Intelligent scheduling method and device serving hybrid energy system

Abstract

The invention relates to the technical field of intelligent scheduling, in particular to an intelligent scheduling method and device serving a hybrid energy system, and the method comprises the steps: determining the power weights of various parameters at the current moment; determining a motion expected distance at the current moment, and determining a motion constraint vector at the current moment in combination with the target vector; determining a weather feature vector at the current moment based on the state change vector and the motion constraint vector, and determining the power fluctuation intensity at the current moment by combining the various parameter power weights; and based on the total climbing power and the power fluctuation intensity, intelligent scheduling of the hybrid energy system is completed. By adjusting the sensitivity of the power grid control system to the voltage offset, the voltage supply stability of the hybrid energy system is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent scheduling technology, and specifically to an intelligent scheduling method and device serving a hybrid energy system. Background Art

[0002] In the power system using hybrid energy supply, new energy power generation methods such as wind power and photovoltaic power are used. This power generation method is affected by the weather and has large fluctuations. Therefore, the power system usually predicts the power generation of wind power and photovoltaic power according to the weather forecast and formulates power generation strategies in advance according to the power generation. At the same time, the power system will set fixed upper and lower voltage limits for grid dispatch control. When the new energy equipment is unstable and the system voltage exceeds the upper and lower limits, the system will dispatch controllable power generation equipment according to the corresponding voltage over-limit situation to maintain voltage stability.

[0003] When the system voltage exceeds the limit, controllable power generation equipment will be used to reduce the peak of the power grid output power, but the controllable voltage equipment has the problem of climbing efficiency. When the power of the power grid fluctuates violently, the excessive difference between the upper and lower thresholds will cause the power grid to react to the scale when dispatching, which will lead to insufficient power output of the power grid and reduce the stability of the voltage supply of the hybrid energy system. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a smart scheduling method and device for a hybrid energy system. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides an intelligent scheduling method for serving a hybrid energy system, the method comprising the following steps:

[0006] For a preset time period before the current moment, multiple types of actual and predicted weather data at each collection moment, as well as the actual and predicted output power of the power grid, are obtained. The absolute value of the difference between each type of actual weather data and the predicted weather data is recorded as each type of weather fluctuation data. The absolute value of the difference between the actual output power and the predicted output power is recorded as the power fluctuation data. The climbing power of all devices at the current moment is obtained and the sum is calculated. The sum is recorded as the total climbing power at the current moment.

[0007] Before the current moment, based on the average distribution of various weather fluctuation data and power fluctuation data at all collection moments, various related gain coefficients at the current moment are determined, and combined with the correlation between various weather fluctuation data and power fluctuation data at all collection moments, various parameter power weights at the current moment are determined;

[0008] Before the current moment, all weather fluctuation data at each collection moment form a weather feature vector. The absolute value of the difference between the corresponding elements in the two weather feature vectors at the collection moments adjacent to and next to the current moment forms the state change vector at the current moment. The weather feature vector at the adjacent collection moment is used as the target vector at the current moment.

[0009] Construct a coordinate system with all types of weather as the coordinate system dimension, determine the motion expectation function at the current moment based on the distribution and discreteness of the distance from the coordinate origin to the projection of all weather characteristic vectors on the target vector, so as to determine the motion expectation distance at the current moment, and determine the motion constraint vector at the current moment in combination with the target vector; determine the weather characteristic vector at the current moment based on the state change vector and the motion constraint vector, and determine the power fluctuation intensity at the current moment in combination with the power weights of the various parameters;

[0010] Based on the total climbing power and the power fluctuation intensity, intelligent scheduling of the hybrid energy system is completed.

[0011] Preferably, the method for determining various types of correlation gain coefficients at the current moment is:

[0012] Calculate the mean of the power fluctuation data at all collection times within the preset time before the current moment, and record it as the mean power fluctuation at the current moment; calculate the mean of various weather fluctuation data at all collection times, and record it as the mean weather fluctuation at the current moment;

[0013] The various related gain coefficients at the current moment are the ratios of the mean power fluctuation at the current moment to the mean weather fluctuations of various types.

[0014] Preferably, the expression of the power weight of each parameter at the current moment is: i =B i ×C i Where A i represents the power weight of the i-th parameter at the current moment; B i represents the i-th type correlation gain coefficient at the current acquisition moment; C i It represents the correlation between the power fluctuation data of all collection moments within a preset time period before the current collection moment and the i-th type of weather fluctuation data.

[0015] Preferably, the method for determining the motion expectation function at the current moment is:

[0016] Calculate the mean and standard deviation of the distance from the coordinate origin to the projection of all weather feature vectors on the target vector before the current moment, use the mean and standard deviation as the mean and standard deviation in the one-dimensional Gaussian function, and obtain the distribution probability function at the current moment;

[0017] The expression of the motion expectation function at the current moment is: g(x)=(Xx)×f(x); where g(x) represents the motion expectation function at the current moment; f(x) represents the distribution probability function at the current moment; X represents the distance from the target vector to the origin of the coordinate system at the current moment, and x represents the distance from the origin of the coordinate system to the projection of the weather feature vector at any acquisition moment on the target vector.

[0018] Preferably, the expected motion distance at the current moment is the integral of the expected motion function at the current moment over the interval [-3σ, 3σ], wherein σ represents the expectation of the expected motion function at the current moment.

[0019] Preferably, the motion constraint vector at the current moment is the result of multiplying the expected motion distance at the current moment by the unit vector of the target vector.

[0020] Preferably, the weather characteristic vector at the current moment is the sum vector of the state change vector and the motion constraint vector at the current moment.

[0021] Preferably, the method for determining the power fluctuation intensity at the current moment is:

[0022] Calculate the product of the power weights of various parameters at the current moment and the corresponding class elements in the weather feature vector, and take the cumulative sum of all products as the power fluctuation intensity at the current moment.

[0023] Preferably, the intelligent scheduling of the hybrid energy system includes:

[0024] If the power fluctuation intensity at the current moment is less than the total climbing power, the upper and lower voltage threshold coefficients are set to preset values; otherwise, the result of multiplying the ratio of the total climbing power to the power intensity by the preset value is used as the upper and lower voltage threshold coefficients;

[0025] Upper and lower voltage thresholds = preset standard voltage ± preset standard voltage × upper and lower voltage threshold coefficients;

[0026] If the voltage at the current moment exceeds the upper voltage threshold, the power of the thermal power units in the power grid will be reduced. If the voltage at the current moment is lower than the lower voltage threshold, the power of the thermal power units in the power grid will be increased. If the voltage at the current moment is between the upper and lower voltage thresholds, the power of the thermal power units in the power grid will not be changed.

[0027] In a second aspect, an embodiment of the present application also provides an intelligent scheduling device serving a hybrid energy system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned intelligent scheduling methods serving a hybrid energy system are implemented.

[0028] This application has at least the following beneficial effects:

[0029] The present application determines various related gain coefficients at the current moment by analyzing the average distribution of various weather fluctuation data and the average distribution of power fluctuation data at all acquisition moments, and determines various parameter power weights at the current moment in combination with the correlation between various weather fluctuation data and power fluctuation data at all acquisition moments. The beneficial effect is that it can judge the degree of influence of different types of weather data on the voltage fluctuation of the power grid and improve the accuracy of determining the upper and lower limits of the voltage. The present application determines the motion expectation function at the current moment based on the distribution and discreteness of the distance from the coordinate origin to the projection of all weather characteristic vectors on the target vector to determine the expected motion distance at the current moment, and determines the motion constraint vector at the current moment in combination with the target vector. The weather characteristic vector at the current moment is determined based on the state change vector and the motion constraint vector, and the power fluctuation intensity at the current moment is determined in combination with the various parameter power weights. The beneficial effect is that it can avoid the inaccurate setting of the upper and lower limit thresholds and affect the dispatch of the power grid, thereby improving the stability of the power supply voltage of the power system. The present application adjusts the sensitivity of the power grid control system to voltage offset based on the total climbing power and the power fluctuation intensity, thereby improving the voltage supply stability of the hybrid energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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 creative work.

[0031] Figure 1 A flowchart of the steps of an intelligent scheduling method for serving a hybrid energy system provided by one embodiment of the present application;

[0032] Figure 2 A flowchart of the steps for obtaining the power weights of various parameters provided in one embodiment of the present application;

[0033] Figure 3 A schematic diagram of a power fluctuation intensity extraction process provided for an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the intelligent scheduling method and device for serving the hybrid energy system proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0035] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0036] The specific scheme of the intelligent scheduling method and device for serving the hybrid energy system provided by the present application is described in detail below with reference to the accompanying drawings.

[0037] See also Figure 1 , which shows a flowchart of a smart scheduling method for serving a hybrid energy system provided by an embodiment of the present application, the method comprising the following steps:

[0038] Step S1: for a preset time period before the current moment, obtain multiple types of actual and predicted weather data at each collection moment, as well as the actual and predicted output power of the power grid; obtain the climbing power of all devices at the current moment.

[0039] The power grid control system obtains multiple types of actual and predicted weather data at each collection time within the preset time t before the current time, as well as the actual and predicted output power of the power grid, and sets the sampling interval to T. The absolute value of the difference between each type of actual weather data and the predicted weather data at each collection time is recorded as each type of weather fluctuation data at each collection time, and the absolute value of the difference between the actual output power and the predicted output power at each collection time is recorded as the power fluctuation data at each collection time. Among them, multiple types of weather data include wind speed, irradiance, temperature, humidity and cloud cover.

[0040] It should be noted that the preset time length t and the sampling interval T are both manually set. In this embodiment, the preset time length t is 1h and the sampling interval T is 1s. The implementer can also set them according to the specific situation. This embodiment does not impose any special restrictions.

[0041] The climbing power of all devices at the current moment is collected through the power grid control system, and the sum of the total climbing power of all devices is recorded as the total climbing power at the current moment.

[0042] Further, in order to eliminate the influence of data dimensions and units, all weather fluctuation data, power fluctuation data and total climbing power are normalized for all weather conditions. There are many commonly used normalization methods. In this embodiment, the z-score normalization method is used to process the data. The implementer can also use the maximum and minimum value normalization method to normalize the data. This embodiment does not impose any special restrictions on the selection of the normalization method. The z-score normalization method is a well-known technology, and the specific process of normalizing the data will not be repeated.

[0043] Step S2: Before the current moment, based on the average distribution of various weather fluctuation data and power fluctuation data at all collection moments, determine the various related gain coefficients at the current moment, and combine the correlation between various weather fluctuation data and power fluctuation data at all collection moments to determine the power weights of various parameters at the current moment.

[0044] Among the weather data obtained, some weather data have a more direct impact on new energy power generation equipment, and its instantaneous changes have a greater impact on the power of new energy equipment, and the fluctuation pressure it brings to the grid voltage is greater.

[0045] Therefore, when dynamically adjusting the upper and lower limits of the grid voltage through weather data, it is necessary to consider the different fluctuation effects of different types of weather data on the grid voltage. By analyzing the average distribution of power fluctuation data before the current moment and various weather fluctuation data at all collection moments, the various related gain coefficients at the current moment are determined. Combined with the correlation between various weather fluctuation data and power fluctuation data at all collection moments, the power weights of various parameters at the current moment are determined to judge the influence of different types of weather data on grid voltage fluctuations, thereby improving the accuracy of determining the upper and lower limits of voltage. Specifically:

[0046] (1) Calculate the mean of the power fluctuation data at all collection times within a preset time before the current time, and record it as the power fluctuation mean at the current time; calculate the mean of the various weather fluctuation data at all collection times, and record it as the various weather fluctuation mean at the current time;

[0047] (2) Further, the ratio of the current power fluctuation mean to the various weather fluctuation mean values ​​is used as the various related gain coefficients at the current moment;

[0048] In particular, when there is no fluctuation in the weather data, that is, when the mean value of the weather fluctuation data is 0, it means that weather changes have no effect on the power fluctuation of the power grid, and the relevant gain coefficient is 0.

[0049] (3) Further, analyzing the correlation between various weather fluctuation data within a preset time period before the current collection time and the power fluctuation data at all collection times;

[0050] It should be noted that there are many methods for measuring the correlation between data groups. In this embodiment, the Pearson correlation coefficient between all types of weather fluctuation data at adjacent collection times before the current collection time and the power fluctuation data at all collection times is calculated to measure the correlation between the power fluctuation data and various types of weather fluctuation data. The implementer may also use other methods for measuring the correlation between data groups, such as the Spearman correlation coefficient or the Kendall rank correlation coefficient. This embodiment does not impose any special restrictions on the selection of methods for measuring the correlation between data groups.

[0051] The calculation process of the Pearson correlation coefficient is a well-known technique, and the specific calculation steps are not described in detail.

[0052] (4) Further, based on the correlation and the various correlation gain coefficients, the power weights of various parameters at the current moment are determined, specifically:

[0053] The power weight of the i-th parameter at the current moment A i The expression is: A i =B i ×C i Where B i represents the i-th type correlation gain coefficient at the current acquisition moment; C i It represents the correlation between the power fluctuation data of all collection moments within a preset time period before the current collection moment and the i-th type of weather fluctuation data.

[0054] Furthermore, according to the power weights of various parameters at the current moment, it can be understood that the larger the relevant gain coefficient at the current moment and the higher the correlation between the power fluctuation data and the weather fluctuation data, the greater the impact of weather changes on the power grid power, and the larger the parameter power weight; conversely, the smaller the relevant gain coefficient at the current moment and the lower the correlation between the power fluctuation data and the weather fluctuation data, the smaller the impact of weather changes on the power grid power, and the smaller the parameter power weight.

[0055] Preferably, the flowchart of the steps for obtaining the power weights of various parameters provided in this embodiment is as follows: Figure 2 shown.

[0056] Step S3: Construct a coordinate system with all types of weather as the coordinate system dimension, determine the motion expectation function at the current moment based on the distribution and discreteness of the distance from the coordinate origin to the projection of all weather characteristic vectors on the target vector, so as to determine the motion expectation distance at the current moment, and determine the motion constraint vector at the current moment in combination with the target vector; determine the weather characteristic vector at the current moment based on the state change vector and the motion constraint vector, and determine the power fluctuation intensity at the current moment in combination with the power weights of the various parameters.

[0057] The weather system is a chaotic system, which refers to a system that cannot be accurately predicted due to insufficient prior conditions, but can be partially predicted. A chaotic system usually describes the characteristics of a system as a multidimensional coordinate system, and any coordinate point in the coordinate system represents a state of the system. The system state will fluctuate over time and cannot be accurately predicted. In the coordinate system, it is manifested as a coordinate point moving randomly over time. Although the system state of a chaotic system cannot be predicted, its movement is usually constrained within a certain range, and its random movement has a certain probability.

[0058] Therefore, in this embodiment, a coordinate system is constructed with various types of weather as coordinate axes, and each coordinate axis represents a type of weather. As time changes, the weather state fluctuates around the coordinate origin. The more severe the weather fluctuation, the greater the impact on the voltage and power in the power grid. Therefore, based on the distribution and discreteness of the distance from the coordinate origin to the projection of all weather characteristic vectors on the target vector, the expected movement distance at the current moment is determined, and the movement constraint vector at the current moment is determined in combination with the target vector; the weather characteristic vector at the current moment is determined based on the state change vector and the movement constraint vector, and the power fluctuation intensity at the current moment is determined in combination with the power weights of the various parameters, and the severity of the electric energy fluctuation in the power grid is judged to avoid inaccurate upper and lower limit threshold settings that affect the dispatch of the power grid, and improve the stability of the power supply voltage of the power system. Specifically:

[0059] (1) Before the current moment, all types of weather fluctuation data at each collection moment constitute a weather feature vector. The absolute value of the difference between the corresponding elements in the two weather feature vectors at the adjacent and next adjacent collection moments to the current moment constitutes the state change vector at the current moment. The weather feature vector at the adjacent collection moment is used as the target vector at the current moment.

[0060] (2) Further, the mean and standard deviation of the distance from the coordinate origin to the projection of all weather feature vectors on the target vector before the current moment are calculated, and the mean and standard deviation are used as the mean and standard deviation in the one-dimensional Gaussian function to obtain the distribution probability function at the current moment;

[0061] The expression of the motion expectation function at the current moment is: g(x)=(Xx)×f(x); where g(x) represents the motion expectation function at the current moment; f(x) represents the distribution probability function at the current moment; X represents the distance from the target vector to the origin of the coordinate system at the current moment, and x represents the distance from the origin of the coordinate system to the projection of the weather feature vector at any acquisition moment on the target vector.

[0062] Among them, the one-dimensional Gaussian function is a well-known technology, and the specific principle will not be repeated here.

[0063] (3) Further, the integral of the current motion expectation function on the interval [-3σ, 3σ] is taken as the current motion expectation distance, where σ represents the expectation of the current motion expectation function.

[0064] Among them, the 3σ principle, obtaining the expectation of a function, and finding the area under the curve of a function are all commonly used techniques in the field of data processing, and their specific principles and calculation processes will not be repeated here.

[0065] (4) Furthermore, the result of multiplying the expected motion distance at the current moment by the unit vector of the target vector is used as the motion constraint vector at the current moment; and the sum vector of the state change vector at the current moment and the motion constraint vector is used as the weather feature vector at the current moment.

[0066] (5) Calculate the product of the power weights of various parameters at the current moment and the corresponding class elements in the weather feature vector, and take the cumulative sum of all products as the power fluctuation intensity at the current moment.

[0067] Furthermore, according to the power fluctuation intensity at the current moment, it can be understood that the more drastic the weather change, the greater the value of the parameter power weight, the greater the element value in the weather characteristic vector, and the greater the power fluctuation intensity, indicating that the weather change has too much impact on the power fluctuation. At the current moment, smaller upper and lower limit voltages of the power grid should be used to control the hybrid energy system, so that the power grid control is more sensitive and avoids the power grid due to climbing efficiency problems; conversely, the more moderate the weather change, the smaller the value of the parameter power weight, and the smaller the element value in the weather characteristic vector, the smaller the power fluctuation intensity, indicating that the weather change has little impact on the power fluctuation, and the upper and lower limit voltages can be appropriately adjusted. Preferably, the schematic diagram of the power fluctuation intensity extraction process provided in this embodiment is as follows: Figure 3 shown.

[0068] Step S4: Based on the total climbing power and power fluctuation intensity at the current moment, complete the intelligent scheduling of the hybrid energy system.

[0069] The power supply stability effect of the hybrid energy grid is improved by adjusting the upper and lower voltage threshold coefficients of the hybrid energy grid. Therefore, it is necessary to establish a connection between the power fluctuation intensity and the grid voltage. In this embodiment, the power fluctuation intensity and the total ramp power are combined to establish a connection between power and voltage, and the upper and lower voltage threshold coefficients are obtained. The specific method is:

[0070] If the power fluctuation intensity at the current moment is less than the total ramp power, the upper and lower voltage threshold coefficients are set to preset values; otherwise, the result of multiplying the ratio of the total ramp power to the power intensity by the preset value is used as the upper and lower voltage threshold coefficients. In particular, when the product is less than 3%, 3% is used as the threshold coefficient.

[0071] It should be noted that in this embodiment, the threshold coefficient of the fixed upper and lower limit voltages of the power grid is L=10%, and the preset standard voltage is 220kV, which means that the voltage is within the range of ±10% of the voltage stability value, that is, the fixed upper limit voltage is 242kV and the lower limit voltage is 198kV.

[0072] Among them, when the power fluctuation intensity is large, the upper and lower voltage threshold coefficients are reduced to improve the sensitivity of power grid dispatching and avoid power grid instability due to climbing efficiency problems; at the same time, the minimum upper and lower voltage threshold coefficients are set to avoid the power grid system being too sensitive, resulting in frequent switching of equipment and equipment loss.

[0073] Upper and lower voltage thresholds = preset standard voltage ± preset standard voltage × upper and lower voltage threshold coefficients;

[0074] If the voltage at the current moment exceeds the upper voltage threshold, the power of the thermal power units in the power grid will be reduced. If the voltage at the current moment is lower than the lower voltage threshold, the power of the thermal power units in the power grid will be increased. If the voltage at the current moment is between the upper and lower voltage thresholds, the power of the thermal power units in the power grid will not be changed.

[0075] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent scheduling device serving a hybrid energy system, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of any one of the above-mentioned intelligent scheduling methods serving a hybrid energy system are implemented.

[0076] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0078] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. An intelligent dispatching method for a hybrid energy system, characterized in that: The method comprises the following steps: For a preset time period before the current moment, multiple types of actual and predicted weather data at each collection moment, as well as the actual and predicted output power of the power grid, are obtained. The absolute value of the difference between each type of actual weather data and the predicted weather data is recorded as each type of weather fluctuation data. The absolute value of the difference between the actual output power and the predicted output power is recorded as the power fluctuation data. The climbing power of all devices at the current moment is obtained and the sum is calculated. The sum is recorded as the total climbing power at the current moment. Before the current moment, based on the average distribution of various weather fluctuation data and power fluctuation data at all collection moments, various related gain coefficients at the current moment are determined, and combined with the correlation between various weather fluctuation data and power fluctuation data at all collection moments, various parameter power weights at the current moment are determined; Before the current moment, all weather fluctuation data at each collection moment form a weather feature vector. The absolute value of the difference between the corresponding elements in the two weather feature vectors at the collection moments adjacent to and next to the current moment forms the state change vector at the current moment. The weather feature vector at the adjacent collection moment is used as the target vector at the current moment. Construct a coordinate system with all types of weather as the coordinate system dimension, determine the motion expectation function at the current moment based on the distribution and discreteness of the distance from the coordinate origin to the projection of all weather characteristic vectors on the target vector, so as to determine the motion expectation distance at the current moment, and determine the motion constraint vector at the current moment in combination with the target vector; determine the weather characteristic vector at the current moment based on the state change vector and the motion constraint vector, and determine the power fluctuation intensity at the current moment in combination with the power weights of the various parameters; Based on the total climbing power and the power fluctuation intensity, intelligent scheduling of the hybrid energy system is completed.

2. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The method for determining various types of related gain coefficients at the current moment is: Calculate the mean of the power fluctuation data at all collection times within the preset time before the current moment, and record it as the mean power fluctuation at the current moment; calculate the mean of various weather fluctuation data at all collection times, and record it as the mean weather fluctuation at the current moment; The various related gain coefficients at the current moment are the ratios of the mean power fluctuation at the current moment to the mean weather fluctuations of various types.

3. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The expression of the power weight of various parameters at the current moment is: i =B i ×C i Where A i represents the power weight of the i-th parameter at the current moment; B i represents the i-th type correlation gain coefficient at the current acquisition moment; C i It represents the correlation between the power fluctuation data of all collection moments within a preset time period before the current collection moment and the i-th type of weather fluctuation data.

4. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The method for determining the motion expectation function at the current moment is: Calculate the mean and standard deviation of the distance from the coordinate origin to the projection of all weather feature vectors on the target vector before the current moment, use the mean and standard deviation as the mean and standard deviation in the one-dimensional Gaussian function, and obtain the distribution probability function at the current moment; The expression of the motion expectation function at the current moment is: g(x)=(Xx)×f(x); where g(x) represents the motion expectation function at the current moment; f(x) represents the distribution probability function at the current moment; X represents the distance from the target vector to the origin of the coordinate system at the current moment, and x represents the distance from the origin of the coordinate system to the projection of the weather feature vector at any acquisition moment on the target vector.

5. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The expected motion distance at the current moment is the integral of the expected motion function at the current moment over the interval [-3σ, 3σ], where σ represents the expectation of the expected motion function at the current moment.

6. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The motion constraint vector at the current moment is the result of multiplying the expected motion distance at the current moment by the unit vector of the target vector.

7. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The weather characteristic vector at the current moment is the sum vector of the state change vector and the motion constraint vector at the current moment.

8. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The method for determining the power fluctuation intensity at the current moment is: Calculate the product of the power weights of various parameters at the current moment and the corresponding class elements in the weather feature vector, and take the cumulative sum of all products as the power fluctuation intensity at the current moment.

9. The intelligent dispatching method for serving a hybrid energy system according to claim 1, characterized in that: The intelligent scheduling of the hybrid energy system includes: If the power fluctuation intensity at the current moment is less than the total climbing power, the upper and lower voltage threshold coefficients are set to preset values; otherwise, the result of multiplying the ratio of the total climbing power to the power intensity by the preset value is used as the upper and lower voltage threshold coefficients; Upper and lower voltage thresholds = preset standard voltage ± preset standard voltage × upper and lower voltage threshold coefficients; If the voltage at the current moment exceeds the upper voltage threshold, the power of the thermal power units in the power grid will be reduced. If the voltage at the current moment is lower than the lower voltage threshold, the power of the thermal power units in the power grid will be increased. If the voltage at the current moment is between the upper and lower voltage thresholds, the power of the thermal power units in the power grid will not be changed.

10. An intelligent dispatching device serving a hybrid energy system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent scheduling method serving the hybrid energy system as described in any one of claims 1-9 are implemented.

Images