CN116128211A - Wind-light-water combined short-term optimization scheduling method based on wind-light uncertainty prediction scene - Google Patents

Abstract

The invention discloses a wind-light-water combined short-term optimization scheduling method based on a wind-light uncertainty prediction scene, which comprises the steps of preprocessing historical wind-light output data and dividing the hierarchy; building a wind and light forecasting scene building model and a reduction model to generate a wind and light forecasting typical scene set; establishing a scene migration probability calculation model to obtain migration probabilities among different periods of the actual value of the wind-light output; according to a typical scene set of wind and light forecast, combining real-time wind and light output measured data and scene migration probability information at each time to update a forecast scene; and carrying out wind-light-water combined short-term optimized scheduling. Based on the prediction and actual measurement data of the historical wind-light output, the invention provides a new method and technology for optimizing and dispatching a multi-energy complementary system connected with new energy by constructing a wind-light output prediction scene and considering the influence of uncertainty on wind-light-water combined short-term optimizing and dispatching.

Description

A short-term optimal dispatching method for wind, solar and water combined based on wind and solar uncertainty forecast scenario

Technical Field

The present invention relates to a wind-solar-water joint short-term optimization scheduling method considering the uncertainty of wind and solar power, and specifically to a wind-solar-water joint short-term optimization scheduling method based on a wind-solar-water uncertainty forecast scenario.

Background Art

Renewable energy is a green and low-carbon energy source, and is an important part of my country's multi-wheel-driven energy supply system. It is of great significance to improve the energy structure, protect the ecological environment, respond to climate change, and achieve sustainable economic and social development. In the past decade, renewable energy has become the main body of my country's new installed capacity for power generation. The increase in my country's renewable energy power generation will account for more than 50% of the increase in electricity consumption in the whole society, and wind power and solar power generation will double again. However, there is uncertainty in wind, solar and photovoltaic power generation. Direct access will bring a greater impact to the power grid. However, by taking advantage of the flexible output of hydropower, by bundling wind, solar and hydropower for external transmission, the volatility of wind and solar power can be smoothed to a certain extent, reducing the impact of its uncertainty.

At present, domestic and foreign scholars have focused their research on the short-term optimal dispatching method of wind, solar and water combined with the consideration of wind and solar uncertainty on modeling methods based on Bayesian theory and fuzzy mathematics theory. For example, Liu Qiaobo (2018) fitted the distribution of wind power and photovoltaic prediction errors at different output levels based on historical data, introduced the spearman correlation coefficient to describe the complementarity of wind and solar prediction errors by season, and established a wind and solar joint prediction error distribution model; Zhang Juntao (2020) used coupled quantile regression based on stochastic programming theory to transform historical statistical information from a deterministic prediction sequence into a scenario set; Xu Yechi (2022) established a random optimization dispatching model considering frequency response by generating wind power output scenarios describing the randomness of wind power based on the wind power randomness analysis method of prediction error distribution. However, the above methods are all based on historical data to describe a single scenario or multiple unrelated independent scenarios for the formulation of optimal dispatching plans, and cannot consider the correlation between scenarios and the optimization of the dispatching system by the measured values updated at different time periods. The accuracy of describing wind and solar uncertainty will affect the formulation of the optimal dispatching plan, and ultimately cause a deviation in the dispatching target.

Summary of the invention

Purpose of the invention: In view of the problems and shortcomings of the prior art, the present invention provides a wind-solar-water joint short-term optimal scheduling method based on wind-solar uncertainty forecast scenarios. Based on the forecast and measured data of historical wind-solar output, a scene-based wind-solar scenario forecast model, a scene reduction model, and a scene migration probability calculation model are established. By updating the typical scene set of wind-solar forecasts and their migration probability coefficients hourly, the optimal scheduling decision is calculated and updated hourly, and the wind-solar-water joint short-term optimal scheduling is performed.

Technical solution: A wind-solar-water combined short-term optimization scheduling method based on wind-solar uncertainty forecast scenario, including the following steps:

S1. Select historical wind and solar power output data, process missing values and outliers, normalize the processed data, and divide the sample levels;

S2. Establish a wind and solar scenario forecast model based on scenario construction, use sample data of each level to analyze sample characteristics within the level, use the analysis results to forecast wind and solar scenarios based on the day-ahead forecast data of wind and solar output, and obtain a wind and solar forecast scenario set;

S3, establishing a scenario reduction model, performing scenario reduction on the initial wind and solar forecast scenario set, iteratively calculating and selecting the most representative wind and solar forecast typical scenarios, and forming a wind and solar forecast typical scenario set;

S4. Establish a scenario migration probability calculation model based on the historical measured values of wind and solar power output, divide the measured values into intervals, and calculate the migration probability between the measured values with time correlation;

S5. According to the results of typical wind and solar forecast scenarios, based on the hourly measured data of wind and solar output, the optimized scheduling decision is updated hourly, and the short-term optimized scheduling of wind, solar and water is carried out according to the principle of best source-load matching.

Further, step S1 is specifically as follows: the historical wind and solar power output data mainly include the day-ahead forecast wind output data and the measured wind output data with consistent temporal and spatial correlation, as well as the day-ahead forecast photovoltaic output data and the measured photovoltaic output data with consistent temporal and spatial correlation; the method for processing missing values is: the data is supplemented by the linear interpolation method according to two adjacent groups of data; the method for processing outliers is: firstly, the outliers are deleted, and the missing data is supplemented according to the missing value method; the processed data is sample normalized, and the sample normalization method is:

s′＝(s-μ)/σ

Where s′ is the normalized sample value; s is the original sample data; μ is the mean of the original sample set; σ is the standard deviation of the original sample set.

Furthermore, the structure of the scene-based forecast model established in step S2 is:

Based on the forecast and measured data sets obtained after sample normalization, they are classified according to the numerical value of the forecast value, and the characteristic value of the data in each level is calculated. The characteristic value calculation method is as follows:

Where ε′ _i,j is the relative error value of the jth sample in the i-th level; sp′ _i,j is the normalized value of the predicted sample; and st′ _i,j is the normalized value of the measured sample.

为层级的第一特征值；n_i为第i层级的样本相对误差值数量。In the formula,

is the first eigenvalue of the level; _ni is the number of relative error values of samples in the i-th level.

为层级的第二特征值。In the formula,

is the second eigenvalue of the level.

Furthermore, based on the two eigenvalues in the sample level, super Latin square sampling is used to generate a set of wind and solar output forecast scenarios.

Furthermore, step S3 specifically includes: using K-means random centroid clustering method to reduce the scenes, and controlling the clustering result between 4 and 8.

Further, step S4 is specifically: according to the normalized results of the wind and solar power output measured data, the interval is divided and a scene migration probability calculation model is established. The probability calculation method is as follows:

st″＝(st′-μ′)/σ′

Where st″ represents the standard score of the standard normal distribution; μ′ represents the mean of the normalized values of the measured samples; σ′ represents the standard deviation of the normalized values of the measured samples.

Where Pst′ _{(u, d)} represents the probability that the next measured value will be st′ after normalization when the current measured value is in the interval (u, d) after normalization.

Further, step S5 is specifically as follows: based on the results of the typical scene set of wind and solar forecast, the probability of occurrence of each typical scene is calculated hourly, and the decision scene for short-term optimization scheduling calculation is continuously generated. The calculation method is as follows:

Where _P′q is the migration probability coefficient of the qth scene in the typical scene set of wind and solar forecast.

Where _x′p represents the wind and solar forecast scenario value of the pth hour during the optimization scheduling period; _xp,q represents the value of the pth hour in the wth scenario of the typical wind and solar forecast scenario value.

Furthermore, a wind-solar-water joint short-term optimal scheduling model is constructed with the goal of optimizing source-load matching. Based on the continuously generated decision scenarios of short-term optimal scheduling, the wind-solar-water joint short-term optimal scheduling considering the uncertainty of wind and solar is realized. The calculation method is as follows:

Nh _p =N ^w +N ^s +N ^h

为水电站第j时的发电流量；H_j为水电站第j时的发电水头。Where, _Nv is the source-load matching rate; _Nyp is the total system output at the pth hour; _Nhp is the system load at the pth hour; ^Nw , ^Ns , and ^Nh are the wind power, photovoltaic, and hydropower output values, respectively;

is the power generation flow of the hydropower station at the jth time; _Hj is the power generation head of the hydropower station at the jth time.

A wind-solar-water combined short-term optimization dispatching system based on wind-solar uncertainty forecasting scenarios, comprising:

The data processing module is used to classify the input historical wind and solar power output data and calculate the characteristic values of the historical data at each level for scene generation;

The scenario generation module is used to establish a wind and solar scenario forecast model and a scenario reduction model. Based on the day-ahead forecast data, the characteristic values of samples at each level are used to generate a scenario set, and iterative clustering is used to reduce the scenario set, and a typical wind and solar forecast scenario set is output;

The scene migration probability calculation module is used to calculate the migration probability between measured values with time correlation and output the migration probability coefficient of each scene in the typical scene set of wind and solar forecast;

The optimization scheduling module is used to formulate a wind, solar and water joint optimization scheduling plan. Based on the typical scene set of wind and solar forecasts and the migration probability coefficient of each scene, it performs wind, solar and water joint short-term optimization scheduling calculations in accordance with the principle of best source-load matching.

A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the wind-solar-water combined short-term optimization scheduling method based on the wind-solar uncertainty forecast scenario as described above is implemented.

A computer-readable storage medium stores a computer program for executing the wind-solar-water combined short-term optimization scheduling method based on the wind-solar uncertainty forecast scenario as described above.

Beneficial effects: Compared with the prior art, the technical effects of the present invention are as follows: (1) Based on the forecast and measured data of historical wind and solar output, the present invention establishes a scene-based wind and solar forecast model, a scene reduction model and a scene migration probability calculation model, and formulates a wind, solar and water joint dispatch plan by generating a typical wind and solar forecast scene set, and proposes a new wind, solar and water joint short-term optimal dispatch method considering uncertainty; (2) By updating the typical wind and solar forecast scene set and its migration probability coefficient hour by hour, the optimized dispatch decision can be calculated and updated hour by hour. The data required for the uncertain information extraction part of this method are all historical data, and a PYTHON program can be written to cope with the wind, solar and water joint short-term optimal dispatch calculation under different input data in any dispatch period; (3) The principle is simple, the operation is simple and flexible, and it is easy to implement. This technical method performs optimized dispatch calculation based on scene construction and reduction and scene migration probability model, with fast calculation speed and short response time; (4) It can provide support for the subsequent access of other renewable energy sources; This technology provides a new method and technology for the optimal dispatch of multi-energy complementary systems accessing new energy, and also lays a good foundation for the consumption of new energy in multi-energy complementary systems, reducing grid shocks and optimizing energy structure.

BRIEF DESCRIPTION OF THE DRAWINGS

Fig. 1 is a flow chart of the method of the present invention;

FIG. 2 is a system structure block diagram of the present invention.

DETAILED DESCRIPTION

The present invention is further explained below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. After reading the present invention, various equivalent forms of modifications to the present invention by those skilled in the art all fall within the scope defined by the claims attached to this application.

Based on the prediction and measured data of historical wind and solar power output, the present invention establishes a wind and solar scene forecast model, a scene reduction model and a scene migration probability calculation model based on scenario construction. By updating the typical scene set of wind and solar forecast and its migration probability coefficient hourly, the optimized scheduling decision is calculated and updated hourly to carry out the short-term optimal scheduling of wind, solar and water joint.

As shown in FIG1 , a wind-solar-water joint short-term optimization scheduling method based on a wind-solar uncertainty forecast scenario of the present invention comprises the following steps:

S1. Select historical wind and solar output data, process missing values and outliers, normalize the processed data, and divide the sample levels. The specific steps are as follows:

S1.1. First, the historical wind and solar power output data are screened, and the atmospheric environment measurement point data near the relevant wind farms and photovoltaic power stations are selected for calculation. The data accuracy is controlled within 1-15min, and the overall consistency of the data samples is guaranteed to ensure its temporal and spatial correlation.

S1.2. After screening the historical wind and solar power output forecast and measured data, it is necessary to process the missing values and outliers. For wind and solar power output data, there will be no negative values or data exceeding the range of the measuring instrument. In particular, for photovoltaic output data, the measured value before the sun rises should always be zero. Therefore, the selected historical data requires complete and relatively reasonable wind and solar power output forecast and measured data.

S1.3. Normalize the processed samples. The sample normalization method is:

s′＝(s-μ)/σ

Where s′ is the normalized sample value; s is the original sample data; μ is the mean of the original sample set; σ is the standard deviation of the original sample set.

S2. Establish a wind and solar scenario forecast model based on scenario construction, use sample data of each level to analyze sample characteristics within the level, use the analysis results to forecast wind and solar scenarios based on the day-ahead forecast data of wind and solar output, and obtain a wind and solar forecast scenario set. The specific steps are as follows:

S2.1. Calculate the forecast error of the forecast value at each time point in the data set, and divide the layers according to the statistical results of the forecast error. The error value can be used for ladder division or the number of error samples can be evenly divided to determine the upper and lower boundaries of the samples within the layer for subsequent sampling for scene generation.

S2.2. Calculate the characteristic value of the data in each level. The characteristic value calculation method is as follows:

Where ε′ _i,j is the relative error value of the jth sample in the i-th level; sp′ _i,j is the normalized value of the predicted sample; and st′ _i,j is the normalized value of the measured sample.

为层级的第一特征值；n_i为第i层级的样本相对误差值数量。In the formula,

is the first eigenvalue of the level; _ni is the number of relative error values of samples in the i-th level.

为层级的第二特征值。In the formula,

is the second eigenvalue of the level.

S2.3. Based on the two eigenvalues in the sample level, super Latin square sampling is used to generate a set of wind and solar output forecast scenarios. Super Latin square sampling (LHS) accurately establishes the input distribution through sampling with a smaller number of iterations. Compared with Monte Carlo, the key is to stratify the input probability and establish intervals with equal cumulative probability scales. By extracting samples from each interval or layer of the input distribution, the sampling results are forced to represent the values of each interval, so the input probability distribution is forced to be reconstructed. The generation strategy of the wind and photovoltaic forecast scenario set is: the entire sampling process adopts the "sampling without replacement" principle, and the number of stratifications of the cumulative distribution is the same as the number of iterations in the entire execution process. It should be noted that when using this method for sampling, the independence between variables needs to be maintained. The independence is maintained by randomly selecting sampling intervals for each variable, which can effectively avoid unintentional correlation between variables.

S3. Establish a scenario reduction model, perform scenario reduction on the initial wind and solar forecast scenario set, iteratively calculate and select the most representative wind and solar forecast typical scenarios to form a wind and solar forecast typical scenario set.

The K-means algorithm is a basic algorithm in clustering and an algorithm in unsupervised learning. Its basic principle is to randomly determine k initial points as cluster centroids, then calculate the distance between each point in the sample data and the cluster centroid, and classify the samples based on this distance. By continuously iterating the position of the cluster centroid, better clustering results can be obtained.

The specific steps are as follows:

S3.1. Based on the initial set of scenery forecast scenes, we select 4-8 initial centroids, which are the typical cluster centroids.

S3.2. Calculate the distance between other elements in the entire scene set and the centroid of the typical cluster. Here, the distance is calculated using Euclidean distance.

S3.3. Select a new cluster centroid and calculate the classification of the entire scene set under the new cluster centroid. By continuously repeating S3.2-S3.3, the classification results of the entire scene set converge, indicating that clustering is completed.

S4. A scenario migration probability calculation model is established based on the historical measured values of wind and solar power output, and the measured values are divided into intervals to calculate the migration probability between the measured values with time correlation. The specific steps are as follows:

S4.1. Calculate the normal distribution standard score of the corresponding situation of each scenario in the typical scenario set. The calculation method is as follows:

st″＝(st′-μ′)/σ′

Where st″ represents the standard score of the standard normal distribution; μ′ represents the mean of the normalized values of the measured samples; σ′ represents the standard deviation of the normalized values of the measured samples.

S4.2. According to the normalized results of the wind and solar measured data, the intervals are divided and a scene migration probability calculation model is established. The probability calculation method is as follows:

Where Pst′ _{(u, d)} represents the probability that the next measured value will be st′ after normalization when the current measured value is in the interval (u, d) after normalization.

S5. According to the results of the typical scene of wind and solar forecast, based on the hourly measured data of wind and solar output, the optimized dispatch decision is updated hourly, and the short-term optimized dispatch of wind, solar and water is carried out according to the principle of the best source-load matching. The specific steps are as follows:

S5.1. Based on the migration probability values of each scene in the typical scene set of wind and solar forecast, the migration probability coefficient of each scene is calculated. The calculation method is as follows:

Where _P′q is the migration probability coefficient of the qth scene in the typical scene set of wind and solar forecast.

S5.2. Based on the migration probability coefficient of each scenario, generate a calculation scenario for short-term optimization scheduling. The calculation method is as follows:

Where _x′p represents the wind and solar forecast scenario value of the pth hour during the optimization scheduling period; _xp,q represents the value of the pth hour in the qth scenario of the wind and solar forecast typical scenario value.

S5.3. A wind-solar-water joint short-term optimal dispatch model is constructed with the goal of optimizing source-load matching. Based on the continuously generated decision scenarios for short-term optimal dispatch, a wind-solar-water joint short-term optimal dispatch considering the uncertainty of wind and solar is realized. The calculation method is as follows:

Nh _p =N ^w +N ^s +N ^h

为水电站第j时的发电流量；H_j为水电站第j时的发电水头。Where, _Nv is the source-load matching rate; _Nyp is the total system output at the pth hour; _Nhp is the system load at the pth hour; ^Nw , ^Ns , and ^Nh are the wind power, photovoltaic, and hydropower output values, respectively;

is the power generation flow of the hydropower station at the jth time; _Hj is the power generation head of the hydropower station at the jth time.

Based on the forecast and measured data of historical wind and solar output, the present invention establishes a scene-based wind and solar scenario forecast model, a scene reduction model, and a scene migration probability calculation model. By updating the typical scene set of wind and solar forecast and its migration probability coefficient hourly, the optimized scheduling decision is calculated and updated hourly, and the short-term optimized scheduling of wind, solar and water joint is performed. This technology provides new methods and technologies for the optimized scheduling of multi-energy complementary systems connected to new energy, and also lays a good foundation for the consumption of new energy in multi-energy complementary systems, reducing grid shocks, and optimizing energy structure.

As shown in Figure 2, the wind-solar-water combined short-term optimization dispatching system based on the wind-solar uncertainty forecast scenario includes:

The data processing module is used to divide the input data into layers and calculate the characteristic values of the historical data at each layer for scenario generation;

The scenario generation module is used to establish a wind and solar scenario forecast model and a scenario reduction model. Based on the day-ahead forecast data, the characteristic values of samples at each level are used to generate a scenario set, and iterative clustering is used to reduce the scenario set, and a typical wind and solar forecast scenario set is output;

The scene migration probability calculation module is used to calculate the migration probability between measured values with time correlation and output the migration probability coefficient of each scene in the typical scene set of wind and solar forecast;

The optimization scheduling module is used to formulate a wind, solar and water joint optimization scheduling plan. Based on the typical scene set of wind and solar forecasts and the migration probability coefficient of each scene, it performs wind, solar and water joint short-term optimization scheduling calculations in accordance with the principle of best source-load matching.

The implementation process and method of the system are the same and will not be repeated here.

Obviously, those skilled in the art should understand that the various steps of the wind-solar-water joint short-term optimal scheduling method based on the wind-solar uncertainty forecast scenario and the various modules of the wind-solar-water joint short-term optimal scheduling system based on the wind-solar uncertainty forecast scenario of the above-mentioned embodiment of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented with executable program codes of the computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

Claims (10)

1. A wind-solar-water joint short-term optimization scheduling method based on wind-solar uncertainty forecast scenario, characterized by comprising the following steps: S1. Select historical wind and solar power output data, process missing values and outliers, normalize the processed data, and divide the sample levels; S2. Establish a wind and solar scenario forecast model based on scenario construction, use sample data of each level to analyze sample characteristics within the level, use the analysis results to forecast wind and solar scenarios based on the day-ahead forecast data of wind and solar output, and obtain a wind and solar forecast scenario set; S3, establishing a scenario reduction model, performing scenario reduction on the initial wind and solar forecast scenario set, iteratively calculating and selecting the most representative wind and solar forecast typical scenarios, and forming a wind and solar forecast typical scenario set; S4. A scene migration probability calculation model is established based on the historical measured values of wind and solar power, the measured values are divided into intervals, and the migration probability between the measured values with time correlation is calculated; S5. According to the results of typical wind and solar forecast scenarios, based on the hourly measured data of wind and solar output, the optimized scheduling decision is updated hourly, and the short-term optimized scheduling of wind, solar and water is carried out according to the principle of best source-load matching. 2. According to the wind-solar-water combined short-term optimization scheduling method based on the wind-solar uncertainty forecast scenario of claim 1, it is characterized in that in said S1, the historical wind-solar output data include: the day-ahead forecast wind output and the measured wind output data with consistent temporal and spatial correlation, and the day-ahead forecast photovoltaic output data and the measured photovoltaic output data with consistent temporal and spatial correlation; the processing method for missing values is: the linear interpolation method is used to supplement the data according to two adjacent groups of data; the processing method for outliers is: firstly, the outliers are deleted, and the missing data is supplemented according to the missing value method; the sample normalization method is: s′＝(s-μ)/σ Where s′ is the normalized sample value; s is the original sample data; μ is the mean of the original sample set; σ is the standard deviation of the original sample set. 3. The wind-solar-water combined short-term optimization scheduling method based on wind-solar uncertainty forecast scenario according to claim 1 is characterized in that, in said S2, the structure of the wind-solar scenario forecast model based on scenario construction is: Based on the forecast and measured data sets obtained after sample normalization, they are classified according to the numerical value of the forecast value, and the characteristic value of the data in each level is calculated. The characteristic value calculation method is as follows:

Where ε′ _i,j is the relative error value of the jth sample in the i-th level; sp′ _i,j is the normalized value of the predicted sample; st′ _i,j is the normalized value of the measured sample;

In the formula,

is the first eigenvalue of the level; _ni is the number of relative error values of samples in the i-th level.

In the formula,

is the second eigenvalue of the level; Based on the two eigenvalues in the sample level, super Latin square sampling is used to generate the wind and solar output forecast scenario set. 4. According to the wind-solar-water joint short-term optimization scheduling method based on wind-solar uncertainty forecast scenarios according to claim 1, it is characterized in that the scene reduction method used in S3 is the K-means clustering method using random centroids for clustering, and the clustering result is controlled between 4-8. 5. The wind-solar-water combined short-term optimization scheduling method based on wind-solar uncertainty forecast scenario according to claim 1 is characterized in that, in S4, interval division is performed according to the normalized result of wind-solar measured data, and a scene migration probability calculation model is established, and the probability calculation method is as follows: st″＝(st′-μ′)/σ′ Where st″ represents the standard score of the standard normal distribution; μ′ represents the mean of the normalized values of the measured samples; σ′ represents the standard deviation of the normalized values of the measured samples.

Where Pst′ _{(u, d)} represents the probability that the next measured value will be st′ after normalization when the current measured value is in the interval (u, d) after normalization. 6. The wind-solar-water combined short-term optimal scheduling method based on wind-solar uncertainty forecast scenarios according to claim 1 is characterized in that, in S5, based on the results of the typical scene set of wind-solar forecast, the probability of each typical scene occurring is calculated hour by hour, and decision scenarios for short-term optimal scheduling calculation are continuously generated, and the calculation method is as follows:

Where _P′q is the migration probability coefficient of the qth scene in the typical scene set of wind and solar forecast;

Where _x′p represents the wind and solar forecast scenario value of the pth hour during the optimization scheduling period; _xp,q represents the value of the pth hour in the qth scenario of the wind and solar forecast typical scenario value. 7. The wind-solar-water joint short-term optimal scheduling method based on wind-solar uncertainty forecast scenarios according to claim 1 is characterized in that in said S5, a wind-solar-water joint short-term optimal scheduling model is constructed with the goal of optimizing the source-load matching degree, and the wind-solar-water joint scheduling is performed based on the continuously generated short-term optimal scheduling decision scenarios, and the calculation method is as follows:

Nh _p =N ^w +N ^s +N ^h

Where, _Nv is the source-load matching rate; _Nyp is the total system output at the pth hour; _Nhp is the system load at the pth hour; ^Nw , ^Ns , ^Nh are the wind power, photovoltaic, and hydropower output values, respectively;

is the power generation flow of the hydropower station at the jth time; _Hj is the power generation head of the hydropower station at the jth time. 8. A wind-solar-water combined short-term optimization scheduling system based on wind-solar uncertainty forecast scenarios, characterized by comprising: The data processing module is used to classify the input historical wind and solar power output data and calculate the characteristic values of the historical data at each level for scene generation; The scenario generation module is used to establish a wind and solar scenario forecast model and a scenario reduction model. Based on the day-ahead forecast data, the characteristic values of samples at each level are used to generate a scenario set, and iterative clustering is used to reduce the scenario set, and a typical wind and solar forecast scenario set is output; The scene migration probability calculation module is used to calculate the migration probability between measured values with time correlation and output the migration probability coefficient of each scene in the typical scene set of wind and solar forecast; The optimization scheduling module is used to formulate a wind, solar and water joint optimization scheduling plan. Based on the typical scene set of wind and solar forecasts and the migration probability coefficient of each scene, it performs wind, solar and water joint short-term optimization scheduling calculations in accordance with the principle of best source-load matching. 9. A computer device, characterized in that the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the wind, solar, and water combined short-term optimization scheduling method based on the wind and solar uncertainty forecast scenario as described in any one of claims 1 to 7 is implemented. 10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the wind-solar-water combined short-term optimization scheduling method based on the wind-solar uncertainty forecast scenario as described in any one of claims 1 to 7.

Images