118 results about "Wind power forecasting" patented technology

The invention discloses a wind power forecasting method based on a genetic algorithm optimization BP neural network, comprising the steps: acquiring forecasting reference data from a data processing module of a wind power forecasting system; establishing a forecasting model of the BP neural network to the reference data, adopting a plurality of population codes corresponding to different structures of the BP neural network, encoding the weight number and threshold of the neural network by every population to generate individuals with different lengths, evolving and optimizing every population by using selection, intersection and variation operations of the genetic algorithm, and finally judging convergence conditions and selecting optimal individual; then initiating the neural network, further training the network by using momentum BP algorithm with variable learning rate till up to convergence, forecasting wind power by using the network; and finally, repeatedly using a forecasted valve to carry out a plurality of times of forecasting in a circle of forecast for realizing multi-step forecasting with spacing time interval. In the invention, the forecasting precision is improved, the calculation time is decreased, and the stability is enhanced.

The invention relates to a large grid real-time scheduling method for accepting access of wind power, which belongs to the technical field of power system operation and control. The method comprises: according to the characteristics of wind power and load fluctuation and the control characteristics of generator sets, classifying the generator sets in the whole grid; acquiring the current plan, real-time output, connecting line plan, numerical weather prediction and other related information of each generator set; performing ultrashort period load prediction and wind power output prediction towork out the output regulation amount at next moment of real-time scheduling generator sets and construct an active real-time scheduling model with the smallest wind loss; working out the output regulation amount of the real-time scheduling generator sets including the wind power generator sets by using a simplex method; and transmitting the next output regulation amount of thermal power generator sets directly, and giving the output maximum value at next moment of the wind power generator sets. In the invention, the combined optimized scheduling of the wind power generator sets and traditional generator sets is performed to eliminate wind power generation prediction deviation and load prediction deviation in advance, so the wind power accepting capability of a power grid is improved to the maximum extent while the operation economy of the power grid is guaranteed.

The invention discloses a wind power short-term prediction method based on a long-term and short-term memory network, comprising a long-term and short-term memory neural network training algorithm, ashort-term wind power prediction error distribution algorithm and a wind turbine generator power short-term prediction model design. A long-term and short-term memory network algorithm (LSTM)-based wind pow prediction model is established based on the depth learning network, and the Gaussian mixture model (GMM) is used to analyze the error distribution characteristics of the short-term wind powerprediction. The invention can obtain different confidence intervals of two units through the GMM model. It is proved that LSTM method has higher precision and faster convergence rate, and GMM method has practical application value for wind power dispatching.

The invention discloses a dispatching method for achieving robust operation of an electrical power system. The dispatching method comprises the steps that S1, original data information is obtained; S2, under a certain confidence coefficient level, an upper limit and a lower limit of a mean value of day-ahead, intra-day and real-time wind power generation forecast errors, an upper limit and a lower limit of day-ahead, intra-day and real-time photovoltaic power generation forecast errors, and an upper limit and a lower limit of day-ahead, intra-day and real-time load forecast errors are obtained; S3, a day-ahead dispatching plan, a robust safe operation range corresponding to the day-ahead dispatching plan, an intra-day dispatching plan, a robust safe operation range corresponding to the intra-day dispatching plan, a real-time dispatching plan and a robust safe operation range corresponding to the real-time dispatching plan are obtained. According to the method, the rolling coordination technologies of forecast information, current operation information and historical operation information are considered simultaneously, the robust safe operation ranges of the system are obtained, and therefore the dispatching plans are not limited to a unique preset value, and flexible dispatching in the robust ranges can be achieved. The obtained dispatching plans can be used for coping with stochastic volatility of new energy power generation better, and safety and economical efficiency are both considered.

The invention discloses an ultra-short-term wind power prediction method based on a small wavelength short-term memory network, which generates input variables according to historical data and takes the corresponding wind power historical data as output to obtain a training sample. Using wavelet analysis method to decompose the training samples into four wavelet samples, and using short-term and long-term memory network model to train the four wavelet samples respectively, the small-wavelength short-term memory network prediction model after training is obtained. According to the actual data of the four wavelet samples at the time to be predicted, the test input data are generated and input to the prediction model, and the output is the ultra-short-term wind power prediction value at the time to be predicted. The invention combines wavelet analysis method with long-term and short-term memory depth network, can realize data stabilization processing and depth learning at the same time, improves prediction accuracy and enhances model generalization ability.

The invention discloses an ultra-short term wind power forecasting method based on a time series method. The forecasting method comprises the following steps: 1. gathering wind measurement data of an anemometer tower adjacent to a wind power station; 2. processing data: carrying out smoothing and stabilizing treatments on the wind speed recorded by the anemometer tower; 3. carrying out wind speedprediction modeling by utilizing the time series method, respectively modeling the wind speed data subjected to the smoothing and stabilizing treatments in the step 2 according to a forecasting time resolution, and establishing 16 prediction models, and figuring out the forecast wind speed within 0-4 hours; and 4. calculating the ultra-short term wind power: calculating the prediction models which are used for forecasting the wind speed input wind power to obtain a wind power prediction result within the forecast validity. By utilizing the method provided by the invention, the wind power output within 0-4 hours of the wind power station can be forecast in a rolling mode, reasonable data support can be provided for electric network frequency modulation and the maintenance of the stable operation of the electric network, so that a dispatching department can adopt solutions in advance for various mutational situations caused by haste changes of the wind power during the electric network operation by the dispatching department.

The invention discloses a wind power prediction method based on continuous time slice clustering and support vector machine (SVM) modeling. The method comprises the following steps of: (1) performing annual similar day unsupervised clustering according to the wind characteristic; (2) partitioning an entire year into n continuous time slices according to a similar day clustering result obtained in the step (1), and clustering and classifying every time slice according to the frequency of each type of date within every time slice and the wind characteristic in the continuous time slices; and (3) modeling the time slices of the same type in the step (2) by using an SVM for predicting the same time of future years. An annual continuous time slice clustering method is adopted on the basis of day similarity, so that day similarity and time continuity are considered simultaneously, and the similarity of a training sample in a prediction model and the accuracy of wind power prediction are increased greatly. Compared with the conventional method, the wind power prediction method has the advantages that: the relative power prediction error is decreased by 7.2 percent, and the prediction accuracy of the wind power is up to 83.96 percent.

The present invention provides a wind power forecasting system, which utilizes the meteorological element forecast value output by a numerical weather forecast system and works out the forecast value of generation power of a wind power field in the determined future time through the calculation by a calculation processing unit. The wind power forecasting system can work out the generation power of wind power field at the future time ahead, thus providing a reliable basis for absorbing wind power by a grid, reducing peak regulation cost and improving wind power quality.

The invention relates to a large grid active power real time control method in a restricted wind power state, and belongs to the technical field of operation and control of electric systems. The method comprises the following steps: firstly obtaining the current restriction quantity of a wind power field by using a benchmark dynamo method or a theoretic estimation method according to wind speed data, acquired in real time, of the wind power field and relative parameters of a generator; and then establishing a model in active real time control by the system according to the minimum wind-abandoning principle, optimizing and solving the model by using a suggested solving algorithm to obtain the current maximum absorptive wind power quantity of the system and an optimal adjusting strategy of other water-fire generator systems, and interpolating the obtained adjusting strategy by using a difference value method so as to be compatible with the existing ACE (access control entry) order format. The method provided by the invention has the following advantages: a real-time control loop using the minimum wind-abandoning loss as a target is added between a real-time plan and the ACG (application control gateway) control, so as to implement the joint optimization scheduling of the wind power and the traditional unit through the wind power field wind-abandoning quantity obtained by real-time computation, so that the wind-abandoning electric quantity caused by the prediction error of wind power generation is maximally reduced, and to the accepting capability of the grid to the wind power is furthest improved while the economical efficiency of the grid operation is ensured.

The invention relates to a model correction based wind power forecasting system and a method. The model correction based wind power forecasting system comprises a numerical weather forecasting server, a fan, an anemometer tower, a wind power forecasting server, a database server and a wind power forecasting system client. The model correction based wind power forecasting method comprises the following steps: firstly using a numerical weather forecasting model provided by the meteorological department to forecast the weather situation of a wind power plant, and then building a real-time forecasting model, and converting the forecasting value of the numerical weather forecasting model to power output of the wind power plant. The system and the method are adopted to reduce various model errors and ensure the accuracy rate of forecasting results.

The invention provides a wind power probability forecasting method based on numerical weather forecasting ensemble forecasting results. Numerical weather forecasting serves as the foundation, basic input data are provided for short-period wind power forecasting through a numerical weather forecasting ensemble forecasting technology, and a short-period forecasting model is established for each ensemble member to obtain a plurality of groups of forecasting results. For the obtained plurality of groups of forecasting results, and different characteristic forecast errors are classified through an ensemble forecasting configuration characteristic classification method and a forecasting power level classification method to obtain future forecast error bands under certain confidence level. According to the wind power probability forecasting method, under the same confidence level, the error band section is narrower, and for power grids containing large-scale wind power integration, under the condition of the same safety margin, the power grid operation cost can be effectively reduced, and the power grid operation economical property can be improved.

The invention belongs to the field of electric system forecasting, and provides a method for estimating a wind power forecasting error burst based on a hidden markov model. A wind power ultrashort term forecasted value reported to a dispatching department for a wind power plant is a deterministic point forecasting and given in a curved mode, but the problem that the forecasting accuracy is not high exists. By introducing an HMM model, modeling is performed on the wind power ultrashort term forecasting error, the error burst is processed by means of a locally weighted regression scatter plot smoothing method, the result accuracy is improved and the result conservation is lowered. The wind power forecasting error burst can be obtained, an error fluctuation state transition matrix can be obtained, and references are provided for dispatching operation.

The invention relates to the field of machine learning and wind power generation, and particularly relates to a wind power forecast method based on continuous period clustering. The wind power forecast method comprises the steps that an Elman neural network and a support vector machine are used as a forecast model to perform iterative forecasting on the basis of a similar day forecast method so asto determine the similar period length; the similarity measure standard is determined through combination of the power vector and the meteorological information according to the similar period lengththrough a two-stage search strategy, and the optimal similar period set is found in the historical data; and a wind power forecast model is created based on the Elman neural network, and the obtainedoptimal similar period set acts as the training data to perform iterative computation through the wind power forecast model so as to complete wind power forecasting of the future periods. The meteorological factor is introduced on the basis of the similar day forecast method, and the clustering-classifying-based similar period selection strategy is adopted so that the optimal similar period set can be rapidly searched and the forecast precision and accuracy can be enhanced.

The invention provides a thermal-storage cogeneration and wind power coordinated scheduling method. The method includes of: obtaining the initial day-ahead plan data of a system and the thermal storage parameter of a thermal storage device; establishing, according to the initial day-ahead plan data of the system and the thermal storage parameter of the thermal storage device, the day-ahead plan model of a thermal-storage cogeneration and wind power coordinated scheduling system and establishing the day-ahead scheduling plan of the thermal storage device; acquiring intraday rolling forecasting data; based on the day-ahead plan data and the intraday rolling forecasting data, establishing an thermal-storage cogeneration and wind power coordinated operation intraday rolling plan model and an intraday rolling scheduling plan. In order to cope with the uncertainty of wind power forecasting, the thermal-storage cogeneration and wind power coordinated scheduling method takes account of a promotion effect of thermal storage on wind power consumption from two aspects of day-ahead rolling and intraday rolling, and establishes a corresponding thermal-storage cogeneration and wind farm scheduling plan so as to achieve reasonable output of each unit.

The invention discloses a rolling optimal dispatching method based on wind power output prediction error, which comprises the following steps: determining the output power plan value of a corresponding unit through optimization and the size of wind power reserve capacity; The uncertainty of wind power forecasting error is modeled and analyzed from two angles of time and power. The wind power prediction error probability density function of different power under different time section is obtained. Formulate the strategy of positive and negative rotation reserve within the day, underestimate thecost, and join the rolling scheduling layer within the day; To positive, negative rotation reserve high, underestimating the cost; The minimum cost of rolling adjustment is the objective function ofthe intra-day scheduling layer, which satisfies the constraints of climbing rate and rotating reserve capacity of each time section of the unit, and the results of the day-ahead planning layer are optimized. The risk caused by prediction errors is effectively controlled, and under the constraint of line capacity, rolling optimization of unit output and reserve capacity is achieved, so as to to achieve the optimal scheduling of economy.

The present invention relates to an ensemble wind power forecasting platform system and the operational method thereof. According to the present invention, a great amount of wind energy predictions from multiple sources, including numerical weather prediction information, multi-grid prediction information, and multiple wind-energy predicting methods, are integrated and processed for providing users with an ensemble prediction. Thereby, the trend and the possible variation range of the output capacity of a wind farm can be mastered. In addition, by means of the integration platform, the predicted results by different prediction modes can be compared and the history data and the predicted results can be compared as well, which can be used as a basis for improving modes for prediction-mode developers.

The invention relates to a super short-term wind power forecasting method based on a back propagation (BP) neural network, which is technically characterized by comprising the steps that: data is grouped through a cross grouping method as the input of a training process of the BP neural network; the training of the BP neural network is carried out through modified learning rate algorithm; and a forecasting result is obtained by calculating the wind power of a wind farm. The super short-term wind power forecasting method based on the BP neural network has a reasonable design, adopts the improved algorithm of the BP neural network, solves the problem that the convergence rate is slow during the training process by modifying the learning rate in the training process, can greatly improve the convergence rate in the training process, simultaneously selects data to train the neural network through the cross grouping method, can approach any continuous non-linear function by any precision; and with the increased scale of the wind farm and the non-linear increase of the wind speed changes, the adopted wind power forecasting method has very good robustness.

The invention discloses a multi-power joint optimized scheduling operation method based on wind-nuclear coordination, which relates to the technical field of power grid control systems. The multi-power joint optimized scheduling operation method comprises the steps of: establishing an optimized unit combination scheduling operation method model according to a set number and operation parameters ofthermal power generating units, a set number and operation parameters of wind power generating units, a set number and operation parameters of nuclear power generating units and a set number and operation parameters of pumped-storage unit in a power system, and load data and wind power forecasting data of the power system; and calculating a unit joint operation result with maximum power grid revenue and maximum wind power consumption according to the optimized unit combination scheduling operation method model. The multi-power joint optimized scheduling operation method takes power grid scheduling cost minimization and wind power consumption maximization as optimization goals, and can meet the requirements for power grid revenue maximization and wind power consumption maximization.

The invention provides a wind power forecasting method dividing based on weather process. The wind power forecasting method comprises the following steps of: determining a numerical weather prediction matrix M and a numerical weather prediction standard matrix X; analyzing principle components of the numerical weather prediction standard matrix X; clustering a matrix Y composed of the first m-th principle components in the numerical weather prediction standard matrix X which is subjected to the principle component analysis; and establishing a wind power forecasting model, and forecasting wind power. According to the wind power forecasting method dividing based on weather process, based on the wind speed, wind direction and diurnal variation of pressure in NWP data, a sample is subjected to dimension reduction process by the principle component analysis, weather processes are classified by a clustering analysis method, weather types are divided into a high pressure stable type, a low pressure unstable type and the like according to the size and stability of control air pressure and the variation characteristics of wind speed and wind direction, and a forecasting model is established by adopting a BP neural network with respect to each weather process, and thereby the forecasting accuracy is effectively improved.

The invention discloses a wind power field active power control method based on power forecasting information, wherein the control method comprises the following steps: firstly, pre-treating wind power forecasting information; secondly, calculating the power regulating amount of a wind power field; thirdly, formulating a preliminary distribution scheme of a wind generation set group; fourthly, formulating an optimized distribution scheme of the wind generation set group; fifthly, selecting a regulating machine group; sixthly, distributing the power regulation amount of the wind power field; and seventhly, determining the control time delay and triggering the next control. According to the invention, wind generation sets are grouped reasonably according to the ultra-short-term wind power forecasting information and short-time power forecasting information, the active power distribution scheme of the wind power field within a certain confidence interval is formulated accurately, the unified planning and control for the active power of the wind power field are realized, the regulating times of the wind generation sets can be reduced, and the influences of frequency regulation on the service lives of the wind generation sets are reduced.

A neural network wind power forecasting method and system includes: collecting numerical weather forecasting data at forecasting time; the wind power prediction value is obtained by substituting the numerical weather forecast data into the prediction model constructed in advance. The prediction model is based on principal component analysis and neural network. The technical scheme of the inventioneffectively improves the prediction accuracy, shows that the method has certain feasibility and advancement in wind power prediction based on numerical weather prediction, and has certain advantagesin processing large sample data.

The invention provides a neural network wind power short-term forecasting method based on a fuzzy partition theory. The neural network wind power short-term forecasting method based on the fuzzy partition theory adopts the mode of combining a fuzzy theory, artificial intelligence and a statistical theory through analyzing the important features of wind velocity variation and the relationship between wind velocity and power. When wind power forecasting is conducted, wind scale fuzzy partition processing is conducted on wind velocity data obtained from weather forecasting according to periods of time, BP neural network partition forecasting is conducted, a forecast power value is obtained through multiplying a partition forecast value by a membership degree value of the partition forecast value and adding all partition values, a probability statistics modified algorithm is conducted, and the forecast power is obtained. The neural network wind power short-term forecasting method based on the fuzzy partition theory improves the accuracy of a forecasting model effectively.

The invention relates to a short-term wind power forecasting method based on a hybrid algorithm, which includes the following steps: S1 decomposing the original wind power into a series of intrinsic mode function (IMF) sub-modal components by using the integrated empirical mode decomposition technique, S2 extracting the main trend components of IMF and RES components except the first IMF componentIMF1 decomposed by the integrated empirical mode decomposition (IMD) technique by using the singular spectrum analysis (SSA) method to obtain more obvious sub-modal components, S3 preserving IMF1 andR, and decomposing IMF1 and R into a series of stationary sub-modal components by wavelet packet decomposition. S4 making use of on-line robust limit learning machine to to establish a prediction model for all the sub-modes obtained in the step S1-S3,, and obtaining a final wind power prediction result by superposing the sub-modes; The invention can effectively and accurately predict the actual wind power system, and provides an important reference for the operation and planning of the electric power system.

The invention discloses an error evaluation method of wind power forecasting. The error evaluation method of wind power forecasting includes error evaluation index of wind power forecasting is calculated, wherein sample data includes predict data and measured data, according to sample data of the wind power forecasting. Principal component analysis is applied to the error evaluation index of wind power forecasting to choose main effective components. Weight coefficient is calculated by the corresponding main effective components. Comprehensive evaluation index is calculated by the main effective components and weight coefficient calculated by the main effective components accordingly. The error evaluation method of wind power forecasting has the advantages of evaluating the forecasting level of wind power in a comprehensive way, avoiding uncertainty created by different ranking produced from multiple indicators , and making the error evaluation more general and accurate.

The invention discloses an economic dispatching method based on a general wind power forecasting error model. General distribution is employed for fitting of PDF and CDF of practical wind power powers on different wind power forecasting intervals, the method is relatively suitable for wind power forecasting error modeling at any time scale and any amplitude, the model fitting precision is higher than conventional Gauss distribution and beta distribution, moreover, an improved linear sequence algorithm taking consideration of wind power forecasting nondeterminacy is employed and provides new thinking for calculating an economic dispatching problem containing wind power field nondeterminacy, as the general distribution CDF and the corresponding inverse function have specific analysis expressions, a general wind power forecasting model is employed to make differential operation have the specific analysis expression, and difficulty in solving an economic dispatching problem containing undetermined wind power access is solved.

The invention relates to a regional wind power forecasting method and belongs to the technical field of wind power generation. The method includes collecting wind power data of different wind power fields in a region connected to one circuit typology; according to the correlation and aggregation between the power data and wind speed data in the wind power data of different wind power fields, grouping the wind power fields in the region; according to the wind power data of the wind power fields in different wind power groups, establishing a forecasting model; according to the forecasting model, forecasting the power of different wind power group; superposing the obtained wind power of the different wind power fields and obtaining a regional wind power forecasting value. According to the invention, the correlation and aggregation between the wind speed data and the power data of the different wind power fields in the region are taken into account, wind power data aggregation is realized by adopting a clustering algorithm and regional wind power forecasting is realized through establishing a depth neural network model. Regional wind power forecasting accuracy is improved.

The invention relates to a method for analyzing the influence of output power fluctuation of a wind farm on a power grid, which comprises the following steps of: calculating forecast ACE (Area Control Error fluctuation) of a next moment by using the wind power forecasting data of a single wind farm in an area power grid, the actual wind power data of the area power grid and the ACE fluctuation data of the area power grid, wherein the ACE is an error value formed according to the current load, power generation, power collection, frequency and other factors of the power grid, and reflects the power balance condition of an area;, comparing the ACE fluctuation with an ACE threshold, and giving out early warning. The method lays the foundation for large-scale wind power grid-connected access and scheduling, is favorable for improving the utilization efficiency of green energy and has obvious economic and social benefits.

The invention discloses a plateau mountain area wind power forecasting method based on different wind speed sections. The method comprises the following steps that: collecting the geographic coordinates of n pieces of fans of a wind power plant, the topographic map, which contains a coordinate direction, of a wind power plant area, the wind speed data of a numerical value weather forecast, historical wind speed data and a wind direction rose diagram; dividing positions where the n pieces of fans are positioned into a flat area, the front side of a hillside and the back side of the hillside; clustering the historical wind speed data of the area where the wind power plant is positioned to obtain m wind speed sections; utilizing the historical wind speed data of the area where the wind power plant is positioned to aim at three classes of positions to independently carry out segmentation fitting on the wind speed of the m pieces of wind speed sections to obtain a wind speed model which considers the fan position of the plateau mountain area; establishing an annual wind speed set; taking the wind speed set as a sample set to cluster the wind speed to establish the wind power forecasting model of a support vector machine; and calling the wind power forecasting model of the support vector machine to carry out wind power forecasting. By use of the method, the technical problems of low accuracy, big errors and the like since an air return phenomenon and different positions of the fans are not considered can be solved.

The invention provides a short-term wind power forecasting method and system, comprising: collecting forecasting meteorological data; Inputting the forecasted meteorological data into a short-term wind power forecasting model created in advance to obtain a wind power forecasting value; The training data set of the short-term wind power prediction model is obtained by taking historical meteorological data related to the total output power of the wind turbine as modeling data and extracting the modeling data by PCA principal component. The technical proposal provided by the invention improves the operation speed and the modeling accuracy.

The invention discloses a method and system for predicting hybrid wind power generation. The method comprises the following steps: acquiring wind directions, wind speeds and historical data of corresponding wind power output power of a wind farm, sampling from the historical data to obtain sample data; conducting judgment and analysis on statistical features of the sample data, acquiring wind directions that are featured by an integrated wind frequency and have a wind power output power difference which reaches a difference threshold value, and based on the acquired wind directions and corresponding relations between the wind directions, and the wind speeds and the wind power output power, adopting the fuzzy hierarchy clustering method in dividing the sample data into three types; adopting the neural network algorithm in training each type of samples, correspondingly forming three types of specific wind generation prediction models, then conducting combination and processing, establishing a hybrid wind generation prediction model which is intended for predicting wind power generation capacity. Therefore, the method, through the implementation, can conduct model prediction on different wind directions and wind speeds in a specific manner and can increase precision of prediction the wind power generation power.