New energy power generation scheduling method and device, storage medium and computer equipment

Abstract

According to the new energy power generation scheduling method and device, the storage medium and the computer equipment, in the power generation control process, the power generation time sequence data is firstly determined, the wind speed probability model and the illumination probability model are obtained, and the probability models are constructed based on the historical data and updated regularly; the wind speed probability model and the illumination probability model are sampled respectively to obtain a wind speed prediction sample and an illumination prediction sample which are closer to reality, and the prediction precision of the generating capacity can be improved based on prediction of the wind generating capacity and the photovoltaic generating capacity. Meanwhile, the adjustment demand quantity of the power system can be calculated according to the power generation time sequence data, so that the charging and discharging behaviors of the energy storage equipment in the power system can be accurately scheduled according to the predicted wind power generation capacity, photovoltaic power generation capacity and adjustment demand quantity, and the power supply and demand of the power system can be better balanced; and the wind power and photovoltaic power generation conditions can be predicted in advance through accurate prediction of the power generation amount, and rapid response to the power change of the power system is realized.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a new energy power generation scheduling method, device, storage medium and computer equipment. Background Art

[0002] Renewable energy management refers to the efficient management of renewable energy generation, storage and dispatch through advanced technical means to achieve sustainable energy utilization and improve the stability and reliability of power grid operation. With the growing global demand for low-carbon and green energy, renewable energy management technology plays an increasingly important role in the transformation of the global energy structure.

[0003] However, due to the volatility and uncertainty of renewable energy power generation, when the proportion of renewable energy in the power system increases, the regulation capacity of the power system will decrease, making it difficult for traditional automatic power generation control methods to meet the needs of rapid response and precise regulation. Summary of the invention

[0004] The purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defects in the prior art that since renewable energy power generation has the characteristics of volatility and uncertainty, when the proportion of renewable energy in the power system increases, the regulation capacity of the power system will decrease, resulting in the traditional automatic power generation control method being difficult to meet the needs of rapid response and precise regulation.

[0005] In a first aspect, the present application provides a new energy power generation scheduling method, the method comprising:

[0006] Determine the power generation timing data and obtain the pre-built wind speed probability model and sunlight probability model;

[0007] Based on the wind speed probability model and the light probability model, sampling is performed to generate wind speed prediction samples and light prediction samples, and wind power generation and photovoltaic power generation are predicted according to the wind speed prediction samples and the light prediction samples to obtain predicted wind power generation and predicted photovoltaic power generation;

[0008] Calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data;

[0009] The energy storage equipment in the power system is charged and discharged according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand.

[0010] In one embodiment, the method further comprises:

[0011] Acquire original power generation data corresponding to the power generation time series data, and compare the original power generation data with the power generation time series data to obtain the travel time residual at each acquisition moment; the power generation time series data and the original power generation data both include multiple time series data;

[0012] Extract the travel time residual sequences of different time series data from the travel time residuals at each acquisition moment, and calculate the mean and standard deviation of each travel time residual sequence;

[0013] According to the mean and standard deviation of each travel time residual sequence, the abnormal points in various time series data are determined, and the number of abnormal points in various time series data is counted. When the time series data with the number of abnormal points exceeding the preset abnormal threshold is detected, the corresponding warning signal is generated to trigger the alarm mechanism.

[0014] In one embodiment, the updating process of the wind speed probability model and the light probability model includes:

[0015] Every other statistical day, a wind speed observation sample formed by the wind speed data on the previous statistical day and a light observation sample formed by the light data on the previous statistical day are obtained;

[0016] Calculating the mean and standard deviation of the wind speed observation samples and the light observation samples respectively;

[0017] The wind speed probability model is updated according to the mean and standard deviation of the wind speed observation samples, and the illumination probability model is updated according to the mean and standard deviation of the illumination observation samples.

[0018] In one embodiment, the sampling based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and predicting wind power generation and photovoltaic power generation according to the wind speed prediction samples and the light prediction samples, respectively, includes:

[0019] Using an equal time period sampling method to randomly sample in the wind speed probability model to obtain a wind speed prediction sample, and using an equal time period sampling method to randomly sample in the light probability model to obtain a light prediction sample;

[0020] Obtaining a preset wind power generation model and a photovoltaic power generation model, and inputting the wind speed prediction sample into the wind power generation model to perform power generation prediction to obtain a wind power generation sample, and inputting the light prediction sample into the photovoltaic power generation model to perform power generation prediction to obtain a photovoltaic power generation sample;

[0021] The predicted wind power generation and the predicted photovoltaic power generation are respectively predicted based on the wind power generation samples and the photovoltaic power generation samples according to a preset prediction formula.

[0022] In one embodiment, the calculating the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data includes:

[0023] Obtaining grid load demand, exchange power and grid frequency from the grid time series data, and obtaining wind power generation, photovoltaic power generation and adjustable power generation capacity from the renewable energy power generation data;

[0024] Calculating the difference between the sum of the grid load demand and the exchange power and the sum of the wind power generation and the photovoltaic power generation, and determining the difference as the net load demand;

[0025] The regulation demand is calculated according to the grid frequency, the adjustable generation capacity and the net load demand.

[0026] In one embodiment, the charging and discharging scheduling of the energy storage device in the power system according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand includes:

[0027] When the regulation demand is less than the first preset threshold, if the predicted wind power generation is greater than the second preset threshold or the predicted photovoltaic power generation is greater than the third preset threshold, the charging time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is charged according to the regulation execution amount at the current moment, and the process returns to the step of calculating the regulation execution amount at the current moment and continues to execute until the current moment is not within the charging time period;

[0028] When the regulation demand is greater than the fourth preset threshold, if the predicted wind power generation is less than the fifth preset threshold and the predicted photovoltaic power generation is less than the sixth preset threshold, the discharge time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is discharged according to the regulation execution amount at the current moment, and the step of calculating the regulation execution amount at the current moment is returned to continue execution until the current moment is not in the discharge time period.

[0029] In one embodiment, the calculation process of the adjustment execution amount includes:

[0030] When calculating the adjustment execution amount within the charging time period, the adjustment demand amount at the current moment, the maximum total input power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the adjustment execution amount corresponding to the current moment;

[0031] When calculating the regulation execution amount within the discharge time period, the regulation demand at the current moment, the maximum total output power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the regulation execution amount corresponding to the current moment.

[0032] In a second aspect, the present application provides a new energy power generation scheduling device, the device comprising:

[0033] A data determination module, used to determine power generation timing data and obtain a pre-built wind speed probability model and a light probability model;

[0034] A power generation prediction module, used to perform sampling based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and predict wind power generation and photovoltaic power generation according to the wind speed prediction samples and the light prediction samples, respectively, to obtain predicted wind power generation and predicted photovoltaic power generation;

[0035] A demand calculation module, used to calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data;

[0036] A power generation scheduling module is used to schedule the charging and discharging of energy storage equipment in the power system according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand.

[0037] In a third aspect, the present application provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the new energy power generation scheduling method described in any of the above embodiments.

[0038] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;

[0039] The memory stores computer-readable instructions, and when the one or more processors execute the computer-readable instructions, the steps of the new energy power generation scheduling method described in any of the above embodiments are performed.

[0040] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0041] The new energy power generation scheduling method, device, storage medium and computer equipment provided by the present application can first determine the power generation time series data in the process of power generation control of the new energy power system, and obtain the pre-built wind speed probability model and light probability model. The wind speed probability model and the light probability model are constructed based on historical climate data and updated regularly, so that when sampling is performed based on the wind speed probability model and the light probability model, wind speed prediction samples and light prediction samples that are closer to the actual can be obtained. Based on this prediction of wind power generation and photovoltaic power generation, the prediction accuracy of power generation can be improved. At the same time, the regulation demand of the power system can also be calculated according to the power grid time series data and the new energy power generation data in the power generation time series data, so that the charging and discharging behavior of the energy storage device in the power system can be accurately scheduled according to the predicted wind power generation, photovoltaic power generation and regulation demand. On the one hand, the power supply and demand of the power system can be better balanced, and the instability of the power grid caused by the fluctuation of new energy power generation can be avoided to the greatest extent. On the other hand, through real-time data acquisition and accurate prediction of power generation, wind and photovoltaic power generation can be predicted in advance to carry out advanced power generation scheduling, thereby achieving rapid response to power changes in the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 A schematic diagram of the structure of a new energy power generation dispatching system provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram of a process flow of a new energy power generation scheduling method provided in an embodiment of the present application;

[0045] Figure 3 A flowchart of a triggering alarm mechanism provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of a process for generating prediction samples and predicting wind power generation and photovoltaic power generation provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of a flow chart for scheduling charging and discharging of energy storage equipment in a power system according to predicted wind power generation, predicted photovoltaic power generation and regulation demand provided in an embodiment of the present application;

[0048] Figure 6A schematic diagram of the structure of a new energy power generation dispatching device provided in an embodiment of the present application;

[0049] Figure 7 An internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] like Figure 1 As shown, in one of the embodiments, the present application provides a new energy power generation scheduling system. The following embodiments are described by applying to the new energy power generation scheduling system, hereinafter referred to as the system, which can be deployed in a computer device. Specifically, the system includes a data acquisition module, a scheduling evaluation module, an abnormality perception module, a condition perception module and a feedback regulation module; the data acquisition module is used to collect original power generation data at each preset time interval, and perform data cleaning on the original power generation data based on the Kalman filter to obtain power generation time series data; the scheduling evaluation module is used to calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data; the condition perception module is used to construct a wind speed probability model and a light probability model, and is also used to determine the predicted wind power generation and the predicted photovoltaic power generation based on the wind speed probability model and the light probability model; the abnormality perception module is used to calculate the number of abnormal points based on the original power generation data and the power generation time series data, and generate corresponding warning signals to send to the feedback regulation module for warning; the feedback regulation module is used to perform charging and discharging scheduling of energy storage equipment in the power system according to the predicted wind power generation, predicted photovoltaic power generation and regulation demand, and is also used to receive warning signals and trigger warning mechanisms. Based on this, Figure 2 As shown, the present application provides a new energy power generation scheduling method, the method comprising:

[0052] S101: Determine power generation timing data, and obtain a pre-built wind speed probability model and a light probability model.

[0053] In this step, when the power system is unstable, the user can start the power generation dispatch instruction through the system. When the system receives the power generation dispatch instruction, it regularly collects the original power generation data and cleans the original power generation data to determine the power generation time series data. Then, when determining the power generation time series data, the pre-built current wind speed probability model and light probability model are obtained.

[0054] The wind speed probability model refers to a mathematical model used to describe the statistical distribution of wind speed, and the light probability model refers to a data model used to describe the statistical distribution of light intensity. The power generation time series data contains a variety of time series data. For example, the power generation time series data can be expressed as ={ , , , , , , , , }, where t represents the time, t=1,2,……,t, Indicates the grid frequency, Indicates that the power grid meets the demand. represents the exchange power, Indicates the ACE system adjustment error, represents the wind power generation, represents the photovoltaic power generation, Indicates adjustable power generation capacity, Indicates wind speed, Indicates light intensity.

[0055] In one example, when determining the power generation time series data, it includes: collecting the original power generation data, and using the Kalman filter to clean the original power generation data, further specifically including:

[0056] For each time series data in the collected original power generation data, the state vector and observation vector are defined, and a linear dynamic system model is constructed, where the state vector, observation vector and linear dynamic system model can be expressed as:

[0057]

[0058]

[0059]

[0060] In the formula, Represents the state vector of various time series data at time t, Defined as the true value of various time series data at time t, It is defined as the real change rate of various time series data at time t. Represents the observation vector of various time series data at time t, Defined as the observed values ​​of various time series data at time t, Defined as the observed change rate of various time series data at time t. Represents the state variables of various time series data at time t-1, Refers to the preset observation matrix, which represents the mapping relationship from true value to observation value. It refers to the preset state transfer matrix, which represents the mapping relationship between the real value of the time series data from time t-1 to time t. Refers to the control input item, which indicates the influence of possible external scheduling signals on the true value of the time series data. When there is no external scheduling signal, The value of is 0, represents the process noise, It is important to note that process noise and measurement noise are Gaussian noises with a mean of 0 and different variances. The observed value refers to the collected data, and the true value refers to the data after data cleaning.

[0061] At each preset time interval, the predicted value of the time series data at the current time t is calculated using the following formula:

[0062]

[0063] In the formula, Represents the predicted value of various time series data at time t, Represents the predicted value of various time series data at time t-1.

[0064] At the same time, the prediction covariance of the time series data at the current time t is calculated by the following formula:

[0065]

[0066] In the formula, Represents the predicted covariance of various time series data at time t, Represents the predicted covariance of various time series data at time t-1, Represents the covariance matrix of the process noise.

[0067] At the same time, the Kalman gain at the current time t is calculated by the following formula:

[0068]

[0069] In the formula, Represents the Kalman gain of various time series data at time t, Represents the observation matrix The transposed matrix of Represents the covariance matrix of the measurement noise.

[0070] Next, the prediction value and covariance matrix are updated using the following formula:

[0071]

[0072] In the formula, Represents the state vector of various time series data at time t, that is, the updated prediction value, represents the updated covariance matrix, is the identity matrix.

[0073] Finally, extract the time series data in the predicted value As a result of data cleaning, the original power generation data is cleaned by using a Kalman filter to remove noise and outliers, thus ensuring the accuracy of subsequent power generation forecasts and demand adjustment calculations.

[0074] S102: Sampling is performed based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and wind power generation and photovoltaic power generation are predicted based on the wind speed prediction samples and the light prediction samples to obtain predicted wind power generation and predicted photovoltaic power generation.

[0075] Among them, the wind speed prediction sample is a set of values ​​generated based on the light speed probability model, which is used to simulate the change of wind speed in the future period of time. The light prediction sample is a set of values ​​generated based on the light probability model, which is used to simulate the change of light intensity in the future period of time. The predicted wind power generation refers to the predicted amount of electric energy generated by the wind turbine under specific wind speed conditions, and the predicted photovoltaic power generation refers to the predicted amount of electric energy generated by the photovoltaic system under specific light intensity.

[0076] In this step, wind speed prediction samples and light prediction samples are generated from these probability models through random sampling technology. These samples reflect the possible wind speed and light intensity in the future. Subsequently, the power generation is predicted based on the wind speed prediction samples and the light prediction samples to obtain the predicted wind power generation and predicted photovoltaic power generation of the current power system. Specifically, for wind power generation, the power generation corresponding to each sample can be calculated based on the wind speed prediction samples and the power curve of the wind turbine, and then the predicted power generation can be obtained by integrating the time interval; for photovoltaic power generation, the power generation corresponding to each sample is calculated based on the light prediction samples and the photoelectric conversion efficiency of the photovoltaic panel, and then the predicted power generation is obtained by time integration. Finally, by summarizing the power generation prediction results of all samples, the overall predicted wind power generation and predicted photovoltaic power generation are obtained.

[0077] S103: Calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data.

[0078] Among them, the grid time series data refers to the key parameters of the power system operation within a specific time series, such as grid load demand, exchange power, etc., and the renewable energy power generation data refers to the renewable energy related parameters of the power system within a specific time series, such as wind power generation, photovoltaic power generation, and adjustable power generation capacity, etc. The regulation demand refers to the regulation power or energy required to balance the difference between grid load and power generation through regulation means to maintain the stable operation of the power system.

[0079] In this step, the grid time series data and renewable energy generation data can be extracted from the grid time series data, and then the regulation demand required to maintain the stability of the current power system can be calculated based on the grid time series data and renewable energy generation data. In this way, the intermittent and volatile nature of renewable energy generation can be effectively dealt with by using demand-side response measures. This ensures the stable operation of the power system, improves the absorption capacity of renewable energy, and optimizes the economic operation of the power grid and reduces operating costs.

[0080] S104: Scheduling charging and discharging of energy storage devices in the power system according to predicted wind power generation, predicted photovoltaic power generation and regulation demand.

[0081] In this step, the charge and discharge power instructions of the energy storage device at the current moment are calculated based on the predicted wind power generation and predicted photovoltaic power generation, combined with the current power system regulation demand. For example, when the regulation demand is low and the predicted renewable energy generation (wind power or photovoltaic) is high, the energy storage device is dispatched to enter the charging state to absorb excess electricity to reduce the phenomenon of wind and solar abandonment; conversely, when the regulation demand is high and the predicted renewable energy generation (wind power and photovoltaic) is low, the energy storage device is dispatched to enter the discharging state to release energy to the grid to fill the power gap.

[0082] Specifically, the charging and discharging scheduling of energy storage equipment can be adjusted in real time according to the dynamic changes of the power system. For example, during the peak period of wind power and photovoltaic power generation, energy storage equipment can be charged during the off-peak electricity price period, and discharged during the peak power consumption period or when the power generation of new energy is insufficient, thereby achieving the supply and demand balance of the power system and optimizing resource utilization.

[0083] The new energy power generation scheduling method, device, storage medium and computer equipment provided by the present application can first determine the power generation time series data in the process of power generation control of the new energy power system, and obtain the pre-built wind speed probability model and light probability model. The wind speed probability model and the light probability model are constructed based on historical climate data and updated regularly, so that when sampling is performed based on the wind speed probability model and the light probability model, wind speed prediction samples and light prediction samples that are closer to the actual can be obtained. Based on this prediction of wind power generation and photovoltaic power generation, the prediction accuracy of power generation can be improved. At the same time, the regulation demand of the power system can also be calculated according to the power grid time series data and the new energy power generation data in the power generation time series data, so that the charging and discharging behavior of the energy storage device in the power system can be accurately scheduled according to the predicted wind power generation, photovoltaic power generation and regulation demand. On the one hand, the power supply and demand of the power system can be better balanced, and the instability of the power grid caused by the fluctuation of new energy power generation can be avoided to the greatest extent. On the other hand, through real-time data acquisition and accurate prediction of power generation, wind and photovoltaic power generation can be predicted in advance to carry out advanced power generation scheduling, thereby achieving rapid response to power changes in the power system.

[0084] like Figure 3 As shown, the embodiment of the present application also provides a flowchart of triggering an alarm mechanism, and the specific steps include:

[0085] S201: Acquire original power generation data corresponding to the power generation time series data, and compare the original power generation data with the power generation time series data to obtain the travel time residual at each acquisition moment.

[0086] The power generation time series data and the original power generation data both include multiple time series data.

[0087] Specifically, the travel time residual between the original power generation data and the power generation time series data at each acquisition moment can be calculated according to the following expression:

[0088]

[0089] In the formula, represents the travel time residual at time t, represents the data at time t in the original power generation data, Represents the data at time t in the power generation time series data.

[0090] S202: extracting travel time residual sequences of different time series data from the travel time residuals at each acquisition moment, and calculating the mean and standard deviation of each travel time residual sequence.

[0091] It can be understood that, since the original power generation data and the power generation time series data contain multiple time series data, when calculating the travel time residuals at each acquisition moment, the obtained travel time residuals contain the travel time residuals of each data in different time series data, and the travel time residuals of the same time series data can be extracted from the calculated travel time residuals at each acquisition moment to obtain the travel time residual sequence of the time series data, and this step can be repeated to extract the travel time residual sequence of each time series data from the travel time residuals at each acquisition moment.

[0092] S203: Determine the abnormal points in various time series data according to the mean and standard deviation of each travel time residual sequence, and count the number of abnormal points in various time series data. When time series data with the number of abnormal points exceeding the preset abnormal threshold is detected, a corresponding warning signal is generated to trigger an alarm mechanism.

[0093] In this step, when determining the mean and standard deviation of each travel time residual sequence, for the time series data corresponding to each travel time residual sequence, the normal range is calculated according to the mean and standard deviation of the travel time residual sequence. If there is data that is not within the normal range in the time series data, the data that is not within the normal range is marked as an abnormal point, and the time at which the abnormal point is located is recorded. Then, the number of abnormal points in the time series data is counted. When determining the number of abnormal points in the time series data corresponding to each travel time residual sequence, the number of abnormal points in each time series data is detected. When it is detected that there is time series data with the number of abnormal points exceeding the preset abnormal threshold, a warning signal is generated according to the abnormal point and the time at which it is located, thereby triggering an alarm mechanism.

[0094] In an example, assuming that the mean of the travel time residual sequence is μ and the standard deviation is σ, the normal range can be determined as [μ-3σ, μ+3σ].

[0095] In this embodiment, since data collection is performed regularly, the collected data will be regularly tested for abnormal points, so that data anomalies can be automatically and regularly detected, thereby prompting relevant personnel to take corresponding measures in a timely manner to avoid potential risks as much as possible.

[0096] In one embodiment, the updating process of the wind speed probability model and the light probability model includes:

[0097] S1: every other statistical day, obtain a wind speed observation sample formed by the wind speed data in the previous statistical day and a light observation sample formed by the light data in the previous statistical day.

[0098] Specifically, the statistical date can be determined according to a fixed interval, or it can be determined by calculation according to specific rules, and this application does not impose specific restrictions on this. In one example, when a fixed interval is used for determination, assuming that the fixed interval is 2 days, the first statistical day is the 2nd, then the next statistical days are the 5th, 8th, 11th..., when the current statistical day is the 8th, the wind speed data and light data from 0:00 to 24:00 on the previous statistical day, the 5th, are obtained, and then wind speed observation samples and light observation samples are generated based on the wind speed data and light data, respectively.

[0099] S2: Calculate the mean and standard deviation of wind speed observation samples and light observation samples respectively.

[0100] S3: Update the wind speed probability model according to the mean and standard deviation of the wind speed observation samples, and update the light probability model according to the mean and standard deviation of the light observation samples.

[0101] Among them, the wind speed probability model and the light probability model can be expressed as follows:

[0102]

[0103]

[0104] In the formula, represents the wind speed probability model, represents the standard deviation of wind speed observation samples, represents the mean of wind speed observation samples, Indicates wind speed value. represents the illumination probability model, represents the standard deviation of the illumination observation samples, represents the mean of the illumination observation samples, Indicates the light intensity value.

[0105] In this embodiment, the wind speed probability model and the light probability model are updated by using the wind speed data and light data of the statistical day every other statistical day, so as to ensure that the probability model always reflects the latest environmental change characteristics, thereby improving the accuracy and reliability of subsequent power generation forecasts. And this method can allow the probability model to dynamically adapt to seasonal changes in meteorological conditions, long-term trends, and sudden weather events, so that the wind speed prediction samples and light prediction samples generated based on the probability model are closer to the actual operating conditions. For example, during seasonal changes or extreme weather conditions, the distribution of wind speed and light intensity may change significantly. Regularly updating the model can capture these changes in a timely manner, thereby optimizing the prediction accuracy of wind power generation and photovoltaic power generation.

[0106] like Figure 4As shown, in one embodiment, sampling is performed based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and wind power generation and photovoltaic power generation are predicted based on the wind speed prediction samples and the light prediction samples, respectively, including:

[0107] S301: using an equal time period sampling method to perform random sampling in a wind speed probability model to obtain a wind speed prediction sample, and using an equal time period sampling method to perform random sampling in a light probability model to obtain a light prediction sample.

[0108] In this step, a day can be divided into equal time periods according to a preset first sample capacity, and then a wind speed value is randomly extracted from the wind speed probability model for each time period. When the wind speed values ​​of all divided time periods are extracted, wind speed prediction samples are generated according to these wind speed values. Similarly, a day can be divided into equal time periods according to a preset second sample capacity, and then a light intensity value is randomly extracted from the light probability model for each time period. When the light intensity values ​​of all divided time periods are extracted, light prediction samples are generated according to these light intensity values.

[0109] S302: Obtain a preset wind power generation model and a photovoltaic power generation model, and input a wind speed prediction sample into the wind power generation model to perform power generation prediction, thereby obtaining a wind power generation sample.

[0110] Among them, the wind power generation model is used to estimate the wind power generation based on the wind speed value and combined with parameters related to the wind turbine and the environment, and the photovoltaic power generation model is used to estimate the photovoltaic power generation based on the light intensity value and combined with parameters related to the photovoltaic module and the environment.

[0111] In this step, a wind power generation model is obtained, and then the wind speed values ​​in the wind speed prediction sample are sequentially input into the wind power generation model to obtain the wind power generation in each time period to form a wind power generation sample.

[0112] In one example, the wind power generation model can be expressed as follows:

[0113]

[0114] In the formula, represents the wind power generation, represents the wind speed value in the wind speed forecast sample, represents the number of wind turbines, Represents the overall conversion efficiency of the wind turbine. Indicates the preset wind energy coefficient, represents the average swept area of ​​the wind rotor, represents the air density, represents the minimum value in the wind speed forecast sample, represents the maximum value in the wind speed forecast sample, Indicates the maximum value of wind power generation.

[0115] S303: Inputting the illumination prediction sample into the photovoltaic power generation model to perform power generation prediction, and obtaining the photovoltaic power generation sample.

[0116] In this step, a photovoltaic power generation model is obtained, and then the photovoltaic power generation in each time period is obtained by sequentially inputting the light intensity values ​​in the light prediction sample into the photovoltaic power generation model to form a photovoltaic power generation sample.

[0117] In one example, the photovoltaic power generation model can be expressed as follows:

[0118]

[0119] In the formula, represents the photovoltaic power generation, Represents the light intensity value in the light prediction sample, represents the conversion efficiency of photovoltaic modules in the power system, represents the radiation constant, represents the effective area of ​​the photovoltaic panel, Represents the maximum value in the illumination prediction sample, Indicates the maximum value of photovoltaic power generation.

[0120] S304: predicting the predicted wind power generation and the predicted photovoltaic power generation based on the wind power generation samples and the photovoltaic power generation samples according to a preset prediction formula.

[0121] In this step, the predicted wind power generation and the predicted photovoltaic power generation are calculated based on the wind power generation samples and the photovoltaic power generation samples respectively by using specific formulas. Specifically, the preset prediction formula can be expressed as follows:

[0122]

[0123] In the formula, To predict wind power generation, To predict photovoltaic power generation, n is the number of wind power prediction samples, m is the number of light prediction samples, represents the wind power generation corresponding to sample i in the wind power generation sample, represents the photovoltaic power generation corresponding to sample j in the photovoltaic power generation sample, represents the time difference between sample i+1 and sample i in the wind power generation sample, Represents the time difference between sample j+1 and sample j in the PV power generation sample.

[0124] In this embodiment, the equal time period sampling method is used to randomly sample from the wind speed probability model and the light probability model, and the obtained prediction samples are respectively input into the wind power generation model and the photovoltaic power generation model for power generation prediction, so as to obtain the predicted wind power generation and the predicted photovoltaic power generation. The wind speed and light prediction samples that conform to the probability distribution are simulated by random sampling, and the input data close to the actual operation situation is provided for the power generation prediction. These prediction samples are input into the preset power generation model to generate statistically representative power generation samples. This method based on probability model and random sampling can effectively reflect the uncertainty and volatility of renewable energy power generation, making the prediction results more scientific and practical. In this way, not only can the prediction accuracy of wind and photovoltaic power generation be improved, but also a more accurate decision-making basis can be provided for the operation of the power grid, and the operation efficiency and reliability of the power system can be optimized.

[0125] In one embodiment, calculating the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data includes:

[0126] S1: Obtain grid load demand, exchange power and grid frequency from the grid time series data, and obtain wind power generation, photovoltaic power generation and adjustable power generation capacity from the renewable energy power generation data.

[0127] Among them, grid load demand refers to the total demand for electric energy by all electricity users in the power system, that is, the electric power or electric energy that the power system needs to provide to meet the needs of electricity users. Exchange power refers to the electric power exchanged between the power grid and the external system. Grid frequency refers to the frequency of alternating current in the power system. Adjustable power generation capacity refers to the total capacity of power generation equipment in the power system that can adjust power output according to the grid operation requirements.

[0128] S2: Calculate the difference between the sum of the grid load demand and the exchange power and the sum of the wind power generation and the photovoltaic power generation, and determine the difference as the net load demand.

[0129] Among them, net load demand refers to the load demand that needs to be met by traditional power generation equipment or adjustable power generation resources in the power system.

[0130] Specifically, the net load demand can be calculated according to the following expression:

[0131]

[0132] In the formula, t represents the time, represents the net load demand, represents the grid load demand, represents the wind power generation, represents the photovoltaic power generation, Indicates the switching power.

[0133] S3: Calculate the regulation demand based on the grid frequency, adjustable generation capacity and net load demand.

[0134] Specifically, according to the grid frequency, adjustable generation capacity and net load demand, the regulation demand is calculated according to the following expression:

[0135]

[0136] In the formula, t represents the time, Indicates the regulation demand. Indicates the preset adjustment coefficient. Indicates the preset standard value of the power grid frequency. Indicates the grid frequency, Indicates adjustable power generation capacity.

[0137] In this embodiment, the grid load demand, exchange power and grid frequency are obtained from the grid time series data, and the wind power generation, photovoltaic power generation and adjustable power generation capacity are obtained from the renewable energy power generation data. The net load demand is obtained by calculating the sum of the grid load demand and the exchange power, and then subtracting the sum of wind power and photovoltaic power generation. The adjustment demand is calculated in combination with the grid frequency, adjustable power generation capacity and net load demand. In this way, the real-time power balance state of the grid can be accurately grasped, so as to reasonably allocate adjustable power generation resources in the future, cope with the intermittent and uncertain nature of renewable energy power generation, thereby optimizing the grid dispatching strategy and ensuring the safe and stable operation of the grid.

[0138] like Figure 5 As shown, in one embodiment, the energy storage device in the power system is charged and discharged according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand, including:

[0139] S401: Determine whether the adjustment demand is less than a first preset threshold or whether the adjustment demand is greater than a fourth preset threshold.

[0140] The first preset threshold is the lower limit of the preset range corresponding to the adjustment demand, and the fourth preset threshold is the upper limit of the range corresponding to the adjustment demand.

[0141] In this step, after the predicted wind power generation, predicted photovoltaic power generation and regulation demand are determined, numerical analysis can be performed on these data to schedule the charging and discharging of energy storage devices in the power system based on the results of the numerical analysis.

[0142] S402: When the regulation demand is less than the first preset threshold, if the predicted wind power generation is greater than the second preset threshold or the predicted photovoltaic power generation is greater than the third preset threshold, the charging time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is charged according to the regulation execution amount at the current moment, and the process returns to the step of calculating the regulation execution amount at the current moment and continues to execute until the current moment is no longer in the charging time period.

[0143] The second preset threshold is the upper limit of the preset range corresponding to the wind power generation, and the third preset range is the upper limit of the preset range corresponding to the photovoltaic power generation.

[0144] When determining the charging time period, it may specifically include: obtaining a preset charging scheduling time, and determining the time period formed after the current moment passes through the charging scheduling time as the charging time period. In an example, assuming that the preset charging scheduling time is t1, taking the current time t0 as the starting time, the time period (t0, t0+t1) formed from the current moment to the charging scheduling time is determined as the charging time period.

[0145] Specifically, when the regulation demand is less than the first preset threshold, it indicates that there is excess power generation in the power grid. At this time, if the predicted wind power generation is greater than the second preset threshold or the predicted photovoltaic power generation is greater than the third preset threshold, it indicates that renewable energy power generation is in a high-yield state. At this time, the regulation execution amount at the current moment is calculated, and then the energy storage device is charged according to the power corresponding to the regulation execution amount at the current moment, and then the above process is repeated at the next moment until the current moment is not in the charging time period. This can effectively absorb excess electric energy, avoid wind and light abandonment, and improve the utilization rate of renewable energy. The regulation execution amount can be calculated in real time and used to charge the energy storage device, which can improve the responsiveness of power generation scheduling and the fineness of regulation.

[0146] S403: When the regulation demand is greater than the fourth preset threshold, if the predicted wind power generation is less than the fifth preset threshold and the predicted photovoltaic power generation is less than the sixth preset threshold, the discharge time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is discharged according to the regulation execution amount at the current moment, and the step of calculating the regulation execution amount at the current moment is returned to continue until the current moment is not in the discharge time period.

[0147] Among them, the fifth preset threshold is the lower limit of the preset range corresponding to the wind power generation, and the sixth preset threshold is the lower limit of the preset range corresponding to the photovoltaic power generation.

[0148] When determining the discharge time period, it may specifically include: obtaining a preset discharge scheduling time, and determining the time period formed after the current moment passes the discharge scheduling time as the discharge time period. In an example, assuming that the preset discharge scheduling time is t2, taking the current time t0 as the starting time, the time period (t0, t0+t2) formed from the current moment to the discharge scheduling time is determined as the discharge time period.

[0149] When the regulation demand is greater than the fourth preset threshold, it indicates that there is a power gap in the power grid. At this time, if the predicted wind power generation is less than the fifth preset threshold and the predicted photovoltaic power generation is less than the sixth preset threshold, it means that renewable energy power generation is in a low-yield state and cannot meet the power demand of the power grid. Therefore, after determining the discharge time period, the regulation execution amount at the current moment is calculated, and then the energy storage device is discharged according to the power corresponding to the regulation execution amount at the current moment, and then the above process is repeated at the next moment until the current moment is not in the discharge time period, so that the power gap can be filled in time to maintain the power balance and frequency stability of the power grid. Through the rapid response capability of the energy storage device, the real-time regulation capability of the power grid is optimized to ensure the stable operation of the power grid when renewable energy generation is insufficient. In addition, the regulation execution amount can be calculated in real time, and the energy storage device is discharged accordingly, which can improve the responsiveness of power generation scheduling and improve the fineness of regulation.

[0150] In one embodiment, the process of calculating the adjustment execution amount includes:

[0151] S1: When calculating the regulation execution amount during the charging time period, the regulation demand at the current moment, the maximum total input power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the regulation execution amount corresponding to the current moment.

[0152] In one example, the adjustable power generation capacity at the current moment and the maximum total input power of the energy storage device are obtained from the power generation time series data, and the adjustment demand at the current moment is determined according to the calculation method of the adjustment demand, and then the smallest data among the three determined data is determined as the adjustment execution amount at the current moment. The expression for calculating the adjustment execution amount is as follows:

[0153]

[0154] In the formula, Indicates the current moment, Indicates the amount of adjustment execution. Indicates the adjustment demand. represents the maximum total input power of the energy storage device, Indicates adjustable power generation capacity.

[0155] S2: When calculating the regulation execution amount during the discharge time period, the regulation demand at the current moment, the maximum total output power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the regulation execution amount corresponding to the current moment.

[0156] In one example, the adjustable power generation capacity and the maximum total output power of the energy storage device at the current moment are obtained from the power generation time series data, and the adjustment demand at the current moment is determined according to the calculation method of the adjustment demand, and then the smallest data among the three determined data is determined as the adjustment execution amount at the current moment. The expression for calculating the adjustment execution amount is as follows:

[0157]

[0158] In the formula, Indicates the current moment, Indicates the amount of adjustment execution. Indicates the adjustment demand. Indicates the maximum total output power of the energy storage device, Indicates adjustable power generation capacity.

[0159] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0160] The following is a description of the new energy power generation scheduling device provided in an embodiment of the present application. The new energy power generation scheduling device described below and the new energy power generation scheduling method described above can be referenced to each other.

[0161] like Figure 6 As shown, the present application provides a new energy power generation scheduling device 500, the device comprising:

[0162] The data determination module 501 is used to determine the power generation time series data and obtain the pre-built wind speed probability model and light probability model;

[0163] The power generation prediction module 502 is used to perform sampling based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and predict the wind power generation and photovoltaic power generation according to the wind speed prediction samples and the light prediction samples, respectively, to obtain the predicted wind power generation and the predicted photovoltaic power generation;

[0164] The demand calculation module 503 is used to calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data;

[0165] The power generation scheduling module 504 is used to schedule the charging and discharging of energy storage devices in the power system according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand.

[0166] In one embodiment, the new energy power generation dispatching device further includes:

[0167] The residual determination module is used to obtain the original power generation data corresponding to the power generation time series data, and compare the original power generation data with the power generation time series data to obtain the travel time residual at each acquisition moment; the power generation time series data and the original power generation data both include multiple time series data;

[0168] A data calculation module is used to extract travel time residual sequences of different time series data from the travel time residuals at each acquisition moment, and calculate the mean and standard deviation of each travel time residual sequence;

[0169] The early warning trigger module is used to determine the abnormal points in various time series data according to the mean and standard deviation of each travel time residual sequence, and to count the number of abnormal points in various time series data. When the time series data with the number of abnormal points exceeding the preset abnormal threshold is detected, a corresponding early warning signal is generated to trigger the alarm mechanism.

[0170] In one embodiment, the data determination module includes:

[0171] The sample acquisition submodule is used to obtain, every other statistical day, a wind speed observation sample formed by the wind speed data on the previous statistical day and a light observation sample formed by the light data on the previous statistical day;

[0172] The data calculation submodule is used to calculate the mean and standard deviation of wind speed observation samples and light observation samples respectively;

[0173] The model updating submodule is used to update the wind speed probability model according to the mean and standard deviation of the wind speed observation samples, and to update the light probability model according to the mean and standard deviation of the light observation samples.

[0174] In one embodiment, the power generation prediction module includes:

[0175] The sample extraction submodule is used to perform random sampling in the wind speed probability model using an equal time period sampling method to obtain wind speed prediction samples, and to perform random sampling in the light probability model using an equal time period sampling method to obtain light prediction samples;

[0176] The sample prediction submodule is used to obtain a preset wind power generation model and a photovoltaic power generation model, and input the wind speed prediction sample into the wind power generation model to perform power generation prediction to obtain a wind power generation sample, and input the light prediction sample into the photovoltaic power generation model to perform power generation prediction to obtain a photovoltaic power generation sample;

[0177] The power generation calculation submodule is used to predict the predicted wind power generation and the predicted photovoltaic power generation based on the wind power generation samples and the photovoltaic power generation samples according to the preset prediction formula.

[0178] In one embodiment, the demand calculation module includes:

[0179] The data acquisition submodule is used to obtain the grid load demand, exchange power and grid frequency from the grid time series data, and to obtain the wind power generation, photovoltaic power generation and adjustable power generation capacity from the renewable energy power generation data;

[0180] The difference calculation submodule is used to calculate the difference between the sum of the grid load demand and the exchange power and the sum of the wind power generation and the photovoltaic power generation, and determine the difference as the net load demand;

[0181] The demand calculation submodule is used to calculate the regulation demand according to the grid frequency, adjustable power generation capacity and net load demand.

[0182] In one embodiment, the power generation scheduling module includes:

[0183] A charging scheduling submodule is used to determine a charging time period when the regulation demand is less than a first preset threshold value, if the predicted wind power generation is greater than a second preset threshold value or the predicted photovoltaic power generation is greater than a third preset threshold value, and after calculating the regulation execution amount at the current moment, charge the energy storage device according to the regulation execution amount at the current moment, and return to the step of calculating the regulation execution amount at the current moment to continue executing until the current moment is not in the charging time period;

[0184] The discharge scheduling submodule is used to determine the discharge time period when the regulation demand is greater than the fourth preset threshold, if the predicted wind power generation is less than the fifth preset threshold and the predicted photovoltaic power generation is less than the sixth preset threshold, and calculate the regulation execution amount at the current moment, discharge the energy storage device according to the regulation execution amount at the current moment, and return to the step of calculating the regulation execution amount at the current moment to continue execution until the current moment is not in the discharge time period.

[0185] In one embodiment, the charging scheduling submodule or the discharging scheduling submodule includes:

[0186] The first determination submodule is used to obtain the current regulation demand, the maximum total input power of the energy storage device and the adjustable power generation capacity when calculating the regulation execution amount in the charging time period, and determine the minimum data among the obtained data as the regulation execution amount corresponding to the current moment;

[0187] The second determination submodule is used to obtain the current regulation demand, the maximum total output power of the energy storage device and the adjustable power generation capacity when calculating the regulation execution amount within the discharge time period, and determine the minimum data among the obtained data as the regulation execution amount corresponding to the current moment.

[0188] The division of each module in the above-mentioned renewable energy power generation dispatching device is only for illustration. In other embodiments, the renewable energy power generation dispatching device can be divided into different modules as needed to complete all or part of the functions of the above-mentioned renewable energy power generation dispatching device. Each module in the above-mentioned renewable energy power generation dispatching device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0189] In one embodiment, the present application also provides a storage medium, which stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the new energy power generation scheduling method as described in any of the above embodiments.

[0190] In one embodiment, the present application also provides a computer device, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the new energy power generation scheduling method as described in any of the above embodiments.

[0191] Indicatively, Figure 7 As shown, Figure 7 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 600 may be provided as a server. Figure 7The computer device 600 includes a processing component 602, which further includes one or more processors, and a memory resource represented by a memory 601, for storing instructions executable by the processing component 602, such as an application. The application stored in the memory 601 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 602 is configured to execute instructions to perform the new energy generation scheduling method of any of the above embodiments.

[0192] The computer device 600 may further include a power supply component 603 configured to perform power management of the computer device 600, a wired or wireless network interface 604 configured to connect the computer device 600 to a network, and an input / output (I / O) interface 605. The computer device 600 may operate based on an operating system stored in the memory 601, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0193] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0194] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish an entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. Moreover, the term "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only include those elements, but also include other elements that are not clearly listed, or also include elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements limited by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. Herein, the singular "one", "one" and "described / the" may also include plural forms, unless the context clearly indicates another way. It should also be understood that the terms "include / comprise" or "have" etc. specify the existence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the existence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0195] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0196] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A new energy power generation scheduling method, characterized in that: The method comprises: Determine the power generation timing data and obtain the pre-built wind speed probability model and sunlight probability model; Based on the wind speed probability model and the light probability model, sampling is performed to generate wind speed prediction samples and light prediction samples, and wind power generation and photovoltaic power generation are predicted according to the wind speed prediction samples and the light prediction samples to obtain predicted wind power generation and predicted photovoltaic power generation; Calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data; The energy storage equipment in the power system is charged and discharged according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand.

2. The new energy power generation dispatching method according to claim 1, characterized in that: The method further comprises: Acquire original power generation data corresponding to the power generation time series data, and compare the original power generation data with the power generation time series data to obtain the travel time residual at each acquisition moment; the power generation time series data and the original power generation data both include multiple time series data; Extract the travel time residual sequences of different time series data from the travel time residuals at each acquisition moment, and calculate the mean and standard deviation of each travel time residual sequence; According to the mean and standard deviation of each travel time residual sequence, the abnormal points in various time series data are determined, and the number of abnormal points in various time series data is counted. When the time series data with the number of abnormal points exceeding the preset abnormal threshold is detected, the corresponding warning signal is generated to trigger the alarm mechanism.

3. The new energy power generation dispatching method according to claim 1, characterized in that: The updating process of the wind speed probability model and the light probability model includes: Every other statistical day, a wind speed observation sample formed by the wind speed data on the previous statistical day and a light observation sample formed by the light data on the previous statistical day are obtained; Calculating the mean and standard deviation of the wind speed observation samples and the light observation samples respectively; The wind speed probability model is updated according to the mean and standard deviation of the wind speed observation samples, and the illumination probability model is updated according to the mean and standard deviation of the illumination observation samples.

4. The new energy power generation dispatching method according to claim 1, characterized in that: The sampling based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and predicting wind power generation and photovoltaic power generation according to the wind speed prediction samples and the light prediction samples, respectively, includes: Using an equal time period sampling method to randomly sample in the wind speed probability model to obtain a wind speed prediction sample, and using an equal time period sampling method to randomly sample in the light probability model to obtain a light prediction sample; Obtaining a preset wind power generation model and a photovoltaic power generation model, and inputting the wind speed prediction sample into the wind power generation model to perform power generation prediction to obtain a wind power generation sample, and inputting the light prediction sample into the photovoltaic power generation model to perform power generation prediction to obtain a photovoltaic power generation sample; The predicted wind power generation and the predicted photovoltaic power generation are respectively predicted based on the wind power generation samples and the photovoltaic power generation samples according to a preset prediction formula.

5. The new energy power generation dispatching method according to claim 1, characterized in that: The calculating the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data includes: Obtaining grid load demand, exchange power and grid frequency from the grid time series data, and obtaining wind power generation, photovoltaic power generation and adjustable power generation capacity from the renewable energy power generation data; Calculating the difference between the sum of the grid load demand and the exchange power and the sum of the wind power generation and the photovoltaic power generation, and determining the difference as the net load demand; The regulation demand is calculated according to the grid frequency, the adjustable generation capacity and the net load demand.

6. The new energy power generation dispatching method according to claim 1, characterized in that: The charging and discharging scheduling of the energy storage device in the power system according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand includes: When the regulation demand is less than the first preset threshold, if the predicted wind power generation is greater than the second preset threshold or the predicted photovoltaic power generation is greater than the third preset threshold, the charging time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is charged according to the regulation execution amount at the current moment, and the process returns to the step of calculating the regulation execution amount at the current moment and continues to execute until the current moment is not within the charging time period; When the regulation demand is greater than the fourth preset threshold, if the predicted wind power generation is less than the fifth preset threshold and the predicted photovoltaic power generation is less than the sixth preset threshold, the discharge time period is determined, and after the regulation execution amount at the current moment is calculated, the energy storage device is discharged according to the regulation execution amount at the current moment, and the step of calculating the regulation execution amount at the current moment is returned to continue execution until the current moment is not in the discharge time period.

7. The new energy power generation dispatching method according to claim 6, characterized in that: The calculation process of the adjustment execution amount includes: When calculating the adjustment execution amount within the charging time period, the adjustment demand amount at the current moment, the maximum total input power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the adjustment execution amount corresponding to the current moment; When calculating the regulation execution amount within the discharge time period, the regulation demand at the current moment, the maximum total output power of the energy storage device and the adjustable power generation capacity are obtained, and the smallest data among the obtained data is determined as the regulation execution amount corresponding to the current moment.

8. A new energy power generation dispatching device, characterized in that: The device comprises: A data determination module, used to determine power generation timing data and obtain a pre-built wind speed probability model and a light probability model; A power generation prediction module, used to perform sampling based on the wind speed probability model and the light probability model to generate wind speed prediction samples and light prediction samples, and predict wind power generation and photovoltaic power generation according to the wind speed prediction samples and the light prediction samples, respectively, to obtain predicted wind power generation and predicted photovoltaic power generation; A demand calculation module, used to calculate the regulation demand of the power system according to the power grid time series data and the new energy power generation data in the power generation time series data; A power generation scheduling module is used to schedule the charging and discharging of energy storage equipment in the power system according to the predicted wind power generation, the predicted photovoltaic power generation and the regulation demand.

9. A storage medium, characterized in that: The storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the new energy power generation scheduling method as described in any one of claims 1 to 7.

10. A computer device, characterized in that: include: one or more processors, and memory; The memory stores computer-readable instructions, and when the computer-readable instructions are executed by the one or more processors, the steps of the new energy power generation scheduling method as described in any one of claims 1 to 7 are performed.

Images