based on the load characteristics according to claim 1, wherein after the load prediction model is input to obtain a load prediction value, the method further comprises the following steps: and if the transformer substation is a wind and water power station, adding the load predicted value to the planned power generation power of the power plant on the prediction day to obtain a transformer substation bus load prediction result.
9. The substation bus load prediction method based on the load characteristics according to claim 1, further comprising a data preprocessing step after the historical data is acquired, and specifically comprising:
if the load data at a certain moment is defective or lost, carrying out linear interpolation patching by using the load data in adjacent time;
if the load data are 0 for several consecutive days, judging the load data as abnormal load data, and deleting the abnormal load data;
and integrating all data in the historical data into a unified preset table.
10. The substation bus load prediction method based on load characteristics according to claim 1, wherein training a load prediction model with the feature vectors specifically comprises: and (3) arranging and combining values in the given parameter list to obtain each group of parameters, training the load prediction model under each group of parameter configuration by using the characteristic vector, evaluating the effect of each trained load prediction model by using a cross validation method, and selecting the load prediction model with the best effect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315037.4A CN115660893A (en) | 2022-10-26 | 2022-10-26 | Transformer substation bus load prediction method based on load characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211315037.4A CN115660893A (en) | 2022-10-26 | 2022-10-26 | Transformer substation bus load prediction method based on load characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115660893A true CN115660893A (en) | 2023-01-31 |
Family
ID=84991327
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211315037.4A Pending CN115660893A (en) | 2022-10-26 | 2022-10-26 | Transformer substation bus load prediction method based on load characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115660893A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117293824A (en) * | 2023-11-23 | 2023-12-26 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for power demand prediction |
-
2022
- 2022-10-26 CN CN202211315037.4A patent/CN115660893A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117293824A (en) * | 2023-11-23 | 2023-12-26 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for power demand prediction |
| CN117293824B (en) * | 2023-11-23 | 2024-04-12 | 宁德时代新能源科技股份有限公司 | Method, apparatus and computer readable storage medium for power demand prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Behera et al. | Solar photovoltaic power forecasting using optimized modified extreme learning machine technique | |
| Jahangir et al. | Deep learning-based forecasting approach in smart grids with microclustering and bidirectional LSTM network | |
| Chang et al. | An improved neural network-based approach for short-term wind speed and power forecast | |
| Wang et al. | Research and application of a hybrid forecasting framework based on multi-objective optimization for electrical power system | |
| Eseye et al. | Short-term wind power forecasting using a double-stage hierarchical hybrid GA-ANN approach | |
| CN108694470A (en) | A kind of data predication method and device based on artificial intelligence | |
| Bagheri et al. | A novel wind power forecasting based feature selection and hybrid forecast engine bundled with honey bee mating optimization | |
| Ma et al. | Meta learning-based hybrid ensemble approach for short-term wind speed forecasting | |
| Ghofrani et al. | Hybrid clustering-time series-bayesian neural network short-term load forecasting method | |
| Staudt et al. | Predicting transmission line congestion in energy systems with a high share of renewables | |
| Tavares et al. | Comparison of PV power generation forecasting in a residential building using ANN and DNN | |
| CN111489038A (en) | Method for improving accuracy of ultra-short-term power prediction of wind power plant | |
| CN115660893A (en) | Transformer substation bus load prediction method based on load characteristics | |
| Pappala et al. | Predictive optimal control of wind farm reactive sources | |
| Panapakidis et al. | A hybrid ANN/GA/ANFIS model for very short-term PV power forecasting | |
| Buonanno et al. | Comprehensive method for modeling uncertainties of solar irradiance for PV power generation in smart grids | |
| Ibrahim et al. | LSTM neural network model for ultra-short-term distribution zone substation peak demand prediction | |
| Raza et al. | A multivariate ensemble framework for short term solar photovoltaic output power forecast | |
| Shayanfar et al. | Wind power prediction model based on hybrid strategy | |
| Yuan et al. | Short-term wind speed forecasting using STLSSVM hybrid model | |
| Chang et al. | Forecasting wind power generation by a new type of radial basis function-based neural network | |
| Ramırez-Rosado et al. | An advanced model for short-term forecasting of mean wind speed and wind electric power | |
| Pappala et al. | Management of distributed generation units under stochastic load demands using particle swarm optimization | |
| Bantupalli et al. | Wind Speed forecasting using empirical mode decomposition with ANN and ARIMA models | |
| Wang et al. | An alternative method for estimating wind-power capacity credit based on reliability evaluation using intelligent search |
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 |