112 results about "Generative power" patented technology

The invention discloses a physical prediction method for wind power station power based on a computational fluid mechanics model. The physical prediction method comprises the following steps: establishing a computational fluid mechanics model; performing discretization on wind conditions of a wind power station, and taking the discretized wind as boundary conditions for conditions numerical simulation of the computational fluid to obtain space flow filed distribution of the wind power station at the discretized wind conditions; establishing data base of hub height, wind speed, wind direction and generated power of wind generation sets under the discretized wind conditions; and taking numerical weather prediction parameters as input data, and utilizing the data base to figure out the wind speeds and the wind directions of the wind generation sets so as to figure out the generated powers of the wind generation sets, and accordingly obtain predicted value of the wind power station power. According to the invention, the physical prediction method is applicable to multiple wind power stations, has small calculated amount in the power prediction stage and has short calculation time.

The invention discloses a photovoltaic power generation capacity / power prediction device which comprises a monitoring system, a data reading module, a data base, a data processing module, a weather information processing module and a prediction module. The data reading module reads photovoltaic power station data information monitored by the monitoring system in real time. The data base stores data information needed by prediction. The data processing module performs classification and classification result assessment on historical power generation capacity / power data and various weather data in the data base in a fuzzy cluster analysis method to obtain a similar day sample set. The weather information processing module processes weather forecast data. The prediction module comprises a BP prediction sub module, a grey prediction sub module and a support vector machine prediction sub module, and prediction results of all the prediction sub modules are combined to obtain the final prediction result. The photovoltaic power generation capacity / power prediction device combines functions of information monitoring and prediction to obtain the prediction result and provides a complete technical solution.

The invention discloses a photovoltaic generated power prediction method based on multi-period comprehensive similar days. The method comprises the steps that firstly, the Euclidean distance method is adopted for classifying weather types and segmenting prediction days; historical similar days are selected at different periods of time, and the BP neural network is adopted for predicting the generated power of the corresponding period of time; a day feature similar day function is applied for predicting the first period of time to obtain a prediction power value of the first period of time; the obtained power value of the first period of time is combined with a linear comprehensive similar day function to obtain the comprehensive similar days, and the comprehensive similar days are applied for predicting the second period of time to obtain a prediction power value of the second period of time; then, power values of the follow-up periods of time are predicted by repeatedly executing the method for the second period of time according to the prediction power values obtained by the previous period of time; the prediction results of the periods of time are combined, and therefore photovoltaic generated power output data of the whole day to be predicted are obtained. According to the prediction method, the photovoltaic generated power prediction accuracy can be effectively improved.

The invention discloses a method for predicating the short-period output power of photovoltaic power generation based on a BP (Back Propagation) neural network. According to the method, the BP neural network is adopted for predicating the output power of a photovoltaic power generation system, and the influence of weather factors on the output power of the photovoltaic power generation system is subjected to statistical analysis. The method comprises the following steps of firstly mapping weather types as day types used as the input data of the BP neural network, and utilizing power generation power during each time period of a prediction day as output data; then determining the quantity of hidden layer nodes through formula calculation and repeated cut-and-try operations according to the quantity of input and output units; performing normalization treatment on the input data, performing reverse normalization treatment on the output data, and training the BP neural network by utilizing the treated operating data; and finally predicating the power generation power of the predication day by utilizing a trained model, thereby obtaining the predication result. The data processing method and a prediction model can be used for effectively predicating the short-period output power in photovoltaic power generation under multiple weather types.

The invention discloses a photovoltaic power generation power prediction method and system. A correlation analysis method is adopted to analyze historical data and determine a radiation intensity predication correlation time and a power generation power predication correlation time. A BP neural network is adopted to train a solar radiation intensity prediction sample and a photovoltaic power generation power prediction sample so as to obtain a solar radiation intensity prediction model and a photovoltaic power generation power prediction model. The solar radiation intensity prediction model is utilized to compute sun radiation intensity at prediction time of a prediction day; the photovoltaic power generation power prediction model is utilized to compute photovoltaic power generation power at prediction time of the prediction day. A grey relational analysis method is adopted to remove solar radiation intensity at the radiation intensity correlation time with a low relational degree in the historical data, and the predication accuracy of the solar radiation intensity is improved. By the adoption of the good nonlinear function approximation capability of the BP neural network, the solar radiation intensity prediction sample and the photovoltaic power generation power prediction sample are trained, the prediction models are built, and predication accuracy of the prediction models is improved.

The invention discloses a wind and photovoltaic generation power prediction system with multiple prediction modes. The system is characterized by comprising a numerical value weather prediction data acquisition module for inputting numerical value weather forecast data serving as basic data of a prediction algorithm, a prediction mode selection module used for selecting a proper prediction algorithm to predict the power of a wind power plant or a photovoltaic power plant, a prediction algorithm module used for predicting the power of the wind power plant or the photovoltaic power plant and comprising a physical model, an adaptive logic network algorithm model and a BP neural network model, and a prediction result storage module for storing result data predicted by the prediction algorithm module. According to the method, the numerical value weather forecast data is used as input data of the prediction algorithm, the most proper prediction method is selected through the mode selection module, and a power prediction result is obtained.

The invention discloses a short-term photovoltaic power prediction method based on a meteorological factor weight similar day. The method comprises the following steps that: S01: calculating the Pearson coefficient of photovoltaic power and a meteorological factor to extract a main impact factor; S02: classifying historical days by a k-means clustering algorithm; S03: according to grey relationalanalysis, obtaining the weight of the meteorological factors for generation power in different categories; S04: according to similarity statistic magnitude with weight, calculating a similarity between a new sample and each clustering center, and taking the category with the high similarity as the category of the new sample; S05: selecting seven historical days with the highest similarity as similar days to obtain a similar day sample training set; and S06: establishing an RBF-BF (Radial Basis Function-Back Propagation) combined neural network model based on genetic algorithm optimization forprediction. By use of the short-term photovoltaic power prediction method based on the meteorological factor weight similar day, photovoltaic power prediction accuracy can be effectively improved, andthe method is high in practicality.

The invention relates to the technical field of power systems, and particularly discloses a multi-time-scale prediction method of photovoltaic generation power. The multi-time-scale prediction methodof the photovoltaic generation power includes: acquiring basic data required for photovoltaic generation power prediction, wherein the basic data include season types, weather types, temperature, windspeed and historical photovoltaic generation power; classifying historical photovoltaic generation power of the same season according to the weather types; establishing a feature set for photovoltaicgeneration power data under the same weather type; establishing a photovoltaic generation power prediction model of a deep ridgelet neural network (DRNN) according to the feature set; and acquiring amulti-time-scale prediction result of the photovoltaic-method generation power through the established photovoltaic generation power prediction model of the deep ridgelet neural network. The multi-time-scale prediction method of the photovoltaic generation power provided by the invention has the advantages of high running efficiency and high prediction precision.

The invention discloses a method for optimizing and designing island wind electricity generator, diesel engine and storage battery electricity generation power based on an improved particle swarm. The method comprises the following steps of: acquiring island wind resource data at an average wind speed per hour as a unit; acquiring loading data corresponding to the wind speed at the same time at an average load per hour as a unit; determining an island wind, diesel and storage load electricity generation system; linearizing a wind-speed-power curve of the wind turbine; improving a particle swarm optimization (PSO) algorithm; adopting a unit watt cost calculation model; adopting a power loss rate LLP as a ratio of the system power failure time to the estimation period time; output a result so as to obtain the number of wind electricity generators and diesel engines as well as the capacitance of a storage battery when the electricity cost is lowest, and forecasting the unit watt cost. Inthe method, the improved particle swarm algorithm is applied to power supply combined by the wind electricity generator, the diesel engine and the storage battery on the island; according to an energy optimization and scheduling method, the electricity expense is lowest under the condition of meeting the electricity requirement. The method has the advantages of simpleness, high efficiency and accuracy of the obtained optimized result.

The invention provides a multi-objective scheduling method for a wind power-electric automobile-thermal power combined operation model, relating to the field of electrical power systems. The method comprises the steps: S1, a plurality of groups of 24-time-interval wind speed values are generated randomly through the Weibull distribution function; S2, 24-time-interval wind power output and an average value of daily output of the wind power are calculated; S3, an electric automobile is charged and discharged, the charging power and discharging power of the electric automobile are obtained, and the generated output of a thermal power generating unit is calculated; S4, the maximum value and the minimum value of two functions are calculated respectively; S5, fuzzy processing is carried out on the two functions so as to obtain the maximum desirability function; and S6, population evolution is carried out on the maximum desirability function so as to obtain the optimal output. Aiming at the random and indeterminate output of the wind power, the invention provides the method of using ordered charging and discharging of electric automobiles, namely an energy storage system, to stabilize the fluctuation of the wind power, and abandoned wind power is reduced. And meanwhile, the fluctuation of the wind power is reduced, so peak-load regulation and spinning reserve pressure of the thermal power generating unit is reduced, and economic benefits of a wind power-electric automobile-thermal power combined operation system are maximized.

The invention relates to a method for optimizing the proportion of high-proportion renewable energy under the cooperative access of transmission and distribution network, which comprises the followingsteps: 1) acquiring basic data; 2) clustering based on that basic data to obtain a typical plan scene; 3) for that typical plan scenario, establishing a collaborative planning model of transmission and distribution network, The objective of the collaborative planning model is to minimize the cost. The constraints include the independent constraints of the transmission and distribution network andthe collaborative constraints of the transmission and distribution network. The decision variables include the investment capacity of renewable energy units in the transmission and distribution network, the power generated by conventional units, the discarded energy power of renewable energy sources and the load shedding power of renewable energy units. 4) solving that transmission and distribution network collaborative planning model to obtain the optimal renewable energy investment capacity scheme; 5) obtaining the optimal distribution ratio of the high-proportion renewable energy in the transmission and distribution network based on the optimal renewable energy investment capacity scheme. Compared with the prior art, the invention has the advantage of high accuracy, strong practicability and high efficiency.

The invention provides a master-slave type micro-grid power load prediction system based on load balancing. The master-slave type micro-grid power load prediction system comprises a main server; the main server is used for carrying out high-complexity mathematical calculation and large-scale data storage; information interaction can be carried out through an Ethernet switch and distributed secondary stations of the prediction system; the distributed secondary stations of the prediction system can transmit tasks which are required to be subjected to large-scale calculation to the main server; the main server performs calculation of the tasks; and each distributed secondary station of the prediction system is used for acquiring real-time data of fans in a micro-grid or a secondary micro-grid, real-time data of photovoltaic generated power and load data of a region. The power and the load of the micro-grid can be predicted precisely, a prediction result provides precise data support for an energy management system and a micro-grid controller, the prediction cost is reduced, and the using efficiency of a server of the prediction system and the using efficiency of a device of the prediction system are improved. Data-level load balancing can be realized on the system, and network element internal threading-level load balancing is realized in each network element.

The invention discloses a diesel engine and storage battery coordinated micro grid scheduling method with multiple optimization objectives. According to the structure of an independent micro grid system which includes photovoltaic power generation, wind power generation, diesel engine power generation and energy storage, operational characteristics at the aspects including the photovoltaic power generation, wind power generation, diesel engine power generation and energy storage are comprehensively analyzed, a mathematic model and a target function of multi-objective-optimization scheduling which considers the cost of diesel engine power generation and the cycled electric quantity of storage batteries are provided, and constraint conditions for charging power of the storage batteries, SOC range, generating power of the diesel engines, power balance of the system and the like are established. Frontier of a non-dominated solution is obtained via the related multi-objective-optimization algorithm, and further multiple Pareto optimal solutions are obtained. The optimal scheduling schemes are determined according to different weather conditions. According to the method, a multi-objective mathematic model is established on the basis of the independent micro grid system of an island in the sea, the method aims at reducing the cost of diesel engine power generation and the cycled electric quantity of storage batteries, theoretical basis and technical support are provided for solving problems in power supply of the island in future, and the method is conducive to improving the whole operational economical efficiency of the independent island micro grid.

The invention discloses a photovoltaic power generation power prediction method, which comprises the following steps that: S1: obtaining data, and reading the historical data of all photovoltaic powergeneration power and corresponding meteorological data from a system database; S2: carrying out data preprocessing, and carrying out normalization on each data variable in a dataset to (-1,1); S3: establishing a prediction network model; S4: training the model, and according to the preprocessed sample data, adopting an error counterpropagation training method to train the model; S5: testing and assessing the model; S6: storing the model, and storing the model which passes the test and is assessed to be qualified in S5 into a computer ROM (Read Only Memory) unit; and S7: predicting the photovoltaic power generation power, calling a photovoltaic power generation power prediction model stored in S6 from the computer ROM unit, and carrying out calculation to obtain the prediction value of thephotovoltaic power generation power.

The invention discloses an economic dispatching method with robust collaborative consistency. The method comprises the following specific steps: determining a laplacian matrix L; obtaining a total power P<D>, and initializing power generating powers of various units and calculating power deviations; correcting the laplacian matrix L in real time; calculating a consistency gain function c(k); updating a virtual consistency variable of a leader and a follower; calculating real consistency variables of various units; solving the power generating powers P<Gi> of the units; determining power deviations [delta]P and judging whether a power error margin P<error> is met or not; and if so, ending iteration and outputting an optimization result. According to the economic dispatching method, the problem that a traditional CCA algorithm excessively depends on an ideal communication network is solved; the economic dispatching method has robustness on transmission delay and noise interference; the vulnerability that a traditional CCA algorithm cuts off the units from a key position of a communication topology is solved; and plug and play characteristics of the units are considered.

The invention discloses a photovoltaic system power generation power prediction device and method based on a meteorological parameter and a solar panel operation state parameter. The device is characterized in that the device comprises a field data collection system and a master-control room data processing system, wherein the field data collection system comprises first to Nth monitoring units which have the same structure; each monitoring unit comprises a photovoltaic subarray which is connected with a combiner box; the combiner box is connected with an intelligent electric meter; the intelligent electric meter is connected with a monitor; the monitors of the first to Nth monitoring units are communicated through a wireless serial port module; the master-control room data processing system comprises a data receiving processor connected with a capture card; the capture card is connected with an industrial personal computer; the sensor of an aerometeograph is connected with a case; and the monitors of the first to Nth monitoring units of the field data collection system are all communicated with the data receiving processor of the master-control room data processing system through the wireless serial port module.

The invention relates to a method for real-time power prediction of photovoltaic power station based on a SAGA-FCM-LSSVM model, which includes collecting power generated in corresponding period of time of photovoltaic power station and corresponding meteorological parameters on meteorological station, and obtaining meteorological data; power parameter samples of the daily weather being pretreated;based on four statistical indexes and simulated annealing genetic algorithm, the fuzzy C-mean clustering algorithm clustering the samples from the first day of the history day to the day before the forecast day. According to the meteorological eigenvalue of each cluster sample set, the center point of each cluster meteorological eigenvalue is calculated, and the classification of the forecast date is judged by Euclidean distance. The least square support vector machine is trained by using the same kind of parameter samples as the predicted date, and the training model is obtained. The meteorological parameters and power values of the first 2 hours of the time to be predicted are input into the training model for real-time prediction of the power generation at each time of the time to be predicted. The invention can predict the output power value of the photovoltaic power station at each time in real time.

The invention provides a method and a device for real-time prediction of generation power of a photovoltaic system. The method includes steps: A, acquiring historical weather data of a specified date and historical photovoltaic power station running date of the corresponding date; B, classifying the historical weather data according to weather types into historical weather data corresponding to different weather type, building a mapping relation between the historical photovoltaic power station running data and the weather types of corresponding time, and adding a data label for daily photovoltaic station running data; C, acquiring the historical weather data in different weather types corresponding to the historical photovoltaic station running data according to the data labels, and performing data cleaning and normalization processing on the historical weather data; D, respectively acquiring photovoltaic system generation power real-time prediction models corresponding to different weather types according to processed data; selecting the photovoltaic system generation power real-time prediction model corresponding to current weather type to predict current generation of the photovoltaic system. In this way, generation power prediction accuracy is improved.

The invention discloses an ordered electric automobile charging method orientated to an active intelligent distribution network in the technical field of intelligent power grids. The method comprises the following steps of: predicting the conventional load power, the generated energy of a distributed power supply and the charge capacity, so as to obtain a power reference value of total load power in a set time period; obtaining the charging load power reference value of the electric automobile through the actual conventional load power and the actual generated power of the distributed power supply; and adjusting the charging power of the electric automobile through the actual value of the charging load power of the electric automobile. The charging load power of the electric automobile is controlled, so that the fluctuation of the conventional power load and new energy load is suppressed, and the operating economical efficiency and controllability of the distribution network and the new energy consumption capacity are improved.

The invention relates to a photovoltaic power station ultra-short-term power prediction method based on meteorological data similarity analysis and an LSTM neural network. The method comprises steps of selecting power generation power and corresponding meteorological data in the same time period of each day of one month before a day the predicted time period belongs to; carrying out Pearson correlation degree analysis on each meteorological data and the power output; selecting meteorological data with the highest correlation degree, and selecting an initial value, an average value and a tail value of the data in the time period to form a three-dimensional coordinate point; carrying out similarity analysis on meteorological data of unit time before the prediction time and a corresponding meteorological data set of a selected time period by utilizing Euclidean metric; and obtaining meteorological data and power data in a similar time period in which the Euclidean value is smaller than aspecified value, and finally predicting the generated power by adopting the trained LSTM model. According to the method, the generated power of the ultra-short-term photovoltaic power station can be predicted quickly and accurately.

The invention provides a short-term photovoltaic power generation prediction method and system. The short-term photovoltaic power generation prediction method comprises the following steps: acquiringpower generation power and meteorological historical data of a photovoltaic power station at the same moment, and constructing a training set and a test set; grouping the training set and the test setaccording to a preset time interval; independently clustering the samples of each group of training set and test set into sample data of a preset number of weather types; generating power data in thesample data of each weather type is decomposed step by step according to different fluctuation scales by adopting an NACEMD signal decomposition algorithm to obtain components with different time-frequency characteristics, and then combining the components with corresponding weather type characteristics to construct characteristic vectors of each group of training set and test set; training and testing the deep LSTM sequence neural network model by using the feature vectors of the training set and the test set respectively; and predicting the generated power of short-term photovoltaic power generation by using the trained deep LSTM sequence neural network model.

The invention discloses an electric load predication optimization method for N-section intervals of a combined heat and power generation set. The method comprises the following steps: reading heating historical data of the combined heat and power generation set in each hour in N time intervals when approximate linear change of the outdoor temperature occurs in 24 hours of the past day, fitting N linear regression curves of the outdoor temperature and the thermal load of a building through a least square method according to the historical data, substituting the outdoor temperature in a predicate day into the linear regression curves, estimating the thermal load of predicate day, establishing a digital model of a set heating condition diagram through the historical data of the combined heat and power generation set and the least square method, substituting the thermal load of predicate day into the digital model, and calculating the minimum generated power and the maximum generated power of set at certain thermal load according to boundary conditions of the digital model, so as to fix a generation load interval of the set at certain thermal load. The method can be used for accurately predicating thermal load and electric load intervals of a heating system of the combined heat and power generation set in the next 24 hours.

The present invention relates to the technical field of distributed renewable energy, more particularly, to a short-term wind power generation power prediction method and system based on DWT and LSTM,comprising: decomposing wind power raw data into low-frequency signals and high-frequency signals; standardizing the low frequency and high frequency signals using the z-score normalization method. so that the normalized data obeys normal distribution; dividing low frequency signal and the high frequency signal into a training set, a verification set and a test set according to the time sequence.The independent LSTM is used to train the training set and the verification set, and the test set of each signal is predicted to obtain the predicted value of each component, and the predicted valueof each component is summed up to obtain the predicted result. The invention can more fully mine the main information and the secondary information contained in the detailed information contained in the approximate signal in the data, can effectively avoid the problems of gradient disappearance and gradient explosion, and can better improve the prediction accuracy of the wind power generation.

The invention relates to an electricity generation power instruction feed-forward control method of a thermal power generating unit coordination control system. The electricity generation power instruction feed-forward control logic includes the step that automatic generation control (AGC) instructions are divided into two paths after passing through a change amplitude limiting link, wherein one path of AGC instructions is subjected to a change rate limiting link so that actual electricity generation power instructions can be generated, and the other path of AGC instructions is subjected to a linear filtering link, a change rate limiting link and a leading link, so that electricity generation power instruction feed-forward output can be obtained. According to the electricity generation power instruction feed-forward control system of the thermal power generating unit coordination control system of the invention, the boiler of a thermal power generating unit is reasonably utilized to store heat, so that a contradiction between the improvement of AGC instruction response rate and the reduction of boiler fuel quantity fluctuation under a power regulation dispatching mode (R dispatching mode) can be alleviated; the stability of steam pressure of a steam turbine can be ensured when the AGC instructions change greatly in a unidirectional manner, and boiler fuel quantity drastic fluctuation when the AGC instructions change slightly and frequently can be avoided. Compared with a traditional feed-forward control scheme, the electricity generation power instruction feed-forward control method of the invention has the advantages of clear physical meaning of set parameters, convenient configuration and debugging process and the like.

The invention provides a wind power prediction system, which comprises a data collection server (1), a database server (2), an application workstation (3), a wind power prediction server (4), a data interface server (5) and reverse physical isolation equipment (6), wherein the data collection server (1) is used for operating data collection software, is communicated with the integrated communication management terminal of a wind power plant, and collects data; the database server (2) processes, carries out statistical analysis and stores the data; the wind power prediction server (4) operatesa wind power prediction module, uses a neural network integrated algorithm based on weighted least squares support vector machine and quantum particle swarm prediction on the basis of a numerical value weather forecast collected or provided by a SCADA (Supervisory Control And Data Acquisition) system, and is combined with the real-time operation working condition of a wind power plant fan to carryout short-term and ultra-short term prediction on the output situation of a single fan and the whole wind power plant; the data interface server (5) is used for obtaining the numerical value weatherforecast; and the reverse physical isolation equipment (6) is used for guaranteeing network safety. The invention also discloses a wind power prediction method, which can guarantee that prediction data which is used in field can embody recent power generation power features.

The invention discloses a short-term photovoltaic power prediction method based on an improved EMD algorithm and an Elman algorithm. The short-term photovoltaic power prediction method comprises the steps: step S1, carrying out clustering analysis on historical data, and determining a category of a to-be-predicted day and corresponding irradiation intensity to-be-predicted time intervals; step S2, establishing a same-type day time sequence in the category of the to-be-predicted day according to main environmental characteristics; step S3, utilizing the improved EMD algorithm to perform median filtering on the same-type day time sequence, carrying out mode decomposition according to fluctuation degrees, and classifying same-type modes into a category; step S4, adopting the Elman algorithm to predict irradiation intensity of each mode category, and further acquiring photovoltaic hourly power generating power value. The short-term photovoltaic power prediction method aims to increase prediction precision of irradiation intensity under the condition of weak irradiation, is proven to be adapt to irradiation intensity prediction of different-type days, and achieves more rapid and accurate prediction.

A power management system may comprise a generative power source, a main bus between the generative power source and electrical loads, a energy accumulator and a main bi directional power converter interposed between the main bus and the energy accumulator unit. The energy accumulator may comprise a plurality of energy storage blocks. The energy storage blocks may individually comprise energy storage units and control units with dedicated DC / DC bidirectional power converters.